Ultra-short-term wind power prediction based on empirical mode decomposition and multi-branch neural network
MENG Xinyu1, WANG Ruihan1, ZHANG Xiping2, WANG Mingjie3, QIU Gang4, WANG Zhengxia5
1. School of Information Science and Engineering, Chongqing Jiaotong University, Chongqing 400074, China; 2. China Datang Corporation Renewable Energy Science and Technology Research Institute Company Limited, Beijing 100043, China; 3. Integrated Electronic Systems Laboratory Company Limited, Jinan Shandong 250104, China; 4. State Grid Xinjiang Electric Power Company, Urumqi Xinjiang 830002, China; 5. School of Computer Science and Cyberspace Security, Hainan University, Haikou Hainan 570228, China
Abstract：Wind power prediction is an important basis for the monitoring and information management of wind farms. Ultra-short-term wind power prediction is often used to balance load and optimize scheduling and requires high prediction accuracy. Due to the complex environment of wind farm and many uncertainties of wind speed, the wind power time series signals are often non-stationary and random. Recurrent Neural Network (RNN) is suitable for time series tasks, but the non-periodic and non-stationary time series signals will increase the difficulty of network learning. To overcome the interference of non-stationary signal in the prediction task and improve the prediction accuracy of wind power, an ultra-short-term wind power prediction method combining empirical model decomposition and multi-branch neural network was proposed. Firstly, the original wind power time series signal was decomposed by Empirical Mode Decomposition (EMD) to reconstruct the data tensor. Then, the convolution layer and Gated Recurrent Unit (GRU) layer were used to extract the local features and trend features respectively. Finally, the prediction results were obtained through feature fusion and full connection layer. Experimental results on the dataset of a wind farm in Inner Mongolia show that compared with AutoRegressive Integrated Moving Average (ARIMA) model, the proposed method improves the prediction accuracy by nearly 30%, which verifies the effectiveness of the proposed method.
[1] ZHANG J, CUI M, HODGE B M, et al. Ramp forecasting performance from improved short-term wind power forecasting over multiple spatial and temporal scales[J]. Energy,2017,122:528-541. [2] SHEN Y,WANG X,CHEN J. Wind power forecasting using multiobjective evolutionary algorithms for wavelet neural networkoptimized prediction intervals[J]. Applied Sciences,2018,8(2):No. 185. [3] LI L,ZHAO X,TSENG M L,et al. Short-term wind power forecasting based on support vector machine with improved dragonfly algorithm[J]. Journal of Cleaner Production,2020,242:No. 118447. [4] YUAN X,CHEN C,YUAN Y,et al. Short-term wind power prediction based on LSSVM-GSA model[J]. Energy Conversion and Management,2015,101:393-401. [5] KIM D,HUR J. Short-term probabilistic forecasting of wind energy resources using the enhanced ensemble method[J]. Energy,2018, 157:211-226. [6] LIU R,PENG M,XIAO X. Ultra-short-term wind power prediction based on multivariate phase space reconstruction and multivariate linear regression[J]. Energies,2018,11(10):No. 2763. [7] PIOTROWSKI P,BACZYŃSKI D,KOPYT M,et al. Analysis of forecasted meteorological data (NWP) for efficient spatial forecasting of wind power generation[J]. Electric Power Systems Research,2019,175:No. 105891. [8] CIULLA G, D' AMICO A,DI DIO V,et al. Modelling and analysis of real-world wind turbine power curves:assessing deviations from nominal curve by neural networks[J]. Renewable Energy,2019, 140:477-492. [9] PANDIT R K,INFIELD D. Comparative analysis of Gaussian process power curve models based on different stationary covariance functions for the purpose of improving model accuracy[J]. Renewable Energy,2019,140:190-202. [10] RAJAGOPALAN S,SANTOSO S. Wind power forecasting and error analysis using the autoregressive moving average modeling[C]//Proceedings of the 2009 IEEE Power and Energy Society General Meeting. Piscataway:IEEE,2009:1-6. [11] BILLINTON R,CHEN H,GHAJAR R. A sequential simulation technique for adequacy evaluation of generating systems including wind energy[J]. IEEE Transactions on Energy Conversion,1996, 11(4):728-734. [12] LI J,MAO J. Ultra-short-term wind power prediction using BP neural network[C]//Proceedings of the 9th IEEE Conference on Industrial Electronics and Applications. Piscataway:IEEE,2014:2001-2006. [13] GHADIMI N,AKBARIMAJD A,SHAYEGHI H,et al. Two stage forecast engine with feature selection technique and improved metaheuristic algorithm for electricity load forecasting[J]. Energy, 2018,161:130-142. [14] 薛阳, 王琳, 王舒, 等. 一种结合CNN和GRU网络的超短期风电预测模型[J]. 可再生能源,2019,37(3):456-462.(XUE Y, WANG L,WANG S,et al. An ultra-short-term wind power forecasting model combined with CNN and GRU networks[J]. Renewable Energy Resources,2019,37(3):456-462.) [15] 李东福, 董雷, 礼晓飞, 等. 基于多尺度小波分解和时间序列法的风电场风速预测[J]. 华北电力大学学报,2012,39(2):43-48.(LI D F,DONG L,LI X F,et al. A wind speed forecasting method for wind farms based on different scales wavelet decomposition and time series analysis[J]. Journal of North China Electric Power University,2012,39(2):43-48.) [16] 管胜利. 基于局域波分解及时间序列的风电场风速预测研究[J]. 华北电力技术,2009(1):10-13.(GUAN S L. Wind speed forecasting in wind farm based on local wave decomposition and time series[J]. North China Electric Power,2009(1):10-13.) [17] 栗然, 王粤, 肖进永. 基于经验模式分解的风电场短期风速预测模型[J]. 中国电力,2009,42(9):77-81.(LI R,WANG Y, XIAO J Y. Short-term wind speed forecasting for wind farms based on empirical mode decomposition model[J]. Electric Power, 2009,42(9):77-81.) [18] 王贺, 胡志坚, 陈珍, 等. 基于集合经验模态分解和小波神经网络的短期风功率组合预测[J]. 电工技术学报,2013,28(9):137-144.(WANG H,HU Z J,CHEN Z,et al. A hybrid model for wind power forecasting based on ensemble empirical mode decomposition and wavelet neural networks[J]. Transactions of China Electrotechnical Society,2013,28(9):137-144.) [19] BARRON A R. Universal approximation bounds for superpositions of a sigmoidal function[J]. IEEE Transactions on Information Theory,1993,39(3):930-945. [20] LAI G,CHANG W,YANG Y,et al. Modeling long-and shortterm temporal patterns with deep neural networks[C]//Proceedings of the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval. New York:ACM,2018:95-104. [21] HODGE B M,ZEILER A,BROOKS D,et al. Improved wind power forecasting with ARIMA models[J]. Computer Aided Chemical Engineering,2011,29:1789-1793. [22] CAI L,GU J,MA J,et al. Probabilistic wind power forecasting approach via instance-based transfer learning embedded gradient boosting decision trees[J]. Energies,2019,12(1):No. 159.
2021, Vol. 41 
