基于PSO-BP神经网络的风电功率备用容量估计模型

doi:10.16180/j.cnki.issn1007-7820.2021.12.007

摘要/Abstract

摘要：

针对风电波动性和随机性对电网调度带来影响,文中提出一种基于神经网络的风力发电功率备用容量估计模型。该模型通过粒子群算法优化BP神经网络中各连接层之间的权值来提高对未来风力发电的功率值的预测,并利用皮尔逊相关系数提取与预测误差正相关的影响因素,再使用多元线性回归方法将提取的影响因素关联起来进行风电功率的备用容量的计算。文中通过公开的比利时风电场实际运行数据进行算例分析,仿真结果表明有80%的预测误差在该模型的估计区间内,进一步验证了该模型的有效性。

关键词: 风力发电, 风力发电功率, 神经网络, 粒子群优化算法, 预测误差, 皮尔逊相关系数, 多元线性回归, 备用容量

Abstract:

In view of the effect of the volatility and randomness of wind power on the dispatching of the power grid, a neural network-based wind power reserve capacity estimation model is proposed. In this model, the weights of each link layer in BP neural network are optimized by particle swarm optimization algorithm to improve the prediction of wind power value in the future. The Pearson correlation coefficient is used to extract the influence factors which are positively correlated with the prediction error, and then the multiple linear regression method is used to associate the extracted influencing factors to calculate the reserve capacity of wind power. The simulation results show that 80% of the prediction error is within the estimation range of the model, further verifying the effectiveness of the model.

Key words: wind power generation, wind power, neural network, particle swarm optimization algorithm, prediction error, Pearson correlation coefficient, multiple linear regression, reserve capacity

中图分类号:

TP393

朱成名,魏云冰,蒋成成,朱健安. 基于PSO-BP神经网络的风电功率备用容量估计模型[J]. 电子科技, 2021, 34(12): 36-41.

ZHU Chengming,WEI Yunbing,JIANG Chengcheng,ZHU Jian'an. Estimation Model of Wind Power Reserve Capacity Based on PSO-BP Neural Network[J]. Electronic Science and Technology, 2021, 34(12): 36-41.

图/表 9

图1

图2

表1

皮尔逊相关系数取值范围及其相关强度"

