Search

Short-term power load forecasting is of great significance for the reliable and safe operation of power systems. In order to improve the accuracy of short-term load forecasting, for the problems of random fluctuation in load and the complexity of load-influencing factors, this paper proposes a two-stage short-term load forecasting method, SSA–VMD-LSTM-MLR-FE (SVLM–FE) based on sparrow search algorithm (SSA), to optimize variational mode decomposition (VMD) and feature engineering (FE). Firstly, an evaluation criterion on the loss of VMD decomposition is proposed, and SSA is used to find the optimal combination of parameters for VMD under this criterion. Secondly, the first stage of forecasting is carried out, and the different components obtained from SSA–VMD are predicted separately, with the high-frequency components input to a long short-term memory network (LSTM) for forecasting and the low-frequency components input to a multiple linear regression model (MLR) for forecasting. Finally, the forecasting values of the components obtained in the first stage are input to the second stage for error correction; factors with a high degree of influence on the load are selected using the Pearson correlation coefficient (PCC) and maximal information coefficient (MIC), and the load value at the moment that has a great influence on the load value at the time to be predicted is selected using autocorrelation function (ACF). The forecasting values of the components are fused with the selected feature values to construct a vector, which is fed into the fully connected layer for forecasting. In this paper, the performance of SVLM–FE is evaluated experimentally on two datasets from two places in China. In Place 1, the RMSE, MAE, and MAPE are 128.169 MW, 102.525 MW, and 1.562%, respectively; in Place 2, the RMSE, MAE, and MAPE are 111.636 MW, 92.291 MW, and 1.426%, respectively. The experimental results show that SVLM–FE has high accuracy and stability. [ABSTRACT FROM AUTHOR]

Purpose: Visible and near-infrared reflectance spectroscopy has been proven to be an efficient method for predicting soil properties, and the wavelength optimization can improve the simulation accuracy of SOM (soil organic matter), but the best combination of wavelength optimization algorithms and inversion model is unknown for alpine ecosystem soil. Methods: In this study, 269 topsoil samples were collected in the Three-Rivers Source Region of China and were used to build the inversion model of SOM content. Four kinds of wavelength optimization algorithms were conducted, i.e., correlation analysis, uninformative variable elimination (UVE), successive projection algorithm, and competitive adaptive reweighted sampling (CARS) after spectral pre-treatments. Then, partial least squares regression, support vector machine, and random forest (RF) were used to develop the inversion model of SOM content. Various combinations of wavelength optimization algorithms and inversion models were constructed, and the accuracies were compared. Results: The combination of the UVE-CARS-RF achieved the highest simulation accuracy (R2 = 0.902, RPD = 3.218). For the single band selection method, the CARS algorithm has the highest simulation accuracy, especially the combination of CARS-RF (R2 = 0.899, RPD = 3.133). Conclusion: Appropriate combination of the wavelength optimization algorithm and inversion model not only can significantly reduce computational load but improve the prediction precision. In total, RF obtained the best predication effect. [ABSTRACT FROM AUTHOR]

Accurate prediction of wind power is of great significance to the stable operation of the power system and the vigorous development of the wind power industry. In order to further improve the accuracy of ultra-short-term wind power forecasting, an ultra-short-term wind power forecasting method based on the CGAN-CNN-LSTM algorithm is proposed. Firstly, the conditional generative adversarial network (CGAN) is used to fill in the missing segments of the data set. Then, the convolutional neural network (CNN) is used to extract the eigenvalues of the data, combined with the long short-term memory network (LSTM) to jointly construct a feature extraction module, and add an attention mechanism after the LSTM to assign weights to features, accelerate model convergence, and construct an ultra-short-term wind power forecasting model combined with the CGAN-CNN-LSTM. Finally, the position and function of each sensor in the Sole du Moulin Vieux wind farm in France is introduced. Then, using the sensor observation data of the wind farm as a test set, the CGAN-CNN-LSTM model was compared with the CNN-LSTM, LSTM, and SVM to verify the feasibility. At the same time, in order to prove the universality of this model and the ability of the CGAN, the model of the CNN-LSTM combined with the linear interpolation method is used for a controlled experiment with a data set of a wind farm in China. The final test results prove that the CGAN-CNN-LSTM model is not only more accurate in prediction results, but also applicable to a wide range of regions and has good value for the development of wind power. [ABSTRACT FROM AUTHOR]

Runoff prediction with high accuracy is vital to protect people's properties and lives. In this study, a Short-Term Streamflow Forecasting Framework combining Long Short-Term Memory (LSTM) with Self-Organizing Map (SOM) is proposed, which clusters hydro-meteorological factors through SOM network to cluster the streamflow into several flow modes with different physical characteristics, converting complex global modeling into local modeling. The framework also considers the temporal characteristics of the streamflow, so the data of different flow modes are fitted with multiple LSTM separately. Besides, Random Forest is used in the framework for feature selection. The model is used for streamflow forecasting 1 to 3 day(s) ahead in the Qingxi River Basin in China, and the performance is compared with those of SVR, ANN, LSTM, SOM-SVR, SOM-ANN, FCM-LSTM, and K-means-LSTM. In addition, SOM-LSTM with three and four clusters were compared. The results show that (1) the sub-processes obtained by SOM clustering show some physical characteristics consistent with the actual process. (2) SOM-LSTM significantly improves the prediction accuracy of short-term streamflow forecasting. (3) All the integrated models using different clustering methods can improve the prediction accuracy of a single LSTM, and SOM-LSTM has the most reliable prediction when the lead time is 1–2 day(s). (4) The number of clusters being set to 4 is more suitable for the proposed prediction framework. The overall results show that the SOM-LSTM provides an efficient method for short-term streamflow forecasting. [ABSTRACT FROM AUTHOR]

With the deepening reform of the power system, power sales companies need to adopt new power sales strategies to provide customers with better economic marketing solutions. Customer-side configuration of an energy storage system (ESS) can participate in power-related policies to reduce the comprehensive cost of electricity for commercial and industrial customers and improve customer revenue. For power sales companies, this can also attract new customers, expand sales and quickly capture the market. However, most of the ESS evaluation models studied so far are based on historical data configuration of typical daily storage capacity and charging and discharging scheduling instructions. In addition, most models do not adequately consider the performance characteristics of the ESS and cannot accurately assess the economics of the energy storage model. This study proposes an intelligent power sales strategy based on load forecasting with the participation of optimal allocation of ESS. Based on long short-term memory (LSTM) artificial neural network for predictive analysis of customer load, we evaluate the economics of adding energy storage to customers. Based on the premise of the two-part tariff, the ESS evaluation model is constructed with the objective of minimizing the annual comprehensive cost to the user by considering the energy tariff and the savings benefits of the basic tariff, assessing the annualized cost of ESS over its entire life cycle, and the impact of battery capacity decay on economics. The particle swarm optimization (PSO) algorithm is introduced to solve the model. By simulating the arithmetic example for real customers, their integrated electricity costs are significantly reduced. Moreover, this smart power sales strategy can provide different sales strategies according to the expected payback period of customers. This smart sales strategy can output more accurate declared maximum demand values than other traditional sales strategies, providing a more economical solution for customers. [ABSTRACT FROM AUTHOR]

