摘要
为准确预测光伏发电量,减少并网光伏对大电网的影响,引入相似日概念,对夏季预测日的平均温度、最高温度、最低温度以及天气类型进行分析。在历史数据中选取具有相似天气特征的发电功率数据和天气数据作为神经网络的训练样本,建立ACO-BP神经网络光伏发电功率预测模型,并将预测结果与传统BP神经网络和PSO-BP神经网络预测结果相比较。实验结果表明,该模型具有较高的预测精度。
To accurately predict photovoltaic power generation and reduce the impact of grid-connected photovoltaic on the large power grid,this paper introduces the concept of similar day,analyzes average,maximum and minimum temperature and weather type of summer forecastday,and selects the power generation data and the weather data with similar weather characteristics as training samples of neural network from the historical data.Based on the analysis of the characteristics of the photovoltaic power generation and its affecting factors,an ACO-BP neural network photovoltaic power prediction model is established,and the prediction results are compared with the traditional BP neural network and PSO-BP neural network prediction results.Experimental results show that the model is of high prediction accuracy.
作者
陈智雨
陆金桂
CHEN Zhiyu;LU Jingui(School of Mechanical and Power Engineering,Nanjing University of Technology,Nanjing 211816,China)
出处
《机械制造与自动化》
2020年第1期173-175,187,共4页
Machine Building & Automation
关键词
光伏发电系统
光伏发电功率预测
神经网络
蚁群优化
photovoltaic power generation system
photovoltaic generating efficiency forecasting
neural network
ant colony optimization
作者简介
第一作者:陈智雨(1994-),男,江苏扬州人,硕士研究生,研究方向为光伏发电技术。
