基于粒子群优化方法的短期电力负荷组合预测  

Short-term power load combination forecasting based on PSO algorithm

作　　者：拜润卿 何欣[1] 赵红[1] 郭文科[1] 

机构地区：[1]国网甘肃省电力公司电力科学研究院,甘肃兰州730050

出　　处：《电子测试》2015年第2X期46-48,共3页Electronic Test

摘　　要：短期电力负荷预测是实现电力系统安全、经济运行的基础,其准确性对电力系统运行的可靠性、经济性都有重要意义。本文在灰色模型、ARIMA模型以及指数平滑族模型的基础上,提出了一种基于以上三种模型的组合预测模型,并用粒子群优化算法对其组合权重系数进行了优化。对澳大利亚新南威尔士州2011年9月实际电力负荷数据进行实例分析,其结果表明本文提出的组合模型确实能够提高短期电力负荷预测的精度。The short-term power load forecasting is the foundation of the safe and economic electric power system.Thus,the accuracy of the short-term power load forecasting is significant for the reliability and economy of power system.In this paper,a combined forecasting model based on grey model,ARIMA model and exponential smoothing models is proposed,of which the weight coefficients are optimized by particle swarm optimization algorithm.Then,the results of case study of the electric load data of New South Wales, Australia, in September 2011 show that the proposed combined model can indeed improve the accuracy of the short-term power load forecasting.

关 键 词：短期电力负荷预测 组合预测 粒子群优化算法 灰色模型 ARIMA模型 指数平滑族 

分 类 号：TM715[电气工程—电力系统及自动化]