A new intelligent hybrid forecasting method for power load considering uncertainty

Abstract

Accurate load forecasting plays an important role in promoting low-carbon energy and high-quality utilization of electricity, as well as carbon reduction and safety in energy and power systems. The complexity of power system trends leads to widespread uncertainty in load forecasting. This article analyzes the internal mechanisms of load and meteorological factors at the level of multidimensional uncertainty and proposes a bidirectional memory feature hybrid model based on a new intelligent optimization method. The VMD optimized by gray wolf decomposes the electricity load data into different information modal components. The decomposed components are statistically analyzed with multidimensional uncertainty analysis to extract statistical patterns. The GTO part is optimized according to the fitness value to update the population and global optimal solution. Furthermore, convolutional neural networks (CNN) are used to extract potential features from load and meteorological data and enhance the correlation between input and output data. Then, short-term load forecasting is realized by using bi-directional short-term memory neural network (BiLSTM). The results show that the proposed model has smaller errors than several commonly used models, and has higher prediction accuracy. It can provide some new ideas for relevant departments to carry out power economic dispatch work in low-carbon modes.