Search

Accurate PV power forecasting is becoming a mandatory task to integrate the PV plant into the electrical grid, scheduling and guaranteeing the safety of the power grid. In this paper, a novel model to forecast the PV power using LSTM-TCN has been proposed. It consists of a combination between Long Short Term Memory and Temporal Convolutional Network models. LSTM is used to extract the temporal features from input data, then combined with TCN to build the connection between features and outputs. The proposed model has been tested using a dataset that includes historical time series of measured PV power. The accuracy of this model is then compared to LSTM and TCN models in different seasons, time periods forecast, cloudy, clear, and intermittent days. For one step forecasting, the results show that our proposed model outperforms the LSTM and TCN model. It has carried out a reduction of 8.47%, 14.26% for the autumn season, 6.91%,15.18 for the winter season, 10.22%,14.26% for spring season and 14.26%, 14.23% for the summer season on the Mean Absolute Error compared with LSTM, TCN. For multistep forecasting, LSTM-TCN surpassed all compared models in different time periods forecast from 2 steps to 7 steps PV power forecasting. [ABSTRACT FROM AUTHOR]

Offshore wind turbines are exposed during their serviceable lifetime to a wide range of loads from aero-, hydro- and structural dynamics. This complex loading scenario will have an impact on the lifetime of the asset, with fatigue remaining the key structural design driver for the substructure, e.g. the monopile. The ability to monitor the progression of fatigue life of these assets has recently become an operational concern. To achieve a monitoring alternative to strain gauges (cost-prohibitive farm-wide installation), supervisory control and data acquisition (SCADA) systems, often coupled with acceleration measurements, have been used. Existing work focused primarily on ten-minute fatigue load estimation. However, fatigue accumulates over time and the ability to accurately monitor this accumulation of fatigue over a longer time-window is paramount. In this contribution we investigate a novel approach using nine months of real-world SCADA and acceleration ten-minute statistics as inputs of a neural network model for long-term DEM estimation. This is further enhanced by including physical information relative to the problem at hand into the neural network model, in a so-called physics-informed machine learning approach. Specifically, we employ a custom loss function – the Minkowski logarithmic error – which prioritizes conservativeness (over-prediction of fatigue rates) and to embed the damage accumulation into the machine learning model. In the results and discussion section, we use Tower-TP interface load measurements for three real-world turbines to demonstrate the concept. First a model is trained on one turbine, before being applied to all three locations. The model performance is compared to direct measurements of fatigue progression at all three locations and a control loss function (the mean squared logarithm error) in both the Fore-Aft and Side-Side loading directions. The novel physics-informed model clearly outperforms the control loss function in accumulated fatigue predictions with errors below 3% on accumulated damage equivalent moment estimates. Additionally, the model's long-term performance is checked according to varying timescales (hourly, daily, weekly or monthly accumulation of DEM) and it is seen that the spread on the error rapidly reduces and converges to zero. Finally, the long-term DEM is accumulated into a monthly accumulated fatigue damage. We also see how the error on this begins to converge after 6+ months, which opens the door for extrapolation. • RUL/fatigue estimation on XL monopiles of OWTs using 9 months of real data. • SCADA and acceleration data as alternatives to strain gauge measurements. • Physics-guided learning of neural networks greatly increases model performance. • SCADA and acceleration data can be used for long-term fatigue damage estimation. • Errors on DEM are kept below 3% and on damage below 15%. [ABSTRACT FROM AUTHOR]

Accurate short-term load forecasting is of great significance to the safe and stable operation of power systems and the development of the power market. Most existing studies apply deep learning models to make predictions considering only one feature or temporal relationship in load time series. Therefore, to obtain an accurate and reliable prediction result, a hybrid prediction model combining a dual-stage attention mechanism (DA), crisscross grey wolf optimizer (CS-GWO) and bidirectional gated recurrent unit (BiGRU) is proposed in this paper. DA is introduced on the input side of the model to improve the sensitivity of the model to key features and information at key time points simultaneously. CS-GWO is formed by combining the horizontal and vertical crossover operators, to enhance the global search ability and the diversity of the population of GWO. Meanwhile, BiGRU is optimized by CS-GWO to accelerate the convergence of the model. Finally, a collected load dataset, four evaluation metrics and parametric and non-parametric testing manners are used to evaluate the proposed CS-GWO-DA-BiGRU short-term load prediction model. The experimental results show that the RMSE, MAE and SMAPE are reduced respectively by 3.86%, 1.37% and 0.30% of those of the second-best performing CSO-DA-BiGRU model, which demonstrates that the proposed model can better fit the load data and achieve better prediction results. [ABSTRACT FROM AUTHOR]

Short-term wind speed forecasting is fundamental to improving the stability of power grid operation and enhancing its transmission efficiency; thus, it has long been a research hotspot. Nonetheless, quantities of literature in this field only used the single prediction model and overemphasized deterministic prediction, which resulted in deficient forecasting performance. To address these issues, a novel point and interval combination prediction system was developed in this paper. Specifically, wind speed time series were reconstructed by dividing windows and fuzzification to input highly effective data; next, four single prediction models and a multi-objective weight-determining mechanism were integrated to obtain the point prediction results; and their distributions were assessed to implement interval prediction under distinct confidence levels. In the meantime, this study demonstrated that the proposed system reached the Pareto optimal by the theoretical proof, and empirical research was conducted based on 10-min real wind speed data from the wind farm in China. Judging from the experimental results, the combination prediction system was always capable of providing the most satisfactory forecasting performance by contrast with the comparative models. Consequently, it has broad application prospects in guiding the operation of wind farms and optimizing the power grid dispatching. [ABSTRACT FROM AUTHOR]

This study calibrated the Soil Conservation Service Curve Number (SCS-CN) model to predict decadal runoff in Peninsula Malaysia and found a correlation between the reduction of forest area, urbanization, and an increase in runoff volume. The conventional SCS-CN runoff model was found to commit a type II error in this study and must be pre-justified with statistics and calibrated before being adopted for any runoff prediction. Between 1970 and 2000, deforestation in Peninsula Malaysia caused a decline in forested land by 25.5%, resulting in a substantial rise in excess runoff by 10.2%. The inter-decadal mean runoff differences were more pronounced in forested and rural catchments (lower CN classes) compared to urban areas. The study also found that the CN value is a sensitive parameter, and changing it by ±10% can significantly impact the average runoff estimate by 40%. Therefore, SCS practitioners are advised not to adjust the CN value for better runoff modeling results. Additionally, NASA's Giovanni system was used to generate 20 years of monthly rainfall data from 2001–2020 for trend analysis and short-term rainfall forecasting. However, there was no significant uptrend in rainfall within the period studied, and occurrences of flood and landslide incidents were likely attributed to land-use changes in Peninsula Malaysia. [ABSTRACT FROM AUTHOR]

