基于深度学习的风光场群功率预测方法研究

刘永前; 林爱美; 阎洁; 韩爽; 李莉; 孟航

doi:10.16513/j.2096-2185.DE.2106032

PDF(2868 KB)

分布式能源 ›› 2021, Vol. 6 ›› Issue (2) : 14-21. DOI: 10.16513/j.2096-2185.DE.2106032

学术研究

基于深度学习的风光场群功率预测方法研究

刘永前 ¹^,² ,
林爱美 ¹^,² ,
阎洁 ¹^,² ,
韩爽 ¹^,² ,
李莉 ¹^,² ,
孟航 ¹^,²

作者信息 +

Research on Power Forecasting Method for Wind Farms and Photovoltaic Stations Based on Deep Learning

Yongqian LIU ¹^,² ,
Aimei LIN ¹^,² ,
Jie YAN ¹^,² ,
Shuang HAN ¹^,² ,
Li LI ¹^,² ,
Hang MENG ¹^,²

Author information +

文章历史 +

摘要

随着风光场站集群化发展，大规模的风光电力接入电力系统会威胁电力系统的安全稳定运行。精准的风光功率预测能有效缓解这一问题，但是现有的风光功率预测方法多集中在场站级别，区域总出力对电力系统制定调度计划、安排旋转备用容量具有重要的意义。为此，提出了基于堆叠降噪自编码器的风光功率预测模型实现场站－区域风光功率预测。以分布在我国某省的风光场群的运行数据为例，验证所提模型的有效性。结果表明：与场站原有预测系统精度相比，平坦地形风电场功率预测精度平均提高了15.56%，光伏场站功率预测精度平均提高了21.75%；复杂地形风电场功率预测精度平均提高了3.28%。

Abstract

With the development of clusters of wind and solar power stations, large-scale wind and solar power access to the power system will threaten the safe and stable operation of the power system. Accurate power forecasting can effectively alleviate this problem, but the existing power forecasting methods are mostly concentrated at the station level and the total regional output is of great significance for the power system to formulate dispatch plans and arrange spinning reserve capacity. Therefore, a regional wind and solar power forecasting model based on Stacked Denoising auto-encoder is proposed to realize station-region wind and solar power forecasting. Taking the operating data of a group of wind and solar farms distributed in a certain province of our country as an example, the validity of the proposed model is verified. The results show that, compared with the accuracy of the original station prediction system, the prediction accuracy of wind farms in the flat terrain has increased by 15.56% on average, the prediction accuracy of solar power stations has increased by 21.75% on average, and the prediction accuracy of wind farms in the hilly terrain has increased by 3.28% on average.

导出引用

刘永前, 林爱美, 阎洁, 等. 基于深度学习的风光场群功率预测方法研究[J]. 分布式能源. 2021, 6(2): 14-21 https://doi.org/10.16513/j.2096-2185.DE.2106032

Yongqian LIU, Aimei LIN, Jie YAN, et al. Research on Power Forecasting Method for Wind Farms and Photovoltaic Stations Based on Deep Learning[J]. Distributed Energy Resources. 2021, 6(2): 14-21 https://doi.org/10.16513/j.2096-2185.DE.2106032

中图分类号： TK81

参考文献

列表( 原文顺序 | 文献年度倒序 | 文中引用次数倒序 ) 可视化分析

[1]	国家统计局. 中华人民共和国2020年国民经济和社会发展统计公报[EB/OL]. 北京，国家统计局，2021(2021-02-28) [2021-03-31]. http://www.stats.gov.cn/tjsj/zxfb/202102/t20210227_1814154.html 本文引用 [1]

[2]	李锋，陆一川. 大规模风力发电对电力系统的影响[J]. 中国电力，2006, 39(11): 80-84. LI Feng, LU Yichuan. Influences of large-scale wind energy converters on transmission systems[J]. Electric Power, 2006, 39(11): 80-84. 本文引用 [1]

[3]	QUAN H, SRINIVASAN D, KHOSRAVI A. Short-term load and wind power forecasting using neural network-based prediction intervals[J]. IEEE Transactions on Neural Networks & Learning Systems, 2017, 25(2): 303-315. 本文引用 [1]

[4]	张一平，宋红，罗敏，等. 人工神经网络算法在光伏发电短期功率预测中的应用[J]. 太阳能，2019(4): 47-53. ZHANG Yiping, SONG Hong, LUO Min, et al. Application of artificial neural network algorithm in short-term power prediction of PV power generation[J]. Solar Energy, 2019(4): 47-53. 本文引用 [1]

[5]	段炼，乡立，吴琼，等. 基于数据驱动的差分－RBF神经网络的台区短期负荷预测方法[J]. 广东电力，2020, 33(11): 66-74. DUAN Lian, XIANG Li, WU Qiong, et al. Short-term load forecasting method based on data-driven difference RBF neural network[J]. Guangdong Electric Power, 2019, 33(11): 66-74. 本文引用 [1]

