Abstract：With the increase of the capacity of photovoltaic generated systems, how to eliminate the problem caused by the randomness of power output for photovoltaic system becomes more significant. A novel neutral network power forecasting model based on weather forecast is proposed to solve the randomness of power output for photovoltaic system. According to historical power and weather data provided by experiment, all factors which influence photovoltaic generated energy are discussed and neutral network forecasting module is trained and evaluated by adopting generated power series of photovoltaic arrays, day-type and temperature. Forecasting results show the high precision and high efficiency of this forecasting model which is applied in stable operation of photovoltaic generation system.
陈昌松, 段善旭, 殷进军. 基于神经网络的光伏阵列发电预测模型的设计[J]. 电工技术学报, 2009, 24(9): 153-158.
Chen Changsong, Duan Shanxu, Yin Jinjun. Design of Photovoltaic Array Power Forecasting Model Based on Neutral Network. Transactions of China Electrotechnical Society, 2009, 24(9): 153-158.
[1] Femia N, Petrone G, Spagnuolo G, et al. Optimization of perturb and observe maximum power point tracking method[J]. IEEE Transactions on Power Electronics, 2005, 20(4): 963-973. [2] Kim I S, Kim M B, Youn M J. New maximum power point tracker using sliding-mode observer for estimation of solar array current in the grid-connected photovoltaic system[J]. IEEE Transactions on Industrial Electronics, 2006, 53(4): 1027-1035. [3] Xiao W, Lind M G J, Dunford W G, et al. Real-time identification of optimal operating points in photovoltaic power systems[J]. IEEE Transactions on Industrial Electronics, 2006, 53(4): 1017-1026. [4] 廖志凌, 阮新波. 一种独立光伏发电系统双向变换器的控制策略[J]. 电工技术学报, 2008, 23(1): 97-103. [5] Chakraborty S, Weiss M D, Simoes M G. Distributed intelligent energy management system for a single-phase high-frequency AC microgrid[J]. IEEE Transactions on Industrial Electronics, 2007, 54(1): 97-109. [6] Yona A, Senjyu T, Funabashi T. Application of recurrent neural network to short-term-ahead generating power forecasting for photovoltaic system[C]. IEEE Power Engineering Society General Meeting, 2007. [7] Tsikalakis A G, Hatziargyriou Nikos D. Centralized control for optimizing microgrids operation[J]. IEEE Transactions on Energy Conversion, 2008, 23(1): 241-248. [8] Kem E C, Culachenski E M, Ken G A. Cloud effects on distributed photovoltaic generation: slow transients at the gardner, massachusetts photovoltaic experiment[J]. IEEE Transactions on Energy Conversion, 1989, 4(2): 184-190. [9] Jewell W T, Unruh T D. Limits on cloud-induced fluctuation in photovoltaic generation[J]. IEEE Transactions on Energy Conversion, 1999, 5(1):8-14. [10] Mellit A, Arab A H, Khorissi N, et al. An ANFIS-based forecasting for Solar radiation data from sunshine duration and ambient temperature[C]. IEEE Power Engineering Society General Meeting, 2007. [11] Sera D, Teodorescu R, Hantschel J, et al. Optimized maximum power point tracker for fast-changing environmental conditions[J]. IEEE Transactions on Industrial Electronics, 2008, 55(7):2629-2637. [12] 飞思科技产品研发中心. 神经网络理论与MATLAB7实现[M]. 北京: 电子工业出版社, 2003. [13] 韩力群. 人工神经网络理论、设计及应用[M]. 北京：化学工业出版社, 2001.
2009, Vol. 24 
