Search

Variable renewable energy-based power is expected to increase toward a sustainable society, although the power cannot be dispatched effectively due to its intermittent nature. To accelerate renewable energy implementation, we simulated energy flows of paper mills installing wind energy and evaluated their potentials to function as energy hubs for appropriate early-stage design. We targeted 39 Japanese paper mills assumed to have thermal energy storage, wind–thermal energy converters and regional woody biomass installed, and analyzed the amount of power and heat selling and life cycle greenhouse gas emissions. The results for the paper mills were compared with conventional mills to examine effective conditions for greenhouse gas reduction. The amount of power or heat selling depended on the capacity of the paper mill and the installed equipment. Most paper mills could reduce greenhouse gas using thermal energy storage, wind energy, and woody biomass. The paper mill with the highest life cycle greenhouse gas reduction, compared with conventional mills, could achieve a 190% reduction. To function as a cogeneration energy hub, the equipment installed in paper mills should be designed according to the conditions of the paper mills and their regions. • Paper mills have potential as energy hubs by integrating variable renewable energy. • Thermal energy storage and wind–thermal energy converters were studied. • Energy flows and greenhouse gas emissions of paper mills were simulated. • Most mills could provide stable power and/or heat supplies and reduce emissions. [ABSTRACT FROM AUTHOR]

Power generation by variable renewable energy (VRE) is expected to expand for decarbonization, although it is difficult to ensure stabilization of the energy demand due to fluctuations in the power output from VRE. To accelerate VRE implementation, wind-powered thermal energy systems (WT th -ES), which can provide dispatchable power using wind–thermal energy converter (WEC th) and thermal energy storage (TES), have been proposed. In this study, we are tackling the installation of VRE, i.e., wind energy, by TES with WEC th compared with wind turbine (WT p) in paper mills to demonstrate the applicability of TES in an industrial sector. Conventional and alternative energy systems in paper mills with TES were mathematically modeled and simulated to analyze the transmittable power output and the greenhouse gas (GHG) emissions by life cycle assessment. With the installation of TES and wind energy, transmittable power could be increased with GHG emissions reduction. However, their excess installation or unbalanced combination resulted in an increase in GHG emissions and a decrease in transmittable power. By comparing the cases, the combination of paper mill, TES, and WEC th could convert thermal energy efficiently and mitigate fossil fuel consumption for multiple production of paper and power from the paper mill. • A wind-thermal energy converter (WEC th) and a wind turbine (WT p) were compared. • Energy flows and GHG emissions of paper mills with TES and wind were simulated. • Paper mills reduced GHG of power generation less than fossil fuel-fired power plants. • Excess TES reduces dispatchable power generation and increases GHG emissions. • Paper mills with WEC th s and TES have the potential to be regional energy suppliers. [ABSTRACT FROM AUTHOR]

Deep Learning (DL) models, such as Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU), have been widely used to predict the intermittency of wind power; however, the non-linear activation functions and backpropagation mechanisms in DL models increase computational complexity and energy consumption. This paper proposes a prediction model based on Green Learning (GL) to reduce energy consumption. The proposed GL model replaces the feature extraction of activation functions with a hybrid feature extraction approach combining categorical and numerical features. We also employ cluster centroids and quantile regression forest for classification/regression to eliminate the need for backpropagation in optimizing hyperparameters. Using Taiwan as a case study, this paper evaluates the risk of fluctuations in regional wind power generation in 2030. In simulations, the proposed GL model achieved excellent accuracy with energy consumption significantly lower than that of DL models. Our analysis also revealed that by 2030, fluctuations in wind power generation during the winter will exceed 40% of the peak supply capacity in the central region, indicating the need to enhance the resilience of regional power systems. • This is the first study to apply green learning to wind power prediction. • This study discriminated seasonal climate patterns at the regional level. • This study assessed the fluctuation risk under large-scale wind power integration. • The maximum hourly variability in wind power is projected to exceed 6,010 MWh by 2030. • We recommend the continued deployment of regional energy storage systems. [ABSTRACT FROM AUTHOR]

Floating offshore wind turbines, as large equipment for deep-sea wind energy utilization, must be carefully studied for their aerodynamic performances under platform motions. In experiments, the model wind turbine designed by the traditional thrust coefficient similarity is usually insufficient for unsteady aerodynamic reproductions of the prototype wind turbine. In this paper, a dynamic aerodynamic similarity criterion based on the mapping of the optimal tip speed ratio is introduced for wind tunnel model tests, and a model wind turbine is designed using the NREL 5-MW prototype wind turbine. In this case, to avoid the over-height model tower aroused in pitch motions, a method of equivalent surge motions instead of pitch motions is proposed and validated for feasibility. Then dynamic aerodynamic similarities under different pitch amplitudes and frequencies are validated by the Unsteady Blade Element Momentum theory. Results indicate that temporal and spatial characteristics and hysteresis effects of thrust and power coefficients all maintain better similarity with those of the prototype wind turbine than those of the model wind turbine designed by the traditional criterion. This paper provides a criterion with equivalent pitch motions for unsteady aerodynamic studies in wind tunnel model tests, especially the high-fidelity Hardware/Software-In-the-Loop test. • A new similarity criterion is proposed for FOWT wind tunnel model tests. • The feasibility of equivalent surge motions instead of pitch motions is verified. • The problem of over-height model tower is avoided by equivalent pitch motions. • Spatiotemporal and hysteresis characteristics of unsteady aerodynamics are analyzed. • Unsteady aerodynamic performances of the prototype can be reflected more accurately. [ABSTRACT FROM AUTHOR]

Wind power is a critical source of renewable energy, but the variability of wind speed can impact the efficiency and reliability of wind power generation. To improve the accuracy of wind speed prediction, this paper proposes a novel system that combines deep learning and decomposition algorithms based on ensemble optimization methods. Firstly, the paper proposes an innovative hybrid modal decomposition (HMD) method that extracts accurate features from wind speed data using Singular Value Decomposition (SVD), modal number selection method, and Variational Mode Decomposition (VMD). Secondly, the variable screening method identifies relevant factors affecting wind speed as fixed inputs. Then, the stationary test method is used to identify the sequences of different features in the mode and establish different prediction models: a bidirectional long-term short-time neural network model (Bi-LSTM) model optimized by artificial hummingbird algorithm (AHA) is used for non-stationary sequences; an ARIMA model is used for stationary sequences. Data from Sotavento and Changma wind farms are used to test this forecasting system. Simulation experiments are carried out from multiple dimensions. The results show that all error indicators are significantly improved, and the proposed prediction system is better than other comparative forecasting schemes. • The research can be practically applied in the field of wind power generation. • The research can help improve the energy utilisation of wind power generation. • A new data decomposition algorithm called HMD is proposed. • A new prediction system based on ensemble optimization idea is proposed. • Combining AHA-optimized neural networks and ARIMA to predict wind speed. [ABSTRACT FROM AUTHOR]

As installed wind power capacity continues to rise, the cost of onshore wind power generation in China has fallen, far exceeding the world average. The purpose of this study is to explore the main factors affecting onshore wind power in China and to identify ways to reduce costs. So as to reduce the cost of wind power and promote the large-scale grid-connected use of wind power. Therefore, this paper summarizes various factors that affect the development of onshore wind power. We also provide a comprehensive and repeatable MFLC (multi-factor learning curve) method to evaluate the factors affecting the cost of onshore wind power. Subsequently, the learning rates of various factors are calculated using this method. The results show that empirical learning by increasing installed capacity/generation, improving technology and selecting sites which are rich in natural resources, and appropriately reducing capital investment and material prices can significantly reduce the LCOE (levelized cost of electricity) of onshore wind power in China. Compared with wind power giants of the United States and Germany, the reduction in the cost of onshore wind power generation in China is more dependent on inputs such as capital investment and raw materials, while experience plays a relatively minor role. The ability to make full use of natural resources and to convert wind energy into electricity more efficiently is crucial to reducing the cost of wind power. • This paper summarizes various factors that affect the development of onshore wind power. • A comprehensive and repeatable MFLC method is built in this paper. • The learning rates of various factors are calculated. [ABSTRACT FROM AUTHOR]

