基于PSO-SVR的电力负荷预测

Power Load Forecasting Based on PSO-SVR

电力系统负荷预测精度直接决定了预测模型的质量。为了降低预测模型输出结果的预测误差,提出了粒子群算法优化支持向量机回归这一智能预测方法。通过对环境温度、节假日、工作日、日期的采集与分析作为模型的输入,以日平均负荷作为模型的输出。最后,通过仿真,对引入粒子群算法的支持向量机回归模型的预测结果进行对比分析。结果表明:优化后的智能模型取得了更为理想的预测结果。

The accuracy of power system load forecasting directly determines the quality of forecasting model.In order to reduce the prediction error of the output results of the prediction model,an intelligent prediction method of particle swarm optimization support vector machine regression was proposed.Through the collection and analysis of environmental temperature,holidays,working days and dates as the input of the model,daily average load as the output of the model.Finally,through simulation,the prediction results of support vector machine regression model with particle swarm optimization algorithm were compared and analyzed.The results showed that the optimized intelligent model achieved better prediction results.