基于MGWO-SD模型的户用光伏装机容量预测研究

Research on installed capacity forecast of household PVs based on MGWO-SD model

文章分析了影响户用光伏装机规模发展的因素,结合系统动力学(SD)模型,建立了基于改进灰狼优化算法(MGWO)的预测模型。首先,分析了影响户用装机规模增长的各类因素,基于系统动力学理论搭建了户用光伏装机容量预测模型;其次,为了对模型中的参数进行寻优,将传统灰狼优化算法中线性减小的收敛因子改为非线性规律变化;最终建立了基于MGWO-SD模型的户用光伏装机容量预测模型。预测结果表明,该预测模型相对于其他预测方法精度更高,平均绝对百分比误差和均方根误差更小,并且比传统的灰狼优化算法能够更快地到达收敛。该预测方法对于电网科学有序地构建新型电力系统,具有一定的理论和实践价值。

This paper analyzes the influencing factors of the development of household photovoltaic(PV)installed capacity,and establishes a forecast model based on the improved gray wolf optimizer(MGWO)combined with the system dynamics(SD)model.Firstly,various factors that affect the growth of household PV installed capacity are analyzed.Based on the SD theory,a prediction model of household PV installed capacity is built.Then,in order to optimize the parameters in the model,the linearly reduced convergence factor in the traditional Grey Wolf optimizer(GWO)is changed into nonlinear parameter,and finally a prediction model based on MCWO-SD model is established.The prediction results show that the prediction model proposed in this paper is more accurate than other prediction methods,and the average absolute percentage error and root mean square error are smaller.Moreover,the MGWO proposed in this paper can reach the convergence faster than GWO.The accurate forecast of household PV installed capacity is also helpful for the power grid to build a new power system scientifically and orderly under the background of'double carbon',which has certain theoretical and practical value.