遗传优化支持向量机在电力负荷预测中的应用

研究电力负荷准确预测问题,电力负荷与影响因子之间呈现复杂非线性关系,传统预测方法无法刻画其变化规律,预测精度低。为提高电力负荷预测精度,提出一种采用遗传优化支持向量机的电力负荷预测模型。采用最小二乘支持向量机的非线性逼近能力去描述电力负荷与影响因子间的复杂非线性关系,并采用自适应遗传算法优化最小二乘支持向量机的参数。采用某省1990～2008年电力负荷数据仿真测试,结果表明,遗传优化支持向量机提高了电力负荷的预测精度,预测平均误差低于其它对比模型,电力负荷预测提供了一种新的研究思路和途径。

Application of Support Vector Machine Optimized by Genetic Algorithm in Electric load Prediction

Study power load forecasting.Load and impact factor have complex nonlinear relation,and the traditional forecasting method can not describe the change rule,which leads to low accuracy of prediction.In order to improve the accuracy of load forecasting,the paper proposed an electric power load forecast model based on genetic optimization of support vector machine.The nonlinear approximation capability of least squares support vector machine was used to describe the power load and influence factors in complex nonlinear relation,and the adaptive genetic algorithm was used to optimize the parameters of least squares support vector machines.A province’s power load data of 1990 ~ 2008 year were used for simulation test.The results show that the support vector machine can improve the precision of load forecast,and the average forecasting error is less than other contrast models.