Photovoltaic power prediction based on G-L-R model
Liu Qiong1, Tian Xiaoli1, Hua Lingfeng2, Liu Xiaoqiang2
1. State Grid Dingxi Electric Power Company, Dingxi, Gansu 743000; 2. State Grid Telecommunications Industry Group Anhui Jiyuan Software Co., Ltd, Hefei 230088
Abstract：Photovoltaic power prediction is one of the key technologies for distributed photo- voltaics. Based on gradient boosting decision tree (GBDT) and light gradient boosting machine (LightGBM) algorithm, the Ridge algorithm with L2 regular term is used as the fusion strategy, and the G-L-R model is designed. The short-term prediction and ultra-short-term prediction of photovoltaic power prediction are accurately carried out. The experiment was carried out on the data of a photovoltaic station in Anhui in 2018. The results show that with reference to the East China regional assessment standard, the accuracy of photovoltaic power prediction is 91.31%, among which, the accuracy of sunny prediction is 96.34%, and the accuracy of sudden weather prediction is 87.22%.
[1] 国家能源局. 太阳能发展“十三五”规划[EB/OL]. [2016-12-08]. http://zfxxgk.nea.gov.cn/auto87/201612/t20161216_2358.htm. [2] 高冲, 王凯. 基于微源控制-小波神经网络的微网功率预测[J]. 电测与仪表, 2015, 52(18): 68-73, 89. [3] Tsikalakis A G, Hatziargyriou N D.Centralized control for optimizing microgrids operation[J]. IEEE Transa- ctions on Energy Conversion, 2008, 23(1): 241-248. [4] 王仕俊, 平常, 薛国斌, 等. 影响光伏功率输出因素的研究与分析[J]. 电气技术, 2018, 19(8): 68-71. [5] 赵普志, 李鹏, 王凯, 等. 光伏电站与电气化铁路对电网电能质量交互影响分析[J]. 电气技术, 2019, 20(3): 79-83. [6] 赖昌伟, 黎静华, 陈博, 等. 光伏发电出力预测技术研究综述[J]. 电工技术学报, 2019, 34(6): 1201-1217. [7] 赵书强, 王明雨, 胡永强, 等. 基于不确定理论的光伏出力预测研究[J]. 电工技术学报, 2015, 30(16): 213-220. [8] 钟彦平, 帅挽澜, 余笑侬, 等. 基于“国网芯”的含光伏配电网保护研究[J]. 电气技术, 2019, 20(8): 126-130. [9] Pedro H C, Coimbra C M.Assessment of forecasting techniques for solar power production with no exogenous inputs[J]. Solar Energy, 2012, 86(7): 2017-2028. [10] Zeng J, Qiao W.Short-term solar power prediction using a support vector machine[J]. Renewable Energy, 2013, 52: 118-127. [11] Shi J, Lee W J, Liu Y, et al.Forecasting power output of photovoltaic systems based on weather classification and support vector machines[J]. IEEE Transactions on Industry Applications, 2012, 48(3): 1064-1069. [12] Gensler A, Henze J, Sick B, et al.Deep learning for solar power forecasting-an approach using autoencoder and LSTM neural networks[C]//2016 IEEE Inter- national Conference on Systems, Man, and Cybernetics (SMC), 2016: 2858-2865. [13] 王昕, 黄柯, 郑益慧, 等. 基于PNN/PCA/SS-SVR的光伏发电功率短期预测方法[J]. 电力系统自动化, 2016, 40(17): 156-162.
2020, Vol. 21 
