两种基于相空间重构的电力系统短期负荷预测方法分析  

Analysis on power system short-term load forecasting based on two phase space reconstruction methods

作　　者：张立[1] 韩晶[1] 陈凯[2] 

机构地区：[1]黑龙江工程学院电气与信息工程学院,黑龙江哈尔滨150050 [2]哈尔滨工程大学信息与通信工程学院,黑龙江哈尔滨150001

出　　处：《黑龙江工程学院学报》2015年第2期5-7,29,共4页Journal of Heilongjiang Institute of Technology

基　　金：黑龙江省教育厅科学技术研究项目(12531540)

摘　　要：短期负荷预测是电力系统调度运营部门一项重要的基础工作,预测精度的高低直接影响到电网运行的安全性、经济性以及电能质量。采用符合短期负荷特性的混沌理论对短期负荷进行预测,在相空间重构和混沌识别的基础上,建立短期负荷加权一阶局域多步预测模型和最大Lyapunov指数的预测模型,通过对一组实际的短期负荷数据进行预测,仿真结果表明:两种方法都能较准确地预测短期负荷,对于一周内的预测结果,最大Lyapunov指数预测模型的预测精度略高于加权一阶局域多步预测模型的预测精度。Short-term load forecasting is an important and basic component in the operation of any electric utility of which the accuracy directly influences power system ’s security ,profit and quality .This paper tries to forecast the short-term load based on the chaotic theory just corresponds to that character .Two chaotic short-term load forecasting melhods based on a local-region multi-steps forecasting model and the largest Lyapunov model are built .Methods are used to predict the real load data .The results show that the two prediction methods can be used in the prediction of load with considerably high accuracy ,and the largest Lyapunov model has higher forecasting precision for short-term load in one week .

关 键 词：短期负荷预测 混沌 LYAPUNOV指数 局域预测 相空间重构 

分 类 号：TM715[电气工程—电力系统及自动化]