1. Center of Electrical & Electronic Technology Shanghai Jiao Tong University Shanghai。200240 China 2.Key Laboratory of Control of Power Transmission and Conversion Ministry of Education Shanghai Jiao Tong University Shanghai 200240 China 3. Yanji Power Supply Company,Jilin Electric Power Co. Ltd Yanbian 133000 China
Abstract：In order to overcome the irregularity of wind power and improve wind power load forecasting accuracy. The frequency domain decomposition methods use in wind power load forecasting can find the wind power law and overcome the irregularity of wind power on a certain extent. With the frequency domain decomposition method,the original load data will be decompose into daily cycle,week cycle,the low and high frequency four parts. Part of the daily cycle will use neural network methods for training and prediction. The low-frequency part will use a linear regression method. The method of combining lifting wavelet and neural network will be used in training and forecasting the high-frequency part. Finally,the various parts of the forecasting results add up to achieve high-precision wind power load forecasting. In this paper,the actual data are used for simulation,the experimental results show that the method based on the frequency domain decomposition,can more easily find the wind power law,benefit short term load forecasting by different methods in different part,greatly improve the precision of forecasting. The test shows that the method used for the wind power load forecast is feasible and effective.
[1] 李钇里. 富锦风电场一期工程接入对黑龙江省电网的影响[J]. 黑龙江电力, 2008, 30(3): 189-191. Li Yili. Effect of connecting with power grid for first-stage construction of Fujin wind power plant on heilongjiang power grid[J]. Power of Heilongjiang, 2008, 30(3):189-191. [2] 王丽婕, 廖晓钟, 高爽. 并网型大型风电场风力发电功率-时间序列的混沌属性分析[J]. 北京理工大学学报, 2007, 27(12): 1077-1080. Wang Lijie, Liao Xiaozhong, Gao Shuang. Chaos characteristics analysis of wind power generation time series for a grid connecting wind farm [J]. Transactions of Beijing Institute of Technology, 2007, 27(12): 1077-1080. [3] 王白玲. 电力负荷组合预测的理论方法及影响因素分析[D]. 北京: 华北电力大学, 2005. [4] George Sideratos and Nikos D. Hatziargyriou. An advanced statistical method for wind power forecasting [J]. IEEE Transactions on Power Systems, 2007, 22(1): 258-265. [5] T H M El-Fouly, E F El-Saadany, M M A Salama. Grey predictor for wind energy conversion systems output power prediction[J]. IEEE Transactions on Power Systems, 2006, 21(3): 1450-1452. [6] 于希宁,牛成林,李建强. 基于决策树和专家系统的短期电力负荷预测系统[J]. 华北电力大学学报, 2005, 32 (5): 57-61. Yu Xining, Niu Chenglin, Li Jianqiang. Electric load forecast based on decision tree and expert system [J]. Journal of North China Electric Power University, 2005, 32 (5): 57-61. [7] 杨期余, 汪卫华, 蓝信军. 长期电力负荷预测的模糊数学方法[J]. 湖南大学学报(自然科学版), 2002. 29 (6): 67-70. Yang Qiyu, Wang Weihua, Lan Xinjun. A fuzzy mathematic method for long term load forecasting [J]. Journal of Hunan University (Natural Sciences Edition), 2002, 29(6): 67-70. [8] 赵海青. 神经网络优选组合预测模型在电力负荷预测中的应用[J]. 运筹与管理, 2005, 14 (1): 115-118. Zhao Haiqing. The application to power load forecasting of ANN optimization combinatorial predication model [J]. Operations Research and Management Science, 2005, 14(1): 115-118. [9] J P S Catal#x000e3;o, H M I Pousinho, V M F Mendes. Hybrid wavelet-PSO-ANFIS approach short-term wind power forecasting in portugal [J]. IEEE Transactions on Sustainable Energy, 2011, 2(1): 50-59. [10] 庞松岭, 穆钢, 王修权, 等. 基于负荷规律性分析的支持向量机短期负荷预测方法[J]. 东北电力大学学报, 2006, 26(4): 1-6. Pang Songling, Mu Gang, Wang Xiuquan, et al. Short term load forecasting method based on load regularity analysis for supporting vector machines[J]. Journal of Northeast Dianli University Natural Science Edition, 2006, 26(4): 1-6. [11] Hans Bludszuweit, Jos#x000e9; Antonio Dom#x000ed;nguez-Navarro, Andr#x000e9;s Llombart. Statistical analysis of wind power forecast error[J]. IEEE Transactions on Power Systems, 2008, 3(23):983-991. [12] Nima Amjady, Farshid Keynia, Hamidreza Zareipour. Wind power prediction by a new forecast engine composed of modified hybrid neural network and enhanced particle swarm optimization[J]. IEEE Transactions on Sustainable Energy, 2011, 3(2): 265-276. [13] Saurabh Tewari, Charles J Geyer, Ned Mohan. A statistical model for wind power forecast error and its application to the estimation of penalties in liberalized markets[J]. IEEE Transactions on Power Systems, 2011, 26(4):2031-2039. [14] 王丽婕, 冬雷, 廖晓钟, 等. 基于小波分析的风电场短期发电功率预测[J]. 中国电机工程学报, 2009, 29(28): 30-33. term power prediction of a wind farm based on wavelet analysis[J]. Proceedings of the CSEE, 2009, 29(28): 30-33. [15] 姜玉山, 刘嘉婧, 卢毅. 基于回归分析的频域分解短期负荷预测方法[J]. 电力需求侧管理, 2011, 13(5): 12-16. Jiang Yushan, Liu Jiajing, Lu Yi. Short term load forecasting based on frequency analysis of regression [J]. Power Demand Side Management, 2011, 13(5): 12-16.
2013, Vol. 28 