Based on the counted power system emission factors of North China Power Grid, a community carbon emissions sample database is constructed. The support vector regression (SVR) model is trained to forecast the power carbon emissions, which is optimized by genetic algorithm (GA). A community carbon emission warning system is designed according the results. The dynamic emission coefficient curve of the power system is obtained by fitting the annual carbon emission coefficients. The time series SVR carbon emission prediction model is constructed, while the GA is improved to optimize its parameters. Taking Beijing Caochang Community as an example, a carbon emission sample database is generated based on the electricity consumption and emission coefficient curve to train and test the SVR model. The results show that the GA–SVR model fits well with the training set and the testing set, and the prediction accuracy of the testing set reaches 86%. In view of the training model in this paper, the carbon emission trend of community electricity consumption in the next month is predicted. The carbon emission warning system of the community is designed, and the specific strategy of community carbon emission reduction is proposed. [ABSTRACT FROM AUTHOR]

To improve the accuracy of short-term wind speed forecasting, we proposed a Gated Recurrent Unit network forecasting method, based on ensemble empirical mode decomposition and a Grid Search Cross Validation parameter optimization algorithm. In this study, first, in the process of decomposing, the set empirical mode of decomposition was introduced to divide the wind time series into high-frequency modal, low-frequency modal, and trend modal, using the Pearson correlation coefficient. Second, during parameter optimization, the grid parameter optimization algorithm was employed in the GRU model to search for the combination of optimal parameters. Third, the improved GRU model was driven with the decomposed components to predict the new components, which were used to obtain the predicted wind speed by modal reorganization. Compared with other models (i.e., the LSTM, GS-LSTM, EEMD-LSTM, and the EEMD-GS-LSTM), the proposed model was applied to the case study on wind speed of a wind farm, located in northwest China. The results showed that the presented forecasting model could reduce the forecasting error (RMSE) from 1.411 m/s to 0.685 m/s and can improve the accuracy of forecasts. This model provides a new approach for short-term wind speed forecasting. [ABSTRACT FROM AUTHOR]

Accurate short-term load forecasting is the key to ensuring smooth and efficient power system operation and power market dispatch planning. However, the nonlinear, non-stationary, and time series nature of load sequences makes load forecasting difficult. To address these problems, this paper proposes a short-term load forecasting method (EPT-VMD-TCN-TPA) based on the hybrid decomposition of load sequences, which combines ensemble patch transform (EPT), variational modal decomposition (VMD), a temporal convolutional network (TCN), and a temporal pattern attention mechanism (TPA). In which, the trend component (Tr(t)) and the residual fluctuation component (Re(t)) of the load series are extracted using EPT, and then the Re(t) component is decomposed into intrinsic modal function components (IMFs) of different frequencies using VMD. The Tr(t) and IMFs components of the fused meteorological data are predicted separately by the TCN-TPA prediction model, and finally, the prediction results of each component are reconstructed and superimposed to obtain the final predicted value of the load. In addition, experiments after reconstructing each IMF component according to the fuzzy entropy (FE) values are discussed in this paper. To evaluate the performance of the proposed method in this paper, we used datasets from two Areas of the 9th Mathematical Modeling Contest in China. The experimental results show that the predictive precision of the EPT-VMD-TCN-TPA model outperforms other comparative models. More specifically, the experimental results of the EPT-VMD-TCN-TPA method had a MAPE of 1.25% and 1.58% on Area 1 and Area 2 test sets, respectively. [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]

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]

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]

The randomness and instability of wind power bring challenges to power grid dispatching. Accurate prediction of wind power is significant to ensure the stable development of power grid. In this paper, a new ultra-short-term wind power forecasting model based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and long-short-term memory (LSTM) network optimized by improved whale optimization algorithm (IWOA) is proposed. Firstly, CEEMDAN is applied to decompose the power history data into several intrinsic mode functions (IMFs) and a residual (RS) to reduce the complexity and unsteadiness of the original data. Then the partial autocorrelation method is used to analyze and select the input variables of each IMF and the residual. Finally, the IWOA-LSTM prediction model is established, and the parameters of LSTM are optimized by using the improved whale optimization algorithm. Each IMF and the residual are predicted respectively. The prediction results are superimposed to obtain the final wind power prediction value. The hybrid model is applied to the ultra-short-term wind power prediction of a wind farm in northern China. The prediction results of comparison experiments with other 11 models prove the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

The power industry has significantly contributed to the prosperity of the national economy, and accurate prediction can reflect the development trend of the power system and power market. The short-term electricity consumption of a country exhibits both annual growth certainty and random change uncertainty, which can be suitably considered with the grey forecasting model. Regarding the short-term trends of electricity consumption in China, this study established an optimized multivariate grey forecasting model with variable background values (OGM(1, N) model) to forecast the electricity consumption level in China. The established model could be converted into the GM(1, N) model and different variant models by adjusting the model parameters. With Beijing, Tianjin and Shanghai as examples, the OGM(1, N) model is compared to the GM(1, N) model and its variant model. The excellent prediction results confirm the feasibility of the proposed model. Then, the proposed model is applied to study China's electricity consumption. The research results indicated that the OGM(1, N) model attains an extraordinarily high precision in the prediction of electricity consumption and can provide a practical reference for accurate electricity consumption prediction. [ABSTRACT FROM AUTHOR]

As the scale of distributed renewable energy represented by wind power and photovoltaic continues to expand and load demand gradually changes, the future evolution of the smart distribution network will be directly driven by both distributed generation and user demand. The smart distribution network contains a wide range of flexible resources, and its flexibility and uncertainty will bring great challenges to grid data acquisition and control feedback. To adapt to the precise control and feedback of smart distribution network access equipment under the high proportion of new energy access and to ensure the safe operation of the system, it is urgent to accelerate the study of the evolution of the future distribution grid based on the existing distribution grid. Hence, a multi-stage planning method for distribution networks based on source–load prediction is proposed in this paper. Firstly, a distribution network source–load prediction method based on the autoregressive integrated moving average model (ARIMA) and error gradient sampling is proposed, using ARIMA to predict the scale of source–load development and error gradient sampling based on the generation of source–load scenarios with error intervals. K-means is further used for scenario reduction, to explore multiple operating scenarios of China's distribution network source–load, and the unit's output forecast interval and load demand from 2021 to 2030 for typical regions are derived using rolling forecasts by combining the unit's output, end-demand and clean energy share over the years. Secondly, the planning model of distribution grid evolution in different stages is constructed to analyze the future evolution form of the distribution grid considering the distribution network's load cross-section, respectively, and to provide a development path reference for the future construction of distribution grid form in China. [ABSTRACT FROM AUTHOR]