Three numerical methods, including element instantaneous failure, continuum damage mechanics, and extended finite element methods, are mainly used to simulate the fracture in cortical bone structure. Although many simulations focus on the cortical bone fracture, few have investigated the differences in prediction accuracy among the three numerical methods. The purpose of this study was to evaluate the prediction accuracy and applicability of the three numerical methods in simulating cortical bone fracture under bending load. The rat femur samples were first used to perform the three-point bending experiment. Then, the three numerical methods were respectively used to conduct fracture simulation on the femoral finite element models. Each result was compared with the experimental data to determine the prediction accuracy. The results showed that fracture simulation based on the continuum damage mechanics method was in better agreement with the experimental results, and observable differences in the failure processes could be seen in the same model under the three simulations due to various element failure strategies. The numerical method that was suitable for simulating cortical bone fracture under bending load was determined; meanwhile, the variations in the failure simulations were observed, and the cause of the variations in the predicted results using different numerical methods was also discussed, which may have potential to improve the prediction accuracy of cortical bone fracture. [ABSTRACT FROM AUTHOR]

In order to defraud state subsidies, some unscrupulous users use improper means to steal photovoltaic (PV) power. This behavior brings potential safety hazards to photovoltaic grid-connected operations. In this paper, a photovoltaic power-stealing identification method based on similar-day clustering and interval prediction of the quantile regression model for long short-term memory neural network (QRLSTM) is proposed. First, photovoltaic data are clustered into three similar days by the similar-day clustering according to weather conditions. Second, compared with the quantile regression neural network (QRNN) prediction method, the good prediction performance of the QRLSTM method is illustrated. Third, using the prediction intervals with different confidence levels on three similar days, according to the time scale (short-term, medium-term and long-term) combined with different electricity-stealing judgment indicators, a three-layer photovoltaic power-stealing screening framework is constructed, and the degree of user power stealing is qualitatively analyzed. Last, the power generation data of eight photovoltaic users in a certain region of northwest China and the data of four groups of artificially constructed power-stealing users are used as an example for simulation. The simulation results prove the feasibility of the proposed method in this paper. [ABSTRACT FROM AUTHOR]

Power load forecasting is an important part of smart grid, and its accuracy will directly affect the control and planning of power system operation. In the context of electricity market reform, real-time electricity prices affect users' electricity consumption patterns. A short-term load forecasting model based on support vector regression (SVR) with whale optimization algorithm (WOA) considering real-time electricity price is proposed in this paper. Meta-heuristics are very promising in optimizing the parameters of SVR, and the WOA algorithm is used to determine the appropriate combination of SVR's parameters to accurately establish a forecasting model. The initial value of the original WOA algorithm lacks ergodicity, and has defects such as easy to fall into local optimum and low convergence accuracy. Chaos mechanism and elite opposition-based learning strategy are introduced into WOA to balance the exploration and exploitation of the algorithm and improve the algorithm convergence speed. Numerical examples involving two power load datasets show that the proposed model can achieve better forecasting performance in comparison with other models, such as SVR, BPNN. At the same time, it proves that the forecasting accuracy with electricity price is higher than that without electricity price. [ABSTRACT FROM AUTHOR]

As the energy crisis intensifies, wind energy generated by wind turbines, commonly known as a promising renewable energy source, is being more frequently employed. As a result, wind energy forecasting, particularly wind speed forecasting, plays a crucial role for wind energy management. Due to their importance, many wind speed forecasting methods have been proposed. However, many of the traditional prediction models did not account for data pre-processing, or the constraints of an individual forecasting model, resulting in poor prediction accuracy. The purpose of this article is to present a unique forecasting model that incorporates noise-processing methods, statistical techniques, deep learning frameworks, and optimization algorithms to improve on existing methods. The suggested ensemble model was tested using 10-minute wind speed data from real-world conditions. The experimental results show that the mean absolute percentage error of the 10-minute prediction of the proposed model is 5.73%, which is also about 17% improvement compared to the competing model (mean absolute percentage error of 6.71%). [ABSTRACT FROM AUTHOR]

Forecasting the electrical load is essential in power system design and growth. It is critical from both a technical and a financial standpoint as it improves the power system performance, reliability, safety, and stability as well as lowers operating costs. The main aim of this paper is to make forecasting models to accurately estimate the electrical load based on the measurements of current electrical loads of the electricity company. The importance of having forecasting models is in predicting the future electrical loads, which will lead to reducing costs and resources, as well as better electric load distribution for electric companies. In this paper, deep learning algorithms are used to forecast the electrical loads; namely: (1) Long Short-Term Memory (LSTM), (2) Gated Recurrent Units (GRU), and (3) Recurrent Neural Networks (RNN). The models were tested, and the GRU model achieved the best performance in terms of accuracy and the lowest error. Results show that the GRU model achieved an R-squared of 90.228%, Mean Square Error (MSE) of 0.00215, and Mean Absolute Error (MAE) of 0.03266. [ABSTRACT FROM AUTHOR]

Computer servers in cloud data centers are known to consume a huge amount of energy in their operations. For energy saving, load balancing has been used but it is only effective when CPU loads are predicted accurately. Noise in the energy consumption data is often a detrimental factor responsible for the CPU load prediction error. In prior arts, denoising has not been considered as an approach to subside the prediction error. Therefore, a novel prediction approach called CEEMDAN-RIDGE that is centered on denoising is proposed and reported in this paper. Firstly, CEEMDAN is applied to decompose the CPU consumption data which is in the form of a time series. The curvature similarity between a pair of the original series and its corresponding decomposed series is measured. By referencing to this similarity measure, an effective series is obtained from filtration of the noise series. The effective series after the noise series is filtered out is reconstructed to a new fitting curve for CPU load prediction. The prediction accuracy is further enhanced by doing some error correction called RIDGE, which is made possible by predicting the error a priori from the historical error data from the previous prediction. In order to validate CEEMDAN-RIDGE, a series of experiments are conducted with Google trace data. The experiment results show that the LSTM model using the proposed CPU load prediction approach outperforms other models significantly in three performance metrics: RMSE, MAE and MAPE. [ABSTRACT FROM AUTHOR]

