基于斑点鬣狗算法优化支持向量机的短期风电功率预测

Short Term Wind Power Forecast Based on Support Vector Machine Optimized by Spotted Hyena Optimization Algorithm

为提高短期风电功率预测精度,提出了一种基于斑点鬣狗算法优化支持向量机的短期风电功率预测方法。采用斑点鬣狗算法对支持向量机的惩罚系数和核参数进行优化,建立基于SHO-SVM的短期风电功率预测模型,并采用实际风电场运行数据进行仿真分析。仿真结果表明,SHO-SVM模型的平均相对误差和均方根误差分别为4.15%和0.196,预测精度和数据波动性均优于其他模型,验证了短期风电功率预测方法的正确性和实用性。

In order to improve the accuracy of short-term wind power prediction,a short-term wind power prediction method based on support vector machine optimized by spotted hyena optimization algorithm is proposed.The speckle hyena optimization algorithm is used to optimize the penalty coefficient and kernel parameters of support vector machine,and a short-term wind power prediction model based on SHO-SVM is established.The actual wind farm operation data are used for simulation analysis.The simulation results show that the average relative error and root mean square error of the SHO-SVM model are 4.15%and 0.196,respectively,and the prediction accuracy and data volatility are better than other models,which verifies the correctness and practicability of the short-term wind power prediction method.