Ultra-Short-term Electric Load Forecasting Based on VMD-BiLSTM Model

Abstract

Fast and accurate ultra-short-term load forecasting is beneficial for building an efficient and modern smart grid. This paper proposes an ultra-short-term load forecasting model based on Variational Mode Decomposition (VMD) and improved Bi-directional Long Short-Term Memory (BiLSTM) network. The model first decomposes the complex load historical sequence using VMD, reducing the non-stationarity and complexity of the load sequence to facilitate the prediction task using neural networks. Then, the improved BiLSTM network is used to allow input data to skip some transformations in the network, thereby deeply and bidirectionally mining various hidden information from historical sequences. Finally, this paper selects temperature as the factor most correlated with power load forecasting and incorporates it into the prediction process to achieve effective ultra-short-term load forecasting. Compared with existing models such as LSTM, SVM, LeNet, DRNet4-7, and unimproved VMD-BiLSTM based on example data, the simulation results show that the proposed model can predict the load changes within one hour in the future, achieving ultra-short-term load forecasting, and has good prediction accuracy and algorithm robustness.