The smooth operation of the power system imposes high requirements on wind power forecasting. Given the forecasting challenges brought by the coexistence of strong and weak disturbances in wind power data, this paper proposes a hierarchical anti-disturbance mechanism to raise the accuracy of single-point wind power prediction. In the first-level disturbance processing, we prioritize the treatment of strong disturbances in wind power data through a dual-branch multi-source fusion prediction structure. The wind power subsequences with distinct time–frequency characteristics are divided into two sets, processed by the stationary set prediction branch and the drastic set prediction branch, respectively. For the drastic set, we incorporate microenvironmental multi-source data surrounding the wind turbine as input and propose a parallel-structured attention fusion module CA (Convolution attention fusion block) to provide effective data support for the prediction module, then extract rich fusion features through deep temporal LSTM algorithm and ultimately achieve fine-grained forecasting. For weak disturbances that have not been adequately addressed in the previous step, we conduct a secondary treatment through error correction strategy. By employing the hierarchical processing approach, this paper accomplishes a comprehensive handling of disturbances with different intensities. Experimental results on four data sets show that the proposed model DEWFM (Dual-branch and error correction wind power forecast) demonstrates remarkable performance advantages in comparing with the baseline model and other advanced models, the average values of MAE reaching 1.679, revealing the effectiveness of the proposed method in enhancing the precision of short-term wind power prediction. • Present a method to address the uncertainty in short-term wind power prediction. • A time–frequency hybrid prediction, differentially processing subsequences. • Enhanced LSTM with a multi-source data fusion mechanism for fine-grained prediction. • Error correction handles residual weak disturbances, enhancing prediction accuracy. • The performance evaluation shows the superiority of the proposed model. [ABSTRACT FROM AUTHOR]

Nowadays, climate change is a major global societal challenge that significantly increases environmental stress. Most international organizations and policies have promoted initiatives to minimize emissions, reduce fossil fuel dependence and increase renewable energy resource integration into different sectors. An energy transformation towards more renewable systems is thus a priority. Under this scenario, the present paper describes and evaluates an alternative energy conversion matrix-based model to combine sector electrification, power generation units from renewables, and new clean technologies. The proposed green matrix-based model allows analyzing future scenarios, including electricity participation in end-use consumption and electric power generated by renewables – potentially integrated into different sectors –. The proposed model is evaluated in the state of Maine (United States). This case study is focused on decarbonizing both residential heating and transport sector through the integration of large offshore wind power plant. Results and discussion is also included in the paper, providing expected energy demand reductions and decreasing emissions through the integration of renewables. This energy transition integration case study is proposed in three road-maps with different penetration rates and time scales. The proposed green matrix-based model can be also applied to other areas and energy resources, as an alternative way to analyze and estimate renewable integration into different sectors. • Green Electrical Matrix to link electricity supply and end-use for energy transition. • Assesses renewable potential and electrification tech for end uses, e.g., transport. • Applies model to Maine, USA to show reductions in fossil fuels and emissions. • GIS and MCDM for optimal offshore wind location, maximizing electricity generation. • Short, medium, and long-term projections of renewable integration into energy system. [ABSTRACT FROM AUTHOR]

Currently, wind power prediction has so many problems in the ultra-short-term time scale (0–4h), which is difficult to improve the deterministic prediction and probability prediction accuracy of the wind farm cluster because it can not fully explore the spatio-temporal correlation between the physical change process and the wind farm. In this paper, a method of ultra-short-term deterministic and probability prediction of wind farm cluster power based on Graph Convolutional Network (GCN) considering fluctuation correlation (FC) is proposed. Firstly, the adjacency matrix is constructed based on the power sequence fluctuation information of each wind farm, and the GCN is designed. Secondly, the spatio-temporal features of power and Numerical Weather Prediction (NWP) wind speed are extracted and fused based on the network model of dual-channel and dual-adjacency matrix. Thirdly, in order to effectively improve the prediction accuracy, a trend switching mechanism is designed based on the effective trend of NWP. When the fluctuation information of NWP is not accurate, the graph structure is constructed by the adjacency matrix based on geographical location to achieve effective prediction. Finally, the method proposed in this paper is applied to wind farm clusters in three provinces of China, compared with some commonly used methods, the average RMSE is reduced by 1.34 %, 1.62 %, 2.07 %, respectively, and the average CWC is reduced by 6.12 %, 4.49 %, 6.62 %, which verifies the effectiveness of this method. • A method for calculating FCC is proposed. • Combined with FCC, the graph structure of wind farm cluster is constructed. • A two-module GCN is designed. • A trend-switching mechanism is designed. [ABSTRACT FROM AUTHOR]

Wind speed prediction is a crucial aspect in the utilization of wind energy. In this paper, a wind speed prediction model based on an outlier-robust ensemble deep random vector functional link network (ORedRVFL) and arithmetic optimization algorithm-optimized variational mode decomposition (AOA-VMD) is designed. First, the penalty factor and the number of mode decompositions of VMD are optimized using the AOA algorithm and the original data are decomposed using the optimized VMD. Then the decomposed data is predicted using the ensemble deep random vector functional link network (edRVFL) model. The edRVFL uses rich intermediate features for the final decision, which can make the final result closer to the real data. In order to strengthen the anti-interference ability to the outliers, this paper robustly improves the edRVFL model, and the improved model is called ORedRVFL. ORedRVFL reduces the impact of outliers by introducing regularization and norm to balance the relationship between training error and weights. The experiments have proved that the model proposed in this paper outperforms other models in terms of anti-interference ability and prediction accuracy. • An outlier-robust edRVRFL prediction model is developed. • Use VMD to decompose the data and enhance the model prediction capability. • Fuzzy entropy is used as a criterion for data aggregation. • AOA optimizes the VMD hyperparameters to enhance the decomposition effect of VMD. [ABSTRACT FROM AUTHOR]

Carbon emission flow is an effective tool to obtain carbon emission distribution in power systems, which can guide the active carbon reductions of consumers through proper incentive schemes. With the increasing penetration of renewable energy, the existing single-valued carbon emission flow model based on deterministic forecasted power outputs cannot describe the impacts of renewable energy uncertainties on carbon flows. Therefore, this paper mainly focuses on the assessment of the probabilistic carbon emission flow through the power systems considering the impacts of load and renewable energy uncertainties. In this paper, the probabilistic carbon emission flow (PCEF) is innovatively proposed. With the PCEF, consumers can make better energy use plans considering their own risk appetites for carbon emission payment. Firstly, the impact factors of the PCEF are modeled, including load and renewable energy uncertainties and integrated carbon intensity of thermal plants. The uncertainties of load, wind power and photovoltaics are modeled based on a p-box method while the uncertainty of hydropower is modeled based on the multi-state model. Besides, the integrated carbon intensity model of thermal plants are proposed considering the carbon intensity variations during the operating, start-up, and shut-down stages. Furthermore, the probabilistic carbon emission evaluation framework is proposed to assess the probabilistic carbon distribution. In this framework, novel probabilistic carbon indices are defined to precisely characterize the carbon emission situation with probabilistic representations. A solution method based on an adaptive interval point estimation (AIPEM) algorithm is proposed to efficiently solve the developed evaluation problem. Tests on an IEEE-30 node system, and a real provincial power system in China validate the effectiveness and application of the proposed model. The results showed that the PCEF can be a useful tool for obtaining the probabilistic representation of carbon emission flow and guiding the consumers' active carbon reduction in power systems. • Probabilistic carbon emission flow is proposed considering multiple uncertainties. • Integrated carbon intensity model for thermal plants is developed. • A p-box model is used to describe the uncertainties of load and renewable energy. • PCEF can help consumers balance the cost and carbon risk when making decisions. [ABSTRACT FROM AUTHOR]

This paper proposes a distribution network fault emergency power supply recovery strategy based on 5G base station energy storage. This strategy introduces Theil's entropy and modified Gini coefficient to quantify the impact of power supply reliability in different regions on base station backup time, thereby establishing a more accurate base station's backup energy storage capacity model that can fully utilize the base station's energy storage resources to participate in the emergency power supply of distribution network faults. First, the optimal Copula function in each cycle is determined through the Akaike information criterion and squared Euclidean distance to establish a wind power-photovoltaic output scenario. Secondly, the traditional Gini coefficient is modified using the weighted average node degree and influence rate indicators. A comprehensive vulnerability model is established through the modified Gini coefficient and Theil's entropy indicators. Based on the comprehensive vulnerability model, a backup energy storage time model and a modified backup energy storage capacity model of the base station affected by power supply reliability are established. Thus, the callable energy storage capacity of base stations in different areas is obtained. Finally, a two-stage robust optimization model is introduced to minimize system operating costs to solve the volatility of 5G base station communications and wind-solar output, thereby establishing an emergency power supply recovery model for base station energy storage and wind-solar output. Simulated with the improved IEEE-33 node model, the results show that the proposed base station's energy storage model improves the utilization of the base station energy storage resources and, at the same time, effectively reduces the loss of load during the fault phase of the distribution network and improves the absorption of the PV output. • Modeling of 5G base station backup energy storage. Aiming at the shortcomings of existing studies that ignore the time-varying characteristics of base station's energy storage backup, based on the traditional base station energy storage capacity model in the paper [ 18 ], this paper establishes a distribution network vulnerability index to quantify the power supply reliability of the distribution network nodes by adopting the voltage Theil's entropy and the modified Gini coefficient. Based on the power supply reliability of power grid nodes and combined with load level weights, a model for the backup energy storage time of base stations affected by power supply reliability is established. • The model of 5G base station energy storage participating in power supply recovery In view of the impact of changes in communication volume on the emergency power supply output of base station energy storage in distribution network fault areas, this paper introduces a two-stage robust optimization model to deal with the uncertainty of communication volume. Based on the base station energy storage capacity model established in contribution (1), an objective function is established to minimize the system operating cost in the fault area, and the base station energy storage owned by mobile operators is used as an emergency power source to participate in power supply restoration. Establish sub-objective functions of the loss cost of base station energy storage charging and discharging, the subsidy cost of base station energy storage charging and discharging, and the base station energy storage operating cost to supplement the shortcomings of existing research. [ABSTRACT FROM AUTHOR]

