基于粗糙集-混沌时间序列Elman神经网络的短期用电量预测
|
摘要
Elman神经网络由于其具有无限逼近和适应时变特性的能力被广泛用于动态数据预测。短期的用电量存在多种不确定影响因素,为了将所有影响因素考虑其中,引入混沌时间序列的重构相空间技术。由于神经网络在非线性函数中对于峰值预测偏差较大,粗糙集理论可以对其做出修正。因此,引入混沌时间序列理论和粗糙集理论改进Elman神经网络并进行建模。模型应用嵌入维度和延迟时间重构相空间恢复原来系统的动力学形态,将处理好的数据代入Elman神经网络进行用电量预测。最后引入粗糙集修正误差较大的峰值点,提高预测精度。收集了Heriot-Watt大学某宿舍楼30天的用电量数据,以5 min为计数频率共8 640个计数点作为数据集进行预测仿真。预测结果与Elman神经网络和混沌时间序列Elman神经网络进行对比,验证了该模型在短时间预测的有效性。
Elman neural network is widely used for dynamic data prediction because of its ability to approximate and adapting to time-varying characteristics. There are many uncertain factors in the short-term electricity consumption. In order to take all the factors into account, this paper introduces the reconstruction phase space technology of chaotic time series. Due to the large deviation from the neural network of the peak prediction in nonlinear functions, it can be modified by rough set theory. Therefore, the chaotic time series theory and rough set theory are introduced to improve the Elman neural network. The model applies embedded dimension and delay time to reconstruct the phase space to restore the original system's dynamic morphology. The processed data is brought into the Elman neural network to predict the electricity consumption. Finally, the peak point corrected by the rough set is introduced to improve the prediction accuracy. This paper collects the data from a dormitory building in Heriot-Watt university of Edinburgh. It uses thirty days electricity data with 8 640 points as the data set to do predict simulation. The prediction results are compared with the Elman neural network and chaotic time series Elman neural network, and the validity of the model are verified in a short-time prediction.
Elman neural network is widely used for dynamic data prediction because of its ability to approximate and adapting to time-varying characteristics. There are many uncertain factors in the short-term electricity consumption. In order to take all the factors into account, this paper introduces the reconstruction phase space technology of chaotic time series. Due to the large deviation from the neural network of the peak prediction in nonlinear functions, it can be modified by rough set theory. Therefore, the chaotic time series theory and rough set theory are introduced to improve the Elman neural network. The model applies embedded dimension and delay time to reconstruct the phase space to restore the original system's dynamic morphology. The processed data is brought into the Elman neural network to predict the electricity consumption. Finally, the peak point corrected by the rough set is introduced to improve the prediction accuracy. This paper collects the data from a dormitory building in Heriot-Watt university of Edinburgh. It uses thirty days electricity data with 8 640 points as the data set to do predict simulation. The prediction results are compared with the Elman neural network and chaotic time series Elman neural network, and the validity of the model are verified in a short-time prediction.
引文
[1]祖其武,牛玉刚,邹媛媛,等.基于弹性负荷分时调度和多电源联合供电的微网经济运行[J].电力系统保护与控制,2018,46(4):20-27.ZU Qiwu,NIU Yugang,ZOU Yuanyuan,et al.Economic operation of microgrid based on elastic load sub-period dispatch and combined power supply of multiple energy[J].Power System Protection and Control,2018,46(4):20-27.
[2]廖旎焕,胡智宏,马莹莹,等.电力系统短期负荷预测方法综述[J].电力系统保护与控制,2011,39(1):147-152.LIAO Nihuan,HU Zhihong,MA Yingying,et al.Asummary of short-term load forecasting methods for power systems[J].Power System Protection and Control,2011,39(1):147-152.