Accurate forecasting of natural gas load forecasting is of great practical significance to balance supply and demand of gas system. Load forecasting is categorized in long-term, mid-term and short-term. Among them, mid-term load forecasting that monitors monthly operations is of decisive significance to urban gas pipe network planning, gas engineering project construction and design. In this study, we adopt Prophet model that reflects the seasonal fluctuations and holidays influence to forecasting the monthly gas load of urban gas and compare the results with the other two forecasting methods such as autoregressive integrated moving average model (ARIMA) and exponential smoothing prediction method (ESM). The models were trained and tested on gas consumption data gathered in one central city in China from 2017 to 2021. The result shows that an increasing trend with an average growth rate between 10% and 20% year by year, a decreasing trend at an average rate of 14.9% on legal holiday. According to this study, the Prophet model has an excellent performance in monthly natural gas forecasting. [ABSTRACT FROM AUTHOR]

The economic growth in the new normal is no longer limited to the total amount and scale of economic growth in the traditional and neoclassical periods, but has changed to "quality" and "development" under the dual requirements of historical changes and tasks of the times. The quality of regional economic growth is an important part of the quality of China's economic development and an important part of the quality of China's economic development in the new era. Therefore, this paper proposes a BP neural network based on visual recognition in a regional economic prediction model and conducts application experiments. This regional economic forecasting model is relying on data technology for economic panel data mining, then graphical processing of panel data, followed by the selection of visual recognition technology for economic panel map analysis, to derive its various component coefficients, and finally then using the BP neural network to fit the prediction, at the same time, through long-term and short-term prediction, to predict the future development quality of each region's change trends and fluctuations, to predict the institution's role, so as to avoid major transitions and deteriorating alarms, and to provide support for the macroregulation of regional economic development quality. [ABSTRACT FROM AUTHOR]

Photovoltaic power generation is greatly affected by weather factors. To improve the prediction accuracy of photovoltaic power generation, complete ensemble empirical mode decomposition with an adaptive noise algorithm (CEEMDAN) is proposed to preprocess the power sequence. Then, the full convolutional network (FCN) model optimized based on the sparrow search algorithm (SSA) is used to predict the short-term photovoltaic power. SSA can more reasonably determine the parameters of FCN and improve the prediction performance of FCN. Therefore, the FCN model optimized by the SSA algorithm is used to establish prediction models for subsequences and predict each subsequence, respectively. Finally, the predicted value of each subsequence is superimposed. Taking the actual data of a photovoltaic power station in Jiangsu province of China as an example, by comparing some different common prediction models, it is proved that the proposed method is reasonable and feasible. [ABSTRACT FROM AUTHOR]

Accurate solar and wind generation forecasting along with high renewable energy penetration in power grids throughout the world are crucial to the days-ahead power scheduling of energy systems. It is difficult to precisely forecast on-site power generation due to the intermittency and fluctuation characteristics of solar and wind energy. Solar and wind generation data from on-site sources are beneficial for the development of data-driven forecasting models. In this paper, an open dataset consisting of data collected from on-site renewable energy stations, including six wind farms and eight solar stations in China, is provided. Over two years (2019–2020), power generation and weather-related data were collected at 15-minute intervals. The dataset was used in the Renewable Energy Generation Forecasting Competition hosted by the Chinese State Grid in 2021. The process of data collection, data processing, and potential applications are described. The use of this dataset is promising for the development of data-driven forecasting models for renewable energy generation and the optimization of electricity demand response (DR) programs for the power grid. Measurement(s) renewable energy generation Technology Type(s) supervisory control and data acquisition system Sample Characteristic - Location China [ABSTRACT FROM AUTHOR]

With the rapid development of re‐electrification, traditional load forecasting faces a significant increase of influencing factors. Existing literature focuses on examining the influencing factors related to load profiles in order to improve the prediction accuracy. However, a large number of redundant features may lead to the overfitting of the forecasting engine. To enhance the performance of extreme learning machine (ELM) under massive data scale, this paper presents a kernel extreme learning machine (KELM) based method which can be used for short‐term load prediction. First, a feature dimensionality reduction is performed using a kernelized principal component analysis, which aims to eliminate redundant input vectors. Then, the hyperparameters of KELM are optimized to improve the prediction accuracy and generalization. Case studies based on a province‐level power system in China demonstrate that the presented method can significantly improve the accuracy of load forecasting by 3.14% in contrast to traditional ELM. [ABSTRACT FROM AUTHOR]

Long-term electricity consumption forecasting has been a hot issue due to its importance in power systems planning. Recently, system dynamics (SD) have been considered a potential method for electricity consumption forecasting. However, traditional SD methods are failed in forecasting future power systems toward low-carbon, due to the complex influencing factors and the simple SD model structure. In this study, a novel method combining SD and the ImPACT equation is proposed to solve the above problem. First, a new influencing factor system including emerging factors is established to consider the development of future power system. Subsequently, the ImPACT equation is employed to decompose the electricity consumption into four subsystems. By doing this, the linkage between factors and electricity consumption can be better revealed, which helps to improve the forecasting accuracy. Next, models for quantifying the correlation between subsystems and factors are established using SD. Finally, the proposed method is verified by forecasting the power consumption of China in the future year 2030 to 2050. Furthermore, various scenarios are set to analyze the changing trend of future power consumption by different influencing factors. The results of this article can provide important basic information for power supply and power grid planning. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the traditional wind power forecasting is difficult to deal with a large amount of strong volatility data and limited processing capacity of time series, a wind power forecasting method based on multi-model combination under stacking framework was proposed. First, the wind turbine data are cleaned by density-based spatial clustering of applications with the noise clustering method. Considering the differences of data observation and training principles, the proposed stacking method embedded multiple machine learning algorithms to utilize their diversified strength. The stacking base-learner includes the CBLSTM model, which has the advantages of deep architecture feature extraction, and takes into account data timing and nonlinear relationship as well as XGBoost and other tree ensemble learning models that were suitable for complex data modeling. The feasibility of the algorithm was verified by using the actual wind power data of two wind farms in Northeast and Western China. Experimental results show that the stacking ensemble learning method proposed has better forecasting performance and stability than other single forecasting models, which is of great significance to guide wind power dispatching operation and improve wind power consumption capacity. [ABSTRACT FROM AUTHOR]