The integration of large-scale wind power into power grids has made accurate short-term wind power forecasting a key technology for the safe and economical operation of power grids. A novel method based on variational mode decomposition (VMD), temporal convolutional network (TCN), and Gaussian mixture model (GMM) was proposed for accurate short-term wind power forecasting and uncertainty analysis. First, the wind speed information was decomposed into different mode components via VMD. Second, TCN was employed to capture accurately the time-series dependence of data by training and forecasting different mode component data. On this basis, GMM was used to calculate the distribution characteristics of short-term wind power forecasting errors and quantify the confidence interval of wind power forecasting. Results demonstrated that the root mean square error (RMSE) value of the VMD-TCN model for wind power forecasting for 4 h during winter is 4.69%, 3.13%, 2.48%, 1.21%, and 0.7% lower than the RMSE values of wavelet neural network, BP neural network, PSO-BP hybrid model, long short-term memory model, and TCN model, respectively. The proposed method has a certain promoting effect on improving the accuracy of short-term wind power forecasting. [ABSTRACT FROM AUTHOR]

The energy Internet (EI) equipment may face threats that attackers poison federated learning (FL) models to disturb electricity load forecasting. To mitigate this vulnerability, it is important to study load forecasting disturbance approaches. This article proposes a side-channel analysis (SCA)-based disturbance approach. First, we design an FL SCA scheme to extract power information from the FL chip running forecasting model. Second, we propose an FL data speculation method using an optimized convolutional neural network trained with SCA information. Third, we design a label-flipping-based poisoning scheme with speculated data characteristics for load forecasting disturbance. Experimental results show attackers can successfully poison and disturb FL-based load forecasting. The average accuracy of EI load data speculation is 99.8%. This work is the first to study EI load forecasting disturbance from an SCA perspective. [ABSTRACT FROM AUTHOR]

Short-term power load forecasting provides important guidance for the improvement of power marketing and control levels of power enterprises. In this paper, a novel method, named RF-TStacking, is proposed to forecast the short-term load. This study starts from the influence factors of the power load, the random forest is applied to estimate the importance of the influence factors of short-term load. Based on Stacking strategy, the integration of LightGBM and random forest is realized to achieve short-term power load forecasting. To improve the generalization ability of the load model, random put back sampling is used to sample each primary learner, and the average value is taken as the result of each primary learner. The Bayesian optimization is used to adjust the super parameters of the model to improve the accuracy of the selection of influencing factors. The load data of a region in northwest China are used for the testing, and it is found that the model can provide stable prediction results. [ABSTRACT FROM AUTHOR]

Photovoltaic power generation fluctuates, photovoltaic output is easily affected by various meteorological characteristics, and traditional TCN networks tend to over-enhance spatial characteristics and weaken individual characteristics. In view of these problem, a short-term photovoltaic power generation prediction model based on VMD and improved TCN is proposed in this study. The original photovoltaic power generation time series is decomposed into several modal components of different frequencies through VMD, and each modal component and the corresponding meteorological data are input to the improved TCN network for modeling and learning. The center frequency method is used to determine the optimal decomposition modal number of VMD. On the basis of the traditional TCN prediction model, DropBlock regularization is used to replace Dropout regularization to achieve the effect of suppressing information synergy in the convolutional layer, and the attention mechanism is introduced to autonomously mine and highlight the impact of key meteorological input characteristics and quantify the impact of various meteorological factors on photovoltaic power generation to improve forecasting precision. Based on the real data of a photovoltaic power station in Jiangsu, the simulation experiments show that the RMSE of the proposed prediction method is 0.62 MW and the MAPE is 2.03%. [ABSTRACT FROM AUTHOR]

The manager of the electricity supply chain needs to correctly forecast one of the most important variables affecting the management of the electricity chain. This article has proposed a hybrid model for electricity demand forecasting using deep learning. Firstly, the historical electricity demand data is decomposed using empirical mode decomposition (EMD) algorithm. Then, whale optimization algorithm (WOA) is used to determine signal decomposition levels rounds by EMD and the allocation of signals to neural networks. Parameters that promote accuracy of the forecast are selected using principal component analysis (PCA). A group of signals are fed into a back propagation neural network, whose components are decomposed by wavelet transform. The weights of this neural network are determined by using elephant herding optimization (EHO) algorithm (WTBPNN-EHO). The rest of the signals with higher levels of complexity are fed into the long short-term memory (LSTM) neural network. Finally, the load is calculated by aggregating the results of these two neural networks. Finally, the performance of this model has been compared with other existing models. [ABSTRACT FROM AUTHOR]

In the smart grid, the data collected from the smart meters can be used to develop an accurate energy consumption forecasting. A close prediction is beneficial in providing a good energy scheduling, making balance between demand and generation of power which results in reducing the production costs of the energy. Several models are used to give an accurate energy consumption forecast. One of these models is long short-term memory (LSTM). LSTM model may be combined with other models to give better results. On the other hand, LSTM has a drawback of selecting the hyperparameters values. In this paper, we optimize a long short-term memory autoencoder (LSTM-AE) model with the metahuristic algorithm Particle Swarm Optimization (PSO) in order to obtain the optimal parameters for the model to give better results in forecasting and then compared to other forecasting models. The evaluation metrics used for the comparison are mean squareerror (MSE) and root mean square error (RMSE). [ABSTRACT FROM AUTHOR]

Aiming at the problem that wind power generation fluctuates greatly due to environmental changes and a kernel extreme learning machine is easy to fall into the local optimal solution, this paper constructs a short-term wind power prediction model of an optimized kernel extreme learning machine based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) Analysis, wavelet threshold denoising and particle swarm algorithm. Firstly, CEEMDAN is used to decompose the environmental factors that are closely related to the output power of wind power generation, and several modal components with strong regularity are obtained. Besides, the threshold denoising method is used to denoise the first modal component containing much noise to weaken the non-stationarity of environmental factors. Then, after particle swarm optimization, the decomposed subcomponents and historical wind power data are used as the input of the kernel extreme learning machine algorithm for prediction. Finally, the measured data of a wind farm in Zhangjiakou, Hebei Province are selected for experimental comparison and analysis. The experimental results show that the improved wind power forecasting combination model proposed in this paper has higher forecasting accuracy and is suitable for wind power forecasting in different seasons. [ABSTRACT FROM AUTHOR]

