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

摘要
图/表
参考文献
相关文章 (2)

全文: PDF (22453 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要随着大规模的光伏发电接入电网,其输出的随机性和波动性给电网调度管理带来巨大的挑战。基于此,本文提出了一种同时考虑统计（历史光伏输出功率）和物理（历史和未来的气象信息）变量的混合灰色关联分析-广义回归神经网络预测模型。首先,计算多元气象因子与光伏发电功率的皮尔逊相关系数,将相关系数较高的气象因子确定为建立预测模型的气象输入因子;然后,采用灰色关联分析算法计算历史日与待预测日的关联度确定最佳相似日,选取最佳相似日的光伏输出功率和气象输入因子以及待预测日的相关气象参数作为广义回归神经网络模型的输入参数,得到待预测日各个时刻输出功率的预测值;最后,利用澳大利亚DKA太阳能中心网站所提供的光伏电站历史气象数据和功率数据对所设计的模型进行训练和测试,验证模型在不同季节下的预测效果。结果表明,与所选择的对比模型相比,本文所建模型具有较好的预测性能。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	彭周宁
	林培杰
	赖云锋
	程树英
	陈志聪

关键词 ：光伏功率预测, 灰色关联分析, 广义回归神经网络, 最佳相似日

Abstract：With the large-scale photovoltaic (PV) power generation connected to the grid, the randomness and volatility of its output brings great challenges to the dispatching management of the grid. Therefore, a hybrid (grey relational analysis and generalized regression neural network, GRA-GRNN) prediction model considering both statistical (historical PV output power) and physical (historical and future meteorological information) variables is proposed. Firstly, the (Pearson correlation coefficient, R²) between multivariate meteorological factors and PV power is calculated, and the meteorological factors with higher correlation coefficient are selected as the meteorological input factors for the establishment of the prediction model. Secondly, the GRA algorithm is applied to calculate the correlation degree between the historical days and the forecasting day to determine the optimal similarity day. Then, the PV power and meteorological input factors of the optimal similarity day and the relevant meteorological parameters of the forecasting day are selected as the input parameters of the GRNN model, and the predicted output power at each time of the forecasting day is obtained. Finally, the designed model is trained and tested by using the historical meteorological datasets and power datasets of a PV power plant provided by the (desert knowledge australia solar center, DAKSC) website to verify the performance of the model in different seasons. The results show that the proposed model is superior to the selected comparison models.

Key words： photovoltaic power prediction grey relational analysis generalized regression neural network optimal similarity day

收稿日期: 2019-03-13 出版日期: 2019-09-29

基金资助:国家自然科学基金（61574038、61601127、51508105）; 福建省科技厅项目（2018J01774、2018J01645、2019J01218、2016H6012）; 福建省教育厅项目（JAT160073）; 福建省经信委行业关键共性技术项目（83016006、830020）

作者简介: 彭周宁（1993-）,女,福建省莆田市人,硕士研究生,主要从事光伏发电功率预测和嵌入式系统的研究工作。

引用本文:

彭周宁, 林培杰, 赖云锋, 程树英, 陈志聪. 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, Cheng Shuying, Chen Zhicong. Short-term power prediction for photovoltaic power plants based on hybrid grey relational analysis-generalized regression neural network. Electrical Engineering, 2019, 20(10): 11-18.

链接本文:

http://dqjs.cesmedia.cn/CN/Y2019/V20/I10/11

[1] 李贞, 崔丽艳, 陶颍军, 等. 基于博弈论赋权的光伏功率组合预测模型[J]. 电气技术, 2017, 18(5): 24-29.
[2] 郭鹏, 文晶, 朱丹丹, 等. 基于源-荷互动的大规模风电消纳协调控制策略[J]. 电工技术学报, 2017, 32(3): 1-9.
[3] 姜雲腾, 李萍. 基于改进粒子群神经网络短期负荷预测[J]. 电气技术, 2018, 19(2): 87-91.
[4] Sobri S, Koohi-Kamali S, Rahim N A.Solar photo- voltaic generation forecasting methods: a review[J]. Energy Conversion & Management, 2018, 156(C): 459-497.
[5] 叶瑞丽, 郭志忠, 刘瑞叶, 等. 基于小波包分解和改进Elman神经网络的风电场风速和风电功率预测[J]. 电工技术学报, 2017, 32(21): 103-111.
[6] Das U K, Tey K S, Seyedmahmoudian M A, et al.Forecasting of photovoltaic power generation and model optimization: a review[J]. Renewable & Sustainable Energy Reviews, 2018, 81(1): 912-928.
[7] Khan I, Zhu Honglu, Yao Jianxi, et al.Hybrid power forecasting model for photovoltaic plants based on neural network with air quality index[J]. International Journal of Photoenergy, 2017(1): 1-9.
[8] Liu F, Li R, Li Y, et al.Takagi-sugeno fuzzy model-based approach considering multiple weather factors for the photovoltaic power short-term forecasting[J]. IET Renewable Power Generation, 2017, 11(10): 1281-1287.
[9] 王昕, 黄柯, 郑益慧, 等. 基于萤火虫算法-广义回归神经网络的光伏发电功率组合预测[J]. 电网技术, 2017, 41(2): 455-461.
[10] 李练兵, 张佳, 韩靖楠, 等. 基于Elman算法的光伏阵列的短期功率预测研究[J]. 太阳能学报, 2017, 38(6): 1560-1566.
[11] 雷鸣宇, 杨子龙, 王一波, 等. 光/储混合系统中的储能控制技术研究[J]. 电工技术学报, 2016, 31(23): 86-92.
[12] 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.
[13] 贾逸伦, 龚庆武, 雷杨, 等. 基于灰色关联与量子粒子群寻优的光伏短期预测[J]. 电网与清洁能源, 2016, 32(2): 109-115, 121.
[14] Konaté A A, Pan H, Khan N, et al.Generalized regression and feed-forward back propagation neural networks in modelling porosity from geophysical well logs[J]. Journal of Petroleum Exploration and Production Technology, 2015, 5(2): 157-166.
[15] Eseye A T, Zhang Jianhua, Zheng Dehua.Short-term photovoltaic solar power forecasting using a hybrid Wavelet-PSO-SVM model based on SCADA and meteorological information[J]. Renewable Energy, 2018, 118: 357-367.
[16] Liu Jun, Fang Wanliang, Zhang Xudong, et al.An improved photovoltaic power forecasting model with the assistance of aerosol index data[J]. IEEE Transactions on Sustainable Energy, 2015, 6(2): 434-442.
[17] Liu L, Liu D, Sun Q, et al.Forecasting power output of photovoltaic system using a BP network method[J]. Energy Procedia, 2017(142): 780-786.
[18] Zhong J, Liu L, Sun Q, et al.Prediction of Photovoltaic power generation based on general regression and back propagation neural network[J]. Energy Procedia, 2018, 152: 1224-1229.
[19] Liu Luyao, Zhao Yi, Sun Qie, et al.Prediction of short-term output of photovoltaic system based on generalized regression neural network[C]//2017 IEEE Conference on Energy Internet and Energy System Integration (EI2), 2017: 1-6.