[3]李奎,李晓倍,郑淑梅,等.基于BP神经网络的交流接触器剩余电寿命预测[J].电工技术学报,2017,32(15):120-127.LI Kui,LI Xiaobei,ZHENG Shumei,et al.Prediction of residual electrical life of AC contactor based on BPneural network[J].Transactions of China Electrotechnical Society,2017,32(15):120-127.
[4]汪清瑶,刘琼.基于Elman神经网络的烧结矿质量在线预测研究[J].仪表技术与传感器,2017(10):98-100,104.WANG Qingyao,LIU Qiong.Research on online prediction of sinter quality based on Elman neural network[J].Meter Technology and Sensors,2017(10):98-100,104.
[5]刘振宇,冯华,杨仁刚.基于混沌时间序列及神经网络的大同电网负荷短期预测研究[J].中北大学学报(自然科学版),2014,35(6):695-698.LIU Zhenyu,FENG Hua,YANG Rengang.Study on short-term load forecasting of datong grid based on chaotic time series and neural network[J].Journal of North University of China(Natural Science Edition),2014,35(6):695-698.
[6]赵腾,王林童,张焰,等.采用互信息与随机森林算法的用户用电关联因素辨识及用电量预测方法[J].中国电机工程学报,2016,36(3):604-614.ZHAO Teng,WANG Lintong,ZHANG Yan,et al.User identification and power consumption forecasting method based on mutual information and random forest algorithm[J].Proceedings of the CSEE,2016,36(3):604-614.
[7]廖峥,熊小伏,李新,等.基于BP神经网络的输电线路舞动预警方法[J].电力系统保护与控制,2017,45(19):154-161.LIAO Zheng,XIONG Xiaofu,LI Xin,et al.Transmission line galloping early warning method based on BP neural network[J].Power System Protection and Control,2017,45(19):154-161.
[8]丁晓,孙虹,郑海雁,等.基于配用电大数据的短期负荷预测[J].电力工程技术,2018,37(3):21-27.DING Xiao,SUN Hong,ZHENG Haiyan,et al.Short-term load forecasting based on large distribution data[J].Electric Power Engineering Technology,2018,37(3):21-27.
[9]杨国田,张涛,王英男,等.基于长短期记忆神经网络的火电厂NOx排放预测模型[J].热力发电,2018,47(10):12-17.YANG Guotian,ZHANG Tao,WANG Yingnan,et al.Prediction model for NOx emissions from thermal power plants based on long-short-term memory neural network[J].Thermal Power Generation,2018,47(10):12-17.
[10]栾开宁,鲍敏,易永仙,等.基于用电模式数的大用户负荷短期预测技术研究[J].电力工程技术,2018,37(3):33-37.LUAN Kaining,BAO Min,YI Yongxian,et al.Research on short-term load forecasting technology for large users based on the number of power use modes[J].Electric Power Engineering Technology,2018,37(3):33-37.
[11]田松峰,吴昭延,王子光,等.基于神经网络的凝汽器污垢热阻预测模型[J/OL].热力发电,2019,48:1-5.[2019-01-17].https://doi.org/10.19666/j.rlfd.201807145.TIAN Songfeng,WU Zhaoyan,WANG Ziguang,et al.Neural network-based prediction model for thermal resistance of condenser fouling[J/OL].热力发电,2019,48:1-5.[2019-01-17].https://doi.org/10.19666/j.rlfd.201807145.
[12]唐静,李瑞轩,黄宇航,等.基于多维特征分析的月用电量精准预测研究[J].电力系统保护与控制,2017,45(16):145-150.TANG Jing,LI Ruixuan,HUANG Yuhang,et al.Research on accurate prediction of monthly electricity consumption based on multidimensional feature analysis[J].Power System Protection and Control,2017,45(16):145-150.
[13]穆海振,孙兰东,侯依玲.上海市全社会月用电量预测模型[J].中国电力,2016,49(6):146-150.MU Haizhen,SUN Landong,HOU Yiling.Shanghai's monthly electricity consumption forecast model for the whole society[J].Electric Power,2016,49(6):146-150.
