RESEARCH ON SO-CNN-LSTM PHOTOVOLTAIC POWER PREDICTION MODEL BASED ON COMPREHENSIVE SIMILAR DAY SELECTION

Liu Fengping; Wang Xu; Li Wei; Song Yu; Xu Ye

doi:10.19912/j.0254-0096.tynxb.2023-2134

PDF(1345 KB)

Acta Energiae Solaris Sinica ›› 2025, Vol. 46 ›› Issue (4) : 301-312. DOI: 10.19912/j.0254-0096.tynxb.2023-2134

RESEARCH ON SO-CNN-LSTM PHOTOVOLTAIC POWER PREDICTION MODEL BASED ON COMPREHENSIVE SIMILAR DAY SELECTION

Song Yu¹, Xu Ye¹, Liu Fengping^1,2, Wang Xu¹, Li Wei¹

Author information +

History +

Abstract

Aiming at the low prediction accuracy of photovoltaic power caused by the single selection standard of similar day, erroneous shape similarity measure results and irrational parameter identification of prediction model, a combined photovoltaic power day-ahead prediction model composed of synthesized similarity index, snake optimization （SO） algorithm and CNN-LSTM model was proposed innovatively. Firstly, the Pearson coefficient method was used to identify the critical meteorological factors. Then, a comprehensive similar day selection method combining the distance similarity and siamese graphic similarity was utilized to designate the similar day and generate the training sample set with the high quality. Finally, the combined photovoltaic output day-ahead forecasting model by aid of SO and CNN-LSTM was established and applied in the photovoltaic power station in Yunnan. Taking the spring season as an example, compared with two types of single similar day selection methods, the MAE value of SO-CNN-LSTM prediction model based on comprehensive similar day selection decreases by 0.15 and 0.13, respectively. In addition, compared with two models （i.e. LSTM and CNN-LSTM） based on comprehensive similar day selection, the MAE values of SO-CNN-LSTM model decreases by 0.73 and 0.15, 0.36 and 0.24, and 0.42 and 0.15, respectively, in the summer, autumn and winter seasons.

Key words

comprehensive similarity index / snake optimization algorithm / convolutional neural network / long short-term memory network / photovoltaic power

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Song Yu, Xu Ye, Liu Fengping, Wang Xu, Li Wei. RESEARCH ON SO-CNN-LSTM PHOTOVOLTAIC POWER PREDICTION MODEL BASED ON COMPREHENSIVE SIMILAR DAY SELECTION[J]. Acta Energiae Solaris Sinica. 2025, 46(4): 301-312 https://doi.org/10.19912/j.0254-0096.tynxb.2023-2134

