受制于外界气象条件和设备性能损失等多方面因素的影响,光伏电站的发电功率呈现出很强的波动性和随机性,精确的光伏出力预测对光伏电站的运营管理和电网的调度运行至关重要。针对传统模糊C均值聚类算法（FCM）无法自主确定聚类数以及欧氏距离在高维数据分类上的不足,在传统FCM的基础上引入自适应因子和加入余弦距离作为样本分类指标,确定与待预测数据相似程度最高的历史样本簇集,创新性地提出一种基于改进FCM和长短期记忆（LSTM）神经网络的短期光伏出力组合预测模型。在云南某光伏电站的应用结果显示,对比其他预测模型,所提方法的历史样本分类效果更佳,发电功率预测精度更高,验证了该方法的有效性与优越性。
Abstract
The electricity generation of photovoltaic power plant is affected by various factors such as external weather condition and equipment performance loss, showing the strong volatility and stochasticity. Therefore, the accurate prediction of PV output is crucial to the operation and management of PV power plant and the scheduling operation of power grid. To solve the shortcomings of traditional fuzzy C-means clustering（FCM） that cannot determine the number of clusters autonomously and the Euclidean distance in classifying high-dimensional data, in this study, the adaptive factor and cosine distance as the sample classification index are integrated with traditional FCM, leading to the set of historical sample clusters with the highest similarity to the data to be predicted. Finally, a short-term PV output portfolio prediction model based on improved FCM and long-short term memory （LSTM） neural network is innovatively established. The applied results in a PV plant in Yunnan show that the proposed method has the better classification of historical samples and the higher prediction accuracy of power generation than other prediction models, which verifies the effectiveness and superiority of the method.
关键词
光伏出力短期预测 /
模糊C均值聚类 /
自适应方法 /
余弦距离 /
长短期记忆神经网络
Key words
photovoltaic output short-term prediction /
fuzzy C-means clustering /
adaptive method /
cosine distance /
long-short term memory neural network
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 国家发展和改革委员会, 国家能源局. 关于促进新时代新能源高质量发展的实施方案[J]. 大众用电, 2022, 37(6): 8-10.
National Development and Reform Commission, National Energy Administration. Implementation plan on promoting the high-quality development of new energy in the new era[J]. Popular utilization of electricity, 2022, 37(6): 8-10.
[2] ZIYABARI S, DU L, BISWAS S.Short-term solar irradiance forecasting based on multi-branch residual network[C]//2020 IEEE Energy Conversion Congress and Exposition (ECCE). Detroit, MI, USA, 2020: 2000-2005.
[3] 刘新志. 环境因素影响下的相似日分析与短期负荷预测[D]. 昆明: 昆明理工大学, 2021.
LIU X Z.Similar day analysis and short-term load forecasting under the influence of environmental factors[D]. Kunming: Kunming University of Science and Technology, 2021.
[4] 刘永涛, 胡冠中, 张晋华, 等. 基于改进相似日和深度置信网络的光伏短期功率预测[J]. 能源与节能, 2022, 206(11): 1-6.
LIU Y T, HU G Z, ZHANG J H, et al.Photovoltaic short-term power prediction based on improved similar day and deep belief network[J]. Energy and energy conservation, 2022, 206(11): 1-6.
[5] ZHU R, GUO W, GONG X.Short-term photovoltaic power output prediction based on k-fold cross-validation and an ensemble model[J]. Energies, 2019, 12(7): 1220.
[6] 王帅. 基于密度峰值聚类和云层分析的光伏发电功率预测[D].太原: 太原理工大学, 2018.
WANG S.Prediction of photovoltaic power generation based on density peak clustering and cloud analysis[D]. Taiyuan: Taiyuan University of Science and Technology,2018.
[7] 谭海旺, 杨启亮, 邢建春, 等. 基于XGBoost-LSTM组合模型的光伏发电功率预测[J]. 太阳能学报, 2022, 43(8): 75-81.
TANG H W, YANG Q L, XING J C, et al.Photovoltaic power prediction based on combined XGBoost-LSTM model[J]. Acta energiae solaris sinica, 2022, 43(8): 75-81.
[8] 张娜, 葛磊蛟. 基于SOA优化的光伏短期出力区间组合预测[J]. 太阳能学报, 2021, 42(5):252-259.