The proper integration of wind power-driven grids relies heavily on a reliable balance between electricity production and demand. Therefore, accurate prediction is essential for planning and efficient operation of wind power systems to ensure their continuous supply. However, increasingly severe power quality disturbance (PQD) constantly disturbs this equilibrium, which affects the accuracy of wind power prediction to a large extent. For this purpose, this paper developed a novel optimization methodology to improve wind power prediction accuracy considering micro PQD dimension reduction and elimination for wind-storage integrated systems. A novel idea has been presented in this optimization methodology to eliminate the barrier of PQD and wind power prediction. In the micro aspect, a PQD dimension reduction and elimination strategy based on dynamic mode decomposition (DMD) and Wiener Filter (WF) is proposed to eliminate the autonomy of PQD. This elimination of autonomy allows the WF to get a higher signal-to-noise ratio (SNR). In the macro aspect, this paper takes PQD of different complexity into full consideration, and compares their effects on improving wind power prediction accuracy based on deep learning-based approaches. Through the experimental verification, it is confirmed that the proposed DMD-WF optimization method has demonstrated an effective dimension reduction and elimination of PQD. Moreover, it is found that the proposed PQD optimization method contributes to improve the deep learning-based prediction accuracy when PQD is more complex. The proposed methodology creates a novel perspective to improve the short-term wind power prediction accuracy, which provides a theoretical and methodological guidance for future development of large-scale integrated wind-storage systems. • Development of a novel methodology of PQD optimization and wind power prediction. • A Wiener Filter and dimension reduction-based PQD optimization method is proposed. • WOA-Attention-LSTM is used to analyze forecast accuracy based on PQD optimization. [ABSTRACT FROM AUTHOR]

With the large-scale EV connected into the wind power grid, the intermittent, fluctuating and stability bring rigorous challenges for power quality and dispatch, thus wind curtailment becomes more serious. This paper proposes an advanced multi-objective collaborative scheduling strategy to improve the accuracy of the predictable wind grid and ensure the stable operation of the grid by optimizing wind power and EV synergistically. Firstly, a hybrid power prediction method is proposed based on density-based spatial clustering applied to noise (DBSCAN) and partial least squares regression (PLSR) combined with long and short-term memory neural network (LSTM). It establishes a linear component prediction mode to predict the nonlinear wind power efficiently. Secondly, a multi-objective optimization scheduling model is established according to the predicted wind power, considering the vehicle-to-grid (V2G) characteristics of EV, grid load fluctuations, wind curtailment capacity, EV charging costs, and grid losses. The global control aims to achieve overall energy balance and optimize the charging and discharging of EV in a time dimension under constrained conditions. Additionally, based on the total number of EV charging and discharging determined by the global level control, a spatial scheduling optimization is conducted for EV and wind power by the distribution network control, with the goal of minimizing network losses in the distribution network system. Finally, through simulation and comparison of four scenarios, the results demonstrate that the proposed method achieves synergistic optimization of wind power and EV. This paper provides an efficient solution for the optimized scheduling of large-scale EV connected to the predictable wind power grid. • It can filter the noise data and reduce the disturbance of abnormal values. • The power prediction accuracy is improved obviously based on local actual wind power data. • It can optimize the charging and discharging of EV under constrained conditions. • The charging costs of EV users is decreased significantly. [ABSTRACT FROM AUTHOR]

In order to solve the security threat brought by the volatility and randomness of large-scale distributed wind power, this paper proposed a wind power prediction model which integrates two-layer decomposition and deep learning, effectively realizing the accurate prediction of wind power series with non-stationary characteristics. Initially, pearson correlation coefficient (PCC) is employed to identify primary meteorological variables as input series. Second, the wind power series are smoothed by implementing complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and then all subseries are decomposed and obtained by utilizing empirical wavelet transform (EWT) for the components with the highest complexity. Subsequently, hidden information related to wind speed, wind direction, and wind power series are extracted through the bidirectional temporal convolutional network (BiTCN), and the obtained information is fed into a bidirectional long short-term memory network (BiLSTM) optimized by attention mechanism for prediction. Finally, the predicted values of all components are summed to derive the final prediction results. In addition, the significant advantages of the prediction model in this paper are verified by five comparison experiments. The mean absolute error (MAE) and root mean square error (RMSE) of the model's one-step prediction in the January dataset are 2.1647 and 2.8456, respectively. • A new wind power prediction method based on signal decomposition and deep learning is proposed • CEEMDAN, EWT is used to decompose the original wind power signal • BiTCN, BiLSTM, Attention are used to predict the decomposed subseries [ABSTRACT FROM AUTHOR]

Wind power point and interval prediction plays an important role in dispatching. However, for obtaining both point estimations and prediction intervals (PIs), the existing models like constructing the probability density function are too complicated. This paper proposes a novel multi-objective upper and lower bound and point estimation (MOULPE) model. It constructs a neural network (NN) with double outputs to directly estimate the prediction intervals (PIs) and the median of PIs is calculated as point estimation. Considering wide decision-making space, the problem formulation of MOULPE is defined as three objectives which covers both evaluation indices of PIs and point prediction. Furthermore, based on elite opposition-based learning (EOBL), this paper improves non-dominated fast sort genetic algorithm-III (INSGA-III) to search the optimal front. Two criteria called prediction interval nominal confidence (PINC) and point prediction nominal error (PPNE) are adopted to pick out the best solution. According to the general requirements in literature, four examples of real wind power data are conducted. Compared with some state-of-the-art methods, the coverage probability of PIs constructed by the proposed model not only reaches the preset PINC, but the average width is also the lowest. Similarly, the point estimation error of the proposed method is less than PPNE. • MOULPE is proposed to obtain PIs and PP results through one RWNN. • Using the median of PI as the PP result in MOULPE to improve the optimization effect. • An improved NSGA-III is proposed for optimizing the weights of NN in MOULPE. • MOULPE can provide a set of decision schemes with different standards for operators. • The proposed MOULPE shows superiority on four real-world datasets. [ABSTRACT FROM AUTHOR]

Accurately predicting wind and photovoltaic power is one of the keys to improving the economy of wind-solar complementary power generation system, reducing scheduling costs and no-load losses, and ensuring grid stability. However, the natural properties of energy result in complex fluctuations in their corresponding power sequences, making accurate predictions difficult. Therefore, this paper proposes an intelligent prediction system that combines decomposition algorithms and deep learning for ultra-short-term prediction of wind and photovoltaic power. First, an improved decomposition algorithm is proposed, based on fuzzy entropy's property that its value increases with the increase of sequence uncertainty, particle swarm optimization (PSO) is used to search for the optimal parameter combinations of variational modal decomposition (VMD), so that it can automatically adjust the parameters for energy data with different characteristics to reduce the human error. Then, a convolutional neural network (CNN) architecture that balances operational efficiency and prediction performance is constructed, and the hyperparameters of the CNN are optimized using the wild horse optimization algorithm (WHO) to improve the stability and accuracy of the prediction model. In this paper, real data from wind power plants and photovoltaic power plants in China are used as experimental objects, and experiments are carried out in three aspects, namely, benchmark model selection, decomposition algorithm comparison and combined model comparison. The results show that selecting CNN as the benchmark model is a good choice; the improved VMD has better decomposition performance than other state-of-the-art decomposition algorithms. The system proposed in this paper is highly generalizable and adaptive, and its prediction performance and accuracy greatly outperform that of other comparative models, with prediction accuracies improved by 72% and 79%, respectively, compared to a single CNN model. • The hyperparameters of VMD are determined by using PSO based on fuzzy entropy. • Optimize convolutional neural network using the wild horse optimization algorithm. • The intelligent prediction system can accurately predict wind power and PV power. • Experiments based on power data from actual wind farms and PV plants. • A deep learning prediction method applied to wind and solar complementary systems. [ABSTRACT FROM AUTHOR]

Wind power prediction technology is important for building novel power systems with a high proportion of renewable energy. The quality of Numerical weather prediction (NWP) has a significant impact on the accuracy of ultra-short-term wind power prediction (USTWPP). However, existing NWP do not reflect the adaptability of different weather processes, because of it' s forecasting errors. In view of this, this paper proposes an USTWPP method based on NWP wind speed correction and division of transitional weather process. The combined prediction method was first used to correct the NWP wind speed, and then we use the double clustering method to divide the transitional weather processes to establish a model for USTWPP based on different scenarios, the overall method was finally applied to a wind farm in west inner Mongolia, China. Compared to the pre-correction, the wind speed forecasted RMSE was reduced by 1.702 and the MAE by 1.366. Based on the wind power ultra-short-term prediction method proposed in this paper, the average reduction in RMSE is 5.93% and in MAE is 4.82% compared to the various comparison methods in the four seasons. The USTWPP method combining wind speed correction and double clustering division of transitional weather scenarios can significantly improve accuracy of USTWPP. • Propose a new NWP correction mechanism to improve the NWP forecasted errors. • Propose a multiple clustering method to improve the wind power prediction accuracy. • Propose weighted evaluation indicators of sequential and non-sequential clustering. • It provides new ideas for wind power prediction under different weather scenarios. • Proposed power prediction idea reduces the RMSE and MAE on average 5.93% and 4.82%. [ABSTRACT FROM AUTHOR]