The uncertainty associated with photovoltaic (PV) systems is one of the core obstacles that hinder their seamless integration into power systems. The fluctuation, which is influenced by the weather conditions, poses significant challenges to local energy management systems. Hence, the accuracy of PV power forecasting is very important, particularly in regions with high PV penetrations. This study addresses this issue by presenting a framework of novel forecasting methodologies based on hybrid data-driven models. The proposed forecasting models hybridize Support Vector Regression (SVR) and Artificial Neural Network (ANN) with different Metaheuristic Optimization Algorithms, namely Social Spider Optimization, Particle Swarm Optimization, Cuckoo Search Optimization, and Neural Network Algorithm. These optimization algorithms are utilized to improve the predictive efficacy of SVR and ANN, where the optimal selection of their hyperparameters and architectures plays a significant role in yielding precise forecasting outcomes. In addition, the proposed methodology aims to reduce the burden of random or manual estimation of such paraments and improve the robustness of the models that are subject to under and overfitting without proper tuning. The results of this study exhibit the superiority of the proposed models. The proposed SVR models show improvements compared to the default SVR models, with Root Mean Square Error between 12.001 and 50.079%. Therefore, the outcomes of this research work can uphold and support the ongoing efforts in developing accurate data-driven models for PV forecasting. [ABSTRACT FROM AUTHOR]

Short-term load forecasting is an important prerequisite for smart grid controls. The current methods are mainly based on the convolution neural network (CNN) or long short-term memory (LSTM) model to realize load forecasting. For the multi-factor input sequence, the existing methods cannot obtain multi-scale features of the time series and the important parameters of the multi-factor, resulting in low accuracy and robustness. To address these problems, a multi-scale feature attention hybrid network is proposed, which uses LSTM to extract the time correlation of the sequence and multi-scale CNN to automatically extract the multi-scale feature of the load. This work realizes the integration of features by constructing a circular network. In the proposed model, a two-branch attention mechanism is further constructed to capture the important parameters of different influencing factors to improve the model's robustness, which can make the network to obtain effective features at the curve changes. Comparative experiments on two open test sets show that the proposed multi-scale feature attention mixture network can achieve accurate short-term load forecasting and is superior to the existing methods. [ABSTRACT FROM AUTHOR]

Copyright of Electric Power Automation Equipment / Dianli Zidonghua Shebei is the property of Electric Power Automation Equipment Press and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Shanghai Jiao Tong University (1006-2467) is the property of Journal of Shanghai Jiao Tong University Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The ever‐evolving electricity distribution network calls for new effective, transparent and fair market procedures to be implemented. This paper offers a systematic framework for real‐time trading in prosumer communities. A data‐driven robust optimization model that deals with uncertainty is proposed using the flexibility requirement envelope concept. Using machine learning techniques, high quality point and quantile forecasts are prepared to form the envelope. Next, this data is fed into the optimization problem to match the peers and the distribution grid, trading power, and flexibility in a short‐term look‐ahead horizon. To increase the quality of forecasts, a clustering approach accompanied by a pattern recognition machine is proposed to determine the cluster to which the recently observed net‐load data belongs. To provide forecasts, a forecasting machine is developed using a hybrid of tree‐based ensemble learning models, which provides intuitive, robust, and accurate results. Finally, the peer matching is done in a decentralized fashion using the alternating direction method of multipliers (ADMM), while each agent calculates its battery storage aging cost. Case studies demonstrate the hybrid model's capability in providing high quality power and flexibility forecasts compared to single models and ARIMA models and its positive impact on reducing the overall cost of the system. [ABSTRACT FROM AUTHOR]

Recently, the increasing penetration of renewable energy resources in power system, especially photovoltaic (PV) systems, has caused severe technical issues due to its randomness and dependency on primary sources. Therefore, precise output power forecast is vital for both system operators and PV system owners to improve grid stability and generation quality, respectively. This article proposes a novel hybrid deep learning model named EDSACL comprising four components, namely, convolutional neural network (CNN), long short‐term memory (LSTM), self‐attention mechanism (SAm), and residual learning (RL) strategy for short‐term PV maximum power prediction with forecast horizon of 1, 2, and 4 h. This proposed model initially extracts spatial‐temporal features of input data based on CNN and LSTM before using SAm to achieve hidden features of LSTM layers. RL strategy is employed to maintain the information flow entering the network. Besides, interval prediction is also implemented based on a combination of the EDSACL model and quantile regression with different probabilities. The forecast accuracy of the proposed model is validated based on two real‐world data sets. The predicted results show the superiority of the proposed model over numerous predictive models; in particular, mean absolute percentage error values of the proposed hybrid model are under 6% in all case studies. [ABSTRACT FROM AUTHOR]

Copyright of Control Theory & Applications / Kongzhi Lilun Yu Yinyong is the property of Editorial Department of Control Theory & Applications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Optimal behind-the-meter energy management often requires a day-ahead electric load forecast capable of learning non-linear and non-stationary patterns, due to the spatial disaggregation of loads and concept drift associated with time-varying physics and behavior. There are many promising machine learning techniques in the literature, but black box models lack explainability and therefore confidence in the models' robustness can't be achieved without thorough testing on data sets with varying and representative statistical properties. Therefore this work adopts and builds on some of the highest-performing load forecasting tools in the literature, which are Long Short-Term Memory recurrent networks, Empirical Mode Decomposition for feature engineering, and k-means clustering for outlier detection, and tests a combined methodology on seven different load data sets from six different load sectors. Forecast test set results are benchmarked against a seasonal naive model and SARIMA. The resultant skill scores range from −6.3% to 73%, indicating that the methodology adopted is often but not exclusively effective relative to the benchmarks. [ABSTRACT FROM AUTHOR]