This paper presents a multi-timescale receding horizon framework for the load forecast of large power customers. The future load pattern of individual users could be very difficult to predict because of its chronological and high volatile properties. Also, the sampling of nonaggregated load data may suffer from severe information missing issues. To address these challenges, we first develop an online singular value thresholding (SVT) algorithm, which utilizes the approximate low-rank property of load data matrices to efficiently recover the missing information. Then, a combinatorial deep learning method is developed, which applies the multi-layer perception (MLP) neural network and the long short-term memory (LSTM) neural network with gated recurrent unit (GRU) to deal with the short-term and ultra-short-term load forecast, respectively. Specifically, an early stopping strategy is designed and implemented to avoid the over-fitting of model training. Moreover, the receding time window is imposed to dynamically update the data recovery and load forecast outcomes, which supports the online computing on a Spark platform. Numerical experiments on real-world load data from North China confirms the effectiveness of the proposed methodology, which can support more complex applications in embedded systems and cyber physical systems. [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.)

Forecasting the electricity consumption has always played an important role in the management of power system management, which requires higher forecasting technology. Therefore, based on the principle of "new information priority", combined with rolling mechanism and Markov theory, a novel grey power-Markov prediction model with time-varying parameters (RGPMM(λ,1,1)) is designed, which overcomes the inherent defects of fixed structure and poor adaptability to the changes of original data. In addition, in order to prove the validity and applicability of the prediction model, we have used the model to predict China's total electricity consumption, and have compared it with the prediction results by a series of benchmark models. The result shows that the can better adapt to the characteristics of electricity consumption data, and it also shows the advantages of the proposed forecasting model. In this paper, the proposed forecasting model is used to predict China's total electricity consumption in the next six years from 2018 to 2023, so as to provide certain reference value for power system management and distribution. [ABSTRACT FROM AUTHOR]

Short‐term load forecasting is essential to power systems management. However, most existing forecasting methods fail to fully consider how to rationally integrate the intrinsic time‐related dimensions of electric load data and the decomposition methods into machine learning models so that their prediction accuracy and robustness still have much room for improvement. To solve this problem, this paper proposes a decomposition‐based multi‐time dimension long short‐term memory (DB‐MTD‐LSTM) model for short‐term electric load forecasting (STELF). In DB‐MTD‐LSTM, empirical mode decomposition with adaptive noise (CEEMDAN) is first introduced to smooth non‐linear non‐stationary electric load data and constrain the modal aliasing or noise of decomposed electric load data in the traditional decomposed method. A joint relevant time dimensions method (JRTDM) is then developed using autocorrelation analysis to rationally extract the temporal characteristics of decomposed data in multiple time dimensions. An improved LSTM called MTD‐LSTM is developed by combining JRTDM with LSTM, which can effectively apply multi‐dimensional time characteristics of the decomposed load to improve the predictive accuracy and robustness. Several datasets from Australia and China are performed to check the predictive performance of DB‐MTD‐LSTM. Experimental results verify that DB‐MTD‐LSTM has better predictive accuracy and satisfactory robustness compared with state‐of‐the‐art and conventional predictive models. [ABSTRACT FROM AUTHOR]

Accurate electricity load forecasting is an important prerequisite for stable electricity system operation. In this paper, it is found that daily and weekly variations are prominent by the power spectrum analysis of the historical loads collected hourly in Tai'an, Shandong Province, China. In addition, the influence of the extraneous variables is also very obvious. For example, the load dropped significantly for a long period of time during the Chinese Lunar Spring Festival. Therefore, an artificial neural network model is constructed with six periodic and three nonperiodic factors. The load from January 2016 to August 2018 was divided into two parts in the ratio of 9 : 1 as the training set and the test set, respectively. The experimental results indicate that the daily prediction model with selected factors can achieve higher forecasting accuracy. [ABSTRACT FROM AUTHOR]

Accurate and stable ultra-short-term wind speed prediction is very valuable for the dispatch planning and operational security for the wind power system, however it's very difficult to obtain satisfactory forecasting results in the wind power system due to the complexity and non-linearity of the wind speed series. In this paper, a novel hybrid model combined multi-objective optimization, data preprocessing technology and Elman neural network was proposed to forecast ultra-short-term wind speed, including 30min and 10min wind speed. To obtain better forecasting results with high accuracy and strong stability, multi-objective optimization target was utilized to balance the variance and bias of the forecasted series. Complementary ensemble empirical mode decomposition was used to remove the noise in the original data and several IMFs were obtained. This paper proposed a new optimization algorithm combined adaptive wind driven optimization and modified simulated annealing to optimize initial weights and thresholds of ENN. Wind speed data from two observation sites in China was involved in this paper to verify the forecasting performance of the proposed model. The simulation results illustrate that the proposed hybrid model has the best forecasting results at all step among all related models. • A new hybrid is proposed to forecast wind speed in this paper. • Data preprocessing technology is introduced to improve the forecasting performance. • Multi-objective optimization target is utilized to obtain stability and accuracy forecasting results. • The results are validated well in China. [ABSTRACT FROM AUTHOR]

In recent years, diverse energy has been integrated into the power system, which constitutes a regional integrated energy system (IES). However, the coupling and complementation of multiple energy sources make load forecasting more difficult. For the time‐sequence and non‐linear characteristics of electric load and the complementarity of different energy in IES, this paper proposed an attention‐based convolutional neural network (CNN) combined with long short‐term memory (LSTM) and bidirectional long short‐term memory (BiLSTM) model for short‐term load forecasting in IES. The historical load, temperature, cooling load, and gas consumption of the past 5 days are used as the input features. CNN integrated with attention block is utilized to extract effective features of the load impact factors. Then the load of the next hour is forecasted by the LSTM combined with BiLSTM layers. Finally, the model is verified by the data from an integrated energy park in North China. The results show that the proposed method has better forecasting performance than CNN‐BiLSTM, CNN‐LSTM, BiLSTM, LSTM, backpropagation neural network (BPNN), random forest regression (RFR), and support vector machine regression (SVR). [ABSTRACT FROM AUTHOR]

