自编码器与PSOA-CNN结合的短期负荷预测模型
|
摘要
提出了一种自编码器与PSO算法优化卷积神经网络结合的电力系统短期负荷预测模型。首先利用自编码器对相关变量数据进行处理,降低所需数据的噪声变量,提高预测效率;然后利用粒子群算法对卷积神经网络的权值和阈值进行优化,可有效提高预测模型的预测精度和预测速度。通过对实际电网的负荷数据进行仿真,验证了模型具有较高的预测精度。
A short-term load forecasting model which combines the autoencoder and convolutional neural network optimized by particle swarm optimization is proposed. Firstly, the autoencoder is used to process the relevant variable data,reduce the noise variable of the required data, and improve the prediction efficiency. Then particle swarm optimization is used to optimize the weight and threshold of the convolutional neural network., which can effectively improve the prediction accuracy and prediction speed of the prediction model. By simulating the load data of the actual power grid, it is verified that the proposed model has higher prediction accuracy.
A short-term load forecasting model which combines the autoencoder and convolutional neural network optimized by particle swarm optimization is proposed. Firstly, the autoencoder is used to process the relevant variable data,reduce the noise variable of the required data, and improve the prediction efficiency. Then particle swarm optimization is used to optimize the weight and threshold of the convolutional neural network., which can effectively improve the prediction accuracy and prediction speed of the prediction model. By simulating the load data of the actual power grid, it is verified that the proposed model has higher prediction accuracy.
引文
[1] 王惠中,周佳,刘轲.电力系统短期负荷预测方法研究综述[J].电气自动化,2015,37(1):1-3.WANG Huizhong,ZHOU Jia,LIU Ke.Summary of research on the short-term load forecasting method of the electric power system[J].Electrical Automation,2015,37(1):1-3.
[2] 朱振伟.气象因素对电网负荷特性影响的研究[D].杭州:浙江大学,2008.ZHU Zhenwei.Study on the influence of weather factors on power grid load characteristics[D].Hangzhou:Zhejiang University,2008.
[3] 黄芸.基于神经网络的短期电力负荷预测模型研究[D].天津:天津大学,2011.HUANG Yun.Research on short-term power load forecasting model based on neural network[D].Tianjin:Tianjin University,2011.
[4] 张前进.基于支持向量机回归的电力负荷预测研究[J].航空计算技术,2006,36(4):105-107.ZHANG Qianjin.Research on electric-power load forecasting based on support vector machine regression technique[J].Aeronautical Computing Technique,2006,36(4):105-107.
[5] 杨帆,吴耀武,熊信银,等.用自适应模糊推理系统预测电力短期负荷[J].高电压技术,2007,33(4):129-133.YANG Fan,WU Yaowu,XIONG Xinyin,et al.Short-term load forecasting in power system based on adaptive network-based fuzzy inference system[J].High Voltage Engineering,2007,33(4):129-133.
[6] 邰能灵,侯志俭.小波模糊神经网络在电力系统短期负荷预测中的应用[J].中国电机工程学报,2004,24(1):24-29.TAI Nengling,HOU Zhijian.New short-term load forecasting principle with the wavelet transform fuzzy neural network for the power systems[J].Proceedings of the CSEE,2004,24(1):24-29.
[7] 张军阳,王慧丽,郭阳,等.深度学习相关研究综述[J].计算机应用研究,2018,35(7):1921-1928,1936.ZHANG Junyang,WANG Huili,GUO Yang,et al.Review of deep learning[J].Application Research of Computers,2018,35(7):1921-1928,1936.
[8] HOSEIN S,HOSEIN P.Load forecasting using deep neural networks[C]//Power & Energy Society Innovative Smart Grid Technologies Conference.Washington:IEEE,2017.
[9] MOCANU D C,BOU AMMAR H,LOWET D,et al.Factored four way conditional restricted Boltzmann machines for activity recognition[J].Pattern Recognition Letters,2015,66(C):100-108.
[10] 陈先昌.基于卷积神经网络的深度学习算法与应用研究[D].杭州:浙江工商大学,2014.CHEN Xianchang.Research on algorithm and application of deep learning based on convolutional neural network[D].Hangzhou:Zhejiang Gongshang University,2014.
[11] 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.CHENG Yuye.Short-term electricity demand forecasting based on artificial neural network[D].Hangzhou:Zhejiang University,2017.