Accurate wind speed forecasting ensures the controllability for the wind power system. In this paper, a structure with density-weighted active learning (DWAL)-based model selection strategy from the perspective of meteorological factors is proposed to improve the accuracy and stability for wind speed deterministic and probabilistic forecasting. To improve training efficiency and accelerate the sample selection process, DWAL is employed. The multi-objective flower pollination algorithm is used to combine best models selected from model space with optimal weights for higher accuracy and stability. Except deterministic forecasts, as large-scale wind power generation integrated into power grid, the wind direction should also be forecasted and the estimation of the wind speed and direction uncertainty is vital, offering various aspects of forecasts for risk management. Thus, both deterministic and probabilistic forecasting for the wind speed vector are included in this paper. Eight datasets from Ontario Province, Canada, are utilized to evaluate forecasting performance of the model selection and the proposed structure. Results demonstrated: (a) the proposed structure is suitable for wind speed vector forecasting; (b) the proposed structure obtains more precise and stable forecasting performance; (c) the proposed structure improves the accuracy of deterministic forecasting and provides probabilistic information for wind speed vector forecasting. • Propose a novel forecasting structure based on meteorological analysis. • The model selection is employed. • The multi-objective flower pollination algorithm is used. • Density-weighted active learning algorithm is applied. • Both deterministic forecasting and probabilistic forecasting are applied. [ABSTRACT FROM AUTHOR]

In co-scheduling of the integrated electrical energy and natural gas systems with high penetration of renewable energy sources, it is vital to have flexible resources to handle uncertainties, viz., continuous wind uncertainty and discrete equipment failures. Accordingly, this paper evaluates the effectiveness of electrical grid flexibility, i.e., optimal grid reconfiguration (OGR), on the scheduling plan of both energy systems. Also, to characterize the continuous/discrete uncertainty sources, this paper aims to develop a new computationally-efficient hybrid stochastic/IGDT (HS-IGDT) optimization framework for the co-scheduling of electrical energy and natural gas systems. Finally, the IEEE Reliability Test System with ten-node gas transmission system have been analyzed to show the efficiency of the proposed framework. • The co-operation of integrated electric and natural gas systems is modeled. • Continuous–time model is developed to capture sub-hourly variations of wind energy. • Responsive demands are used to increase penetration of wind energy sources. • Fuzzy-based IGDT method is proposed to model the uncertainty of wind energy. [ABSTRACT FROM AUTHOR]

in recent years, large-scale electric vehicles connected to the power grid has a significant impact on demand-side resources. In addition, the vehicle-to-grid technology of electric vehicles introduces more uncertainties, which brings great challenges to the optimal scheduling of integrated energy systems. To solve this problem, this paper fully considers the uncertainty and fluctuation of wind power. Firstly, the objective function of joint configuration is constructed to maximize the utilization of wind power and minimize the planned generation cost of the system. Secondly, the linearized power flow equations are used to represent the relations among the state variables, and the second-order cone relaxation method is applied to deal with the branch power flow constraints, which is transformed into a solvable mixed-integer second-order cone programming model. Finally, the validity of the model is verified by an example. The system achieves obvious peak-shaving and valley-filling effect and improves the economic benefit of the system. • The load characteristics and energy storage characteristics of the electric vehicle fully absorb the wind energy. • The proposed second-order cone optimal dispatching strategy realizes the supplementary supply of grid and renewable energy. • The optimal dispatching strategy provides theoretical support for the efficient operation of grid. [ABSTRACT FROM AUTHOR]

Wind prediction is of great significance for wind energy utilization due to the stochastic nature of wind. To effectively facilitate various downstream decision-making tasks such as wind turbine control, predictive wind Scenario Generation (SG), which is capable of providing a set of deterministic instantiated wind prediction results, plays a critical role. In this paper, a novel Graph neural networks-based Adaptive Predictive Generative Adversarial Network (GAPGAN) model is proposed for accurate prediction of short-term future scenarios of a wind field. In GAPGAN, the original multivariate time series data are first reconstructed into the form of a graph, and spatiotemporal features are then extracted using Graph Convolutional Networks (GCNs). Next, a predictive generative adversarial network (PGAN) framework is proposed, which could generate different outputs corresponding to given historical observations as conditions. Finally, an adaptive PGAN training mechanism is introduced to stabilize the training process, and the best SG model is selected based on the proposed comprehensive evaluation system. Based on wind speed data collected from 11 wind turbines, computational experiments validate that the GAPGAN outperforms five benchmarking models in terms of point prediction accuracy, shape similarity, uncertainty prediction quality, and prediction scenario diversity. • Propose a GCN-based adaptive predictive generative adversarial network (GAPGAN). • Employ a novel evaluation framework to assess the generated wind speed scenarios. • Incorporate both temporal and spatial features in the wind speed scenario generation. • Balance both the accuracy and the diversity of the generated wind speed scenarios. • Validate the proposed GAPGAN using real wind farm data. [ABSTRACT FROM AUTHOR]

Offshore wind and wave energies are both important and abundant renewable energy resources. Offshore wind turbines have entered the commercial phase, while wave energy converters are far lagging behind. Combined wind and wave energy conversion system have been proposed and investigated in recent years, to effectively use the ocean space and energy by sharing infrastructures. In this review paper, global wind and wave resources and the potential for combined use are firstly discussed, then various types of combined wind-wave systems are summarized with a new categorization method proposed. Then, a review on conceptual developments and synergies of combined systems based on the new categorization is elaborated on. Numerical methods used in the combined concepts are summarized with a special discussion on control strategy, extreme load effects and survivability. Model testing techniques are also discussed, highlighting the issues due to scaling laws. The economic aspects of the combined system are also discussed with a case study. • A review of global wind and wave energy resources with assessment techniques. • A review on types of combined wind-wave systems, with a new categorization method proposed. • A review on conceptual developments and synergies of combined systems with promising configurations recommended. • Numerical methods and model testing techniques for the combined concepts. • The economic aspects of the combined system. [ABSTRACT FROM AUTHOR]

Wind power has quickly developed in the world owing to the advantages of pure, inexpensive, and inexhaustible. However, strong volatility, unmanageable, and randomness make it difficult to achieve secure wind power generation. An excellent wind power prediction is effective for power system scheduling and safely stable operation. Vision Transformer (ViT) model is introduced for building a connection of the extracted characteristics and desired output. Long-short term memory (LSTM) is combined with ViT, and a new wind power forecasting model is proposed in this paper. For the proposed LSTM-ViT model, the temporal aspects of the weather data and correspondence properties are extracted based on LSTM. The link of the output and characteristic is established in view of the ViT, and the multi-headed self-attentiveness mechanisms in ViT fully exploit the relationship between the inputs. The validity and sophistication of the LSTM-ViT method are validated by the climate statistics and statistics of wind power. The results indicate that the wind power forecasting model is provided with higher prediction accuracy. The forecast results for the fourth quarter are used as analysis cases. The root mean square error of the method is reduced by 41.77%, 16.60%, 28.72%, 26.81%, and 16.25% compared to gate recurrent unit (GRU), LSTM, ViT, convolutional neural network (CNN)-ViT, and GRU-ViT respectively. The mean absolute error of the LSTM-ViT method in the first quarter is 0.327, with model comparison values reduction of 33.71%, 38.30%, 32.99%, 17.63% and 10.65% respectively. • A novel model called LSTM-ViT is proposed for ultra-short term wind power forecasting. • ViT model is introduced for building a connection of the extracted characteristics and desired output. • The multi-headed self-attentiveness mechanisms in ViT fully exploit the relationship between the inputs. • The complex nonlinear relationships are considered in the proposed model. [ABSTRACT FROM AUTHOR]

Accurate and robust wind power forecasting (WPF) is great significance to ensure the safe and stable operation of the power system and promote the transformation of low-carbon energy. However, the high randomness and intermittency of wind power bring great challenges when designing reliable forecasting models. In this paper, a novel spatial-temporal attention graph convolutional network model is proposed. Firstly, the spatial attention mechanism is used to aggregate and extract the spatial correlations of the raw wind power data. Secondly, the temporal attention mechanism is applied to capture the temporal correlations. Then, the extracted spatial-temporal correlations were put into the temporal convolution network and the spatial convolution network to further obtain the temporal and spatial dependencies. Finally, the wind power forecasting results is output through the full connection layer. The proposed method is verified by using wind power data from real wind farm in China. The experimental results reveal that the proposed depth spatiotemporal prediction model has more significant advantages than other advanced models in terms of prediction accuracy and stability. • The spatiotemporal attention mechanism is used to learn the dynamic spatiotemporal correlations. • The spatiotemporal convolution mechanism is applied to enhance feature extraction of wind power. • The proposed model can improve the accuracy of wind power prediction by experiments. • Real datasets from wind farm in China is employed for the modeling study. [ABSTRACT FROM AUTHOR]