References

[1] 周鑫, 李燕, 曾永辉, 等. 基于SARIMAX-SVR的光伏发电功率预测[J]. 电力系统及其自动化学报, 2024, 36(5): 1-8.
ZHOU X, LI Y, ZENG Y H, et al.Forecasting of photovoltaic power generation based on SARIMAX-SVR[J]. Proceedings of the CSU-EPSA, 2024, 36(5): 1-8.
[2] 张帅, 张继红, 李兆泽. 基于K-means的超短期光伏功率组合预测[J]. 热能动力工程, 2025, 40(03): 144-152.
ZHANG S, ZHANG J H, LI Z J.Combined prediction of ultra short-term photovoltaic power based on K-means[J]. Journal of engineering for thermal energy and power, 2025, 40(03): 144-152.
[3] 岳有军, 吴明沅, 王红君, 等. 基于CNN-GRU-ISSA-XGBoost的短期光伏功率预测[J]. 南京信息工程大学学报, 2024, 16(2): 231-238.
YUE Y J, WU M Y, WANG H J, et al.Short term photovoltaic power prediction based on CNN-GRU-ISSA-XGBoost[J]. Journal of Nanjing University of Information Science & Ttechnology (natural science edition), 2024, 16(2): 231-238.
[4] 柴闵康, 夏飞, 张浩, 等. 基于云图特征自识别的光伏超短期预测模型[J]. 电网技术, 2021, 45(3): 1023-1035.
CHAI M K, XIA F, ZHANG H, et al.Ultra-short-term prediction of self-identifying photovoltaic based on sky cloud chart[J]. Power system technology, 2021, 45(3): 1023-1035.
[5] 薛阳, 燕宇铖, 贾巍, 等. 基于改进灰狼算法优化长短期记忆网络的光伏功率预测[J]. 太阳能学报, 2023, 44(7): 207-213.
XUE Y, YAN Y C, JIA W, et al.Photovoltaic power prediction model based on IGWO-LSTM[J]. Acta energiae solaris sinica, 2023, 44(7): 207-213.
[6] 吴硕. 光伏发电系统功率预测方法研究综述[J]. 热能动力工程, 2021, 36(8): 1-7.
WU S.Review of power forecasting methods of photovoltaic power generation system[J]. Journal of engineering for thermal energy and power, 2021, 36(8): 1-7.
[7] 陈弘川, 蔡旭, 孙国歧, 等. 基于智能优化方法的相似日短期负荷预测[J]. 电力系统保护与控制, 2021, 49(13): 121-127.
CHEN H C, CAI X, SUN G Q, et al.Similar day short-term load forecasting based on intelligent optimization method[J]. Power system protection and control, 2021, 49(13): 121-127.
[8] 童占北, 钟建伟, 李祯维, 等. 基于相似日和CNN-LSTM的短期负荷预测[J]. 电工电气, 2022(8): 17-22.
TONG Z B, ZHONG J W, LI Z W, et al.Short-term load forecasting based on grey relational analysis and CNN-LSTM[J]. Electrotechnics electric, 2022(8): 17-22.
[9] 李超然, 潘鹏程, 杨伟荣, 等. 基于改进相似日优化HBA-BiLSTM-KELM的光伏发电功率预测[J]. 太阳能学报, 2024, 45(5): 508-516.
LI C R, PAN P C, YANG W R, et al.Research on PV system power prediction based on improved similar day and HBA-BiLSTM-KELM neural network[J]. Acta energiae solaris sinica, 2024, 45(5): 508-516.
[10] 谢李杰. 基于相似日选择的区域冰蓄冷空调系统负荷预测及优化运行研究[D]. 重庆: 重庆大学, 2022.
XIE L J.Research on load forecasting and optimal operation of regional ice storage air conditioning system based on similar day selection[D]. Chongqing: Chongqing University, 2022.
[11] ZHANG X Y, LI R.Photovoltaic power prediction method based on combined similar days and BiLSTM[J]. Journal of physics: conference series, 2023, 2465(1): 012018.
[12] 白如雪. 基于改进相似日和LSTM神经网络的短期光伏功率预测方法研究[D]. 济南: 山东大学, 2023.
BAI R X.Research on short-term photovoltaic power prediction method based on improved similar day algorithm and LSTM neural network[D]. Ji’nan: Shandong University, 2023.
