Abstract
In an increasingly open electricity market environment, short-term load forecasting (STLF) can ensure the power grid to operate safely and stably, reduce resource waste, power dispatching, and provide technical support for demand-side response. Recently, with the rapid development of demand side response, accurate load forecasting can better provide demand side incentive for regional load of prosumer groups. Traditional machine learning prediction and time series prediction based on statistics failed to consider the non-linear relationship between various input features, resulting in the inability to accurately predict load changes. Recently, with the rapid development of deep learning, extensive research has been carried out in the field of load forecasting. On this basis, a feature selection algorithm based on random forest is first used in this paper to provide a basis for the selection of the input features of the load forecasting model. After the input features are selected, a hybrid neural network STLF algorithm based on multi-model fusion is proposed, of which the main structure of the hybrid neural network is composed of convolutional neural network and bidirectional gated recurrent unit (CNN-BiGRU). The input data is obtained by using long sliding time windows of different steps, then multiple CNN-BiGRU models are trained respectively. The forecasting results of multiple models are averaged to get the final forecasting load value. The load datasets come from a region in New Zealand and a region in Zhejiang, China, are used as load forecast examples. Finally, a variety of load forecasting algorithms are introduced for comparison. The experimental results show that our method has a higher accuracy than comparison models.
Highlights
The smart grid is a key component of future sustainable strategy, and high accuracy of power load forecasting is the precondition of the efficient operation of the smart grid, and decrease the cost of distribution network, energy loss, At the same time, short-term load forecasting (STLF) is the basis of the electric power dispatching department work and guides the economic operation of power system
With the rapid development of calculating machine, deep learning has been widely used in the field of image processing, natural language processing topology identification [2] and load forecasting
Xuan et al.: Multi-Model Fusion STLF Based on Random Forest Feature Selection and Hybrid Neural Network so they are suitable for situations with few influencing factors
Summary
Y. Xuan et al.: Multi-Model Fusion STLF Based on Random Forest Feature Selection and Hybrid Neural Network so they are suitable for situations with few influencing factors. Random forest algorithm is used to select the input features of power system load dataset for a more accurate forecasting results. VOLUME 9, 2021 fusion CNN-BiGRU hybrid neural network is introduced to predict short-term load after feature selection. Random forests are not sensitive to multivariate common linearity, and the results are robust to missing data and unbalanced data They can well predict the role of up to thousands of explanatory variables, which is known as one of the best algorithms at present. The segmentation rule for each node is to randomly select k features from all features, and select the optimal segmentation point from these k features to divide the left and right sub-trees. (The decision obtained here are binary trees); c) Through the second step, many CART regression tree models can be generated; d) The final prediction results of each CART regression tree are the mean values of leaf nodes from the sample point; e) The final prediction result of random forest is the mean of all CART regression tree prediction results
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call