Recently the issue of air quality has become a global public health concern. As air pollution has been reported as the largest single environmental health risk in the world, analysis and prediction of air quality is increasingly important. Normally, either statistical models or CTM ("deterministic chemistry-transport") models are used for forecasting air PM ("particulate matter") levels. Actually, hourly air quality fluctuation is also one time-series. Compared with commonly used deterministic photochemical air quality models, data-driven or time-series-based modeling is simpler and can also perform well even be more accurate. In this study, a called DCT("discrete cosine transform")-based least-squares predictive model is proposed for forecasting hourly AQI ("air quality index") from time-series analysis or data-driven modeling perspective. The proposed DCT-based predictive method is implemented in combination with the least-squares method to compute the called least-squares-optimum DCT coefficients for forecast modeling on the basis of finite hourly AQI observations. The proposed method yields one good result of average 93.24% predictive accuracy in foreca st experiments at five monitoring stations in Xiangtan of China. Experimental results and analysis of performance comparisons of the proposed DCT-based least-squares predictive model with the classical BP-ANN model, the Fourier-series-based least-squares predictive model and the ARIMA model indicate that for the same tasks of forecasting hourly AQI fluctuations, the proposed DCT-based predictive model outperforms the former two competitive models and performs slightly better than or comparable to the ARIMA model. It is indicated that the hourly AQI fluctuations can be well forecasted by the proposed DCT-based least-squares predictive model with using about 12-term least-squares-optimum DCT coefficients. [ABSTRACT FROM AUTHOR]

Objectives: This study was conducted to estimate road traffic deaths and to forecast short-term road traffic deaths in China using the Elman recurrent neural network (ERNN) model.Methods: An ERNN model was developed using reported police data of road traffic deaths in China from 2000 to 2017. Different numbers of neurons of the hidden layer were tested and different combinations of subgroup datasets have been used to develop the optimal ERNN model after normalization. The mean absolute error (MAE), the root mean square error (RMSE), and the mean absolute percentage error (MAPE) were measures of the deviation between predicted and observed values. Predicted road traffic deaths from the ERNN model and the seasonal autoregressive integrated moving average (SARIMA) model were compared using the MAPE.Results: By comparing the MAE, RMSE and MAPE of different numbers of hidden neurons and different ERNN models, the ERNN model provided the best result when the input neurons were set to 3 and hidden neurons were set to 10. The best validated neural model (3:10:1) was further applied to make predictions for the latest 12 months of deaths (MAPE = 4.83). The best SARIMA (0, 1, 1) (0, 1, 1)12 model was selected from various candidate models (MAPE = 5.04). The fitted road traffic deaths using the two selected models matched closely with the observed deaths from 2000 to 2016. The ERNN models performed better than the SARIMA model in terms of prediction of 2017 deaths.Conclusions: Our results suggest that the ERNN model could be utilized to model and forecast the short-term trends accurately and to evaluate the impact of traffic safety programs when applied to historical road traffic deaths data. Forecasting traffic crash deaths will provide useful information to measure burden of road traffic injuries in China. [ABSTRACT FROM AUTHOR]

The difference in electricity and power usage time leads to an unbalanced current among the three phases in the power grid. The three-phase unbalanced is closely related to power planning and load distribution. When the unbalance occurs, the safe operation of the electrical equipment will be seriously jeopardized. This paper proposes a Hierarchical Temporal Memory (HTM)-based three-phase unbalance prediction model consisted by the encoder for binary coding, the spatial pooler for frequency pattern learning, the temporal pooler for pattern sequence learning, and the sparse distributed representations classifier for unbalance prediction. Following the feasibility of spatialtemporal streaming data analysis, we adopted this brain-liked neural network to a real-time prediction for power load. We applied the model in five cities (Tangshan, Langfang, Qinhuangdao, Chengde, Zhangjiakou) of north China. We experimented with the proposed model and Long Short-term Memory (LSTM) model and analyzed the predict results and real currents. The results show that the predictions conform to the reality; compared to LSTM, the HTM-based prediction model shows enhanced accuracy and stability. The prediction model could serve for the overload warning and the load planning to provide high-quality power grid operation. [ABSTRACT FROM AUTHOR]

Data-driven methods are very useful for streamflow forecasting when the underlying physical relationships are not entirely clear. However, obtaining an accurate data-driven model that is sufficiently performant for streamflow forecasting remains often challenging. This study proposes a new data-driven model that combined the variational mode decomposition (VMD) and the prediction models for daily streamflow forecasting. The prediction models include the autoregressive moving average (ARMA), the gradient boosting regression tree (GBRT), the support vector regression (SVR), and the backpropagation neural network (BPNN). The latest decomposition model, the VMD algorithm, was first applied to extract the multiscale features from the entire time series and to decompose them into several subseries, which were predicted after that using forecast models. The ensemble forecast was finally reconstructed by summing. Historical daily streamflow series recorded at the Wushan and Weijiabao hydrologic stations from 1 January 2001 to 31 December 2014 in China were investigated using the proposed VMD-based models. Three quantitative evaluation indexes, including the Nash–Sutcliffe efficiency coefficient (NSE), the root mean square error (RMSE), and the mean absolute error (MAE), were used to evaluate and compare the predicted results of the proposed VMD-based models with two other models such as nondecomposition method (BPNN) and BPNN based on ensemble empirical mode decomposition (EEMD-BPNN). Furthermore, a comparative analysis of the performance of the VMD-BPNN model under different forecast periods (1, 3, 5, and 7 days) was performed. The results evidenced that the proposed VMD-based models could always achieve good performance in the testing stage and had relatively good stability and representativeness. Specifically, the VMD-BPNN model considered both the prediction accuracy and computation efficiency. The results show that the reliability of the forecasting decreased as the foresight period increased. The model performed satisfactorily up to 7-d lead time. The VMD-BPNN model could be applied as a promising, reliable, and robust prediction tool for short-term streamflow forecasting modelling. [ABSTRACT FROM AUTHOR]

Summary Short‐term load forecasting at the distribution transformer level provides a basis for demand‐side aggregators to take part in the power market. However, under the competitive market environment, certain parties might be discriminated and do not have access to enough data and thus the challenge of load forecasting under limited dataset arises. To tackle the small sample forecasting problem at the distribution transformer level, this paper first explores the load unbalance phenomenon and correlation among three‐phase electrical loads. Then, the data augmentation strategy for learning models is proposed. The strategy includes three‐phase datasets fusion and rolling forecast. The aim is to ameliorate overfitting and make sure the distribution of the training and test data as close as possible. The strategy is validated by the realistic data of the distribution transformers from South and East China. Comprehensive case studies demonstrate that, by utilizing the proposed strategy, learning models can achieve better forecast accuracy and the generalization ability is improved. Also, the proposed strategy is proved to boost robustness against the measurement uncertainty. [ABSTRACT FROM AUTHOR]

