杨留锋

• 1:协鑫新能源控股有限公司

摘要(Abstract)：

作为一种新型清洁能源,光伏发电被越来越多地应用于生产、生活中。相较于传统能源,由于受到光照的影响,光伏发电具有间歇性和波动性的特点,这使得该类能源的供需关系变得更加复杂多变。为了更好地利用太阳能,就需要获取光伏电站的实时供需信息,并据此预测未来短期内的供需关系,从而达到更优的供电效果。人工智能算法具有高效处理复杂数据及解决复杂问题的突出优点,越来越多的被应用于光伏发电的各项预测中,包括用电负荷预测、影响光伏发电性能的太阳辐照度的预测等。对人工智能算法在光伏发电预测这一应用场景下的研究现状进行了综述,并对未来人工智能算法和光伏发电预测的深度融合作出了展望。

关键词(KeyWords)： 光伏发电;人工智能算法;负荷预测;太阳辐照度预测

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 杨留锋

参考文献(References)：

• [1] JOSHI P A, PATEL J J. Computational analysis and intelligent control of load forecasting using time series method[C]//Proceedings of the International Conference on Intelligent Systems and Signal Processing, March 24-25, 2017, Gujarat, India. Singapore:Springer, 2018:297-306.
• [2] KHAN M, JAVAID N, IQBAL M N, et al. Load prediction based on multivariate time series forecasting for energy consumption and behavior alanalytics[C]//Proceedings of the Conference on Complex, Intelligent, and Software Intensive Systems, July 4-6, 2018, Matsue, Japan.Singapore:Springer, 2018:305-316.
• [3]李娜.基于相似日选取的马尔科夫短期负荷预测方法[J].电工技术, 2018(4):86-88.
• [4] LI X C, LI C T, CONG L M, et al. Short-term load forecasting based on dynamic weight similar day selection algorithm[J]. Power system protection&control, 2017,45(6):1-8.
• [5]张炀,汪洋,祝宇翔,等.基于PAM和ELM的电力短期负荷预测相似日选取算法[J].贵州电力技术, 2017,20(12):84-87.
• [6]彭钟华.基于遗传算法优化PNN的短期负荷预测[J].电气开关, 2017, 55(1):49-51, 56.
• [7] KUMAR H, SAINI S. Chaotic characterization of electric load demand time series&load forecasting by using GA trained artificial neural network[C]//International Conference on Signal Processing, Communication, Power and Embedded System(SCOPES), October 3-5, 2016,Paralakhemundi, India. IEEE, 2017:1423-1428.
• [8]董明亮,刘培胜,潘振,等.基于SVM-GA模型的城市天然气长期负荷预测[J].辽宁石油化工大学学报, 2017,37(2):31-36.
• [9] HUO J, SHI T T, CHANG J. Comparison of random forest and SVM for electrical short-term load forecast with different data sources[C]//2016 7th IEEE International Conference on Software Engineering and Service Science(ICSESS), August 26-28, 2016, Beijing, China. IEEE, 2017:1077-1080.
• [10] SABER A Y, KHANDELWAL T. Internet of Things based online load forecasting[C]//2017 9th Annual IEEE Green Technologies Conference, March 29-31, 2017, Denver, CO,USA. IEEE, 2017:189-194.
• [11]张宇航,邱才明,贺兴,等.一种基于LSTM神经网络的短期用电负荷预测方法[J].电力信息与通信技术,2017(9):19-25.
• [12] ZHANG W L, HUA H C, CAO J W. Short term load forecasting based on IGSA-ELM algorithm[C]//Proceedings of the 2017 IEEE International Conference on Energy Internet, April 17-21, 2017, Beijing, China. IEEE Computer Society, 2017:296-301.
• [13]袁硕,陈礼定,孙国鹏,等.基于时间序列的电力负荷数据分析[J].应用数学进展, 2016, 5(2):214-224.
• [14]雷绍兰,孙才新,周湶,等.电力短期负荷的多变量时间序列线性回归预测方法研究[J].中国电机工程学报,2006, 26(2):25-29.
• [15] YILDIZ B, BILBAO J I, SPROUL A B. A review and analysis of regression and machine learning models on commercial building electricity load forecasting[J].Renewable and sustainable energy reviews, 2017, 73:1104-1122.
• [16]梁智,孙国强,李虎成,等.基于VMD与PSO优化深度信念网络的短期负荷预测[J].电网技术, 2018, 42(2):598-606.
• [17] YOUSSEF A, EL-TELBANY M, ZEKRY A. The role of artificial intelligence in photo-voltaic systems design and control:A review[J]. Renewable and sustainable energy reviews, 2017, 78:72-79.
• [18] HUANG N, LI R, LIN L, et al. Low redundancy feature selection of short term solar irradiance prediction using conditional mutual information and gauss process regression[J]. Sustainability, 2018, 10(8):2889.
• [19] QING X, NIU Y. Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM[J]. Energy,2018, 148:461-468.
• [20] MOCANU E, MOCANU D C, NGUYEN P H, et al. Online building energy optimization using deep reinforcement learning[J]. IEEE transactions on smart grid, 2019,10(4):3698-3708.
• [21] JOZI A, PINTO T, PRACA I, et al. Energy consumption forecasting using neuro-fuzzy inference systems:Thales TRT building case study[C]//2017 IEEE Symposium Series on Computational Intelligence(SSCI), 27 November-1December, 2017, Honolulu, HI, USA.
• [22] SANSA I, BELLAAJ N M. Solar radiation prediction using NARX model[EB/OL].(2018-02-28). https://www.intechopen.com/books/advanced-applications-for-artificialneural-networks/solar-radiation-prediction-using-narxmodel.
• [23] MEENAL R, SELVAKUMAR A I. Assessment of SVM,empirical and ANN based solar radiation prediction models with most influencing input parameters[J]. Renewable energy, 2018, 121:324-343.
• [24] BENMOUIZA K, CHEKNANE A. Clustered ANFIS network using fuzzy c-means, subtractive clustering, and grid partitioning for hourly solar radiation forecasting[J].Theoretical and applied climatology, 2019(137):31-43.
• [25] KERBOUCHE K, HADDAD S, RABHI A, et al. A GRNN based algorithm for output power prediction of a PV panel[C]//Proceedings of 2017 International Conference in Artificial Intelligence in Renewable Energetic Systems,October 22-24, 2017, Tipaza, Algeria. Singapore:Springer,2018:291-298.
• [26] LI L L, WEN S Y, TSENG M L, et al. Photovoltaic array prediction on short-term output power method in centralized power generation system[J/OL]. Annals of Operations Research.[2018-05-05]. https://doi.org/10.1007/s10479-018-2879-y.
• [27] ZHANG W, DANG H, SIMOES R. A new solar power output prediction based on hybrid forecast engine and decomposition model[J]. Isa transactions, 2018, 81:105-120.
• [28] NETSANET S, ZHANG J, ZHENG D, et al. An aggregative machine learning approach for output power prediction of wind turbines[C]//2018, IEEE Texas Power and Energy Conference(TPEC), February 8-9, 2018, College station,TX, USA. IEEE, 2018:1-6.
• [29] BILAL B O, ADJALLAH K H, SAVA A, et al. Wind turbine power output prediction model design based on artificial neural networks and climatic spatiotemporal data[C]//2018 IEEE International Conference on Industrial Technology(ICIT), February 20-22, 2018, Lyon, France.IEEE, 2018.