For load forecasting, numerous machine learning (ML) approaches have been published. Besides fully connected feedforward neural networks (FFNNs), also called multilayer perceptron, more advanced ML approaches like deep, recurrent or convolutional neural networks or ensemble methods have been applied. However, evaluating the added benefit by novel approaches is difficult. Statistical or rule-based methods constitute a too low benchmark. FFNNs need extensive tuning due to their manifold design choices. To address this issue, a structured, comprehensible five-step FFNN model creation methodology is presented, which constitutes of initial model creation, internal parameter selection, feature engineering, architecture tuning and final model creation. The methodology is then applied to forecast real world heat load data of a hospital in Germany. The forecast constitutes of 192 values (upcoming 48 h in 15 min resolution) and is composed of a multi-model univariate forecasting strategy, with three test models developed at first. As a result, the test models show great similarities which simplifies creation of the remaining models. A performance increase of up to 18% between initial and final models points out the importance of model tuning. As a conclusion, comprehensible model tuning is vital to use FFNN models as benchmark. The effort needed can be reduced by the experience gained through repeated application of the presented methodology. [ABSTRACT FROM AUTHOR]

With the increasing demand of the power industry for load forecasting, improving the accuracy of power load forecasting has become increasingly important. In this paper, we propose an ultra short-term power load forecasting method based on similar day clustering and EEMD (Ensemble Empirical Mode Decomposition). In detail, the K-means clustering algorithm was utilized to divide the historical data into different clusters. Through EEMD, the load data of each cluster were decomposed into several sub-sequences with different time scales. The LSTNet (Long- and Short-term Time-series Network) was adopted as the load forecasting model for these sub-sequences. The forecast results for different sub-sequences were combined as the expected result. The proposed method predicts the load in the next 4 h with an interval of 15 min. The experimental results show that the proposed method obtains higher prediction accuracy than other comparable forecasting models. [ABSTRACT FROM AUTHOR]

With the increasing integration of wind and photovoltaic power, the security and stability of the power system operations are greatly influenced by the intermittency and fluctuation of these renewable sources of energy generation. The accurate and reliable short-term forecasting of renewable energy generation can effectively reduce the impacts of uncertainty on the power system. In this paper, we propose an adaptive, data-driven stacking ensemble learning framework for the short-term output power forecasting of renewable energy. Five base-models are adaptively selected via the determination coefficient (R2) indices from twelve candidate models. Then, cross-validation is used to increase the data diversity, and Bayesian optimization is used to tune hyperparameters. Finally, base modes with different weights determined by minimizing the cross-validation error are ensembled using a linear model. Four datasets in different seasons from wind farms and photovoltaic power stations are used to verify the proposed model. The results illustrate that the proposed stacking ensemble learning model for renewable energy power forecasting can adapt to dynamic changes in data and has better prediction precision and a stronger generalization performance compared to the benchmark models. [ABSTRACT FROM AUTHOR]

To solve the problem of feature selection and error correction after mode decomposition and improve the ability of power load forecasting models to capture complex time series information, a two-stage short-term power load forecasting method based on recursive feature elimination with a cross validation (RFECV) algorithm and time convolution network–efficient channel attention mechanism–long short-term memory network (TCN–ECA–LSTM) is presented. First, the load sequence is decomposed into a relatively stable set of modal components using variational mode decomposition. Then, the RFECV-based method filters the feature set of each modal component to construct the best feature set. Finally, a two-stage prediction model based on TCN–ECA–LSTM is established. The first stage predicts each modal component and the second stage reconstructs the load forecast based on the predicted value of the previous stage. This paper takes actual data from New South Wales, Australia, as an example, and the results show that the method proposed in this paper can build the feature set reliably and efficiently and has a higher accuracy than the conventional prediction model. [ABSTRACT FROM AUTHOR]

Daily electricity peak load forecasting is important for electricity generation capacity planning. Accurate forecasting leads to saving on excessive electricity generating capacity, while maintaining the stability of the power system. The main challenging tasks in this research field include improving forecasting accuracy and reducing computational time. This paper proposes a hybrid model involving variational mode decomposition (VMD), empirical mode decomposition (EMD), fast Fourier transform (FFT), stepwise regression, similar days selection (SD) method, and artificial neural network (ANN) for daily electricity peak load forecasting. Stepwise regression and similar days selection method are used for input variable selection. VMD and FFT are applied for data decomposition and seasonality capturing, while EMD is employed for determining an appropriate decomposition level for VMD. The hybrid model is constructed to effectively forecast special holidays, which have different patterns from other normal weekdays and weekends. The performance of the hybrid model is tested with real electricity peak load data provided by the Electricity Generating Authority of Thailand, the leading power utility state enterprise under the Ministry of Energy. Experimental results show that the hybrid model gives the best performance while saving computation time by solving the problems in input variable selection, data decomposition, and imbalance data of normal and special days in the training process. [ABSTRACT FROM AUTHOR]

This study proposes an effective wind speed forecasting model combining a data processing strategy, neural network predictor, and parameter optimization method. (a) Variational mode decomposition (VMD) is adopted to decompose the wind speed data into multiple subseries where each subseries contains unique local characteristics, and all the subseries are converted into two-dimensional samples. (b) A gated recurrent unit (GRU) is sequentially modeled based on the obtained samples and makes the predictions for future wind speed. (c) The grid search with rolling cross-validation (GSRCV) is designed to simultaneously optimize the key parameters of VMD and GRU. To evaluate the effectiveness of the proposed VMD-GRU-GSRCV model, comparative experiments based on hourly wind speed data collected from the National Renewable Energy Laboratory are implemented. Numerical results show that the root mean square error, mean absolute error, mean absolute percentage error, and symmetric mean absolute percentage error of this proposed model reach 0.2047, 0.1435, 3.77%, and 3.74%, respectively, which outperform the benchmark predictions using popular parameter optimization methods, data processing techniques, and hybrid neural network forecasting models. [ABSTRACT FROM AUTHOR]

Electricity load prediction is an essential tool for power system planning, operation and management. The critical information it provides can be used by energy providers to maximise power system operation efficiency and minimise system operation costs. Long Short-Term Memory (LSTM) and Support Vector Machine (SVM) are two suitable methods that have been successfully used for analysing time series problems. In this paper, the two algorithms are explored further for load prediction; two load prediction algorithms are developed and verified by using the half-hourly load data from the University of Warwick campus energy centre with four different prediction time horizons. The novelty lies in comparing and analysing the prediction accuracy of two intelligent algorithms with multiple time scales and in exploring better scenarios for their prediction applications. High-resolution load forecasting over a long range of time is also conducted in this paper. The MAPE values for the LSTM are 2.501%, 3.577%, 25.073% and 69.947% for four prediction time horizons delineated. For the SVM, the MAPE values are 2.531%, 5.039%, 7.819% and 10.841%, respectively. It is found that both methods are suitable for shorter time horizon predictions. The results show that LSTM is more capable of ultra-short and short-term forecasting, while SVM has a higher prediction accuracy in medium-term and long-term forecasts. Further investigation is performed via blind tests and the test results are consistent. [ABSTRACT FROM AUTHOR]