In recent years, global climate change caused by carbon dioxide emissions has attracted more and more attention. Adjusting the energy mix by predicting energy demands is currently a more effective way to address climate issues and energy supply issues. Based on the panel data from 1999 to 2018 in China, this paper designed a new hybrid prediction model to predict the future electricity consumption of Chinese residents by double improvement of particle swarm optimization. By comparing with the BP neural prediction model without mixing and several BP neural prediction models with other improved and mixed forms, the results show that the BP neural network hybrid prediction model with DPSO-BP is more suitable for forecasting the electricity consumption of Chinese residents. At the same time, the prediction results of the DPSO-BP prediction model show that the annual electricity consumption of Chinese residents will increase from 9685 (100 million kWh) in 2018 to 13,171 (100 million kWh) in 2025 in the next 7 years. The research results provide a reference for future scholars in the design of algorithms and provide suggestions for the government to adjust energy and avoid severe power shortages or surpluses. [ABSTRACT FROM AUTHOR]

Accurate and reliable low-voltage load forecasting is critical to optimal operation and control of distribution network and smart grid. However, compared to traditional regional load forecasting at high-voltage level, it faces tough challenges due to the inherent high uncertainty of the low-capacity load and distributed renewable energy integrated in the demand side. This paper proposes a novel hybrid ensemble deep learning (HEDL) approach for deterministic and probabilistic low-voltage load forecasting. The deep belief network (DBN) is applied to low-voltage load point prediction with the strong ability of approximating nonlinear mapping. A series of ensemble learning methods including bagging and boosting variants are introduced to improve the regression ability of DBN. In addition, the differencing transformation technique is utilized to ensure the stationarity of load time series for the application bagging and boosting methods. On the basis of the integrated thought of ensemble learning, a new hybrid ensemble algorithm is developed via integrating multiple separate ensemble methods. Considering the diversity in various ensemble algorithms, an effective K nearest neighbor classification method is utilized to adaptively determine the weights of sub-models. Furthermore, HEDL based probabilistic forecasting is proposed by taking advantage of the inherent resample idea in bagging and boosting. The effectiveness of the HEDL method for both deterministic and probabilistic forecasting has been systematically verified based on realistic load data from East China and Australia, indicating its promising prospective for practical applications in distribution networks. [ABSTRACT FROM AUTHOR]

Timely and accurate depth estimation of a shallow waterway can improve shipping efficiency and reduce the danger of waterway transport accidents. However, waterway depth data measured during actual maritime navigation is limited, and the depth values can have large variability. Big data collected in real time by automatic identification systems (AIS) might provide a way to estimate accurate waterway depths, although these data include no direct channel depth information. We suggest a deep neural network (DNN) based model, called DDTree, for using the real-time AIS data and the data from Global Mapper to predict waterway depth for ships in an accurate and timely way. The model combines a decision tree and DNN, which is trained and tested on the AIS and Global Mapper data from the Nantong and Fangcheng ports on the southeastern and southwestern coast of China. The actual waterway depth data were used together with the AIS data as the input to DDTree. The latest data on waterway depths from the Chinese maritime agency were used to verify the results. The experiments show that the DDTree model has a prediction accuracy of 91.15%. Therefore, the DDTree model can provide an accurate prediction of waterway depth and compensate for the shortage of waterway depth monitoring means. The proposed hybrid DDTree model could improve marine situational awareness, navigation safety, and shipping efficiency, and contribute to smart navigation. [ABSTRACT FROM AUTHOR]

Demand-side management (DSM) increases the complexity of forecasting environment, which makes traditional forecasting methods difficult to meet the firm's need for predictive accuracy. Since deep learning can comprehensively consider various factors to improve prediction results, this paper improves the deep belief network from three aspects of input data, model and performance, and uses it to solve the short-term load forecasting problem in DSM. In the data optimization stage, the Hankel matrix is constructed to increase the input weight of DSM data, and the gray relational analysis is used to select strongly correlated data from the data set. In the model optimization stage, the Gauss-Bernoulli restricted Boltzmann machine is used as the first restricted Boltzmann machine of the deep network to convert the continuity feature of input data into binomial distribution feature. In the performance optimization stage, a pre-training method combining error constraint and unsupervised learning is proposed to provide good initial parameters, and the global fine-tuning of network parameters is realized based on the genetic algorithm. Based on the actual data of Tianjin Power Grid in China, the experimental results show that the proposed method is superior to other methods. [ABSTRACT FROM AUTHOR]

Grey prediction model has good performance in solving small data problem, and has been widely used in various research fields. However, when the data show oscillation characteristic, the effect of grey prediction model performs poor. To this end, a new method was proposed to solve the problem of modelling small data oscillation sequence with grey prediction model. Based on the idea of information decomposition, the new method employed grey prediction model to capture the trend characteristic of complex system, and ARMA model was applied to describe the random oscillation characteristic of the system. Crops disaster area in China was selected as a case study and the relevant historical eight-year data published by government department were substituted to the proposed model. The modelling results of the new model were compared with those of other traditional mainstream prediction models. The results showed that the new model had evidently superior performance. It indicated that the proposed model will contribute to solve small oscillation problems and have positive significance for improving the applicability of grey prediction model. [ABSTRACT FROM AUTHOR]

At the present stage, China's energy development has the following characteristics: continuous development of new energy technology, continuous expansion of comprehensive energy system scale, and wide application of multi-energy coupling technology. Under the new situation, the accurate prediction of power load is the key to alleviate the problem that the planning and dispatching of the current power system is more complex and more demanding than the traditional power system. Therefore, firstly, this paper designs the calculation method of the power load demand of the grid under the multi-energy coupling mode, aiming at the important role of the grid in the power dispatching in the comprehensive energy system. This load calculation method for regional power grid operating load forecasting is proposed for the first time, which takes the total regional load demand and multi-energy coupling into consideration. Then, according to the participants and typical models in the multi-energy coupling mode, the key factors affecting the load in the multi-energy coupling mode are analyzed. At this stage, we fully consider the supply side resources and the demand side resources, innovatively extract the energy system structure characteristics under the condition of multi-energy coupling technology, and design a key factor index system for this mode. Finally, a least squares support vector machine optimized by the minimal redundancy maximal relevance model and the adaptive fireworks algorithm (mRMR-AFWA-LSSVM) is proposed, to carry out load forecasting for multi-energy coupling scenarios. Aiming at the complexity energy system analysis and prediction accuracy improvement of multi-energy coupling scenarios, this method applies minimal redundancy maximal relevance model to the selection of key factors in scenario analysis. It is also the first time that adaptive fireworks algorithm is applied to the optimization of adaptive fireworks algorithm, and the results show that the model optimization effect is good. In the case of A region quarterly load forecasting in southwest China, the average absolute percentage error of a least squares support vector machine optimized by the minimal redundancy maximal relevance model and the adaptive fireworks algorithm (mRMR-AFWA-LSSVM) is 2.08%, which means that this model has a high forecasting accuracy. [ABSTRACT FROM AUTHOR]

