Short-term Power Load Forecasting Based on Phase Space Reconstruction and EMD-ELM

摘要

With the increasing complexity of the world energy structure, the uncertainty of the power system increases significantly, and the accuracy of the short-term power load forecasting is of great significance to the safe, economical and reliable operation of the power system. In order to further improve the accuracy of short-term power load forecasting, this paper innovatively combines the theories such as phase space reconstruction, empirical mode decomposition, and extreme learning machine to establish a new short-term power load forecasting model based on phase space reconstruction and EMD-ELM. The prediction results show that the root means square error, average relative error and global maximum relative error of the short-term power load forecasting model based on phase space reconstruction and EMD-ELM are much smaller than other forecasting models, which verifies the correctness and effectiveness of the short-term load forecasting method.

关键词