In this work, we provide a smart home occupancy prediction technique based on environmental variables such as CO 2 , noise, and relative temperature via our machine learning method and forecasting strategy. The proposed algorithms enhance the energy management system through the optimal use of the electric heating system. The Long Short-Term Memory (LSTM) neural network is a special deep learning strategy for processing time series prediction that has shown promising prediction results in recent years. To improve the performance of the LSTM algorithm, particularly for autocorrelation prediction, we will focus on optimizing weight updates using various approaches such as Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The performances of the proposed methods are evaluated using real available datasets. Test results reveal that the GA and the PSO can forecast the parameters with higher prediction fidelity compared to the LSTM networks. Indeed, all experimental predictions reached a range in their correlation coefficients between 99.16% and 99.97%, which proves the efficiency of the proposed approaches. [ABSTRACT FROM AUTHOR]

With the rapid development of IoT, big data and artificial intelligence, the research and application of data-driven hydrological models are increasing. However, when conducting time series analysis, many prediction models are often directly based on the following assumptions: hydrologic time series are normal, homogeneous, smooth and non-trending, which are not always all true. To address the related issues, a solution for short-term hydrological forecasting is proposed. Firstly, a feature test is conducted to verify whether the hydrological time series are normal, homogeneous, smooth and non-trending; secondly, a sequence-to-sequence (seq2seq)-based short-term water level prediction model (LSTM-seq2seq) is proposed to improve the accuracy of hydrological prediction. The model uses a long short-term memory neural network (LSTM) as an encoding layer to encode the historical flow sequence into a context vector, and another LSTM as a decoding layer to decode the context vector in order to predict the target runoff, by superimposing on the attention mechanism, aiming at improving the prediction accuracy. Using the experimental data regarding the water level of the Chu River, the model is compared to other models based on the analysis of normality, smoothness, homogeneity and trending of different water level data. The results show that the prediction accuracy of the proposed model is greater than that of the data set without these characteristics for the data set with normality, smoothness, homogeneity and trend. Flow data at Runcheng, Wuzhi, Baima Temple, Longmen Town, Dongwan, Lu's and Tongguan are used as input data sets to train and evaluate the model. Metrics RMSE and NSE are used to evaluate the prediction accuracy and convergence speed of the model. The results show that the prediction accuracy of LSTM-seq2seq and LSTM-BP models is higher than other models. Furthermore, the convergence process of the LSTM-seq2seq model is the fastest among the compared models. [ABSTRACT FROM AUTHOR]

Featured Application: In spite of the significant developments in machine learning methods employed for short-term electrical load forecasting on a Country level, the complexity and diversity of the problem points to the need for investing more research effort in the selection of representative input datasets for the training. This is demonstrated in the example of the Greek electricity system, where careful selection and quality assurance of input data resulted in quite acceptable levels of prediction accuracy, even when training standard, robust feed-forward artificial neural networks. Short-term load forecasting is an essential instrument in power system planning, operation, and control. It is involved in the scheduling of capacity dispatch, system reliability analysis, and maintenance planning for turbines and generators. Despite the high level of development of advanced types of machine learning models in commercial codes and platforms, the prediction accuracy needs further improvement, especially in certain short, problematic time periods. To this end, this paper employs public domain electric load data and typical climatic data to make 24-hour-ahead hourly electricity load forecasts of the Greek system based on two types of robust, standard feed-forward artificial neural networks. The accuracy and stability of the prediction performance are measured by means of the modeling error values. The current prediction accuracy levels of mean absolute percentage error, mean value μ = 2.61% with σ = 0.33% of the Greek system operator for 2022, attained with noon correction, are closely matched with a simple feed-forward artificial neural network, attaining mean value μ = 3.66% with σ = 0.30% with true 24-hour-ahead prediction. Specific instances of prediction failure in cases of unexpectedly high or low energy demand are analyzed and discussed. The role of the structure and quality of input data of the training datasets is demonstrated to be the most critical factor in further increasing the accuracy and reliability of forecasting. [ABSTRACT FROM AUTHOR]

This paper discusses the efficient implementation of a new hybrid approach to forecasting short-term PV power production for four different PV plants in Algeria. The developed model incorporates a time-varying filter-empirical mode decomposition (TVFEMD) and an extreme learning machine (ELM) as an essence regression. The TVF-EMD technique is used to deal with the fluctuation of PV power data by splitting it into a series of more stable and constant subseries. The specified set of features (intrinsic mode functions (IMFs)) is utilized for training and improving our forecasting extreme learning machine model. The adjusted ELM model is used to evaluate prediction e1ciency. The suggested TVF-EMD-ELM model is assessed and verified in various Algerian locations with varying climate conditions. In all examined regions, the TVF-EMD-ELM model generates less than 4% error in terms of normalized root mean square error (nRMSE). [ABSTRACT FROM AUTHOR]

In order to effectively carry out the heavy overload monitoring and maintenance of public transformers in the distribution network, ensure the reliability of the distribution network power supply, and improve customer satisfaction with electricity consumption, this paper presents a short-term heavy overload forecasting method for public transformers based on the LSTM-XGBOOST combined model. The model extracts heavy overload feature variables from four dimensions, including basic parameter information, weather, time, and recent load, and constructs a short-term second highest load prediction model based on the LSTM algorithm to obtain the predicted value of the second highest load rate. After aggregating the heavy overload feature variables and the predicted second highest load rate, the XGboost algorithm is employed to construct a short-term heavy overload prediction model for public transformers to judge whether the public transformers display heavy overload. The test results show that this method has high accuracy in short-term heavy overload forecasting, and can effectively assist in the key monitoring and control of heavy overload in public transformers. [ABSTRACT FROM AUTHOR]

