基于集成学习的分布式光伏发电功率日前预测

doi:10.11930/j.issn.1004-9649.202204083

中国电力 ›› 2022, Vol. 55 ›› Issue (9): 38-45.DOI: 10.11930/j.issn.1004-9649.202204083

• 碳中和背景下农业农村综合能源系统 • 上一篇下一篇

基于集成学习的分布式光伏发电功率日前预测

刘昳娟¹, 陈云龙¹, 刘继彦¹, 张雪梅¹, 吴潇雨², 孔维政²

1. 国网山东省电力公司，山东济南 250002;
2. 国网能源研究院有限公司，北京 102209

收稿日期:2022-04-19 修回日期:2022-06-23 出版日期:2022-09-28 发布日期:2022-09-20
作者简介:刘昳娟（1975—），女，硕士，高级工程师，从事新能源用能优化研究，E-mail：sddllj@163.com;陈云龙（1974—），男，高级工程师，从事电力经济、电力供需研究，E-mail：chyunlong@163.com;刘继彦（1984—），男，硕士，高级工程师，从事电力市场化交易、综合能源管理研究，E-mail：18553829016@163.com;张雪梅（1986—），女，硕士，中级经济师，从事电力经济、综合能源研究，E-mail：1539834847@qq.com;吴潇雨（1991—），男，博士，工程师，从事微网能量管理、综合能源系统规划仿真研究，E-mail：xiaoyu_wu0314@outlook.com;孔维政（1985—），男，硕士，高级工程师，从事能源互联网规划设计、农村能源系统建设与管理研究，E-mail：kongweizheng@sgeri.sgcc.com.cn
基金资助:
国家电网有限公司科技项目（面向乡村振兴的农村能源互联网构建技术与业态模式研究，SGSDWF00FCJS2100201)。

Ensemble Learning-Based Day-Ahead Power Forecasting of Distributed Photovoltaic Generation

LIU Yijuan¹, CHEN Yunlong¹, LIU Jiyan¹, ZHANG Xuemei¹, WU Xiaoyu², KONG Weizheng²

1. State Grid Shandong Electric Power Co., Ltd., Jinan 250002, China;
2. State Grid Energy Research Institute Co., Ltd., Beijing 102209, China

Received:2022-04-19 Revised:2022-06-23 Online:2022-09-28 Published:2022-09-20
Supported by:
This work is supported by Science and Technology Project of SGCC (Research on Construction Technology and Business Mode of Rural Energy Internet for Rural Revitalization, No.SGSDWF00FCJS2100201)

摘要/Abstract

摘要： 对于光伏发电功率精准的日前预测有助于电网设计未来调度计划，降低新能源发电对电网的冲击，提高消纳率。提出一种Boosting集成学习框架下的光伏发电功率日前预测方法。首先，根据光伏出力主要受天气影响的特点，通过皮尔逊系数获得相关性强的气象因素，利用k-means++对与光伏发电功率相关性极强的总水平辐照度进行聚类以获得相似日数据集；然后，将极限学习机（extreme learning machine，ELM）引入Boosting框架，构建光伏出力日前预测模型（B-ELMs）；最后，利用真实光伏电站运行数据验证模型有效性，该模型在试验过程中展现出良好的适应性，最高决策系数（R²）达0.9819。实验结果表明，由于集成学习框架的存在，B-ELMs能对复杂天气下的规律性弱、波动性强的光伏出力曲线提供较为精确的预测结果；同时，相较于深度学习网络，B-ELMs的收敛速度更快，在维持较快训练速度的同时保障更为精确的预测结果。

关键词: 光伏出力预测, 极限学习机, 集成学习, k-means, 日前预测

Abstract: Accurate day-ahead power prediction of photovoltaic generation is helpful to design future scheduling plan of power grid, reduce the impact of new energy generation on power grid and improve the accommodation rate. A day-ahead power forecasting method for photovoltaic generation is proposed based on the Boosting ensemble learning framework. Firstly, according to the characteristics of photovoltaic output which is mainly affected by weather, the meteorological factors with strong correlation are obtained through the Pearson coefficient, and the k-means ++ is used to cluster the total horizontal irradiance that is strongly correlated with photovoltaic generation power to obtain the similar daily datasets. And then, the extreme learning machine (ELM) is introduced into the Boosting framework to build the photovoltaic output day-ahead prediction model (B-ELMs). Finally, the validity of the model is verified using the operation data of real photovoltaic power stations. The proposed model shows good adaptability in the test process and has the highest decision coefficient (R²) of 0.9819. The experimental results show that due to the existence of ensemble learning framework, the B-ELMS can still provide accurate prediction results against the photovoltaic output curves with poor regularity and strong fluctuation under complex weather. At the same time, the B-ELMS has a faster convergence rate compared with deep-learning network, and can provide more accurate prediction results while maintaining faster training speed.

