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.
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)
关键词
次日电力市场
分析与预测
粒子群算法
神经网络
next day electricity market
analysis and forecast
particle swarm algorithm
BP network
