现代电子技术2025，Vol.48Issue(18)：107-113,7.DOI:10.16652/j.issn.1004-373x.2025.18.017
改进秃鹰算法优化ELM的短期电力负荷预测研究
Research on short-term power load forecasting based on ELM optimized by IBES algorithm
摘要
Abstract
In allusion to the increasingly complex power environment at the present stage,and the short-term power load forecasting methods have low forecasting accuracy and slow convergence speed,a short-term power load forecasting model based on extreme learning machine(ELM)optimized by improved bald eagle search(IBES)algorithm is proposed.The original bald eagle search(BES)algorithm is prone to fall into local optimum when determining the connection weights and implicit layer thresholds in the ELM,and the convergence speed is slow,which results in the poor prediction accuracy.On this basis,the Piecewise chaotic mapping is used to initialize the bald eagle population and increase the diversity.The Lévy flight strategy is introduced to expand the search range of the population,so that it can jump out of the local optimum in time.The dynamic weighting factor is introduced to improve the local search ability of bald eagle.The IBES algorithm is used to optimize the two stochastic parameters of ELM,so as to establish the IBES-ELM short-term power load forecasting model.The forecasting analysis is conducted by combining with the actual power load data of a region.The results show that,in comparison with ELM,BES-ELM,PSO-ELM,and DBO-ELM,the improved model has an improvement in forecasting accuracy and convergence speed.关键词
短期电力负荷预测/改进秃鹰搜索算法/极限学习机/Piecewise混沌映射/莱维飞行策略/动态权重因子Key words
short-term power load forecasting/IBES/ELM/Piecewise chaotic mapping/Lévy flight strategy/dynamic weighting factor分类
信息技术与安全科学引用本文复制引用
张旭,汪繁荣..改进秃鹰算法优化ELM的短期电力负荷预测研究[J].现代电子技术,2025,48(18):107-113,7.基金项目
国家自然科学基金项目(61903129) （61903129）