[13] 徐先峰, 赵依, 刘状壮, 等. 用于短期电力负荷预测的日负荷特性分类及特征集重构策略[J]. 电网技术, 2022, 46(4): 1548-1556.
XU X F, ZHAO Y, LIU Z Z, et al.Daily load characteristic classification and feature set reconstruction strategy for short-term power load forecasting[J]. Power system technology, 2022, 46(4): 1548-1556.
[14] 刘如浩. 基于孪生神经网络的视觉目标跟踪算法研究[D]. 无锡: 江南大学, 2022.
LIU R H.Research on visual target tracking algorithm based on siamese neural network[D]. Wuxi: Jiangnan University, 2022.
[15] 郑倩, 李琦. 基于孪生神经网络的牛唇纹识别研究[J]. 科技与创新, 2023(5): 59-61.
ZHENG Q, LI Q.Study on cow lip print recognition based on twin neural network[J]. Science and technology & innovation, 2023(5): 59-61.
[16] 万立志, 张运楚, 葛浙东, 等. 基于孪生神经网络的小样本人脸识别[J]. 山东建筑大学学报, 2022, 37(1): 79-85, 99.
WAN L Z, ZHANG Y C, GE Z D, et al.Small sample face recognition based on Siamese network[J]. Journal of Shandong Jianzhu University, 2022, 37(1): 79-85, 99.
[17] 董俊, 刘瑞, 束洪春, 等. 基于BIRCH聚类的L-Transformer分布式光伏短期发电功率预测[J]. 高电压技术, 2024, 50(9): 3883-3893.
DONG J, LIU R, SHU H C, et al.Short-term distributed photovoltaic power generation prediction based on BIRCH clustering and L-Transformer[J]. High voltage engineering, 2024, 50(9): 3883-3893.
[18] 邓博文, 肖伸平, 廖世英. 二次分解组合CNN-LSTM的短期负荷预测[J]. 控制与信息技术, 2023(4): 54-60.
DENG B W, XIAO S P, LIAO S Y.Short-term load forecasting based on CNN-LSTM with quadratic decomposition combined[J]. Control and information technology, 2023(4): 54-60.
[19] 雷柯松, 吐松江·卡日, 伊力哈木·亚尔买买提, 等. 基于WGAN-GP和CNN-LSTM-Attention的短期光伏功率预测[J]. 电力系统保护与控制, 2023, 51(9): 108-118.
LEI K S, TUOSONGJIANG K R, YILIHAMU Y E M M T, et al. Prediction of short-term photovoltaic power based on WGAN-GP and CNN-LSTM-Attention[J]. Power system protection and control, 2023, 51(9): 108-118.
[20] 王晓霞, 俞敏, 冀明, 等. 基于气候相似性与SSA-CNN-LSTM的光伏功率组合预测[J]. 太阳能学报, 2023, 44(6): 275-283.
WANG X X, YU M, JI M, et al.Photovoltaic power combination forecasting based on climate similarity and SSA-CNN-LSTM[J]. Acta energiae solaris sinica, 2023, 44(6): 275-283.
[21] 宋玮琼, 赵成, 郭帅, 等. 考虑天气类型和历史相似日的短期光伏输出功率预测[J]. 电网与清洁能源, 2023, 39(2): 75-82.
SONG W Q, ZHAO C, GUO S, et al.Short-term forecasting of photovoltaic output power considering weather type and historical similar days[J]. Power system and clean energy, 2023, 39(2): 75-82.
[22] 周新茂, 郑焮元, 于正鑫, 等. 基于相似日理论和LCSSA-BP的短期光伏发电功率预测[J]. 电网与清洁能源, 2022, 38(11): 88-97.
ZHOU X M, ZHENG X Y, YU Z X, et al.Short-term photovoltaic power prediction based on similarity day theory and LCSSA-BP[J]. Power system and clean energy, 2022, 38(11): 88-97.
[23] 张程, 林谷青, 黄靖, 等. 基于AMBOA-DBN结合相似日的短期光伏功率预测[J]. 太阳能学报, 2023, 44(6): 290-299.
ZHANG C, LIN G Q, HUANG J, et al.Short-term PV power prediction based on AMBOA-DBN combined with similar days[J]. Acta energiae solaris sinica, 2023, 44(6): 290-299.
[24] 王超, 刘世明. 基于相似日原理和CPSO-Elman模型的光伏电站短期功率预测[J]. 能源与环保, 2022, 44(2): 208-214.
WANG C, LIU S M.Short term power prediction of photovoltaic power station based on similar day principle and CPSO-Elman model[J]. China energy and environmental protection, 2022, 44(2): 208-214.