With the continuous global increase in installed wind power capacity and subsequent surge in power generation, the contradiction between the safe operation of the grid and the efficient consumption of new energy after large-scale grid connection has become increasingly prominent. This paper presents a hybrid model prediction method to further improve the stability and accuracy of wind power prediction. Firstly, variational modal decomposition (VMD) optimized by the coati optimization algorithm (COA) is employed to decompose original wind power, mitigating the non-stationary characteristics of the power sequence. Subsequently, permutation entropy (PE) is used to recombine the decomposed components, and the combined feature selection method is achieved by integrating the Spearman correlation coefficient (SCC) and the autocorrelation function (ACF). Then, the multivariate combined model is constructed, and the improved multi-objective coati optimization algorithm (IMOCOA) determines the weight coefficients of each model to enhance the performance of the hybrid model. Finally, research and analysis are conducted from multiple scenarios and time scales using historical operating data from a wind farm in Xinjiang. The experimental results show that the proposed prediction model effectively improves the accuracy and stability of the wind power prediction compared with other popular prediction models. • A new hybrid model is proposed to implement wind power prediction. • An improved multi-objective coati optimization algorithm is introduced. • A combined feature selection method is presented. • A new weight coefficients determination method is proposed. [ABSTRACT FROM AUTHOR]

Wind power and pumped storage combined system (WPCS), as an entity integrates multiple energy sources, can provide a reliable overall power supply by optimizing the management of available resources, helping to combat the serious climate change challenges. In order to address the participation of combination system in multiple market operations and multiple uncertainties, this paper proposes a joint declaration strategy for WPCS to participate in the electricity market (EM) and frequency regulation market (FRM). Firstly, the trading mechanism is developed for WPCS to collaborate in power markets. Secondly, a joint declaration and dispatching strategy decision-making model of WPCS is constructed, and the uncertainty of market prices and wind power output in the model is processed by using the information gap decision theory-distribution robust optimization (IGDT-DRO) technique. Finally, simulations implemented on an actual WPCS are delivered to show that: 1) WPCS achieved an expected profit by 8.79% and decrease deviation penalty costs by 58.81% through multi energy complementary operation. 2) Compared with the single market, WPCS can increase the expected profit by 77.5% in the joint declaration of multi-markets.3) IGDT-DRO technology can simultaneously manage the uncertainty of both price and electricity. When the sample size increases tenfold, the runtime increases by less than 40%, which has advantages in data-driven and stable runtime. [Display omitted] • A synergistic trading mode of electric energy and frequency regulation markets is designed. • A declaration-dispatching strategy for wind power and pumped storage participating in EM andFRM is constructed. • The IGDT-DRO technique is used to deal with the uncertainty of market price and wind power generation. • The characteristics of IGDT-DRO model in data-driven feature, non-conservative result and stable run time have been proved. [ABSTRACT FROM AUTHOR]

Cross-regional energy sharing is a promising way to alleviate the imbalance in energy distribution. However, there is a risk that the uncertain fluctuations of intermittent renewable energy sources (RES) could be transmitted across regional transmissions, resulting in large-scale system economic inefficiency and security concerns. To this end, a unified spatial-temporal cooperative framework for the integrated energy system, which considers the coordination between intra-regional multi-energy coupling and cross-regional multi-agent-system energy sharing, is proposed in this paper. First, in the temporal dimension, a multi-time-scale stochastic decision-making model is established based on stochastic model predictive control (SMPC). Thus, slow-response units are arranged to gain economic goals in day-ahead stage and the closed-loop rolling adjustment is implemented on fast-response units to achieve accuracy supply-demand balance in real-time stage. Second, in the spatial dimension, a fully distributed dispatch approach is adopted to address the information sharing barriers, which only requires neighboring information and considers consistency of boundary control variables on border lines. Finally, to improve the computational efficiency, the established complex time sequential model is decomposed into a set of time-discrete parallel sub-problems, using the optimal condition decomposition (OCD) technique. Simulation results on a cross-regional test system demonstrate that proposed framework can increase the wind power consumption capacity and reduce operation cost through cross-regional cooperation, while the parallel decomposition can save 67.25 % of the computation time relative to the serial computation. • A novel unified spatial-temporal cooperative dispatching framework is proposed for the cross-regional IES. • A multi-time-scale rolling stochastic decision-making model is established to handle RES uncertainties. • The ADMM is implemented to achieve cross-regional rapid interactions iteration with only neighboring information. • The OCD is applied to decompose the complex spatial-temporal problem. [ABSTRACT FROM AUTHOR]

Digital twins are digital models that operate within the digital space to perform specific functions. It can positively impact the physical counterpart in terms of improved efficiency, reduced costs, increased safety, and reliability. However, most existing research has limited digital twins to a single digital twin model, and the inherent characteristics and practical applications of single digital twin models make it challenging to fully utilize their advantages in complex and dynamic environments. Therefore, this paper proposes the concept of a multi-digital twin (MDT), as well as its synergistic operation mechanism, and designs two specific implementation methods suitable for processing time series-related tasks: the single metric dynamic preference method and the multi-metrics dynamic fusion method both based on a time window. Then, the results of two experiments show that the average relative improvement of two methods in the MAE, RMSE, and R2 metrics were 7.83 %, 5.01 %, and 1.24 % in 2015, and 4.98 %, 2 %, and 0.29 % in 2017. This means that the proposed methods can improve the accuracy of wind power forecasting. The effectiveness of the MDT synergy operation mechanism is verified, providing new research ideas for digital twins to adapt to complex system changes. • The concept of multi-digital twin is defined, which utilizes the information generated by many single digital twins. • The synergistic operation mechanism for multi-digital twin is proposed, and two methods are designed. • Four single digital twin models were constructed for wind power forecasting task. • Two experiments show that the rational application of multi-digital twin can improve the wind power prediction accuracy. [ABSTRACT FROM AUTHOR]

Accurate total wind power forecasting is essential to wind farms. Conventional methods predict each wind turbine separately, which fails to exploit the spatial correlation between turbines and causes error accumulation through summation. Additionally, numerical weather prediction (NWP) with limited spatial–temporal resolutions is difficult to assist in power forecasting effectively, resulting in decreased performance as the forecasting steps increase. To address these drawbacks, a novel "N encoder-1 decoder" multi-channel fusion group forecasting sequence-to-sequence (seq2seq) architecture with wind resource quality assisted spatial attention (WRQASA) and NWP correction (NWPC) is proposed in this paper. The encoders in the architecture extract the temporal features of each turbine, followed by WRQASA adaptively adjusting their impact on the decoder. NWPC constructs micro-scale meteorological data based on its large-scale counterpart. The decoder takes the output from WRQASA and NWPC, and predicts the total power of the turbine group. The model is evaluated on a real-world wind farm. Ablation studies revealed the effectiveness of the novel architecture, WRQASA and NWPC. In 12, 24, 36 and 72-h multi-step forecasting scenarios, the new method outperformed conventional methods, such as seq2seq, light gradient boosting machine and support vector regression, achieving a more effective prediction of total power. • A multi-channel seq2seq for wind farm's total power prediction is proposed. • Wind resource quality assists self-adjusting each turbine's impact on final output. • Downscaled weather prediction improves wind power forecasting performance. • The common issue of declining performance as prediction steps increase is tackled. [ABSTRACT FROM AUTHOR]

The uncertainty of wind power (WP) poses a significant challenge to power systems with a high percentage of WP. Accurate WP forecasting is an important approach to mitigate this issue. With the increasing demand for electricity, some wind farms (WFs) have been built or expanded. Such WFs lack abundant historical data for establishing forecasting models, i.e., data scarcity. This paper proposes a novel method for very short-term probabilistic forecasting based on transfer learning (TL) and conditional screening for WP. Utilizing numerical weather prediction as predictive features to address deterministic forecast data scarcity. Considering the data orientation, combining bidirectional long short-term memory with attention mechanisms to enhance prediction accuracy. Based on TL and conditional screening, it achieves data completion and singular value filtering to enhance the comprehensive performance of probabilistic forecasting errors. Using real world data, the proposed WP forecasting model reduces MAPE by at least 0.87% and RMSE by at least 0.6483 compared to the benchmark at different forecast steps. The comprehensive performance of probabilistic forecasting improves by at least 1.9134 at different forecast steps and confidence levels. The results indicate that the proposed forecasting model for data scarcity WFs is feasible, providing new insights for data scarcity WF forecasting. • A model tackles data scarcity via transfer learning-based probabilistic forecasting. • Proposed conditional strategy, easing width-coverage conflicts in forecasting. • Incorporates BiLSTM with AM for accurate, very short-term forecasting. • Validated model with real-world wind farm data, displaying robust performance. [ABSTRACT FROM AUTHOR]