[14]马瑞,彭舟,蒋诗谣,等.季节划分下产业用电量关联分析及预测[J].中国电力,2015,48(7):82-88.MA Rui,PENG Zhou,JIANG Shiyao,et al.Electricity consumption association analysis and forecast under seasonal divisions[J].Electric Power,2015,48(7):82-88.
[15]董朝武,白江红,汪鸿,等.基于容量利用特征的行业售电量预测方法研究[J].电力系统保护与控制,2018,46(1):103-109.DONG Chaowu,BAI Jianghong,WANG Hong,et al.Research on forecasting method of electricity consumption based on capacity utilization characteristics[J].Power System Protection and Control,2018,46(1):103-109.
[16]HAN M,XI J,XU S,et al.Prediction of chaotic time series based on the recurrent predictor neural network[J].IEEE Transactions on Signal Processing,2004,52(12):3409-3416.
[17]GIONA M,LENTINI F,CIMAGALLI V.Functional reconstruction and local prediction of chaotic time series[J].Physical Review A,1991,44(6):3496.
[18]KARUNASINGHE D S,LIONG S Y.Chaotic time series prediction with a global model:artificial neural network[J].Journal of Hydrology,2006,323(1):92-105.
[19]CASDAGLI M.Nonlinear prediction of chaotic time series[J].Physica D:Nonlinear Phenomena,1989,35(3):335-356.
[20]MAGUIRE L P,ROCHE B,MCGINNITY T M,et al.Predicting a chaotic time series using a fuzzy neural network[J].Information Sciences,1998,112(1-4):125-136.
[21]LIN D T,DAYHOFF J E,LIGOMENIDES P A.Adaptive time-delay neural network for temporal correlation and prediction[C]//Applications in Optical Science and Engineering,International Society for Optics and Photonics,November,1992:170-181.
[22]KENNEL M B,BROWN R,ABARBANEL H D.Determining embedding dimension for phase-space reconstruction using a geometrical construction[J].Physical Review A,1992,45(6):3403.
[23]叶瑞丽,郭志忠,刘瑞叶,等.基于小波包分解和改进Elman神经网络的风电场风速和风电功率预测[J].电工技术学报,2017,32(21):103-111.YE Ruili,GUO Zhizhong,LIU Ruiye,et al.Wind speed and power prediction of wind farm based on wavelet packet decomposition and improved Elman neural network[J].Transactions of China Electrotechnical Society,2017,32(21):103-111.
[24]夏非,范莉,苏浩益.基于粗糙集理论和启发式径向基函数神经网络的中长期电力负荷预测模型[J].电力系统保护与控制,2012,40(16):21-26.XIA Fei,FAN Li,SU Haoyi.A model for medium and long term load forecasting based on rough set theory and heuristic radial basic function neural network[J].Power System Protection and Control,2012,40(16):21-26.
[25]覃泓皓,牛东晓,钱望月,等.考虑季节特性的改进小波包-RBF用电量预测方法[J].电力科学与技术学报,2016,31(2):37-44.TAN Honghao,NIU Dongxiao,QIAN Wangyue,et al.Electricity consumption forecast method with improved wavelet packet-RBF and seasonal characteristics considered power considering the improved wavelet seasonal characteristics[J].Journal of Electric Power Science and Technology,2016,31(2):37-44.
[26]LI Zhi,YE Lin,ZHAO Yongning,et al.Short-term wind power prediction based on extreme learning machine with error correction[J].Protection and Control of Modern Power Systems,2016,1(1):9-16.DOI:10.1186/s41601-016-0016-y.
[2]廖旎焕,胡智宏,马莹莹,等.电力系统短期负荷预测方法综述[J].电力系统保护与控制,2011,39(1):147-152.LIAO Nihuan,HU Zhihong,MA Yingying,et al.Asummary of short-term load forecasting methods for power systems[J].Power System Protection and Control,2011,39(1):147-152.