Key words: photovoltaic output forecasting, extreme learning machine, integrated learning, k-means, day-ahead forecasting

刘昳娟, 陈云龙, 刘继彦, 张雪梅, 吴潇雨, 孔维政. 基于集成学习的分布式光伏发电功率日前预测[J]. 中国电力, 2022, 55(9): 38-45.

LIU Yijuan, CHEN Yunlong, LIU Jiyan, ZHANG Xuemei, WU Xiaoyu, KONG Weizheng. Ensemble Learning-Based Day-Ahead Power Forecasting of Distributed Photovoltaic Generation[J]. Electric Power, 2022, 55(9): 38-45.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202204083

https://www.electricpower.com.cn/CN/Y2022/V55/I9/38

参考文献

[1] 中国能源网. 2020分布式能源研究报告[R]. 2020.
[2] 姚金楠. 分布式光伏迎来新一轮高速增长[N]. 中国能源报, 2022-03-28(9).
[3] 李丰君, 王磊, 赵健, 等. 基于天气融合和LSTM网络的分布式光伏短期功率预测方法[J/OL]. 中国电力: 1–9[2022-06-14]. http://kns.cnki.net/kcms/detail/11.3265.TM.20220217.0933.006.html.
LI Fengjun, WANG Lei, ZHAO Jian, et al. Research on distributed photovoltaic short-term power prediction method based on weather fusion and LSTM-net[J/OL]. Electric Power: 1–9[2022-06-14]. http://kns.cnki.net/kcms/detail/11.3265.TM.20220217.0933.006.html.
[4] FENG Y, GONG D Z, ZHANG Q W, et al. Evaluation of temperature-based machine learning and empirical models for predicting daily global solar radiation[J]. Energy Conversion and Management, 2019, 198: 111780.
[5] DAS U K, TEY K S, SEYEDMAHMOUDIAN M, et al. Forecasting of photovoltaic power generation and model optimization: a review[J]. Renewable and Sustainable Energy Reviews, 2018, 81: 912–928.
[6] 司志远, 杨明, 于一潇, 等. 基于卫星云图特征区域定位的超短期光伏功率预测方法[J]. 高电压技术, 2021, 47(4): 1214–1223
SI Zhiyuan, YANG Ming, YU Yixiao, et al. Ultra-short-term photovoltaic power prediction method based on satellite image feature region positioning[J]. High Voltage Engineering, 2021, 47(4): 1214–1223
[7] 白捷予, 董存, 王铮, 等. 考虑云层遮挡的光伏发电功率超短期预测技术[J/OL]. 高电压技术: 1−11 [2022-06-14]. DOI: 10.13336/j. 1003-6520. hve. 20211769.
BAI Jieyu, DONG Cun, WANG Zheng, et al. Ultra-short-term prediction of photovoltaic power generation considering cloud cover[J/OL]. High Voltage Engineering: 1−11 [2022-06-14]. DOI:10.13336/j.1003-6520.hve.20211769.
[8] 师浩琪, 郭力, 刘一欣, 等. 基于多源气象预报总辐照度修正的光伏功率短期预测[J]. 电力自动化设备, 2022, 42(3): 104–112
SHI Haoqi, GUO Li, LIU Yixin, et al. Short-term forecasting of photovoltaic power based on total irradiance correction of multi-source meteorological forecast[J]. Electric Power Automation Equipment, 2022, 42(3): 104–112
[9] 韦泽恺. 基于深度学习的光伏短期功率预测方法研究[D]. 北京: 华北电力大学(北京), 2021.
WEI Zekai. Research on photovoltaic short-term power prediction method based on deep learning[D]. Beijing: North China Electric Power University, 2021.
[10] 张波, 王晓晨, 周旺, 等. 基于机器学习的光伏发电功率预测: 以金华市为例[J]. 技术与市场, 2022, 29(3): 17–22
ZHANG Bo, WANG Xiaochen, ZHOU Wang, et al. Photovoltaic power generation prediction based on machine learning-taking Jinhua City as an example[J]. Technology and Market, 2022, 29(3): 17–22
[11] 焦超凡. 基于机器学习的短期光伏发电功率预测方法研究[D]. 郑州: 中原工学院, 2021.
JIAO Chaofan. Research on short-term pv power prediction method based on machine learning[D]. Zhengzhou: Zhongyuan University of Technology, 2021.
[12] 孙建波. 基于EEMD与变权组合预测的光伏发电预测模型及应用研究[D]. 北京: 华北电力大学(北京), 2019.
SUN Jianbo. Photovoltaic generation prediction model based on EEMD-variable weight combination forecasting and application research[D]. Beijing: North China Electric Power University, 2019.
[13] 王振浩, 王翀, 成龙, 等. 基于集合经验模态分解和深度学习的光伏功率组合预测[J/OL]. 高电压技术: 1–10 [2022-06-14]. DOI: 10.13336/j. 1003-6520. hve. 20210971.
WANG Zhenhao, WANG Chong, CHENG Long, et al. Photovoltaic power combined prediction based on ensemble empirical mode decomposition and deep learning[J/OL]. High Voltage Engineering: 1–10 [2022-06-14]. DOI:10.13336/j.1003-6520.hve.20210971.
[14] 吕伟杰, 方一帆, 程泽. 基于模糊C均值聚类和样本加权卷积神经网络的日前光伏出力预测研究[J]. 电网技术, 2022, 46(1): 231–238
LÜ Weijie, FANG Yifan, CHENG Ze. Prediction of day-ahead photovoltaic output based on FCM-WS-CNN[J]. Power System Technology, 2022, 46(1): 231–238
[15] 乔路丽, 方诗琦, 赵庭锐, 等. 基于相似日和IGA-BP的光伏发电功率预测方法研究[J]. 电网与清洁能源, 2022, 38(1): 128–134
QIAO Luli, FANG Shiqi, ZHAO Tingrui, et al. A study on the forecasting method of photovoltaic power generation based on similar day and IGA-BP[J]. Power System and Clean Energy, 2022, 38(1): 128–134
[16] 徐一伦, 张彬桥, 黄婧, 等. 考虑天气类型和相似日的IWPA-LSSVM光伏发电功率预测[J/OL]. 中国电力: 1–9[2022-06-14]. http://kns.cnki.net/kcms/detail/11.3265.TM.20211109.1202.002.html.
XU Yilun, ZHANG Binqiao, HUANG Jing, et al. Forecast of photovoltaic power based on IWPA-LSSVM considering weather type and similar day[J/OL]. Electric Power: 1–9[2022-06-14]. http://kns.cnki.net/kcms/detail/11.3265.TM.20211109.1202.002.html.
[17] NAINGGOLAN R, PERANGIN-ANGIN R, SIMARMATA E, et al. Improved the performance of the K-means cluster using the sum of squared error (SSE) optimized by using the elbow method[J]. Journal of Physics: Conference Series, 2019. DOI:10.1088/1742-6596/1361/1012015.
[18] YANG Y M, YU H, SUN Z. Aircraft failure rate forecasting method based on Holt-Winters seasonal model[C]//2017 IEEE 2 nd International Conference on Cloud Computing and Big Data Analysis. Chengdu. IEEE, 2017: 520–524.

