电力市场下负荷分析与预测优化方法的研究  

Research on electric power market analysis and forecast optimization method

作　　者：马立新[1] 彭华坤[1] 李渊[1] 

机构地区：[1]上海理工大学上海现代光学系统重点实验室,上海200093

出　　处：《信息技术》2013年第9期58-61,共4页Information Technology

基　　金：国家科技部政府间科技合作项目(2009014);国家自然科学基金(F050304)

摘　　要：在电力市场环境下,负荷的分类和预测至关重要。为了提高预测的速度与精度,提出了运用粒子群与误差反向传播(BP)神经网络相结合的预测方法 (POS-BP法)和模型。并根据某市电业局电力负荷数据建立了模型,运用PSO-BP算法对次日负荷进行了预测。从预测结果看该方法收敛速度快、预测精度显著提高。应用于电力市场分析及预测有很好的效果和前景。The classification and prediction of loads are very important, in the power market. In order to improve the accuracy and speed of forecast, it is p that the mixed algorithm of particle swarm and back propagation network and model. And model is established on the basis of the city electric power bureau＇s electric power load data, using the PS0-BP algorithm to the load for forecasting. According to the results of prediction, this method converges fast, prediction accuracy improved significantly. Application in the power market analysis and forecastinz have verv mood effect and orosDect.

关 键 词：次日电力市场 分析与预测 粒子群算法 神经网络 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]