基于PSOEM和神经网络的光伏电站功率预测

Power Prediction of Photovoltaic Power Plants Based on PSOM Algorithm and Neural Network

分析光伏发电输出功率预测的影响因素,确定了基于BP神经网络的功率预测模型,针对BP神经网络本身易陷入局部极值、收敛速度慢等问题,采用粒子群优化算法(PSO)和带扩展记忆粒子群优化算法(PSOEM)这2种群智能算法来优化BP神经网络的初始值和阈值,分别建立了基于PSOBP神经网络和基于PSOEM-BP神经网络的光伏电站输出功率预测模型。根据某光伏电站2月1日—6月30日的光伏发电历史数据,利用所提3种模型对光伏发电系统进行了功率预测。误差对比结果表明,基于PSOEM-BP神经网络的功率预测精度明显高于基于PSO-BP神经网络的功率预测精度,故采用PSOEM优化后BP神经网络模型进行光伏功率预测,具有一定的理论和实用价值。

In this paper,the influencing factors of the output power prediction for photovoltaic plants are analyzed,and the power prediction model based on BP neural network is determined.As the BP neural network itself is easy to fall into local extremum and slow in convergence,two swarm intelligence algorithms,namely the particle swarm optimization(PSO)and the particle swarm optimization with extended memory(PSOEM)are used to optimize the initial value and threshold value of the BP neural network,and the output power prediction model based on PSO-BP neural network and PSOEM-BP neural network are established respectively.Finally,according to the historical data of a photovoltaic power plant from February 1 to June 30,three models are used to predict the output power of the photovoltaic power generation system.The results of error comparison show that the power prediction accuracy of PSOEM-BP neural network is significantly higher than that of PSO-BP neural network,so it has certain theoretical and practical value to use the PSOEM optimized BP neural network model for photovoltaic power prediction.