[25] 田乃倩. 基于孪生神经网络的行人跟踪与再识别研究[D]. 北京: 中国人民公安大学, 2021.
TIAN N Q.Research on pedestrian tracking and re-identification based on twin neural network[D]. Beijing: Chinese People’s Public Security University, 2021.
[26] 李雪. 基于孪生网络的视觉目标跟踪算法研究[D]. 西安: 西安工业大学, 2023.
LI X.Research on visual target tracking algorithm based on siamese network[D]. Xi’an: Xi’an Technological University, 2023.
[27] 叶妮婷. 基于孪生神经网络的裁判文书相似性研究[D]. 南昌: 华东交通大学, 2021.
YE N T.Research on similarity of judgment documents based on siamese neural network[D]. Nanchang: East China Jiaotong University, 2021.
[28] 刘亚珲, 赵倩. 基于聚类经验模态分解的CNN-LSTM超短期电力负荷预测[J]. 电网技术, 2021, 45(11): 4444-4451.
LIU Y H, ZHAO Q.Ultra-short-term power load forecasting based on cluster empirical mode decomposition of CNN-LSTM[J]. Power system technology, 2021, 45(11): 4444-4451.
[29] 丛敬奇, 成鹏飞, 赵振军. 基于CEEMD-CNN-LSTM的股票指数集成预测模型[J]. 系统工程, 2023, 41(4): 104-116.
CONG J Q, CHENG P F, ZHAO Z J.The integrated forecasting model of stock index based on CEEMD-CNN-LSTM[J]. Systems engineering, 2023, 41(4): 104-116.
[30] 张子华, 李琰, 徐天奇, 等. 基于麻雀算法优化的VMD-CNN-LSTM的短期风电功率研究[J]. 电气传动, 2023, 53(5): 77-83.
ZHANG Z H, LI Y, XU T Q, et al.Research on short-term wind power forecasting based on VMD-CNN-LSTM optimized by sparrow algorithm[J]. Electric drive, 2023, 53(5): 77-83.
[31] 张铭玮, 李正权, 方志豪. 基于量子粒子群优化的CNN-LSTM水质预测模型[J]. 中国计量大学学报, 2022, 33(3): 303-309, 323.
ZHANG M W, LI Z Q, FANG Z H.A CNN-LSTM water quality prediction model based on quantum particle swarm optimization[J]. Journal of China University of Metrology, 2022, 33(3): 303-309, 323.
[32] 张子豪. 基于AM-CNN-LSTM光伏短期功率预测研究[D]. 沈阳: 沈阳农业大学, 2023.
ZHANG Z H.Research on photovoltaic short-term power prediction based on AM-CNN-LSTM[D]. Shenyang: Shenyang Agricultural University, 2023.
[33] 刘旭丽, 莫毓昌, 吴哲, 等. 基于DWT-CNN-LSTM的超短期光伏发电功率预测[J]. 郑州大学学报(理学版), 2022, 54(4): 86-94.
LIU X L, MO Y C, WU Z, et al.Super-short-term photovoltaic power forecasting based on DWT-CNN-LSTM[J]. Journal of Zhengzhou University (natural science edition), 2022, 54(4): 86-94.
[34] HASHIM F A, HUSSIEN A G.Snake Optimizer: a novel meta-heuristic optimization algorithm[J]. Knowledge-based systems, 2022, 242: 108320.
[35] 王永贵, 赵炀, 邹赫宇, 等. 多策略融合的蛇优化算法及其应用[J]. 计算机应用研究, 2024, 41(1): 134-141.
WANG Y G, ZHAO Y, ZOU H Y.Multi-strategy fusion snake optimizer and its application[J]. Application research of computers, 2024, 41(1): 134-141.
[36] 石翔, 张暄培, 郭磊. 基于VMD-SO-BP的超短期风电功率预测[J]. 红水河, 2023, 42(3): 50-54, 59.
SHI X, ZHANG X P, GUO L.Ultra-short-term wind power prediction based on VMD-SO-BP[J]. Hongshui river, 2023, 42(3): 50-54, 59.
[37] 徐恒山, 李文昊, 赵铭洋, 等. 基于最小二乘和自适应蛇优化算法的直驱风机LVRT特性辨识[J]. 电力系统及其自动化学报, 2024(2): 55-66.
XU H S, LI W H, ZHAO M Y, et al.Identification of LVRT characteristic of cirect-driven wind turbine generator based on LS and ASO algorithm[J]. Proceedings of the CSU-EPSA, 2024(2): 55-66.