基于神经网络的光伏阵列发电预测模型的设计

摘要

随着光伏发电系统容量的不断扩大,光伏阵列发电预测技术对于减轻光伏阵列输出电能的随机性对电力系统的影响具有重要意义.本文提出了一种加入天气预报信息的神经网络发电预测模型的设计方案.结合历史发电量数据和气象数据分析了影响光伏阵列发电量的各项因素,采用光伏阵列的发电量序列、日类型指数和气温建立了神经网络预测模型,并对训练好的模型进行了测试和评估.预测结果表明,预测模型有较高的精度,能够解决光伏发电的随机化问题,提高系统的稳定运行能力.%With the increase of the capacity of photovoltaic generated systems, how to eliminate the problem caused by the randomness of power output for photovoltaic system becomes more significant. A novel neutral network power forecasting model based on weather forecast is proposed to solve the randomness of power output for photovoltaic system. According to historical power and weather data provided by experiment, all factors which influence photovoltaic generated energy are discussed and neutral network forecasting module is trained and evaluated by adopting generated power series of photovoltaic arrays, day-type and temperature. Forecasting results show the high precision and high efficiency of this forecasting model which is applied in stable operation of photovoltaic generation system.