The high penetration of renewable energy will substantially change the power system operation. Traditionally, the annual operation of a power system can be represented by some typical operation modes and acts as the basis for the power-system-related analysis. The introduction of highly penetrated renewable energy will make the power system operation mode highly diversified and variable. These modes may not follow traditional empirical patterns. In this paper, we propose a data-driven method based on high-dimensional power system operation data (including power flow, unit generation, and load demand) to identify the pattern of the operation modes and analyze the impact of high renewable penetration. Specifically, the proposed data-driven method is composed of simulation, preprocessing, clustering, dimension reduction, and visualization with the aim to provide an intuitive understanding of the operation mode variety under high renewable penetration. In addition, several indices are introduced to quantify the space dispersion, time variation, and seasonal consistency of operation modes. A case study on actual Qinghai provincial power system in China validates the effectiveness of the proposed data-driven method and indicates that the dispersion and time variation of operation mode will significantly increase in the beginning and then saturate with the increase in renewable penetration level. The operation mode is also less correlated with seasons in renewable energy dominated power system. [ABSTRACT FROM AUTHOR]

The development of industrial civilization has greatly enriched the material and spiritual life of human beings, but it is accompanied by the intensification of the consumption of earth resources and environmental pollution. The smog that has emerged in various parts of China in recent years is a typical problem, which not only endangers human health but also affects normal human work and life. It is difficult to control smog in a short time productively, so people need to understand the rule of smog formation gradually, and effectively predict the PM2.5 index to help people continuously analyze relevant mechanisms and timely protect-related hazards. This paper proposes a hybrid model that uses the Complementary Ensemble Empirical Modal Decomposition algorithm to mine the information in the original PM2.5 sequence and then predicts the pertinent random forests. The trend of PM2.5 concentration during the decomposition process is effectively reflected, and the decomposition sequence is modeled by the high tolerance of the random forest to the noise data and the good fitting ability. In the modeling process, the parameters are optimized according to the evaluation function of the model on the verification set, and eventually, the prediction sequences are superimposed to obtain the final predicted PM2.5 concentration value. The validity of the model is verified by the data of several Chinese cities with different geographical features in the past 5 years. The results show that the recommendation model is higher than other comparison models in terms of model stability and prediction accuracy. [ABSTRACT FROM AUTHOR]

Reservoir inflow forecasting is extremely important for the management of a reservoir. In practice, accurate forecasting depends on the feature learning performance. To better address this issue, this paper proposed a feature-enhanced regression model (FER), which combined stack autoencoder (SAE) with long short-term memory (LSTM). This model had two constituents: (1) The SAE was constructed to learn a representation as close as possible to the original inputs. Through deep learning, the enhanced feature could be captured sufficiently. (2) The LSTM was established to simulate the mapping between the enhanced features and the outputs. Under recursive modeling, the patterns of correlation in the short term and dependence in the long term were considered comprehensively. To estimate the performance of the FER model, two historical daily discharge series were investigated, i.e., the Yangtze River in China and the Sava Dolinka River in Slovenia. The proposed model was compared with other machine-learning methods (i.e., the LSTM, SAE-based neural network, and traditional neural network). The results demonstrated that the proposed FER model yields the best forecasting performance in terms of six evaluation criteria. The proposed model integrates the deep learning and recursive modeling, and thus being beneficial to exploring complex features in the reservoir inflow forecasting. Moreover, for smaller catchments with significant torrential characteristics, more data are needed (e.g., at least 20 years) to effectively train the model and to obtain accurate flood-forecasting results. [ABSTRACT FROM AUTHOR]

We use data on the freezing level height (FLH) and summer runoff in the Hotan River, China, from 1960 to 2013, to analyse the nonlinear relationships of atmospheric and hydrological factors at different time scales, by employing three nonlinear decomposition methods. Six hybrid prediction models are established by combining linear regression and back-propagation artificial neural network (BPANN) models. The decomposition results by three nonlinear methods are compared, indicating that the extreme-point symmetric mode decomposition (ESMD) method ensures the best prediction capacity. The runoff and FLH have periods of 3 and 6 years, respectively, at the inter-annual scale, which pass the significance test of 0.05 (P < 0.05) by using the Monte Carlo method, although there were slight differences in the periods at the inter-decadal scale. Among the six models, ESMD-BPANN exhibits the highest accuracy, with good reliability and resolution, according to several performance indicators. The ESMD-BPANN model is thus selected for the simulation and prediction of runoff. [ABSTRACT FROM AUTHOR]

Skilful short-term streamflow forecasting is a challenging task, but useful for addressing a variety of issues associated with water resources planning and management. This study investigates the performance of four popular models for short-term streamflow forecasting, with particular emphasis on the combination of each model with wavelet transform (WT). The autoregressive (AR) model, autoregressive moving average (ARMA) model, artificial neural network (ANN) model, and linear regression (LR) model are used as the base models, and WT-AR, WT-ARMA, WT-ANN, and WT-LR models are used as the composite or hybrid models. These eight models are applied for short-term forecasting of daily streamflow time series in two different river basins in China. Streamflow data from two stations (Yingluoxia and Zhamashike) in the Heihe River basin of North China and two stations (Wuzhou and Longchuan) in the Pearl River basin of South China are considered, and forecasts are made 1-day, 2-day, and 3-day ahead. The accuracy of the models is evaluated using three widely used performance measures: root mean square error, mean absolute error, and correlation coefficient (R). The performances of the eight models are compared, and the influencing role of the wavelet transform in the hybrid models is discussed. The results suggest that the WT-ANN and ANN models are more suitable for the northern basin but perform poorly for the southern basin, while the WT-ARMA model is more suitable for the southern basin. The results also suggest that the wavelet-based hybrid models are better than the single models particularly for longer lead times, offering gradual improvement with increasing lead time. Therefore, the wavelet-based models are especially useful for areas that suffer from frequent natural disasters, fragile ecological environment, and poor self-regulations. [ABSTRACT FROM AUTHOR]

