中南民族大学学报（自然科学版）2025，Vol.44Issue(4)：507-514,8.DOI:10.20056/j.cnki.ZNMDZK.20240752
基于相似日和IWOA优化BiLSTM的短期电力负荷预测
Short-term power load forecasting based on similar days and IWOA optimized BiLSTM
摘要
Abstract
In order to effectively improve the accuracy of short-term load forecasting,a short-term power load forecasting model based on similar days and IWOA optimized BiLSTM was proposed.The model first uses Pearson correlation analysis to select the main influencing factors of the load,and uses the comprehensive matching similarity to select the similar day to provide more effective input for the model;then an IWOA algorithm based on a nonlinear control parameter strategy and a population variation strategy is designed to optimize the parameters of the BiLSTM network and build the IWOA-BilSTM prediction model;finally,taking the Australian real load data set as an example,the experimental results show that the prediction model proposed has higher prediction accuracy than other models,which proves the effectiveness of this method.关键词
短期负荷预测/改进鲸鱼优化算法/相似日/双向长短期记忆网络/超参数寻优Key words
short-term load forecasting/improved whale optimization algorithm/similar day/bidirectional long short-term memory network/hyperparameter optimization分类
计算机与自动化引用本文复制引用
朱莉,李豪,汪小豪,姜成龙,曹明海..基于相似日和IWOA优化BiLSTM的短期电力负荷预测[J].中南民族大学学报（自然科学版）,2025,44(4):507-514,8.基金项目
新能源及电网装备安全监测湖北省工程研究中心开放研究基金资助项目(HBSKF202124) （HBSKF202124）
