基于IDE-WNN的短期风电功率预测及概率评估

系统仿真学报 ›› 2016, Vol. 28 ›› Issue (2): 476-482.

基于IDE-WNN的短期风电功率预测及概率评估

刘增良¹, 周松林¹, 周同旭²

1.铜陵学院电气工程学院,安徽铜陵 244000;
2.皖西学院机械与电子工程学院,安徽六安 237012

收稿日期:2014-10-20 修回日期:2014-12-15 出版日期:2016-02-08 发布日期:2020-08-17
作者简介:刘增良(1959-),男,河北清苑,教授,研究方向为电力系统自动化;周松林(1975-),男,安徽东至,博士,副教授,研究方向为分布式发电及微网。
基金资助:
安徽省高校自然科学基金重点项目(KJ2014 A258); 铜陵学院人才科研启动基金(2014tlxyrc01)

Short -term Prediction of Wind Power Based on IDE-WNN and Probabilistic Evaluation

Liu Zengliang¹, Zhou Songlin¹, Zhou Tongxu²

1. Department of Electrical Engineering, Tongling University, Tongling 244000, China;
2. Department of Mechanical and electronic engineering, West Anhui University, Luan 237012, China

Received:2014-10-20 Revised:2014-12-15 Online:2016-02-08 Published:2020-08-17

摘要/Abstract

摘要： 风电功率预测包括确定性预测和不确定性预测。前者关注预测精度,后者关注预测结果包含的风险。将改进差分进化算法用于小波神经网络的参数优化,在不同方向上广泛地搜索最优解,提高了预测精度。通过计算风电功率预测值关于预测误差和功率波动的条件联合概率及对应的置信区间,对预测结果所包含的风险进行了较为全面地评估,通过仿真实验验证了所提方法的有效性。

关键词: 风电功率预测, 改进差分进化算法, 小波神经网络, 联合条件概率

Abstract: Wind power prediction usually concludes determined and uncertainly prediction. The former puts important on prediction accuracy and the later focus on the the risk of prediction results. For increase the prediction accuracy, an improved differential evolution algorithm was applied to widely search the optimal solution of wavelet neural network in different directions. By calculating joint conditional probability of wind power predictions about prediction error and power fluctuation, the risk of prediction results could be more fully assessed. The effectiveness of the proposed method was verified by simulation experiments.

Key words: wind power prediction, improved differential evolution algorithm, wavelet neural network, joint conditional probability

中图分类号:

TP391.9

刘增良, 周松林, 周同旭. 基于IDE-WNN的短期风电功率预测及概率评估[J]. 系统仿真学报, 2016, 28(2): 476-482.

Liu Zengliang, Zhou Songlin, Zhou Tongxu. Short -term Prediction of Wind Power Based on IDE-WNN and Probabilistic Evaluation[J]. Journal of System Simulation, 2016, 28(2): 476-482.

参考文献 15

[1]	Claus Krog Ekman.On the synergy between large electric vehicle fleet and high wind penetration-Analysis of the Danishcase[J]. Renewable Energy (S0960-1481), 2011, 36(2): 546-553.
[2]	Kusiak Andrew, LiWenyan. Short-term prediction of wind power with a clustering approach[J]. Renewable Energy (S0960-1481), 2010, 35(10): 2362-2369.
[3]	陈宁, 沙倩, 汤奕. 基于交叉熵理论的风电功率组合预测方法[J]. 中国电机工程学报, 2012, 32(4): 29-34.
[4]	潘迪夫, 刘辉, 李燕飞. 风电场风速短期多步预测改进算法[J]. 中国电机工程学报, 2008, 28(26): 87-91.
[5]	杜颖, 卢继平, 李青. 基于最小二乘支持向量机的风电场短期风速预测[J]. 电网技术, 2008, 32(15): 62-66.
[6]	茆美琴, 周松林, 苏建徽. 基于脊波神经网络的短期风电功率预测[J]. 电力系统自动化, 2011, 35(7): 1-5.
[7]	Fernando Castellanos, Nickel James.Average Hourly Wind Speed Forecasting with ANFIS[C]// 11th Americas Conference on Wind Engineering, San Juan, Puerto Rico, American Association for Wind Engineering, 2009: 22-26.
[8]	A Sfetsos.A Comparison of Various Forecasting Techniques Applied to Mean Hourly Wind Speed Time Series[J]. Renewable Energy (S0960-1481), 2000, 21(1): 23-35.
[9]	杨琦, 张建华, 李卫国. 基于小波–神经网络的风速及风力发电量预测[J]. 电网技术, 2009, 33(17): 44-48.
[10]	师洪涛, 杨静玲, 丁茂生. 基于小波-BP神经网络的短期风电功率预测方法[J]. 电力系统自动化, 2011, 35(16): 44-48.
[11]	阎洁, 刘永前, 韩爽. 分位数回归在风电功率预测不确定性分析中的应用[J]. 太阳能学报, 2013, 34(12): 2101-2107.
[12]	Lange M.On the uncertainty of wind power predictions- analysis of the forecast accuracy and statistical distribution of errors[J]. Journal of Solar Energy Engineering (S0199-6231), 2005, 127(2):177-184.
[13]	万东. 差分进化算法研究及其应用[J]. 科学技术与工程, 2009, 9(22): 6673-6676.
[14]	王松岩, 李碧君, 于继来. 风速与风电功率预测误差概率分布的时变特性分析[J]. 电网技术, 2013, 37(4): 967-973.
[15]	周松林, 茆美琴, 苏建徽. 风电功率短期预测及非参数区间估计[J]. 中国电机工程学报, 2010, 31(25): 10-16.