• The training time of Long Short-Term Memory is reduced by changing network structure. • A new hybrid model is proposed for wind speed forecasting. • Four experiments are designed to verify the performance and reliability of the model. Obtaining accurate wind speed forecast result plays a decisive role in ensuring the reliable operation of the power system integrated with large-scale wind power. Deep learning methods are increasingly being used to predict wind speed, which have relatively high prediction accuracy but more time-consuming training processes. The purposes of this study are further to improve the prediction accuracy of the wind speed and reduce the training time of the deep learning method. In this paper, a novel hybrid model, New Cell Update Long Short-Term Memory combined with Empirical Wavelet Transform, is proposed to increase the prediction accuracy in shorter training time. At first, the original wind speed sequence is preprocessed into a series of sub-sequence by the empirical wavelet decomposition. Then each sub-sequence is trained by New Cell Update Long Short-Term Memory which is proposed by this paper respectively and the sum of each sub-sequence is treated as the final prediction results. In order to verify the performance of the proposed model, different decomposition methods and different prediction methods are compared on the four actual wind speed prediction cases in the Inner Mongolia, China from prediction accuracy and training time. The results demonstrate that: (1) New Cell Update Long Short-Term Memory network has slightly higher prediction accuracy and shorter training time than Long Short-Term Memory network. (2) The prediction accuracy of the model is significantly improved after empirical wavelet decomposition. Therefore, New Cell Update Long Short-Term Memory network combined with empirical wavelet decomposition is a competitive wind speed prediction method compared to the existing state-of-the-art approach. [ABSTRACT FROM AUTHOR]

• Minimal Gated Memory Network is proposed to predict wind speed. • Quantile Regression Minimal Gated Memory Network is proposed to quantify uncertainty. • Feature selection and combination are introduced to construct optimal feature inputs. As a renewable and clean energy, wind energy plays an important role in easing the increasingly serious energy crisis. However, due to the strong volatility and randomness of wind speed, large-scale integration of wind energy is limited. Therefore, obtaining reliable high-quality wind speed prediction is of great importance for the planning and application of wind energy. The purpose of this study is to develop a hybrid model for short-term wind speed forecasting and quantifying its uncertainty. In this study, Minimal Gated Memory Network is proposed to reduce the training time without significantly decreasing the prediction accuracy. Furthermore, a new hybrid method combining Quantile Regression and Minimal Gated Memory Network is proposed to predict conditional quantile of wind speed. Afterwards, Kernel Density Estimation method is used to estimate wind speed probabilistic density function according to these conditional quantiles of wind speed. In order to make the model show better performance, Maximal Information Coefficient is used to select the feature variables while Genetic Algorithm is used to obtain optimal feature combinations. Finally, the performance of the proposed model is verified by seven state-of-the-art models through four cases in Inner Mongolia, China from five aspects: point prediction accuracy, interval prediction suitability, probability prediction comprehensive performance, forecast reliability and training time. The experimental results show that the proposed model is able to obtain point prediction results with high accuracy, suitable prediction interval and probability distribution function with strong reliability in a relatively short time on the prediction problems of wind speed. [ABSTRACT FROM AUTHOR]

In this paper, a least squares support vector machine (LSSVM) model with parameter optimization is proposed for solving the problem that the forecast accuracy of neural network model and support vector machine model is not desirable for the sake of improving short-term wind speed forecast accuracy further. The parameters of LSSVM are optimized by the improved ant colony algorithm. Firstly, the parameters of LSSVM are regarded as the position vector of ants. Another argument is that the global search is carried out by selecting some ants randomly from the ant colony to guide the whole ant colony, while searching the optimal ant neighborhood. Furthermore, the optimal parameters of the model are obtained, and the wind speed prediction model of LSSVM is established through parameter optimization. Taking a wind farm in North China as an example, the collected wind speed data were taken in predicted experience, besides the results were compared with the BP neural network model and the LSSVM model. The results show that this model has significant advantages compared with the other two models and has high practical significance. [ABSTRACT FROM AUTHOR]

Energy consumption is an international issue and plays an important role in the national energy security, especially for China of which the energy market is in transition. Accuracy and trustable forecasting of future energy consumption trends with nonlinear data sequences is very important for the decision makers of governments and energy companies. In this paper, a novel nonlinear grey Bernoulli model with fractional order accumulation, abbreviated as FANGBM(1,1) model, is proposed to forecast short-term renewable energy consumption of China during the 13th Five-Year Plan (2016–2020). The new model is discussed in details with the fractional accumulated generating matrix and the Bernoulli equation. Further, the Particle Swarm Optimization algorithm is used to search optimal system parameters. Based on the updated real-world data sets from 2011 to 2015, the FANGBM(1,1) model is established to forecast the total renewable energy consumption, hydroelectricity consumption, wind consumption, solar consumption, and consumption of other renewable energies, respectively. The FANGBM(1,1) model presents high accuracy in all cases and is also proved to be efficient to deal with nonlinear sequences. [ABSTRACT FROM AUTHOR]

Consumers’ transformers play an important role in power systems, and they are essential for operation reliability and commercial benefits. In the past, maintenance personnel had to spend plenty of time on examining consumers’ transformers one by one. Nowadays, with the wide deployment of power user electric energy data acquire system (PUEEDAS), informative metering data are becoming available, which can be utilized for further condition monitoring. Thus, this paper proposes a data-driven abnormal condition monitoring algorithm of data acquisition for consumers’ transformers, which could timely send abnormal condition alerts to operators and maintenance personnel. In the proposed algorithm, Spearman's rank correlation coefficient is utilized to show the degree of correlation among phase currents, and its t-Statistics is used to determine whether abnormal condition of data acquisition exists based on the hypothesis testing. Finally, actual acquisition data from Zhejiang power system in China are employed to validate the effectiveness of the proposed algorithm, and to analyze the characteristics of normal and abnormal conditions, respectively. Sensitive analyses on different significant levels and sampling rates are performed for considering its impact on monitoring results; the application in real power systems is also given to demonstrate the practicality of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Highlights: • Cover wind speeds and multi-state units in power system reliability assessment. • Infuse correlation structure into cross entropy based importance sampling method. • Positive correlation of wind speeds has adverse impacts on power system reliability. • Positive correlation of wind speed and load improves the power system reliability. Abstract With the rapid integration of wind energy, the increasing uncertainty and high reliable property of power systems have resulted in great difficulties in reliability assessment. To solve the problem, traditional cross entropy based importance sampling (CE-IS) methods are improved in this paper. The improved method is capable of efficiently assessing the reliability of composite power systems with wind energy integrated. First, we introduce the differences between the improved CE-IS (ICE-IS) and traditional CE-IS. Particularly, ICE-IS takes the correlation of random variables (RVs) into account and models multi-state RVs with multinomial distribution. Therefore, ICE-IS can obtain much better suboptimal distributions for the RVs than CE-IS, which accelerates the reliability assessment. Then the procedures of ICE-IS are detailed by two parts, which are a pre-simulation stage and a main simulation stage, respectively. Finally, we modify IEEE-RTS 79 and IEEE-RTS 96 test systems based on wind speed data observed in northwest China. Several case studies are designed and carried out on the modified systems to validate the proposed method. [ABSTRACT FROM AUTHOR]