ZHANG N, GE L J.Photovoltaic system short-term power interval hybrid forecasting method based on seeker optimization algorithm[J]. Acta energiae solaris sinica, 2021, 42(5):252-259.
[9] 蒋建东, 余沣, 董存, 等. 基于PSO与ELM组合算法的短期光伏发电功率预测模型[J]. 郑州大学学报:理学版, 2019, 51(3):120-126.
JIANG J D, YU F, DONG C, et al.A short-term photovoltaic power forecasting model based on PSO and ELM combined algorithm[J]. Journal of Zhengzhou University (natural science edition), 2019, 51(3): 120-126.
[10] 韩若冰. 基于聚类分析和特征学习的短期负荷预测研究[D]. 徐州: 中国矿业大学, 2022.
HAN R B.Research on short-term load forecasting based on cluster analysis and feature learning[D]. Xuzhou: China University of Mining and Technology, 2022.
[11] 陈美珍. 基于聚类算法及组合模型的光伏发电功率短期预测[D]. 福州: 福建工程学院, 2022.
CHEN M Z.Short-term prediction of photovoltaic power generation based on clustering algorithm and combined model[D]. Fuzhou: Fujian University of Technology, 2022.
[12] 尚宝. 基于CEEMD-IPSO-GRU的短期光伏功率预测研究[D]. 南昌: 南昌大学, 2022.
SHANG B.Research on short-term photovoltaic power forecasting based on CEEMD-IPSO-GRU[D].Nanchang: Nanchang University, 2022.
[13] 杨浩, 张磊, 何潜, 等. 基于自适应模糊C均值算法的电力负荷分类研究[J]. 电力系统保护与控制, 2010, 38(16):111-115, 122.
YANG H, ZHANG L, HE Q, et al.Study of power load classification based on adaptive fuzzy C means[J]. Power system protection and control, 2010, 38(16): 111-115, 122.
[14] 郭康壮. 超短期光伏功率预测模型精度提升研究[D]. 济南: 济南大学, 2022.
GUO K Z.Research on improving the accuracy of ultra-short-term photovoltaic power forecasting model[D]. Ji’nan: University of Jinan, 2022.
[15] 张永新, 李飞, 张榴晨, 等. 基于线路阻抗聚类的分布式光伏电站等效建模[J]. 太阳能学报, 2022, 43(5): 312-318.
ZHANG Y X, LI F, ZHANG L C, et al.Equivalent modeling of distributed photovoltaic power stations based on line impedance clustering[J]. Acta energiae solaris sinica, 2022, 43(5): 312-318.
[16] 慎慧强. 基于混合预测模型的风光短期功率预测及不确定性分析[D].郑州: 华北水利水电大学, 2022.
SHEN H Q.Short term power prediction and uncertainty analysis of wind and solar energy based on hybrid prediction model[D]. Zhengzhou: North China University of Water Resources and Electric Power, 2022.
[17] 马晓玲, 张祥飞, 庞清乐, 等. 模糊聚类-BP神经网络短期光伏发电预测模型[J]. 物联网技术, 2021, 11(10): 69-72.
MA X L, ZHANG X F, PANG Q L, et al.Fuzzy clustering BP neural network short term photovoltaic power generation prediction model[J]. Internet of things technologies, 2021, 11(10): 69-72.
[18] CAO W S, ZHOU J L, XU Q, et al.Short-term forecasting and uncertainty analysis of photovoltaic power based on FCM-WOA-BILSTM model[J]. Frontiers in energy research, 2022, 10: 926774.
[19] 云南省发展和改革委员会, 云南省工业和信息化厅. 关于印发光伏产业发展三年行动及配套政策措施的通知[EB/OL].[2022-06-15]. https://www.yn.gov.cn/ztgg/yhyshj/zccsydhb/cyyhsj/202303/t20230309_255985.html.
Development and Reform Commission of Yunnan Province, Department of Industry and Information Technology of Yunnan Province. Notice on the Issuance of the Three-Year Action for Photovoltaic Industry Development and Supporting Policy Measures[EB/OL].[2022-06-15]. https://www.yn.gov.cn/ztgg/yhyshj/zccsydhb/cyyhsj/202303/t20230309_255985.html.
PDF(1280 KB)
