云模型优化LSSVR的短期电力负荷预测

Short Term Power Load Forecasting Based on the LSSVR Optimized by Cloud Model

准确的短期电力负荷预测是电力系统安全经济运行的重要依据。针对短期负荷影响因素的非线性特性,研究了基于最小二乘支持向量回归机(LSSVR)的短期负荷预测方法。鉴于LSSVR算法参数选取的难点,提出了云进化算法优化LSSVR的短期电力负荷预测模型(CBEA_LSSVR)。CBEA_LSSVR利用云模型实现LSSVR的参数优化,优化后的模型能够预测下一时刻的电力负荷值。仿真结果表明,与其他进化算法相比,云进化算法优化LSSVR模型具有更高的预测精度和鲁棒性。

Accurate short term power load forecasting is significant basis of safe and economic operation of the power system.In accordance with the nonlinear characteristics of the factors affecting short term load,the long term load forecasting method based on least square support vector regression （LSSVR） is researched.In view of the difficulties of parameter selection for LSSVR,the short term load forecasting model （CBEA_LSSVR） which is based on the LSSVR optimized with cloud model based evolutionary algorithm （CBEA） is proposed.This model implements parameter optimization for LSSVR by using cloud model,the power load at next period is rolling forecasted.The result of simulation shows that comparing with other evolutionary algorithms; the cloud model based evolutionary algorithm well optimizes LSSVR and makes it offer higher forecasting accuracy and robustness.