一种滑动加权最小二乘风电功率预测模型

系统仿真学报 ›› 2016, Vol. 28 ›› Issue (5): 1031-1037.

一种滑动加权最小二乘风电功率预测模型

葛延峰¹, 梁鹏², 高立群³, 翟军昌³

1.国网辽宁省电力有限公司调度控制中心,辽宁沈阳 110004;
2.国网辽宁省电力有限公司锦州供电公司,辽宁锦州 121000;
3.东北大学信息科学与工程学院,辽宁沈阳 110819

收稿日期:2014-12-26 修回日期:2015-03-01 发布日期:2020-07-03
作者简介:葛延峰(1975-),男,沈阳,博士,高工,研究方向为电网的调度与管理;梁鹏(1981-),男,济南,高工,研究方向为电网的调度与管理;高立群(1949-),男,沈阳,教授,博导,研究方向为智能优化与系统辨识。
基金资助:
国家自然科学基金(60674021)

Sliding Weighted Least Square Model for Short-term Wind Power Prediction

Ge Yanfeng¹, Liang Peng², Gao Liqun³, Zhai Junchang³

1. State Grid Liaoning Electric Power Supply Co., Ltd, Shenyang 110004, China;
2. Jinzhou Power Supply Company, Liaoning Power Grid Co. SGCC, Jinzhou 121000, China;
3. School of Information Science & Engineering, Northeastern University, Shenyang 110819, China

Received:2014-12-26 Revised:2015-03-01 Published:2020-07-03

摘要/Abstract

摘要： 针对传统预测方法对风电场输出功率短期预测过度依赖大量的观测数据,不能有效排除早期数据的影响、缺乏自适应性等不足,采用滑动窗口加权递推最小二乘法建立风场输出电功率预测模型。在新的预测模型中,通过加权及“滑动窗口”的方法,使模型侧重于当前数据对预测结果的影响,对外界环境数据的变化具有自适应性,排除了历史数据对预测结果的干扰。针对预测模型的定阶问题,利用和声搜索算法对预测模型的阶数和参数进行优化,可以提高模型的预测精度和适用性。利用辽宁某风电场的真实历史数据建模仿真验证方法的有效性。

关键词: 风电功率预测, 最小二乘法, 滑动窗口, 和声搜索

Abstract: A new approach for wind power forecasting was proposed based on sliding window weighted recursive least squares for the defect of wind power short-term prediction in the traditional prediction methods. The historical data was weighted and the perturbation caused by the historical data was ruled out in this method, which focused on the current data on the result of prediction. This made the model have the adaptability to the change of the environment data. The harmony search algorithm was used to optimize the orders and the parameters of the predict model, which could improve the precision and accuracy of the prediction result. The simulation was carried out for the real historical data of the wind farm in Liaoning Province, China to demonstrate the effectiveness of the proposed method.

Key words: wind power prediction, least square method, sliding window, harmony search

中图分类号:

TP301.6

葛延峰, 梁鹏, 高立群, 翟军昌. 一种滑动加权最小二乘风电功率预测模型[J]. 系统仿真学报, 2016, 28(5): 1031-1037.

Ge Yanfeng, Liang Peng, Gao Liqun, Zhai Junchang. Sliding Weighted Least Square Model for Short-term Wind Power Prediction[J]. Journal of System Simulation, 2016, 28(5): 1031-1037.

参考文献

[1] Ghadi M J, Gilani S H, Afrakhte H, et al.A Novel Heuristic Method for Wind farm power prediction: A case study[J]. International Journal of Electrical Power & Energy Systems (S0142-0615), 2014, 63(2): 962-970.
[2] Gangui Y, Yu L, Gang M, et al.The Ultra-short Term Prediction of Wind Power Based on Chaotic Time Series[J]. Energy Procedia (S1876-6102), 2012, 17(1): 1490-1496.
[3] Tascikaraoglu A, Uzunoglu M.A Review of Combined Approaches for Prediction of Short-term Wind Speed and Power[J]. Renewable and Sustainable Energy Reviews (S1364-0321), 2014, 34(6): 243-254.
[4] Costa A, Crespo A, Navarro J, et al.A Review on the Young History of the Wind Power Short-term Prediction[J]. Renewable and Sustainable Energy Reviews (S1364-0321), 2008, 12(2): 1725-1744.
[5] Hansen A D, Altin M, Margaris I D, et al.Analysis of the Short-term Overproduction Capability of Variable Speed Wind Turbines[J]. Renewable Energy (S0960-1481), 2014, 68(7): 326-336.
[6] Gualtieri G, Secci S.Extrapolating Wind Speed Time Series vs. Weibull Distribution to Assess Wind Resource to the Yurbine Hub Height: A Case Study on Coastal Location in Southern Italy[J]. Renewable Energy (S0960-1481), 2014, 62(3): 164-176.
[7] Guo Z, Chi D, Wu J, et al.A New Wind Speed Forecasting Strategy Based on the Chaotic Time Series Modelling Technique and the Apriori Algorithm[J]. Energy Conversion and Management (S0196-8904), 2014, 84: 140-151.
[8] Louka P, Galanis G, Siebert N, et al.Improvements in Wind Speed Forecasts for Wind Power Prediction Purposes Using Kalman Filtering[J]. Journal of Wind Engineering and Industrial Aerodynamics (S0167-6105), 2008, 96(12): 2348-2362.
[9] Chen K, Yu J.Short-term Wind Speed Prediction Using an Unscented Kalman Filter Based State-space Support Vector Regression Approach[J]. Applied Energy (S0306-2619), 2014, 113(6): 690-705.
[10] Taylor J W, McSharry P E, Buizza R. Wind Power Density Forecasting Using Ensemble Predictions and Time Series Models[J]. Energy Conversion, IEEE Transactions on (S0885-8969), 2009, 24(3): 775-782.
[11] Quan H, Srinivasan D, Khosravi A.Short-term Load and Wind Power Forecasting Using Neural Network-Based Prediction Intervals[J]. Neural Networks and Learning Systems, IEEE Transactions on (S2162-237X), 2014, 25(2): 303-315.
[12] Liu D, Niu D, Wang H, et al.Short-term Wind Speed Forecasting Using Wavelet Transform and Support Vector Machines Optimized by Genetic Algorithm[J]. Renewable Energy (S0960-1481), 2014, 62(3):592-597.
[13] Ren C, An N, Wang J, et al.Optimal Parameters Selection for BP Neural Network Based on Particle Swarm Optimization: A Case Study of Wind Speed Forecasting[J]. Knowledge-Based Systems (S0950-7051), 2014, 56(3): 226-239.
[14] Geem Z W, Kim J H, Loganathan G V.A New Heuristic Optimization Algorithm: Harmony Search[J]. Simulation (S0037-5497), 2001, 76(2): 60-68.