Accurate wind speed prediction is crucial for effective wind power grid integration and energy dispatching. Recent research has explored the combination of decomposition algorithms with forecast models to form hybrid models, aiming to enhance wind speed prediction accuracy. However, these traditional decomposition techniques often lead to high time costs in practical applications, as they require new wind speed sequences to be appended to historical long sequences for decomposition before entering the forecast model. To overcome this challenge, this study introduces and improves the Autoformer model, applying it for the first time to long-term univariate wind speed forecasting. By incorporating decomposition technology as a sub-module of the forecast model, Autoformer not only solves the high time cost issue found in conventional hybrid models but also retains the benefits of decomposition technology in time series processing.Furthermore, in this paper, the decomposition module of Autoformer is replaced with the Mixture of Expert Decomposition Module (MOEDecomp) to better extract complex trend elements of wind speed series. Combined with the auto-correlation mechanism, sequential attention is paid to wind speed for extracting time dependencies in long series. Additionally, the Wavelet Soft Threshold Denoising (WSTD) algorithm is utilised for noise reduction in wind speed sequences. To evaluate the model's performance, two multi-step forecasting strategies were employed to predict wind speeds for the forthcoming 24, 48, 72, 96, and 120 h using four datasets. Experimental results demonstrate that the proposed model surpasses 15 comparative models in terms of prediction accuracy, generalization ability, and handling uncertain data. • Introduces and enhances the Autoformer model for wind speed prediction, replacing its original decomposition module with the MOEDecomp. • Develops the MOEA model, integrating the decomposition techniques as a model sub-module, resolving high time cost issues prevalent in real-world hybrid model applications. • Effectively mitigates noise impact in wind speed predictions using the Wavelet Soft Threshold Denoising (WSTD) algorithm, enhancing prediction accuracy. • Through experimental analysis, compares two multi-step forecasting strategies to identify the most suitable approach for univariate wind speed prediction. • Offers a novel, efficient approach to long-term wind speed prediction, overcoming the high time costs associated with traditional hybrid models. [ABSTRACT FROM AUTHOR]

With the increase of wind power installed capacity, wind energy is playing an increasingly important role in power grids. However, this also aggravates the volatility of a power grid. Accurate wind power prediction is particularly important for grid dispatching and grid connection modes. However, the existing forecasting methods mostly consider the meteorological environmental factors and historical power data and do not consider the impact of wind turbine generator parameters. Therefore, this study proposes a double-layer Shared Weight Long Short-Term Memory Network (SWLSTM) prediction model based on manifold learning considering meteorological environment factors, wind turbine generator parameters, and historical wind power. First, 17 indicators such as meteorological environment factors and wind turbine parameters are determined as influencing factors to construct high-dimensional data sets. Second, manifold learning is used to reduce the dimension of high-dimensional data sets and determine the best dimension reduction. The data after dimensionality reduction and historical wind power are used as the input of the prediction model. Finally, considering the influence of errors on the prediction results, a double-layer SWLSTM prediction model is constructed. The double-layer model is constructed simultaneously, and the final power prediction result is obtained by adding the prediction error of the lower model and the prediction wind power of the upper model. Moreover, a wind farm in Xinjiang is used to verify the effectiveness of the proposed prediction model. The results show that the prediction strategy and the model proposed in this paper have high prediction accuracy. • Meteorological and wind turbine parameters are chosen as influencing power factors. • Manifold learning is used to reduce the dimension of high-dimensional input data. • A Double-Layer SWLSTM prediction model is proposed to predict wind power. • The proposed forecasting model has lower prediction errors and more robust. [ABSTRACT FROM AUTHOR]

Abstract One possible contender to replace conventional reverse osmosis schemes is an energy solution where inexhaustible resources work together with a reverse osmosis plant. Based on the experience of an existing wind-powered desalination scheme run for more than 15 years by Soslaires Canarias S.L., the final objective of this paper is to propose improvements to the scheme so as to achieve a reduction in the cost of water (through restrained capital expenses) for the sake of greater feasibility and efficiency. The cost of the scheme is evaluated assuming a combined use of a reverse osmosis desalination plant and wind energy, using, for this purpose, the (exclusive) information provided by the industrial partner. Results showed that by carrying out the actions suggested in this paper, this scheme would be able to reduce its cost of water (COW) by about 0.022 EUR per cubic meter for the current LCOE of wind turbine technology in the study area (about 6 c€/kWh for the southeast of the island of Gran Canaria, Spain). This would mean that with an additional total capital investment cost of 196 000 € (from the current scheme of Soslaires Canarias S.L.), and supposing an average membrane life expectancy of 10 years for the current state-of-the-art membranes, a net present value of 74 360.95 €, a profitability index of 1.3794, and a 224.4881% internal rate of return would be achieved. Graphical abstract Typical cost structure for RO seawater desalination. Image 1 Highlights • Several configurations of desalination plants based RES have been simulated. • Cost of water has been considered as the central element of the evaluation. • In case of carrying out the actions suggested COW would be reduced. [ABSTRACT FROM AUTHOR]

Abstract Wind energy is the intermittent energy and its output has great volatility. How to accurately predict wind power output is a problem that many researchers have been paying attention to and urgently need to solve. In this paper, a deep belief network (DBN) model is developed for wind power forecasting. The numerical weather prediction (NWP) data was selected as the input of the proposed model and the data directly affects the prediction precision. The NWP data and wind data in the wind farm have the similar characteristics. Therefore, in this paper the k -means clustering algorithm was joined to deal with the NWP data. Through clustering analysis, a large number of NWP samples, which has the great influence in forecasting accuracy, are chosen as the input of the DBN model to improve the efficiency of the model. The DBN model was validated by the Sotavento wind farm in Spain. The results of DBN forecasting were compared with those of Back-propagation neural network (BP) and Morlet wavelet neural network (MWNN). The results show that the forecasting error of DBN model was mostly at a small level, and the forecasting accuracy of the proposed method outperforms BP and MWNN by more than 44%. Highlights • Deep belief network is applied in wind power forecasting. • The seasonality of historical samples is taken into account in this paper. • The instability and complexity of input data is reduced using k -means cluster approach. • The outperformance and depth feature extraction capability of the proposed method were proved. [ABSTRACT FROM AUTHOR]

Abstract The transition to a 100% renewable energy system based on variable renewable energy raises technical but also institutional questions. The smart energy system concept integrates variable renewable energy by addressing the technical challenges through the integration of different energy sectors, but integration of variable renewable energy also entails a change in the cost structures, especially related to electricity. The effect of this change in cost structures on market prices is investigated. This is done through simulation of a 100% renewable energy system that utilises a large degree of cross-sector integration but maintaining the current electricity market structure. The paper uses a 100% renewable energy system scenario for a 2050 Danish energy system. This is reflected in the use of wind energy as the primary renewable energy source. It is concluded that the current electricity market structure is not able to financially sustain the amounts of wind power necessary for the transition to a 100% renewable energy system. Since earlier research shows that neither electricity production costs nor the total system costs is higher for the renewable path than the fossil-based alternatives, the conclusion in this paper points towards a need for reshaping the institutional structure of electricity trade. Highlights • Calculates electricity prices in a renewable energy system with current market design. • Calculates private profitability of wind power investments within such system. • The market design cannot financially sustain wind power in a renewable energy system. [ABSTRACT FROM AUTHOR]

Abstract A shortage of gas supply renders gas expensive and may even cause power outages. Estimation of the failure probability of gas supply is an essential component of an integrated energy system. To ensure that failure probability estimation is relevant to an actual project, energy network constraints should be fully considered in calculations. Here, this paper develops a second-order reliability estimation method to cope with the nonlinearity caused by network constraints. Under conditions of integrated energy supply, correlations exist between the extremes of wind power, the heat loads, and failure of the natural gas supply. This paper illustrates the proposed method by comparing the results to those of other methods. The proposed method is efficient in terms of both accuracy and computational time. Compared to a mixed algorithm, which required 1101.1 s to simulate tens of thousands of samples, the proposed method takes 3.5 s to obtain a failure probability. Also, the proposed method improves accuracy by at least 10-fold compared to that of a first-order reliability method. Highlights • This paper presents the gas supply problems for an integrated energy system. • Practical engineering problems are investigated in China and the United States. • The stochastic behaviours of gas supply deliverability are considered. • The dependencies between extreme wind power, heat loads and gas supply deliverability are modelled. • The application of the proposed method is illustrated using an ideal integrated energy system. [ABSTRACT FROM AUTHOR]

