多变量相空间重构的多核最小二乘支持向量机电力负荷预测优化策略  

Multiple Kernels LS-SVM Power Load Forecasting Optimization Strategy Based on Multiple Variate PSR

作　　者：陈家乾 肖艳炜[2] 李英[2] 卢冰 余泽骎 CHEN Jia-qian;XIAO Yan-wei;LI Ying;LU Bing;YU Ze-qin(State Grid Zhejiang Huzhou Power Supply Company,Huzhou 313000,China;State Grid Zhejiang Electric Power Company LTD,Hangzhou 310007,China)

机构地区：[1]国网浙江省电力公司湖州供电公司,湖州313000 [2]国网浙江省电力公司,杭州310007

出　　处：《科学技术与工程》2020年第29期11956-11962,共7页Science Technology and Engineering

基　　金：国家自然科学基金(71471059);国网浙江省电力公司科技项目(5211DF13500M)。

摘　　要：针对短期电力负荷在线预测问题,结合多变量相空间重构以及多核函数最小二乘支持向量机(least squares support vector machine,LS-SVM),提出一种基于滑动窗口策略与改进人工鱼群算法(artificial fish swarm algorithm,AFSA)的短期电力负荷在线预测综合优化方法。首先,利用多变量相空间重构还原真实电力系统动力学特性;然后,将核函数进行排列组合,从而将组合核函数的构造问题转换为权值系数的优化问题;进一步,将延迟时间、嵌入维数、LS-SVM参数及核函数权值作为整体参数向量,利用混沌自适应人工鱼群算法对训练数据预测精度的适应度函数进行优化,从而得到最优的预测模型参数;最后,通过滑动时窗策略将得到的预测模型对短期电力负荷进行在线预测,结果证明了提出方法的有效性。In order to solve the problem of on-line power load forecasting,a comprehensive optimization method for short-term power load forecasting based on sliding window strategy and improved artificial fish swarm algorithm was proposed,which combined multiple variable phase space reconstruction and least squares support vector machine.Firstly,the multiple variable phase space reconstruction was used to restore the dynamic characteristics of the real power system,and then the kernels were arranged and combined to transform the construction of the combined kernels into the optimization of the weight coefficients.Furthermore,the delay time,embedding dimension,LS-SVM parameters and the weight of the kernel function were taken as the whole parameter vectors,and the adaptive artificial fish swarm algorithm was used to optimize the fitness function of the prediction accuracy of the training data,so as to obtain the optimal parameters of the prediction model.Finally,the short-term power load was predicted on-line by sliding time window strategy.The results prove the effectiveness of the proposed method.

关 键 词：相空间重构 支持向量机 滑动窗口 电力负荷 在线预测 

分 类 号：TM715[电气工程—电力系统及自动化]