Abstract
To fully mine the relationship between temporal features in load data, improve the accuracy and efficiency of short-term load forecasting and overcome the difficulties caused by load nonlinearity and volatility in accurate load forecasting. In this paper, a hybrid neural network short-term load forecasting model based on temporal convolutional network (TCN) and gated recurrent unit (GRU) is proposed. Firstly, the correlation between meteorological features and load is measured with the distance correlation coefficient, and the fixed-length sliding time window method is used to reconstruct the features. Next, temporal convolutional network is adopted to extract the hidden historical information and time relationship including meteorological features, electricity price, etc., and a better-performing gated recurrent unit is utilized for perdition. Furthermore, the state-of-the-art AdaBelief optimizer and Attention mechanism are utilized to enhance the prediction accuracy and efficiency. The effectiveness and superiority of the proposed model are verified by load and weather data from Spain and PJM power system data. Short-term load forecasting results in different periods and comprehensive comparisons with the performance of different models show that the proposed model can provide accurate load forecasting results rather quickly. The highlights of this paper are that temporal convolutional network and gated recurrent unit are combined for load forecasting for the first time, and the forecasting performance is improved by the novel optimizer AdaBelief and feature selection based on distance correlation coefficient.
Highlights
Accurate and fast short-term load forecasting has become an essential task throughout the development of the market and smart grid
The framework is established by four main steps: missing data processing, distance correlation analysis, feature engineering, and load forecasting based on the temporal convolutional network (TCN)-gated recurrent unit (GRU) model
We are able to draw a conclusion that the TCN-GRU load prediction model with Attention layer has improvement in prediction accuracy compared to the model without the Attention layer, but the time required for each Epoch increases
Summary
Accurate and fast short-term load forecasting has become an essential task throughout the development of the market and smart grid. Based on the hybrid model of TCN with GRU, in this work, we firstly analyze the correlation of weather features, electricity price, and date features in load data. H. Shi et al.: Short-Term Load Forecasting Based on Adabelief Optimized TCN and GRU Hybrid Neural Network TABLE 1. A relatively novel data preprocessing method: we use the distance correlation coefficient to analyze the non-linear correlation between various meteorological features and shortterm load, comprehensively consider the features (weather, electricity price, holidays, working hours, etc.). A TCN-GRU algorithm with strong feature extraction capability is proposed to improve the performance of short-term load forecasting while avoiding gradient disappearance problem. Due to actual geographical differences, which weather features should be selected for short-term load forecasting should be analyzed in detail according to the actual situation, and the factors with high correlation should be selected to build the input data set. The larger the value, the stronger the correlation between this feature and short-term load, while the Pearson correlation coefficient is between -1 and 1, the closer the absolute value to 1, the stronger the linear correlation between features and short-term load
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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
