基于VMD-TCN-BIGRU的超短期功率预测

打开文本图片集

中图分类号：TM715 文献标志码：A 文章编号：2097-3853（2025）04-0374-08

Ultra-short-term power prediction based on VMD-TCN-BIGRU

LIN Zhihui 1，2 ， LIU Lisang1，²， ZHANG Liwei 1，2 ， CHEN Wenwei 1，2 （1. Schol of Electronic，Electrical and Physics，Fujian University of Technology，Fuzhou ，China; 2.Technical Development Base of Industrial Integration Automation of Fujian Province，Fuzhou ，China）

Abstract： To improve the accuracy of ultra-short-term power prediction in power systems，a prediction model is proposed based on variational mode decomposition（VMD）and temporal convolutional network-bidirectional gated recurrent unit （TCN-BiGRU）.The grey wolf optimizer （GWO） is used to optimize the number of modes and the penalty factor of VMD，aiming to enhance the quality of signal decomposition and reduce noise interference.The decomposed modes and the featurevectors extracted based on the Pearson correlation coefficient are input into the TCN-BiGRU model to extract short-term and long-term dependence features of time series，thereby improving the prediction accuracy. Experimental results show that the prediction accuracy of this model reaches 99.144% ，which is superior to that of traditional single models and other combined models.It has stronger adaptability in dealing with nonlinear and volatile data and has lower prediction error.

Keywords： grey wolf optimizer（GWO）；variational mode decomposition （VMD）； temporal convolutional network（TCN） ；bidirectional gated recurrent unit（BGRU）

风能的间歇性和不稳定性使风电功率预测颇具挑战，准确的风电功率预测有利于电网调度、降低发电成本、提升交易效率、推动可再生能源整合与碳减排等[1-2] 。（剩余8025字）