基于粒子群优化和支持向量机的电力负荷预测  

Forecasting of Electricity Load Based on Particle Swarm Optimization and Support Vector Machine

作　　者：曾勍炜[1] 徐知海[1] 吴键[2] 

机构地区：[1]南昌大学网络中心,江西南昌330031 [2]江西省电力公司,江西南昌330077

出　　处：《微电子学与计算机》2011年第1期147-149,153,共4页Microelectronics & Computer

摘　　要：提出支持向量机的粒子群优化算法的用电量预测方法.其中,采用粒子群优化算法选取较优的支持向量机训练参数组合.以江西省2008年7月～10月的用电量数据以及相关特征数据作为实验数据,实验结果表明该算法电量负荷预测精度高于BP神经网络.The values of training parameters of support vector machine have close contact with its forecasting accuracy.Therefore,particle swarm optimization algorithm and support vector machine（PSVM）is proposed to predict electricity consumption in the study.In the model,particle swarm optimization algorithm is used to select the optimal training parameters of support vector machine.The electricity consumption data and relevant features data of JiangXi province from July to October in 2008 are used as the experimental data.The experimental results indicate that the PSVM model has higher prediction accuracy than BP neural network in the forecasting of electricity load.

关 键 词：负荷预测 支持向量机 粒子群 BP网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]