[3]李奎,李晓倍,郑淑梅,等.基于BP神经网络的交流接触器剩余电寿命预测[J].电工技术学报,2017,32(15):120-127.LI Kui,LI Xiaobei,ZHENG Shumei,et al.Prediction of residual electrical life of AC contactor based on BPneural network[J].Transactions of China Electrotechnical Society,2017,32(15):120-127.
[4]汪清瑶,刘琼.基于Elman神经网络的烧结矿质量在线预测研究[J].仪表技术与传感器,2017(10):98-100,104.WANG Qingyao,LIU Qiong.Research on online prediction of sinter quality based on Elman neural network[J].Meter Technology and Sensors,2017(10):98-100,104.
[5]刘振宇,冯华,杨仁刚.基于混沌时间序列及神经网络的大同电网负荷短期预测研究[J].中北大学学报(自然科学版),2014,35(6):695-698.LIU Zhenyu,FENG Hua,YANG Rengang.Study on short-term load forecasting of datong grid based on chaotic time series and neural network[J].Journal of North University of China(Natural Science Edition),2014,35(6):695-698.
[6]赵腾,王林童,张焰,等.采用互信息与随机森林算法的用户用电关联因素辨识及用电量预测方法[J].中国电机工程学报,2016,36(3):604-614.ZHAO Teng,WANG Lintong,ZHANG Yan,et al.User identification and power consumption forecasting method based on mutual information and random forest algorithm[J].Proceedings of the CSEE,2016,36(3):604-614.
[7]廖峥,熊小伏,李新,等.基于BP神经网络的输电线路舞动预警方法[J].电力系统保护与控制,2017,45(19):154-161.LIAO Zheng,XIONG Xiaofu,LI Xin,et al.Transmission line galloping early warning method based on BP neural network[J].Power System Protection and Control,2017,45(19):154-161.
[8]丁晓,孙虹,郑海雁,等.基于配用电大数据的短期负荷预测[J].电力工程技术,2018,37(3):21-27.DING Xiao,SUN Hong,ZHENG Haiyan,et al.Short-term load forecasting based on large distribution data[J].Electric Power Engineering Technology,2018,37(3):21-27.
[9]杨国田,张涛,王英男,等.基于长短期记忆神经网络的火电厂NOx排放预测模型[J].热力发电,2018,47(10):12-17.YANG Guotian,ZHANG Tao,WANG Yingnan,et al.Prediction model for NOx emissions from thermal power plants based on long-short-term memory neural network[J].Thermal Power Generation,2018,47(10):12-17.
[10]栾开宁,鲍敏,易永仙,等.基于用电模式数的大用户负荷短期预测技术研究[J].电力工程技术,2018,37(3):33-37.LUAN Kaining,BAO Min,YI Yongxian,et al.Research on short-term load forecasting technology for large users based on the number of power use modes[J].Electric Power Engineering Technology,2018,37(3):33-37.
[11]田松峰,吴昭延,王子光,等.基于神经网络的凝汽器污垢热阻预测模型[J/OL].热力发电,2019,48:1-5.[2019-01-17].https://doi.org/10.19666/j.rlfd.201807145.TIAN Songfeng,WU Zhaoyan,WANG Ziguang,et al.Neural network-based prediction model for thermal resistance of condenser fouling[J/OL].热力发电,2019,48:1-5.[2019-01-17].https://doi.org/10.19666/j.rlfd.201807145.
[12]唐静,李瑞轩,黄宇航,等.基于多维特征分析的月用电量精准预测研究[J].电力系统保护与控制,2017,45(16):145-150.TANG Jing,LI Ruixuan,HUANG Yuhang,et al.Research on accurate prediction of monthly electricity consumption based on multidimensional feature analysis[J].Power System Protection and Control,2017,45(16):145-150.
