杂草算法优化支持向量机的短期负荷预测

Short-Term Load Forecasting Model Based on Support Vector Machine Optimized by Invasive Weed Algorithm

针对支持向量机在短期负荷预测中的参数优化问题,利用杂草算法优异的搜索能力,构建了基于杂草算法优化支持向量机的短期负荷混沌预测模型(IWO-SVM)。该模型首先将支持向量机一组参数看作一个杂草种子,然后通过模拟杂草生存、繁殖过程实现支持向量机参数寻优,最后采用具体短期负荷数据对其性能进行分析。结果表明,IWO-SVM获得了高精度的短期负荷预测结果,能够满足短期负荷预测的实际要求。

Aiming at parameters optimization problem of support vector machine in short-term load forecasting,a novel short-term load forecasting model is proposed based on support vector machine optimized by invasive weed optimization algorithm which has excellent search ability.Parameters of support vector machine are considered as a weed,the optimal parameters are found by invasive weed optimization algorithm,and short-term load data are used to test the performance.The experimental results show that the proposed model has obtained high forecasting accuracy and fastens the model speed,and it can meet the requirements of short-term load forecasting.