摘要
针对不规律的、波动性大的复杂原始负荷数据导致预测精度不高等问题,设计了一种使用变分模态分解(VMD)与改进粒子群算法(IPSO)来优化最小二乘支持向量机(LSSVM)的短期负荷预测模型。针对原始负荷数据存在的波动性大等缺陷,首先使用VMD法将其分解为多个各异的模态分量,然后将分解后的各组数据分别输入改进的动态自适应惯性权重粒子群算法优化后的LSSVM模型,最后将得到的多个各异的模态分量分别经模型预测出的结果进行相加得到最后取得的预测结果。经江苏省某市真实负荷数据仿真,验证了该预测模型的有效性及优越性。
Aiming at the problems of irregular and fluctuating complex raw load data resulting in low prediction accuracy,a short-term load forecasting model using variational mode decomposition(VMD)and improved particle swarm algorithm(IPSO)to optimize the least squares support vector machine(LSSVM)is designed.Firstly,the original load data is decomposed into several different modal components using VMD method to solve the problem of large fluctuation.Then,the decomposed data are fed into the LSSVM model optimized by the improved dynamic adaptive inertial weight particle swarm algorithm.Finally,the obtained multiple different modal components are added to the results predicted by the model to obtain the final prediction results.The validity and superiority of the model are verified by the simulation of real load data of a city in Jiangsu Province.
作者
陆磊
张铭飞
朱浩钰
LU Lei;ZHANG Mingfei;ZHU Haoyu(Institute of Electric Power,North China University of Water Resources and Electric Power,Zhengzhou 450045,China;State Grid Changde Power Supply Company,Changde 415000,China;Water Supply Bureau of Heze Yellow River Bureau,Heze 274000,China)
出处
《电工技术》
2022年第24期175-178,197,共5页
Electric Engineering
关键词
短期电力负荷预测
变分模态分解
改进粒子群算法
最小二乘支持向量机
预测精度
short-term power load forecasting
variational modal decomposition
improved particle swarm optimization
least squares support vector machine
prediction accuracy