[6]	李相俊，许格健. 基于长短期记忆神经网络的风力发电功率预测方法[J]. 发电技术，2019, 40(5): 426-433. LI Xiangjun, XU Gejian. Wind power prediction method based on long short-term memory neural network[J]. Power Generation Technology, 2019, 40(5): 426-433. 本文引用 [1]

[7]	凌武能，杭乃善，李如琦. 基于云支持向量机模型的短期风电功率预测[J]. 电力自动化设备，2013, 33(7): 34-38. LING Wuneng, HANG Naishan, LI Ruqi. Short-term wind power forecasting based on cloud SVM model[J]. Electric Power Automation Equipment, 2013, 33(07): 34-38. 本文引用 [1]

[8]	HAN S J, BAE K Y, PARK H S, et al. Solar power prediction based on satellite images and support vector machine[J]. IEEE Transactions on Sustainable Energy, 2016, 7(3): 1255-1263. 本文引用 [1]

[9]	KAVASSERI R G, SEETHARAMAN K. Day-ahead wind speed forecasting using f-ARIMA models[J]. Renewable Energy, 2009, 34(5): 1388-1393. 本文引用 [1]

[10]	LIU Y, SHI J, YANG Y, et al. Short-term wind-power prediction based on wavelet transform-support vector machine and statistic-characteristics analysis[J]. IEEE Transactions on Industry Applications, 2012, 48(4): 1136-1141. 本文引用 [1]

[11]	TIAN Z, REN Y, WANG G. Short-term wind power prediction based on empirical mode decomposition and improved extreme learning machine[J]. Journal of Electrical Engineering & Technology, 2018, 13(5): 1841-1851. 本文引用 [1]

[12]	桑康伟. 基于EMD-RVM的短期光伏发电预测研究[D]. 芜湖：安徽工程大学，2019. SANG Kangwei. Short-term photovoltaic power generation prediction based on EMD-RVM[D]. Wuhu: Anhui Polytechnic University, 2019. 本文引用 [1]

[13]	ISHIKAWA T, KOJIMA T, NAMERIKAWA T. Short-term wind power prediction for wind turbine via kalman filter based on JIT modeling [J]. Electrical Engineering in Japan, 2016, 198(3): 86-96. 本文引用 [1]

[14]	孙永辉，范磊，卫志农，等. 基于小波分析和集成学习的光伏输出功率短期预测[J]. 电力系统及其自动化学报，2016, 28(4): 6-11, 30. SUN Yonghui, FAN Lei, WEI Zhinong, et al. Short-term forecasting of the PV output power based on wavelet analysis and ensemble learning[J]. Proceedings of the CSU-EPSA, 2016, 28(4): 6-11, 30. 本文引用 [1]

[15]

彭周宁，林培杰，赖云锋，等. 基于混合灰色关联分析－广义回归神经网络的光伏电站短期功率预测[J]. 电气技术，2019, 20(10): 11-18.

PENG

Zhouning

, LIN

Peijie

, LAI

Yunfeng

, et al. Short-term power prediction for photovoltaic power plants based on hybrid grey relational analysis-generalized regression neural network[J]. Electrical Engineering, 2019, 20(10): 11-18.

本文引用 [1]

[16]	钱政，裴岩，曹利宵，等. 风电功率预测方法综述[J]. 高电压技术，2016, 42(4): 1047-1060. QIAN Zheng, PEI Yan, CAO Lixiao, et al. Review of wind power forecasting method[J]. High Voltage Engineering, 2016, 42(4): 1047-1060. 本文引用 [1]

[17]	曹明浩，于继来. 基于分级定价与梯级考核机制的风电场日发电计划优化申报方法[J]. 分布式能源，2019, 4(5): 17-28. CAO Minghao, YU Jilai. Optimal declaring method of daily power generation schedule for wind farm based on stepped pricing and penalizing mechanism[J]. Distributed Energy, 2019, 4(5): 17-28. 本文引用 [1]

[18]	白永祥，房大中，侯佑华，等. 内蒙古电网区域风电功率预测系统[J]. 电网技术，2010, 34(10): 157-162. BAI Yongxiang, FANG Dazhong, HOU Youhua, et al. Regional wind power forecasting system for inner mongolia power grid[J]. Power System Technology, 2010, 34(10): 157-162. 本文引用 [2]

[19]	祝牧，刘吉臻，林忠伟. 单一风电场平滑效应研究[J]. 华北电力大学学报(自然科学版), 2016, 43(3): 51-55. ZHU Mu, LIU Jizhen, LIN Zhongwei. Study on smoothing effect in single wind farm[J]. Journal of North China Electric Power University(Natural Science Edition), 2016, 43(3): 51-55. 本文引用 [1]