This paper describes an approach to compute the maximum value of energy storage systems (ESS) in grid applications under uncertain energy prices. The value obtained is based on an optimal operation (consisting of charge/discharge sequences) of the ESS. In other words, it is the maximum value that may be obtained when the ESS charge/discharge sequence is adapted to the expected operational conditions. To obtain that optimal value, this paper describes a dynamic program approach, with the particularity that the switching decisions are optimized considering an uncertain price evolution and a dynamic calculation of the aging cost. A practical implementation of this approach is proposed, in which the problem is conveniently sliced into matrices corresponding to single decisions. It is shown that such an arrangement, combined with shift and re-indexing operators, provides a fast solution to the optimization problem consisting of a huge number of decision evaluations. The algorithm is then applied to a number of European electricity markets, with a particular focus on arbitrage. The particularities of the algorithm solutions are analyzed, and it is shown that not considering the imperfect foresight and the aging impacts leads to considerable errors in valuing an ESS. [ABSTRACT FROM AUTHOR]

The widespread use of fossil fuels has substantially contributed to global climate change. One of the most crucial ways to address climate change is to minimize carbon emissions in the energy sector. Power-to-Gas (P2G) technology provides a potential solution. In this context, this paper introduces a novel two-stage P2G planning method for the electric-gas coupling system, using carbon emission flow technology. The carbon emission flow model employed facilitates the distribution of carbon emissions across the entire energy network. Central to our planning strategy is the identification of nodes with reduced carbon emissions for the siting of P2G facilities, predicated on the premise that such nodes are indicative of significant renewable energy utilization. Constructing P2G systems at these particular nodes is strategically advantageous for augmenting renewable energy consumption. In the initial phase, a P2G siting planning methodology predicated on a low-carbon criterion is advanced, resulting in a definitive siting scheme. Subsequently, the second phase involves establishing a P2G capacity optimization model that seeks to strike an economic equilibrium between the utilization of surplus wind power and P2G operational investment. An enhanced pigeon optimization algorithm is employed to resolve the proposed model. Our method is verified by simulation. Compared with other conventional models, the accommodation capacity of renewable energy with the proposed method is enhanced, and the carbon emissions and operating costs of IES are also reduced. • This study introduces a new P2G station siting method centered on the carbon flow model. • The research establishes a P2G capacity planning model focused on cost-effectiveness optimization. • The novel P2G planning model addresses the economic balance between investment costs and the level of new energy absorption. • P2G two-stage planning strategy reduces the operating cost of the system and improves the low carbon of the system. [ABSTRACT FROM AUTHOR]

Accurate wind power prediction is significant to the stability of power system. Existing deterministic prediction methods unable to describe the uncertainty of wind power while both the point and probabilistic models have difficulty in tracking the abrupt changes in wind power accurately. To settle these problems, a point-interval prediction model based on combination of improved preprocessing methods and entropy weighted GRU quantile regression network (QR-EGRU) is proposed. Firstly, an improved wavelet threshold denoising (IWTD) is applied to reduce noise interference. An optimized variational mode decomposition (OVMD) based on sparrow search algorithm (SSA) is proposed to decompose the series into subsequences. Secondly, two update gate matrices based on information entropy (IE) are introduced to replace the traditional update gate matrix of the GRU to construct the EGRU. Point prediction results are obtained by using the EGRU model. Furthermore, the QR algorithm with nonlinear loss function is derived to realize the interval prediction of the EGRU. Finally, the proposed model is validated on real wind power data from the Kaggle competition. Experimental results demonstrate that the proposed model performs well in both point and interval prediction. It can track the mutation series more precisely than other models and improve the prediction accuracy. • An improved WTD and optimized VMD algorithms are proposed in this paper to improve the data quality. • Two update gate weight matrices are introduced to replace the traditional update gate weight matrix of the GRU network. • The information entropy is used to emphasize the impact of the update gate weight matrices. • EGRU model is proposed to realize wind power point prediction. • A novel nonparametric interval prediction model based on QR algorithm and EGRU is proposed. [ABSTRACT FROM AUTHOR]

An accurate and reliable wind power prediction model has important significance for the operation of power systems and large-scale grid connection. This paper proposes a hybrid deep learning model, CEEMDAN-SE-TR-BiGRU-Attention, for high and low frequency wind power prediction by combining complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), sample entropy (SE), Transformer (TR) and bidirectional gated recurrent unit with attention mechanism (BiGRU-Attention). Firstly, the CEEMDAN decomposes the original wind power sequence into multiple sub-modes and a residual, and the sample entropy of each sub-sequence is calculated by restructuring the sequence, which can effectively alleviate the impact of the original non-stationary series on the accuracy and computational complexity. Next, the reconstructed sequences are further divided into high and low frequency sequences according to the sample entropy value of the original sequence. The Transformer and BiGRU-Attention models are respectively applied to the prediction of high frequency and low frequency sequences according to the characteristics of each sequence. Finally, the predicted values of all components are superimposed to obtain the final prediction results. Experiments are carried out on four datasets with different seasons, and different models are compared to illustrate the effectiveness and superiority of the proposed model. The experimental results show that the proposed model achieves better prediction accuracy. • A prediction model is proposed by combining CEEMDAN, SE, TR and BiGRU-Attention. • Transformer and BiGRU-Attention are established for high and low frequency sequences. • Extensive experiments show that the proposed model has better prediction accuracy. [ABSTRACT FROM AUTHOR]

The accurate prediction of offshore wind speed is crucial for effective wind energy management. Deep learning models, which utilize large-scale wind speed time series, have emerged as a prominent approach for this task. However, the availability of wind history and other oceanic data is often capriciously incomplete, with intermittent gaps in the time series due to transmission difficulties or measurement device malfunctions. This presents a significant challenge for both data preparation and model training. In this paper, a self-supervised framework, WindFix, is proposed for continuous missing-value imputation of offshore wind time series using meteorological features from both the self-spot and neighboring spots. This cutting-edge innovation integrates multiple masking techniques with enhanced transformer models, resulting in a highly efficient and versatile process that adapts seamlessly to various scenarios. The numerical results validated on wind dataset from Pacific Ocean show that the model can serve for different missing types with a mean squared error around 0.002 for the simplest case. The comprehensive analysis also provided in-depth explanations on the different patterns observed in various imputation types, attributing these to the allocation of attention weights on features. • Novel transformer model is proposed for offshore wind history imputation • The model is self-supervised hence versatile for various recovering types • The neighboring features pose inconsistent effects for different types • Sensitivity tests for different missing types are comprehensively conducted [ABSTRACT FROM AUTHOR]

The growing reliance on hydroelectric power and the risk of future droughts pose significant challenges for power systems, especially in developing countries. To address these challenges, comprehensive long-term energy planning is essential. This paper proposes an optimized electrical system for 2050, using Ecuador as a case study. For forecasting electricity demand, a Neuro-Fuzzy Adaptive Inference System is employed, utilizing real historical data. Subsequently, the EnergyPlan software constructs a long-term energy consumption model, exploring three scenarios based on Ecuador's energy potential. The first scenario represents a 'business as usual' approach, mirroring the current trend in the Ecuadorian electricity system. In contrast to the second scenario, it encompasses a broader range of renewable sources, including offshore wind, pumped storage, biomass, and geothermal energy. The third scenario extends the second one by incorporating demand response systems, such as vehicle-to-grid and hydrogen-to-grid technologies. In terms of novelty, this study highlights the innovative use of the Neuro-Fuzzy Adaptive Inference System for demand forecasting, along with a comprehensive exploration of multiple scenarios to optimize the electrical system. Research findings indicate that the integration of these new renewable energy sources not only reduces electricity import costs but also ensures surplus electricity production. Consequently, it is anticipated that the 2050 electricity system will reduce its dependence on hydroelectric energy while adopting photovoltaic and wind energy with penetration rates of 65 %, 11.2 %, and 9 %, respectively. This transition will be facilitated by a pumped storage system with a 28 % penetration rate and enhanced connectivity with neighboring countries, enabling the seamless integration of electric and hydrogen vehicles. [Display omitted] • Introducing a long-term electricity demand forecast with adaptive neuro-fuzzy inference. • An energy schedule for Ecuador in 2050 is derived from the demand forecast. • Renewable sources reduce costs, surplus electricity, and imports, enabling a 100 % renewable system. • By 2050, Ecuador's electrical system will rely on hydro, photovoltaic, wind, and pumped hydro power. • The optimized Ecuadorian electrical system will enable V2G and H2G integration in 2050. [ABSTRACT FROM AUTHOR]

China has set a goal of carbon neutrality by 2060 and is determined to increase wind and solar power to 1200 GW by 2030, even though it already has the world's largest installed capacity of renewables. However, the lack of flexibility in the power system will limit the development of a higher proportion of renewable energy. This paper evaluates the applicability of different types of flexible power sources in China for the first time. Above all, it describes the current situation of China's power industry and the necessity of increasing flexible power sources, establishes an evaluation system from the perspectives of benefit, opportunity, cost & risk, then determines 19 evaluation criteria. The BOCR-ANP-TOPSIS method was used to evaluate the system, where the ANP method determines the weights and the TOPSIS method ranks the alternatives. The result shows that pumped storage hydropower has the highest overall ranking, followed by the flexibility transformation of coal-fired power. Coupled with sensitivity and comparative analysis, valuable findings that will help future energy policymakers are reported. • Evaluating the applicability of different flexible power sources in China for the first time. • The identification of criteria for the selection of flexible power sources was given. • Making recommendations for China's flexible power source development policy. • The BOCR-ANP-TOPSIS method adopted can be extended to select flexible power sources in different regions meticulously. [ABSTRACT FROM AUTHOR]