Intermittency in the grid creates operational issues for power system operators (PSO). One such intermittent parameter is load. Accurate prediction of the load is the key to proper planning of the power system. This paper uses regression analyses for short-term load forecasting (STLF). Assumed load data are first analyzed and outliers are identified and treated. The cleaned data are fed to regression methods involving Linear Regression, Decision Trees (DT), Support Vector Machine (SVM), Ensemble, Gaussian Process Regression (GPR), and Neural Networks. The best method is identified based on statistical analyses using parameters such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Square Error (MSE), R 2 , and Prediction Speed. The best method is further optimized with the objective of reducing MSE by tuning hyperparameters using Bayesian Optimization, Grid Search, and Random Search. The algorithms are implemented in Python and Matlab Platforms. It is observed that the best methods obtained for regression analysis and hyperparameter tuning for an assumed data set are Decision Trees and Grid Search, respectively. It is also observed that, due to hyperparameter tuning, the MSE is reduced by 12.98%. [ABSTRACT FROM AUTHOR]

With growing interest in sustainability and net-zero emissions, there has been a global trend to integrate wind power into energy grids. However, challenges such as the intermittency of wind energy remain, which leads to a significant need for accurate wind-power forecasting. Therefore, this study focuses on creating a wind-power generation-forecasting model using a machine-learning algorithm. In this study, we used the gradient-boosting machine (GBM) algorithm to build a wind-power forecasting model. Time-series data with a 15 min interval from Jeju's wind farms were applied to the model as input data. The short-term forecasting model trained by the same month with the test set turns out to have the best performance, with an NMAE value of 5.15%. Furthermore, the forecasting results were applied to Jeju's power system to carry out a grid-security analysis. The improved accuracy of wind-power forecasting and its impact on the security of electrical grids in this study potentially contributes to greater integration of wind energy. [ABSTRACT FROM AUTHOR]

Short-term load forecasting is essential for power companies because it is necessary to ensure sufficient capacity. This article proposes a smart load forecasting scheme to forecast the short-term load for an actual sample network in the presence of uncertainties such as weather and the COVID-19 epidemic. The studied electric load data with hourly resolution from the beginning of 2020 to the first seven days of 2021 for the New York Independent Operator is the basis for the modeling. The new components used in this article include the coordination of stacked long short-term memory-based models and feature engineering methods. Also, more accurate and realistic modeling of the problem has been implemented according to the existing conditions through COVID-19 epidemic data. The influential variables for short-term load forecasting through various feature engineering methods have contributed to the problem. The achievements of this research include increasing the accuracy and speed of short-term electric load forecasting, reducing the probability of overfitting during model training, and providing an analytical comparison between different feature engineering methods. Through an analytical comparison between different feature engineering methods, the findings of this article show an increase in the accuracy and speed of short-term load forecasting. The results indicate that combining the stacked long short-term memory model and feature engineering methods based on extra-trees and principal component analysis performs well. The RMSE index for day-ahead load forecasting in the best engineering method for the proposed stacked long short-term memory model is 0.1071. [ABSTRACT FROM AUTHOR]

Radar reflectivity assimilation is often used to initialize hydrometeors, to which Numerical Weather Prediction (NWP) is highly sensitive. To better initialize hydrometeors, this study further developed the background error covariance (BEC) with vertical and multivariable correlations of hydrometeor control variables (H-BEC) in the WRF three-dimensional variational data assimilation system (WRFDA-3DVar). The impacts of the H-BEC are discussed using single radar reflectivity tests and series of cycling data assimilation and forecasting experiments for five multi-type convective rainfall cases. The conclusions are summarized as follows: (1) The vertical correlations can speed up the minimization of the cost function, whereas the multivariable correlations further accelerate this minimization; (2) The vertical correlations slightly improve the precipitation forecasting and only in the first hour, while multivariate correlations lead to a larger improvement and persist into the third hour; (3) The application of H-BEC leads to a more reasonable thermodynamic and dynamical structure of the initial field, thereby improving the capability of short-term precipitation forecasting. [ABSTRACT FROM AUTHOR]

Accurate electricity demand forecasting can provide a timely and effective reference for economic control and facilitate the secure production and operation of power systems. However, electricity data are well known for their nonlinearity and multi-seasonal features, making it challenging to construct forecasting models. This study investigates the combination of singular spectrum analysis to facilitate the construction of decomposition-based forecasting approaches for electricity load. First, we demonstrate and emphasize the importance of separability for specifically extracting different features hidden in the original data; moreover, only by using the separable feature subseries, the constructed individual model can capture the inner and distinct characteristics of original series more effectively. Second, this study decomposes the electricity load into several significant features using singular spectrum analysis. Each feature series is predicted separately to construct aggregate results. In particular, we propose SSA-based period decomposition to not only perform separable decomposition but also overcome the border effect, which has received little attention in previous work. Finally, to verify the effectiveness of the proposed method, we conduct an empirical study and compare the performance of the discussed models. The empirical results show that the proposed approach can obtain the expected forecasting performance and is a reliable and promising tool for extracting different features. [ABSTRACT FROM AUTHOR]

The demand for electrical energy continues to rise at an alarming rate, while supply is not proportional to power demand. Thus, in order to accomplish appropriate preparation and operation of an electrical power system network, it is crucial to properly assess the present and future consumption of electric power systems. Meeting the electric load needs entails actively anticipating the amount of energy required to meet the subscribers' power demand. To forecast energy demand, many algebraic and artificial intelligence schemes have been used. This paper proposes an improved medium-term forecasting scheme that employs an artificial neural network (ANN). The model was developed and trained with the help of an artificial neuro-fuzzy inference system (ANFIS). The data used, which ranged from 2014 to 2019, was obtained from the University of Nigeria Nsukka's (UNN) research and energy Centre, and the works department of the same university. The model was designed and simulated using MATLAB 2018a, and the results were evaluated using MAPE. The proposed system used a robust machine learning based scheme. Unlike conventional systems, the system demonstrated a MAPE of 4.34% and a correlation of 0.91144315 at predicted and actual loads, as shown in Table 2. The proposed system shows that the predicted loads has 25th and 75th percentiles of 0.58MW and 0.98WM, while that of the actual loads are 0.649MW and 0.936MW. [ABSTRACT FROM AUTHOR]