$r$	相关强度
0.8~1.0	极强相关
0.6~0.8	强相关
0.4~0.6	中等程度相关
0.2~0.4	弱相关
0.0~0.2	极弱相关或无相关

表1

表2

图3

表3

图4

表4

图5

参考文献 22

[1]	于智超, 刘帅, 杜克文. 基于神经网络的风力发电并网控制研究[J]. 电子科技, 2018, 31(8):89-95.
	Yu Zhichao, Liu Shuai, Du Kewen. Study on control of wind power generation grid connection based on neural network[J]. Electronic Science and Technology, 2018, 31(8):89-95.
[2]	冯俊杰, 范学强, 张志飞, 等. 一种改进的风电功率短期组合预测[J]. 电气时代, 2018(11):29-31.
	Feng Junjie, Fan Xueqiang, Zhang Zhifei, et al. An improved short-term combined forecasting of wind power[J]. Electric Age, 2018(11):29-31.
[3]	谢辉煌, 郑荣进, 黄晓生. 趋势外推法在连江县电力负荷预测中的应用[J]. 电气时代, 2017(6):78-80.
	Xie Huihuang, Zheng Rongjin, Huang Xiaosheng. Application of trend extrapolation method in power load forecast in lianjiang county[J]. Electric Age, 2017(6):78-80.
[4]	王斌. 基于时间序列ARIMA模型的电力负荷短期预测分析[J]. 石河子科技, 2019(3):43-47.
	Wang Bin. Analysis of short-term power load forecast based on time series ARIMA model[J]. Shihezi Science and Technology, 2019(3):43-47.
[5]	刘有飞, 汤锦慧, 刘娟, 等. 基于线性回归分析的度夏电网特性研究[J]. 江西电力, 2018, 42(2):2-4.
	Liu Youfei, Tang Jinhui, Liu Juan, et al. Study on the characteristics of summer power grid based on linear regression analysis[J]. Jiangxi Electric Power, 2018, 42(2):2-4.
[6]	戴晖, 李峰, 雷文宝, 等. 改进灰色理论预测模型在分布式配电网中长期负荷预测中的应用[J]. 自动化应用, 2019(7):92-94.
	Dai Hui, Li Feng, Lei Wenbao, et al. Application of improved grey theory forecasting model in long-term load forecasting of distributed distribution network[J]. Automation Application, 2019(7):92-94.
[7]	刘瞻. 人工神经网络方法在化学试验中的应用[J]. 电子科技, 2017, 30(7):69-75.
	Liu Zhan. Artificial neural network method used in chemical experiments[J]. Electronic Science and Technology, 2017, 30(7):69-75.
[8]	吴东剑, 张龙港, 朱大君, 等. 基于随机森林的风力发电预测[J]. 电子世界, 2018(22):20-22.
	Wu Dongjian, Zhang Longgang, Zhu Dajun, et al. Wind power forecasting based on random forest[J]. Electronics World, 2018(22):20-22.
[9]	樊国旗, 蔺红, 程林, 等. 基于K均值模式划分改进模糊聚类与BP神经网络的风力发电预测研究[J]. 智慧电力, 2019, 47(5):38-42.
	Fan Guoqi, Lin Hong, Cheng Lin, et al. Wind power prediction based on K-means pattern classification improved fuzzy clustering and BP neural network[J]. Smart Power, 2019, 47(5):38-42.
[10]	师洪涛, 杨静玲, 丁茂生, 等. 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.
	Shi Hongtao, Yang Jingling, Ding Maosheng, et al. A short-term wind power prediction method based on wavelet decomposition and BP neural network[J]. Automation of Electric Power Systems, 2011, 35(16):44-48.
[11]	王丹平, 陈之栩, 涂孟夫, 等. 考虑大规模风电接入的备用容量计算[J]. 电力系统自动化, 2012, 36(21):24-28.
	Wang Danping, Chen Zhixu, Tu Mengfu, et al. Reserve capacity calculation considering large-scale wind power integration[J]. Automation of Electric Power Systems, 2012, 36(21):24-28.
[12]	Khosravi A, Nahavandi S, Creighton D, et al. Uncertainty quantification for wind farm power generation [C].Brisbane:International Joint Conference on Neural Networks, 2012.
[13]	Tewari S, Geyer C J, Mohan N. 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. doi: 10.1109/TPWRS.2011.2141159
[14]	王铮, 王伟胜, 刘纯, 等. 基于风过程方法的风电功率预测结果不确定性估计[J]. 电网技术, 2013, 37(1):242-247.
	Wang Zheng, Wang Weisheng, Liu Chun, et al. Uncertainty estimation of wind power prediction result based on wind process method[J]. Power System Technology, 2013, 37(1):242-247.
[15]	刘晓楠, 周介圭, 贾宏杰, 等. 基于非参数核密度估计与数值天气预报的风速预测修正方法[J]. 电力自动化设备, 2017, 37(10):15-20.
	Liu Xiaonan, Zhou Jiegui, Jia Hongjie, et al. Correction method of wind speed prediction based on non-parametric kernel density estimation and numerical weather prediction[J]. Electric Power Automation Equipment, 2017, 37(10):15-20.
[16]	韩爽, 刘永前, 杨勇平, 等. 风电场超短期功率预测及不确定性分析[J]. 太阳能学报, 2011, 32(8):1251-1256.
	Han Shuang, Liu Yongqian, Yang Yongping, et al. Ultra-shortterm wind power prediction and uncertainty assessment[J]. Journal of Solar Energy, 2011, 32(8):1251-1256.
[17]	Jones L E. Strategies and decision support system for integrating variable energy resources in control centers for reliable grid operations[M]. Columbia:AREVA Federal Services LLC, 2012.
[18]	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, 2011, 31(25):10-16.
	Zhou Songlin, Mao Meiqin, Su Jianhui. Short-term forecasting of wind power and non-parametric confidence interval estimation[J]. Proceedings of the CSEE, 2011, 31(25):10-16.
[19]	王乐, 余志伟, 文福拴. 基于机会约束规划的最优旋转备用容量确定[J]. 电网技术, 2006, 30(20):14-19.
	Wang Le, Yu Zhiwei, Wen Fushuan. A chance-constrained programming approach to determine requirement of optimal spinning reserve capacity[J]. Power System Technology, 2006, 30(20):14-19.
[20]	Sexton R S, Dorsey R E. Reliable classification using neural networks: a genetic algorithm and backpropagation comparison[J]. Decision Support System, 2000, 30(1):11-22. doi: 10.1016/S0167-9236(00)00086-5
[21]	周英, 尹邦德, 任铃, 等. 基于BP神经网络的电网短期负荷预测模型研究[J]. 电测与仪表, 2011, 48(2):68-71.
	Zhou Ying, Yin Bangde, Ren Ling, et al. Study of electricity short term load forecast based on BP neural network[J]. Electrical Measurement & Instrumentation, 2011, 48(2):68-71.
[22]	Dindorf R, Wos P. Contour error of the 3-DoF hydraulic translational parallel manipulator[J]. Advanced Materials Research, 2014, 87(4):57-62.

影响因素	相关系数
实际发电功率的波动系数	0.749 8
预测值发电功率波动系数	0.671 0
预测平均功率	0.236 8

参数	估计值	估计区间
β₀	23.758 3	[11.399 2,36.117 5]
β₁	0.013 4	[-0.002 9,0.029 7]
β₂	0.000 5	[-0.225 3,0.226 2]
β₃	0.131 1	[-0.065 2,0.327 4]

预测模型	MAPE	nRMSE
BP	10.26	3.78
PSO-BP	8.84	2.94