[13]穆海振,孙兰东,侯依玲.上海市全社会月用电量预测模型[J].中国电力,2016,49(6):146-150.MU Haizhen,SUN Landong,HOU Yiling.Shanghai's monthly electricity consumption forecast model for the whole society[J].Electric Power,2016,49(6):146-150.
[14]马瑞,彭舟,蒋诗谣,等.季节划分下产业用电量关联分析及预测[J].中国电力,2015,48(7):82-88.MA Rui,PENG Zhou,JIANG Shiyao,et al.Electricity consumption association analysis and forecast under seasonal divisions[J].Electric Power,2015,48(7):82-88.
[15]董朝武,白江红,汪鸿,等.基于容量利用特征的行业售电量预测方法研究[J].电力系统保护与控制,2018,46(1):103-109.DONG Chaowu,BAI Jianghong,WANG Hong,et al.Research on forecasting method of electricity consumption based on capacity utilization characteristics[J].Power System Protection and Control,2018,46(1):103-109.
[16]HAN M,XI J,XU S,et al.Prediction of chaotic time series based on the recurrent predictor neural network[J].IEEE Transactions on Signal Processing,2004,52(12):3409-3416.
[17]GIONA M,LENTINI F,CIMAGALLI V.Functional reconstruction and local prediction of chaotic time series[J].Physical Review A,1991,44(6):3496.
[18]KARUNASINGHE D S,LIONG S Y.Chaotic time series prediction with a global model:artificial neural network[J].Journal of Hydrology,2006,323(1):92-105.
[19]CASDAGLI M.Nonlinear prediction of chaotic time series[J].Physica D:Nonlinear Phenomena,1989,35(3):335-356.
[20]MAGUIRE L P,ROCHE B,MCGINNITY T M,et al.Predicting a chaotic time series using a fuzzy neural network[J].Information Sciences,1998,112(1-4):125-136.
[21]LIN D T,DAYHOFF J E,LIGOMENIDES P A.Adaptive time-delay neural network for temporal correlation and prediction[C]//Applications in Optical Science and Engineering,International Society for Optics and Photonics,November,1992:170-181.
[22]KENNEL M B,BROWN R,ABARBANEL H D.Determining embedding dimension for phase-space reconstruction using a geometrical construction[J].Physical Review A,1992,45(6):3403.
[23]叶瑞丽,郭志忠,刘瑞叶,等.基于小波包分解和改进Elman神经网络的风电场风速和风电功率预测[J].电工技术学报,2017,32(21):103-111.YE Ruili,GUO Zhizhong,LIU Ruiye,et al.Wind speed and power prediction of wind farm based on wavelet packet decomposition and improved Elman neural network[J].Transactions of China Electrotechnical Society,2017,32(21):103-111.
[24]夏非,范莉,苏浩益.基于粗糙集理论和启发式径向基函数神经网络的中长期电力负荷预测模型[J].电力系统保护与控制,2012,40(16):21-26.XIA Fei,FAN Li,SU Haoyi.A model for medium and long term load forecasting based on rough set theory and heuristic radial basic function neural network[J].Power System Protection and Control,2012,40(16):21-26.
[25]覃泓皓,牛东晓,钱望月,等.考虑季节特性的改进小波包-RBF用电量预测方法[J].电力科学与技术学报,2016,31(2):37-44.TAN Honghao,NIU Dongxiao,QIAN Wangyue,et al.Electricity consumption forecast method with improved wavelet packet-RBF and seasonal characteristics considered power considering the improved wavelet seasonal characteristics[J].Journal of Electric Power Science and Technology,2016,31(2):37-44.
[26]LI Zhi,YE Lin,ZHAO Yongning,et al.Short-term wind power prediction based on extreme learning machine with error correction[J].Protection and Control of Modern Power Systems,2016,1(1):9-16.DOI:10.1186/s41601-016-0016-y.