Maritime surveillance is of utmost priority for a nation's security, and hence it's economy. For maritime awareness, coastal surveillance, and maritime activities in the Region of Interest (ROI) should be monitored. One of the ways to keep this in check is to restrain unwanted infiltration. Monitoring unwanted infiltration is feasible through vessel trajectory forecasting and anomaly detection in real time. Most solutions for trajectory predictions are available but require a huge amount of historical data, and high-power computing resources. Here, the requirement is developing a decision support framework consisting of both lite weight approaches for short-term predictions and deep learning-based techniques for long-term forecasting. This paper aims to find the suitability of Linear Stationary Models (LSM) like the Auto-Regressive Integrated Moving Average Model (ARIMA) for predicting and forecasting the Vessel Trajectory as means of lite weight short-term predictions. For this purpose, the Automatic Identification System (AIS) dataset of the U.S. West Coast is used. The significant effort was for data pre-processing to create a robust dataset for model training. An appropriate model after the model-selection process is used for trajectory forecasting. The model's accuracy is validated using Root Mean Square Error (RMSE) performance indices for residual and forecast errors. A window generator model is integrated with the best-fitted ARIMA model for recursive real-time predictions, with varied sizes and visualization. The proposed time-series model provided a very high accuracy as the RMSE value for prediction and 48 hours forecast are 0.023 and 0.017, respectively. [ABSTRACT FROM AUTHOR]

COVID-19 is a pandemic that has resulted in numerous fatalities and infections in recent years, with a rising tendency in both the number of infections and deaths and the pace of recovery. Accurate forecasting models are important for making accurate forecasts and taking relevant actions. As a result, accurate short-term forecasting of the number of new cases that are contaminated and recovered is essential for making the best use of the resources at hand and stopping or delaying the spread of such illnesses. This paper shows the various techniques for forecasting the covid-19 cases. This paper classifies the various models according to their category and shows the merits and demerits of various fore-casting techniques. The research provides insight into potential issues that may arise during the forecasting of covid-19 instances for predicting the positive, negative, and death cases in this pandemic. In this paper, numerous forecasting techniques and their categories have been studied. The goal of this work is to aggregate the findings of several forecasting techniques to aid in the fight against the pandemic. [ABSTRACT FROM AUTHOR]

Excavation load prediction is of great importance for the prior design and latter performance evaluation of tunnel boring machines (TBMs). In this paper, an improved load prediction model is developed based on classical Colorado school of mines model for TBMs equipped with constant cross-sectional disc cutters. The typical structure and principle are introduced to predict the single cutter force, and the total cutter group load is calculated by defining the equivalent diameter and cutter spacing. Subsequently, the improved model of a more brief and acceptable type is established via summation. Some novel performance indexes, including the reformed field penetration index, torque/thrust penetration index, and specific energy are, respectively, derived in formulaic form. By field data verification in the borehole zones of two cases, the proposed model is proven to be more accurate in the total load prediction. The single-factor regression results show that the reformed field penetration index reveals the nonlinear relationship between TBM load and penetration rate, and the torque/thrust penetration index is a new TBM inherent index to evaluate the working conditions. Specific energy, used to evaluate the excavation efficiency, is positive with rock strength and proved negative with penetration rate via a normalization analysis. Finally, suggestions on the cutter group configuration against abominable stratum are discussed. [ABSTRACT FROM AUTHOR]

Energy efficiency is crucial to greenhouse gas (GHG) emission pathways reported by the Intergovernmental Panel on Climate Change. Electrical overload frequently occurs and causes unwanted outages in distribution networks, which reduces energy utilization efficiency and raises environmental risks endangering public safety. Electrical load, however, has a dynamically fluctuating behavior with notoriously nonlinear hourly, daily, and seasonal patterns. Accurate and reliable load forecasting plays an important role in scheduling power generation processes and preventing electrical systems from overloading; nevertheless, such forecasting is fundamentally challenging, especially under highly variable power load and climate conditions. This study proposed a deep learning–based monotone composite quantile regression neural network (D-MCQRNN) model to extract the multiple non-crossing and nonlinear quantile functions while conquering the drawbacks of error propagation and accumulation encountered in multi-step-ahead probability density forecasting. The constructed models were assessed by an hourly power load series collected at the electric grid center of Henan Province in China in two recent years, along with the corresponding meteorological data collected at 16 monitoring stations. The results demonstrated that the proposed D-MCQRNN model could significantly alleviate the time-lag and biased-prediction phenomena and noticeably improve the accuracy and reliability of multi-step-ahead probability density forecasts on power load. Consequently, the proposed model can significantly reduce the risk and impact of overload faults and effectively promote energy utilization efficiency, thereby mitigating GHG emissions and moving toward cleaner energy production. [ABSTRACT FROM AUTHOR]

Since the outbreak of the Coronavirus Disease 2019 (COVID-19), the spread of the epidemic has been a major international public health issue. Hence, various forecasting models have been used to predict the infectious spread of the disease. In general, forecasting problems often involve prediction accuracy decreasing as the horizon increases. Thus, to extend the forecasting horizon without decreasing performance or prediction, this study developed a Dual Long Short-Term Memory (LSTM) with Genetic Algorithms (DULSTMGA) model. The model employed predicted values generated by LSTM models in short-forecasting horizons as inputs for the long-term prediction of LSTM in a rolling manner. Genetic algorithms were applied to determine the parameters of LSTM models, allowing long-term forecasting accuracy to increase as long as short-term forecasting was accurate. In addition, the compartment model was utilized to simulate the state of COVID-19 and generate numbers of infectious cases. Infectious cases in three countries were employed to examine the feasibility and performance of the proposed DULSTMGA model. Numerical results indicated that the DULSTMGA model could obtain satisfactory forecasting accuracy and was superior to many previous studies in terms of the mean absolute percentage error. Therefore, the designed DULSTMGA model is a feasible and promising alternative for forecasting the number of infectious COVID-19 cases. [ABSTRACT FROM AUTHOR]

The penetration of photovoltaic (PV) energy has gained a significant increase in recent years because of its sustainable and clean characteristics. However, the uncertainty of PV power affected by variable weather poses challenges to an accurate short-term prediction, which is crucial for reliable power system operation. Existing methods focus on coupling satellite images with ground measurements to extract features using deep neural networks. However, a flexible predictive framework capable of handling these two data structures is still not well developed. The spatial and temporal features are merely concatenated and passed to the following layer of a neural network, which is incapable of utilizing the correlation between them. Therefore, we propose a novel dual-encoder transformer (DualET) for short-term PV power prediction. The dual encoders contain wavelet transform and series decomposition blocks to extract informative features from image and sequence data, respectively. Moreover, we propose a cross-domain attention module to learn the correlation between the temporal features and cloud information and modify the attention modules with the spare form and Fourier transform to improve their performance. The experiments on real-world datasets, including PV station data and satellite images, show that our model achieves better results than other models for short-term PV power prediction. [ABSTRACT FROM AUTHOR]