[12] 牛东晓,马天男,王海潮,等.基于KPCA和NSGAII优化CNN参数的电动汽车充电站短期负荷预测[J].电力建设,2017,38(3):85-92.NIU Dongxiao,MA Tiannan,WANG Haichao,et al.Short-term load forecasting of electric vehicle charging station based on KPCA and CNN parameters optimized by NSGAII[J].Electric Power Construction,2017,38(3):85-92.
[13] 张贵勇.改进的卷积神经网络在金融预测中的应用研究[D].郑州:郑州大学,2016.ZHANG Guiyong.Research on the application of improved convolutional neural network in financial forecasting[D].Zhengzhou:Zhengzhou University,2016.
[14] 李思琴,林磊,孙承杰.基于卷积神经网络的搜索广告点击率预测[J].智能计算机与应用,2015,31(5):22-25.LI Siqin,LIN Lei,SUN Chengjie.Search advertisement click through rate prediction based on convolutional neural network [J].Intelligent Computer and Applications,2015,31(5):22-25.
[15] 何明慧,徐怡,王冉,等.改进的粒子群算法优化神经网络及应用[J].计算机工程与应用,2018,54(19):107-113.HE Minghui,XU Yi,WANG Ran,et al.Combination dynamic inertia weight particle swarm optimization algorithm to optimize neural network and application[J].Computer Engineering and Applications,2018,54(19):107-113.
[16] 吴杰康,陈明华,陈国通.基于PSO的模糊神经网络短期负荷预测[J].电力系统及其自动化学报,2007,19(1):63-67.WU Jiekang,CHEN Minghua,CHEN Guotong.Fuzzy neural network model based on particle swarm optimization for short-term load forecasting[J].Proceedings of the CSU-EPSA,2007,19(1):63-67.
[17] 王倩,张智晟,王帅,等.基于PSO-RNN的光伏发电功率预测研究[J].青岛大学学报(工程技术版),2014,29(4):40-43.WANG Qian,ZHANG Zhisheng,WANG Shuai,et al.Study of power forecasting of photovoltaic based on PSO-RNN [J].Journal of Qingdao University(Engineering & Technology Edition),2014,29(4):40-43.
[18] 金士琛,薛会,林霞,等.基于FDNN的电力系统短期负荷预测模型研究[J].青岛大学学报(工程技术版),2017,32(4):12-16.JIN Shichen,XUE Hui,LIN Xia,et al.Study of short-term load forecasting of power system based on fuzzy deep neural network[J].Journal of Qingdao University(Engineering & Technology Edition),2017,32(4):12-16.
[19] 邓俊锋,张晓龙.基于自动编码器组合的深度学习优化方法[J].计算机应用,2016,36(3):697-702.DENG Junfeng,ZHANG Xiaolong.Deep learning algorithm optimization based on combination of auto-encoders[J].Journal of Computer Applications,2016,36(3):697-702.
[20] 王雅思,姚鸿勋,孙晓帅,等.深度学习中的自编码器的表达能力研究[J].计算机科学,2015,42(9):56-60WANG Yasi,YAO Hongxun,SUN Xiaoshuai,et al.Representation ability research of auto-encoders in deep learning[J].Computer Science,2015,42(9):56-60.
[2] 朱振伟.气象因素对电网负荷特性影响的研究[D].杭州:浙江大学,2008.ZHU Zhenwei.Study on the influence of weather factors on power grid load characteristics[D].Hangzhou:Zhejiang University,2008.
[3] 黄芸.基于神经网络的短期电力负荷预测模型研究[D].天津:天津大学,2011.HUANG Yun.Research on short-term power load forecasting model based on neural network[D].Tianjin:Tianjin University,2011.
[4] 张前进.基于支持向量机回归的电力负荷预测研究[J].航空计算技术,2006,36(4):105-107.ZHANG Qianjin.Research on electric-power load forecasting based on support vector machine regression technique[J].Aeronautical Computing Technique,2006,36(4):105-107.
[5] 杨帆,吴耀武,熊信银,等.用自适应模糊推理系统预测电力短期负荷[J].高电压技术,2007,33(4):129-133.YANG Fan,WU Yaowu,XIONG Xinyin,et al.Short-term load forecasting in power system based on adaptive network-based fuzzy inference system[J].High Voltage Engineering,2007,33(4):129-133.
[6] 邰能灵,侯志俭.小波模糊神经网络在电力系统短期负荷预测中的应用[J].中国电机工程学报,2004,24(1):24-29.TAI Nengling,HOU Zhijian.New short-term load forecasting principle with the wavelet transform fuzzy neural network for the power systems[J].Proceedings of the CSEE,2004,24(1):24-29.
