基于AFSA-BP神经网络的光伏功率预测方法A Photovoltaic Power Prediction Method Based on AFSA-BP Neural Network
陈文进,朱峰,张童彦,张俊,张锋明,谢栋,茹伟,宋美雅,范强
CHEN Wenjin,ZHU Feng,ZHANG Tongyan,ZHANG Jun,ZHANG Fengming,XIE Dong,RU Wei,SONG Meiya,FAN Qiang
摘要(Abstract):
为了提高光伏输出功率的预测精度,提出一种利用AFSA(人工鱼群算法)优化BP(反向传播)神经网络的预测方法。该方法基于清洗后的数据,以相关性较高的气象数据作为输入,以光伏输出功率数据作为输出,利用AFSA全局寻优能力和内在并行计算能力优化BP神经网络的权值和阈值,训练得到基于AFSA-BP神经网络的光伏输出功率预测模型。对某光伏电站的仿真分析结果表明,相比于利用BP神经网络、遗传算法优化BP神经网络、粒子群算法优化BP神经网络,所提方法的预测结果准确度更高,与原始数据曲线的拟合程度较优,相关误差评价指标更低,训练耗时较短,能实现对光伏输出功率的快速精确预测。
In order to improve the prediction accuracy of photovoltaic output power,this paper proposes a prediction method using AFSA(artificial fish swarm algorithm)to optimize BP(back-propagation)neural network. Based on the cleaned data,the paper takes highly correlative meteorological data as input,and photovoltaic output power data as output. It uses the global optimization capabilities and inherent parallel computing capabilities of AFSA to optimize the weights and thresholds of the BP neural network. The photovoltaic output power prediction model based on the AFSA-BP neural network is obtained after training. The simulation analysis of a photovoltaic power station shows that compared with using BP neural networks, genetic algorithm optimized BP neural network,and PSO-BP network,the prediction results of this method are more accurate, the degree of fitting to the original data curve is better,the corresponding error evaluation index is lower, and the training is less time-consuming; the method can rapidly and accurately predict the photovoltaic output power.
关键词(KeyWords):
人工鱼群算法;BP神经网络;光伏发电;功率预测
AFSA;BP neural network;photovoltaic power generation;power prediction
基金项目(Foundation): 国网浙江省电力有限公司科技项目(5211SX2000ZM)
作者(Author):
陈文进,朱峰,张童彦,张俊,张锋明,谢栋,茹伟,宋美雅,范强
CHEN Wenjin,ZHU Feng,ZHANG Tongyan,ZHANG Jun,ZHANG Fengming,XIE Dong,RU Wei,SONG Meiya,FAN Qiang
参考文献(References):
- [1]舒印彪,张智刚,郭剑波,等.新能源消纳关键因素分析及解决措施研究[J].中国电机工程学报,2017,37(1):1-9.
- [2]康重庆,姚良忠.高比例可再生能源电力系统的关键科学问题与理论研究框架[J].电力系统自动化,2017,41(9):2-11.
- [3]佚名.国家电网公司发布“碳达峰、碳中和”行动方案[N].国家电网报,2021-03-02(1).
- [4]佚名.国务院发展研究中心与壳牌联合研究成果《全球能源转型背景下的中国能源革命》[J].中国发展观察,2019(10):65.
- [5]龚莺飞,鲁宗相,乔颖,等.光伏功率预测技术[J].电力系统自动化,2016,40(4):140-151.
- [6]闫钇汛,王丽婕,郭洪武,等.基于多特征分析和提取的短期光伏功率预测[J/OL].高电压技术:1-11.[2021-11-26].https://doi.org/10.13336/j.1003-6520.hve.20210701.
- [7]吉锌格.基于波动特性挖掘的短期光伏功率预测研究[D].北京:北京信息科技大学,2021.
- [8]叶林,裴铭,路朋,等.基于天气分型的短期光伏功率组合预测方法[J].电力系统自动化,2021,45(1):44-54.
- [9] ROMERO A F,QUILUMBA F L,ARCOS H N.Shortterm active power forecasting of a photovoltaic power plant using an artificial neural network[C]//2017 IEEE Second Ecuador Technical Chapters Meeting. Salinas,Ecuador:IEEE,2017:1-5.
- [10]郑思达,刘影,杨磊,等.基于改进支持向量机算法的光伏发电功率预测[J/OL].沈阳工业大学学报:1-5.[2021-11-26].http://kns.cnki.net/kcms/detail/21.1189.T.20210907.1404.002.html.
- [11]王琦,季顺祥,钱子伟,等.基于熵理论和改进ELM的光伏发电功率预测[J].太阳能学报,2020,41(10):151-158.
- [12]周逸.基于极限学习机和长短时记忆神经网络的光伏发电功率预测[D].南昌:南昌大学,2020.
- [13] VINOTHKUMAR T,DEEBA K.Hybrid wind speed prediction model based on recurrent long short-term memory neural network and support vector machine models[J].Soft Computing,2020,24(7):5345-5355.
- [14]马晓玲,张祥飞,庞清乐,等.模糊聚类-BP神经网络短期光伏发电预测模型[J].物联网技术,2021,11(10):69-72.
- [15]张慧娥,刘大贵,朱婷婷,等.基于相似日和动量法优化BP神经网络的光伏短期功率预测研究[J].智慧电力,2021,49(6):46-52.
- [16]韩璐,宋海亮,宋佳,等.基于特征提取的FA-BP短期光伏发电预测[J].南昌大学学报(工科版),2021,43(1):85-89.
- [17] ZHAI X M,MA L. Medium and long-term wind power prediction based on artificial fish swarm algorithm combined with extreme learning machine[J]. International Core Journal of Engineering,2019,5(10):265-272.
- [18]王丽婕,厉虹,方市彬.基于人工鱼群优化算法的支持向量机短期风电功率预测模型[J].电气工程学报,2016,11(10):7-12.
- [19]李晓磊,钱积新.人工鱼群算法:自下而上的寻优模式[C]//过程系统工程2001年会论文集.[S.l.]:中国系统工程学会过程系统工程专业委员会,2001:83-89.
- [20]耿博,高贞彦,白恒远,等.结合相似日GA-BP神经网络的光伏发电预测[J].电力系统及其自动化学报,2017,29(6):118-123.
- [21]万亚宁.基于PSO-BP神经网络的光伏系统短期发电功率预测[D].郑州:中原工学院,2020.
- [22]边少聪,王宇.基于PSO-BP神经网络模型的IGBT老化预测[J].浙江电力,2019,38(11):58-64.