基于GWO-SVM与随机森林的组合光伏功率预测模型

A Combined Model for Photovoltaic Power Forecasting Based on GWO-SVM and Random Forest

光伏输出功率具有间接性和随机性,当大规模的光伏并网时,会对电网的稳定性造成破坏,影响供电的质量.为了降低对电网的危害,需要对光伏输出功率进行预测.针对单一的预测模型都有自身的局限性,提出了基于灰狼群算法(Grey Wolf Optimization,GWO)优化支持向量机(Support Vector Ma-chine,SVM)与随机森林(Random Forest,RF)的组合预测模型.通过分别建立GWO-SVM和RF两个单一的预测模型,利用随机森林的非线性映射能力,对权重系数进行调节,确定单一模型的权重,将GWO-SVM和RF两种模型组合起来进行预测,得到光伏功率预测值.实验结果表明,所提模型相对于单一的预测模型具有更好的预测效果.

As the photovoltaic output power is indirect and random,it will damage the stability of the grid and affect the quality of power supply when a large-scale photovoltaic grid is connected to the grid.It is necessary to predict the photovoltaic output power in order to reduce the harm to the grid.Aiming at the limitations of single prediction model,a combined prediction model based on Grey Wolf Optimization(GWO)optimized Support Vector Machine(SVM)and Random Forest(RF)was proposed.Two single prediction models,GWO-SVM and RF,were established respectively,and the weight coefficient was adjusted by using the nonlinear mapping ability of random forests to determine the weight of the single model.The GWO-SVM and RF were combined to predict,and the predicted photovoltaic power was obtained.The experimental results show that the proposed model has better prediction effect than the single prediction model.