蝙蝠算法优化极限学习机的电力负荷预测模型  

Load forecasting based on bat algorithm optimizing extreme learning machine

作　　者：孔令春[1] 孙琼琼[2] 杨照峰[3] 

机构地区：[1]平顶山学院计算机科学与技术学院,河南平顶山467002 [2]平顶山教育学院计算机科学与应用系,河南平顶山467000 [3]平顶山学院软件学院,河南平顶山467002

出　　处：《辽宁工程技术大学学报（自然科学版）》2016年第1期89-92,共4页Journal of Liaoning Technical University (Natural Science)

基　　金：河南省科技计划重点项目(102102210416)

摘　　要：为提高电力负荷预测的准确性,提出蝙蝠算法优化极限学习的电力负荷预测模型.首先收集电力负荷历史数据,然后采用蝙蝠算法对延迟时间和嵌入维以及极限学习的隐含层结点数目进行优化,利用电力负荷历史数据进行重构,最后采用最优隐含层结点数目的极限学习机建立电力负荷预测模型,并采用具体数据仿真测试.实验结果表明:模型建立了整体性能优异的电力负荷预测模型,提高了电力负荷的预测精度.In order to forecast precision of power load, this paper proposed a new power load forecasting model based on extreme learning machine optimized by bat algorithm（BA-ELM）. Firstly, the data of power load are collected, and then the bat algorithm is used to optimize the delay time and the embedding dimension and parameter of extreme learning machine, and phase space reconstruction is use to construct the data of power load, finally, the extreme learning machine which has good parameter is used to establish load forecasting model, and the simulation experiments is carried out on some power load data. The simulation results show that BA-ELM can build an overall performance outstanding power load forecasting model, and improve the power load prediction accuracy.

关 键 词：电力负荷 预测精度 蝙蝠算法 极限学习机 预测模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]