基于进化神经网络的短期电力负荷预测研究
|
摘要
短期负荷预测对于工业、商业、住宅智能电网应用是必不可少的。在分析电力系统负荷预测特点和研究现状的基础上,研究了一种进化神经网络用于电力负荷短期预测。进化神经网络采用遗传算法来优化神经网络的权重,能有效避开BP网络算法中的局部极值问题。采用MATLAB仿真软件构建基于进化神经网络的电力系统负荷预测模型,并利用实际电力负荷数据进行网络训练和模型仿真。为了评估进化神经网络的性能,采用小波神经网络进行比较,通过观察预测结果进行评估。试验结果表明,进化神经网络精度性能优于小波神经网络,适用于电力系统负荷预测。
Short term load forecasting is indispensable for industrial,commercial and residential smart grid(SG)applications.In this paper,based on the analysis of load forecasting characteristics and research status of the power system,an Evolving Neural Network(ENN)has been developed for short term power load prediction.The ENN uses a genetic algorithm to optimize the weight of neural networks,and can effectively avoid local extremum problem in BP neural network algorithm.The power system load forecasting model based on ENN is constructed by using MATLAB simulation software.The actual power load data is used for network training and model simulation.In order to evaluate the performance of ENN,Wavelet Neural Network(WNN)is used for comparison.The evaluation is conducted by observing the prediction results.The experimental results show that the proposed ENN has better accuracy performance than WNN and is suitable for load forecasting of power system.
Short term load forecasting is indispensable for industrial,commercial and residential smart grid(SG)applications.In this paper,based on the analysis of load forecasting characteristics and research status of the power system,an Evolving Neural Network(ENN)has been developed for short term power load prediction.The ENN uses a genetic algorithm to optimize the weight of neural networks,and can effectively avoid local extremum problem in BP neural network algorithm.The power system load forecasting model based on ENN is constructed by using MATLAB simulation software.The actual power load data is used for network training and model simulation.In order to evaluate the performance of ENN,Wavelet Neural Network(WNN)is used for comparison.The evaluation is conducted by observing the prediction results.The experimental results show that the proposed ENN has better accuracy performance than WNN and is suitable for load forecasting of power system.
引文
[1]隋惠惠.基于BP神经网络的短期电力负荷预测的研究[D].哈尔滨:哈尔滨工业大学,2015.
[2]程宇也.基于人工神经网络的短期电力负荷预测研究[D].杭州:浙江大学,2017.
[3]罗育辉,蔡延光,戚远航,等.基于最大偏差相似性准则的BP神经网络短期电力负荷预测算法[J/OL].计算机应用研究,2019,36(11).[2018-08-10].http://www.arocmag.com/article/02-2019-11-018.html.
[4]李若晨,朱帆,朱永利,等.结合受限玻尔兹曼机的递归神经网络电力系统短期负荷预测[J].电力系统保护与控制,2018,46(17):83-88.
[5]王勇,黄国兴,彭道刚.带反馈的多元线性回归法在电力负荷预测中的应用[J].计算机应用与软件,2018,25(1):82-84.
[6]刘琪琛,雷景生,郝珈玮,等.基于Spark平台和并行随机森林回归算法的短期电力负荷预测[J].电力建设,2017,38(10):84-92.
[7]梁智,孙国强,卫志农,等.基于变量选择与高斯过程回归的短期负荷预测[J].电力建设,2017,38(2):122-128.
[8]张智晟,于道林.考虑需求响应综合影响因素的RBF-NN短期负荷预测模型[J].中国电机工程学报,2018,38(6):1631-1638.
[9]万强,王清亮,王睿豪,等.基于支持向量机的某地区电网短期电力负荷预测[J].电网与清洁能源,2016,32(12):14-20.
[10]SONG K B,Baek Y S,HONG D H,et al.Short-term load forecasting for the holidays using fuzzy linear regression method[J].IEEE Trans on Power Systems,2005,20(1):96-101.
[11]WANG Y,GU D,XU J,LI J,et al.Back Propagation Neural Network for Short-term Electricity Load Forecasting with Weather Features[C].Proc.Int.Conf.on Computational Intelligence and Natural Computing:58-61.
[12]陈刚,周杰,张雪君,等.基于BP与RBF级联神经网络的日负荷预测[J].电网技术,2009,33(12):101-105.
[13]张平,潘学萍,薛文超.基于小波分解模糊灰色聚类和BP神经网络的短期负荷预测[J].电力自动化设备,2012,32(11):121-125.
[14]白杨,赵冠,窦金延,等.基于并行膜计算的短期电力负荷组合预测[J].电力系统保护与控制,2017,45(7):35-42.
[15]HE Y,XU Q,WAN J,et al.Short-term power load probability density forecasting based on quantile regression neural network and triangle kernel function[J].Energy,2016,114:498-512.
[2]程宇也.基于人工神经网络的短期电力负荷预测研究[D].杭州:浙江大学,2017.
[3]罗育辉,蔡延光,戚远航,等.基于最大偏差相似性准则的BP神经网络短期电力负荷预测算法[J/OL].计算机应用研究,2019,36(11).[2018-08-10].http://www.arocmag.com/article/02-2019-11-018.html.
[4]李若晨,朱帆,朱永利,等.结合受限玻尔兹曼机的递归神经网络电力系统短期负荷预测[J].电力系统保护与控制,2018,46(17):83-88.
[5]王勇,黄国兴,彭道刚.带反馈的多元线性回归法在电力负荷预测中的应用[J].计算机应用与软件,2018,25(1):82-84.
[6]刘琪琛,雷景生,郝珈玮,等.基于Spark平台和并行随机森林回归算法的短期电力负荷预测[J].电力建设,2017,38(10):84-92.
[7]梁智,孙国强,卫志农,等.基于变量选择与高斯过程回归的短期负荷预测[J].电力建设,2017,38(2):122-128.
[8]张智晟,于道林.考虑需求响应综合影响因素的RBF-NN短期负荷预测模型[J].中国电机工程学报,2018,38(6):1631-1638.
[9]万强,王清亮,王睿豪,等.基于支持向量机的某地区电网短期电力负荷预测[J].电网与清洁能源,2016,32(12):14-20.
[10]SONG K B,Baek Y S,HONG D H,et al.Short-term load forecasting for the holidays using fuzzy linear regression method[J].IEEE Trans on Power Systems,2005,20(1):96-101.
[11]WANG Y,GU D,XU J,LI J,et al.Back Propagation Neural Network for Short-term Electricity Load Forecasting with Weather Features[C].Proc.Int.Conf.on Computational Intelligence and Natural Computing:58-61.
[12]陈刚,周杰,张雪君,等.基于BP与RBF级联神经网络的日负荷预测[J].电网技术,2009,33(12):101-105.
[13]张平,潘学萍,薛文超.基于小波分解模糊灰色聚类和BP神经网络的短期负荷预测[J].电力自动化设备,2012,32(11):121-125.
[14]白杨,赵冠,窦金延,等.基于并行膜计算的短期电力负荷组合预测[J].电力系统保护与控制,2017,45(7):35-42.
[15]HE Y,XU Q,WAN J,et al.Short-term power load probability density forecasting based on quantile regression neural network and triangle kernel function[J].Energy,2016,114:498-512.