With the increase in wind power integration, significant uncertainty leads to enormous requirements for the flexibility and robustness of system operation. To enhance the flexibility of the power system, this paper proposes a robust low-carbon optimization method for energy and reserve scheduling. The system flexibility is improved by various flexible resources including conventional thermal units (CTUs), carbon capture plants (CCPs), energy storage systems (ESSs), and demand response (DR). The operation and regulation characteristics of multiple types of flexible resources are jointly formulated. Moreover, the carbon-capturing mechanism of CCPs is considered to reduce carbon emissions. The operational risk is measured by the conditional value-at-risk (CVaR) to coordinate the wind power accommodation and operational economy. A two-stage robust scheduling model with a flexible uncertainty set is established, which optimizes the energy and reserve scheme in the first stage and checks the feasibility of re-dispatch in the second stage. The column-and-constraint generation (C&CG) algorithm is utilized to solve the proposed robust model. Simulation results on two different scale systems verify the feasibility and effectiveness of the proposed method. • A robust low-carbon optimization method for energy and reserve scheduling is proposed. • Multiple flexible resources are involved to enhance the robustness and flexibility. • The operation and regulation characteristics of multiple types of flexible resources are jointly formulated. • A two-stage robust scheduling model with a flexible uncertainty set is established. [ABSTRACT FROM AUTHOR]

Transferring energy-intensive industries to regions with abundant clean energy is crucial for achieving low-carbon transformation of energy-intensive sectors during carbon neutrality. By manually collecting the project data from energy-intensive enterprises in China, we construct a three-dimensional panel data with 1.86 million observations to empirically examines the impact of the carbon intensity constraint policy (CICP) on the transfer of high energy-intensive projects (HEP). Our findings indicate that the CICP accelerates the transfer of HEP. The transfer direction shows that the HEP transferred from the eastern region to the western region have increased, but the HEP transferred from the western region to the eastern region have not decreased. To explain the above phenomena, we further discuss the underlying mechanism from the perspective of energy structure and industrial agglomeration. From the standpoint of transfer-out regions, the higher the proportion of thermal power in the energy consumption structure, the more HEP will be transferred out. From the standpoint of transfer-in regions, the industrial agglomeration will attract the transfer of the HEP. However, we do not find evidence that wind power and photovoltaics can attract the HEP. This paper provides project-level empirical evidence for promoting the low-carbon transformation of energy-intensive industries. • The carbon intensity constraint accelerates the transfer of energy-intensive projects. • The dynamic effect shows a fluctuating and decreasing trend. • The transfer direction is the net transfer from the east to the west. • The more thermal power, the more energy-intensive projects will be transferred out. • We don't find the attraction of the clean energy for the energy-intensive projects. [ABSTRACT FROM AUTHOR]

Building a multi-energy complementary power generation system is a viable way to encourage the use of renewable energy and decarbonize power generation. However, the intermittent nature of renewable power generation, such as photovoltaic and wind power, has prompted concerns regarding power grid stability. To balance such fluctuations, energy storage systems or other flexible power generation technologies should be integrated. In this paper, the peak regulation ability of integrated solar combined-cycle has been enhanced via employing a gas/oil exchanger between the top and bottom cycle. When integrating high penetration intermittent renewable energy, an appropriate operational strategy towards high-quality steady power output regulation is proposed. Dynamic performance analysis of the system, coupled characteristic of heat and mass transfer between subsystems have been highlighted. The case study demonstrates that fluctuations of the multi-energy complementary system power output can be controlled below 0.3 MW without renewable energy curtailment, even though wind-PV power generation fluctuates from 0.3 MW to 26.1 MW with variations per second reaching −2.8/3.7 MW. Furthermore, the system's levelized cost of electricity is down to 0.0512 $/kWh, which is cost-competitive with conventional power generation technologies. • Combination of integrated solar combined cycle with wind and PV power plant. • Power stability of system with high penetration intermittent energy. • Novel system configuration and operation strategy. • Deviations from target power output below 0.3 MW per second. [ABSTRACT FROM AUTHOR]

Wind and solar power depress market prices at times when they produce the most. This has been termed the 'cannibalization effect', and its magnitude has been established within the economic literature on current and future markets. Although it has a substantial impact on the revenue of VRE technologies, the cannibalization effect is neglected in the capital budgeting literature, including portfolio- and real options theory. In this paper, we present an analytical framework that explicitly models the correlation between VRE production and electricity price, based on the production costs of surrounding generation capacity. We derive closed-form expressions for the expected short-term and long-term revenue, the variance of the revenue and the timing of investments. The effect of including these system characteristics is illustrated with numerical examples, where we find the cannibalization effect to decrease projected profit relative to investment cost from 33% to between 13% and − 40 %, depending on the assumption for the future VRE capacity expansion rate. Using a real options framework, the investment threshold increases by between 13% and 67%, due to the inclusion of cannibalization. • An analytical framework to consider cannibalization in investment decisions for VRE • We present closed-form expressions for the expected value and variance of revenues • An investment timing problem illustrates one potential use of the analytical framework • Expected VRE growth rates have a large impact on the revenues and optimal timing [ABSTRACT FROM AUTHOR]

China is facing the challenge of selecting appropriate policies to implement tradable green certificate (TGC) under the renewable portfolio standards (RPS). This paper proposes a tripartite evolutionary game model among thermal power plants, green power plants and the grid under the RPS and TGC policy to analyze the evolutionary stability strategies (ESSs) of unilateral subjects and systems and use numerical simulation to discuss the influence of different types of TGC purchase ratios and different trading markets on the choice of tripartite strategy. The results are as follows. (1) When the renewable energy consumption quota ratio is 21%, thermal power plants are more and more active in choosing to trade TGC as the ratio of wind power TGC and photovoltaic TGC gradually increases from 1:5 to 5:1. (2) In the TGC market where the price of wind power and photovoltaic TGC is 50 yuan, green power plants are more inclined to hold TGC; in the subsidized TGC market, where the price of wind power TGC is 190 yuan and the price of photovoltaic TGC is 650 yuan, green power plants tend to sell TGC. (3) With the price of excess green electricity consumption gradually decreased from 700 yuan/MWh to 100 yuan/MWh, the activity of three parties participating in TGC trading gradually increased, effectively activating the TGC market. Finally, from the perspective of policy management, we provide suggestions for the long-term sustainable development of the TGC market. • The strategy selection of stakeholders involved in the implementation process of the RPS and TGC policy has been examined. • The evolutionary convergence of tripartite behaviors shows a high dependent degree. • In parity TGC trading markets, the government has the potential to lower the transaction price for excess consumption. • An important policy reference for promoting the balanced development of the RPS and TGC has been provided. [ABSTRACT FROM AUTHOR]

In recent years, wind power has played a significant role in energy generation of micro-grids (MGs). However, randomness nature of wind speed leading to uncertainty in wind power forecast, imposes some problems such as overestimating wind power on optimized scheduling of MG. In this paper, we propose an adaptive probabilistic concept of confidence interval (APCCI) to address these problems. The main purpose of the proposed APCCI is to modify the risk we endure to schedule wind power with other distributed energy resources (DERs) in order to degrade the unnecessary rigors and upgrade the other ones. The forecasting method which is used in this paper is artificial neural network (ANN). In order to increase the accuracy of forecasting, wavelet decomposition (WD) is applied to the wind power time series then the results are sent to ANN. After that, dependable levels for the predicted wind power based on APCCI are obtained. An energy storage system (ESS) is utilized not only to decrease the impact of forecasting errors on the MG but also to increase the flexibility of the planning. A comprehensive formulation with operational constraints is employed to model the optimization problem. An economic dispatch based non-dominated sorting genetic algorithm II (EDNSGA-II) is proposed and applied to solve the multi-objective optimization problem. The optimization algorithm produces some alternatives which consist of different combination of objectives (cost and emission). Techniques for order preference by similarity to an ideal solution (TOPSIS) method is utilized to make a compromised decision between the alternatives. Eventually, the proposed algorithm is applied to a typical MG which consists of micro turbine (MT), fuel cell (FC), photo voltaic (PV), wind turbine (WT) and energy storage system (ESS). Evaluation of the results show that the proposed APCCI works well and can adapt the level of confidence interval in various situations. Moreover, the results confirm the superiority of WNN over ANN. The results also show that the proposed EDNSGA-II is more efficient in comparison with the well-known NSGA-II. [ABSTRACT FROM AUTHOR]