[7] 张军阳,王慧丽,郭阳,等.深度学习相关研究综述[J].计算机应用研究,2018,35(7):1921-1928,1936.ZHANG Junyang,WANG Huili,GUO Yang,et al.Review of deep learning[J].Application Research of Computers,2018,35(7):1921-1928,1936.
[8] HOSEIN S,HOSEIN P.Load forecasting using deep neural networks[C]//Power & Energy Society Innovative Smart Grid Technologies Conference.Washington:IEEE,2017.
[9] MOCANU D C,BOU AMMAR H,LOWET D,et al.Factored four way conditional restricted Boltzmann machines for activity recognition[J].Pattern Recognition Letters,2015,66(C):100-108.
[10] 陈先昌.基于卷积神经网络的深度学习算法与应用研究[D].杭州:浙江工商大学,2014.CHEN Xianchang.Research on algorithm and application of deep learning based on convolutional neural network[D].Hangzhou:Zhejiang Gongshang University,2014.
[11] 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.CHENG Yuye.Short-term electricity demand forecasting based on artificial neural network[D].Hangzhou:Zhejiang University,2017.
[12] 牛东晓,马天男,王海潮,等.基于KPCA和NSGAII优化CNN参数的电动汽车充电站短期负荷预测[J].电力建设,2017,38(3):85-92.NIU Dongxiao,MA Tiannan,WANG Haichao,et al.Short-term load forecasting of electric vehicle charging station based on KPCA and CNN parameters optimized by NSGAII[J].Electric Power Construction,2017,38(3):85-92.
[13] 张贵勇.改进的卷积神经网络在金融预测中的应用研究[D].郑州:郑州大学,2016.ZHANG Guiyong.Research on the application of improved convolutional neural network in financial forecasting[D].Zhengzhou:Zhengzhou University,2016.
[14] 李思琴,林磊,孙承杰.基于卷积神经网络的搜索广告点击率预测[J].智能计算机与应用,2015,31(5):22-25.LI Siqin,LIN Lei,SUN Chengjie.Search advertisement click through rate prediction based on convolutional neural network [J].Intelligent Computer and Applications,2015,31(5):22-25.
[15] 何明慧,徐怡,王冉,等.改进的粒子群算法优化神经网络及应用[J].计算机工程与应用,2018,54(19):107-113.HE Minghui,XU Yi,WANG Ran,et al.Combination dynamic inertia weight particle swarm optimization algorithm to optimize neural network and application[J].Computer Engineering and Applications,2018,54(19):107-113.
[16] 吴杰康,陈明华,陈国通.基于PSO的模糊神经网络短期负荷预测[J].电力系统及其自动化学报,2007,19(1):63-67.WU Jiekang,CHEN Minghua,CHEN Guotong.Fuzzy neural network model based on particle swarm optimization for short-term load forecasting[J].Proceedings of the CSU-EPSA,2007,19(1):63-67.
[17] 王倩,张智晟,王帅,等.基于PSO-RNN的光伏发电功率预测研究[J].青岛大学学报(工程技术版),2014,29(4):40-43.WANG Qian,ZHANG Zhisheng,WANG Shuai,et al.Study of power forecasting of photovoltaic based on PSO-RNN [J].Journal of Qingdao University(Engineering & Technology Edition),2014,29(4):40-43.
[18] 金士琛,薛会,林霞,等.基于FDNN的电力系统短期负荷预测模型研究[J].青岛大学学报(工程技术版),2017,32(4):12-16.JIN Shichen,XUE Hui,LIN Xia,et al.Study of short-term load forecasting of power system based on fuzzy deep neural network[J].Journal of Qingdao University(Engineering & Technology Edition),2017,32(4):12-16.
[19] 邓俊锋,张晓龙.基于自动编码器组合的深度学习优化方法[J].计算机应用,2016,36(3):697-702.DENG Junfeng,ZHANG Xiaolong.Deep learning algorithm optimization based on combination of auto-encoders[J].Journal of Computer Applications,2016,36(3):697-702.
[20] 王雅思,姚鸿勋,孙晓帅,等.深度学习中的自编码器的表达能力研究[J].计算机科学,2015,42(9):56-60WANG Yasi,YAO Hongxun,SUN Xiaoshuai,et al.Representation ability research of auto-encoders in deep learning[J].Computer Science,2015,42(9):56-60.