基于集成学习的分布式光伏发电功率日前预测

Ensemble Learning-Based Day-Ahead Power Forecasting of Distributed Photovoltaic Generation

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

[1]	席磊, 王艺晓, 何苗, 程琛, 田习龙. 基于反向鲸鱼-多隐层极限学习机的电网FDIA检测[J]. 中国电力, 2024, 57(9): 20-31.
[2]	叶煜明, 钱琪琪, 万正东, 张继钢. 基于嵌入法与集成学习的线路工程造价预测[J]. 中国电力, 2024, 57(5): 251-260.
[3]	胡云鹏, 都成刚, 齐军, 郑日红, 阿敏夫, 张浩, 梁永亮. 基于D-S证据理论的配电网接地故障原因综合辨识模型[J]. 中国电力, 2024, 57(10): 133-142.
[4]	王尧平, 李特, 姜凯华, 李文辉, 吴强, 王羽. 基于气象特征挖掘与AdaBoost-MEA-ELM模型的绝缘子盐密预测[J]. 中国电力, 2023, 56(9): 157-167.
[5]	安佳坤, 杨书强, 王涛, 贺春光, 张菁, 袁超, 窦春霞. 电动汽车聚合下的微能源互联网优化调度策略[J]. 中国电力, 2023, 56(5): 80-88.
[6]	杨作祥, 王晶晶, 吴江, 唐莎莎, 侯斌. 计及源荷不确定性的配电网综合节能潜力评估方法[J]. 中国电力, 2022, 55(8): 151-156,164.
[7]	杨建华, 肖达强, 张伟, 余明琼, 易本顺. 基于改进RBFNN的1 000 kV特高压线损预测[J]. 中国电力, 2022, 55(5): 122-127,142.
[8]	范海虹. 基于萤火虫算法的短期电力负荷预测方法[J]. 中国电力, 2021, 54(3): 141-148.
[9]	张林, 刘继春. 基于EEMD-SE和PSO-KELM的短期负荷区间预测方法[J]. 中国电力, 2021, 54(3): 132-140.
[10]	袁优，康积涛，王德林，徐明雨，高超峰. 考虑空间效应的风电场动态特性等值方法研究[J]. 中国电力, 2016, 49(12): 144-149.

模态框（Modal）标题

基于集成学习的分布式光伏发电功率日前预测

Ensemble Learning-Based Day-Ahead Power Forecasting of Distributed Photovoltaic Generation

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics