基于人工鱼群优化算法的支持向量机短期风电功率预测模型

The Model of Wind Power Short-Term Prediction Based on Artificial Fish Swarm Algorithm of Support Vector Machine

为了提高风电功率预测精度,针对支持向量机(SVM)模型在风电功率预测中存在的参数选取问题,提出用人工鱼群算法(AFSA)寻找SVM模型的最优核函数参数和错误惩罚因子的优化方法。建立AFSA-SVM模型,结合聚类分析后的数值天气预报(NWP)数据对风电功率进行预测。经仿真实验并与BP、粒子群优化的支持向量机模型对比,AFSA-SVM优化模型在短期风电功率预测中有更好的预测效果。

In order to improve the accuracy of wind power prediction and solve the parameter selection problem of support vector machine（SVM） model for the wind power prediction, the artificial fish swarm algorithm （AFSA） is proposed to look for the support vector machine＇ s optimal parameter of kernel function and the parameter of error penalty. The model of AFSA-SVM is established to predict the wind power with the numerical weather forecast （NWP） data after clustering analysis. From the result of simulation experiment, it shows that the model of AFSA-SVM has a higher accuracy than the model of BP and the model of PSO-SVM in the short-term wind power prediction.