基于大数据平台的居民负荷变尺度画像技术实现与应用
|
摘要
传统的负荷曲线描述方法难以全面描述负荷变化特征。文章尝试采用用户画像技术进行居民负荷多尺度立体化的用电特性研究。首先,基于大数据平台中的可用数据资源,建立了表征居民负荷用电特性的标签体系。为了快速高效地获取各类典型用户特征,应用标签体系,在大数据平台支撑下,应用分布式聚类算法对海量居民用户用电数据进行聚类分析。最后,针对每类用户,文章绘制了四季的典型日和典型月负荷曲线以及年持续负荷曲线并进行了对比,同时分析了每类用户的负荷波动率和需求响应水平,以构建包含用户的用电时序规律和用电弹性特征的变时间尺度用户画像。分析结果能够可视化地描述居民负荷的时间分布特性及用户用电特性,可为合理制定电价套餐及优化用电模式提供参考。
Traditional load curve description methods are difficult to fully describe the characteristics of load changes.Therefore, this paper attempts to use user portrait to study the multi-scale high-dimensional electrical characteristics of residential load. Firstly, based on the available data resources in the big data platform, a label system is established to characterize the electricity consumption characteristics of residential loads. In order to quickly and efficiently acquire all kinds of typical user characteristics, a distributed clustering algorithm is applied to cluster and analyze massive residential users' electricity data based on the label system and the support of big data platform. Finally, the typical daily and monthly load curves of four seasons and annual continuous load curves are drawn and compared for each type of representative users. At the same time, the load fluctuation rate and demand response level of each type of users are analyzed to construct a variable time scale user portrait including users' electricity timing law and electroelastic characteristics. The analysis results of this paper can visually describe the distribution characteristics of residential load and the electricity consumption characteristics of users, which can provide a reference for the rational formulation of electricity price and the adjustment of electricity consumption patterns.
Traditional load curve description methods are difficult to fully describe the characteristics of load changes.Therefore, this paper attempts to use user portrait to study the multi-scale high-dimensional electrical characteristics of residential load. Firstly, based on the available data resources in the big data platform, a label system is established to characterize the electricity consumption characteristics of residential loads. In order to quickly and efficiently acquire all kinds of typical user characteristics, a distributed clustering algorithm is applied to cluster and analyze massive residential users' electricity data based on the label system and the support of big data platform. Finally, the typical daily and monthly load curves of four seasons and annual continuous load curves are drawn and compared for each type of representative users. At the same time, the load fluctuation rate and demand response level of each type of users are analyzed to construct a variable time scale user portrait including users' electricity timing law and electroelastic characteristics. The analysis results of this paper can visually describe the distribution characteristics of residential load and the electricity consumption characteristics of users, which can provide a reference for the rational formulation of electricity price and the adjustment of electricity consumption patterns.
引文
[1]张小可,沈文明,杜翠凤.贝叶斯网络在用户画像构建中的研究[J].移动通信,2016,40(22):22-26.ZHANG Xiaoke,SHEN Wenming,DU Cuifeng.Research on Bayesian network in user portrait construction[J].Mobile Communications,2016,40(22):22-26.
[2]李映坤.大数据背景下用户画像的统计方法实践研究[D].北京:首都经济贸易大学,2016.
[3]王庆福.贝叶斯网络在用户兴趣模型构建中的研究[J].无线互联科技,2016(12):101-102.WANG Qingfu.Research on user interest model construction based on Bayes network[J].Wireless Internet Technology,2016(12):101-102.
[4]刘海,卢慧,阮金花,等.基于“用户画像”挖掘的精准营销细分模型研究[J].丝绸,2015,52(12):37-42,47.LIU Hai,LU Hui,RUAN Jinhua,et al.Research on precision marketing segmentation model based on mining“persona”[J].Journal of Silk,2015,52(12):37-42,47.
[5]曾鸿,吴苏倪.基于微博的大数据用户画像与精准营销[J].现代经济信息,2016(16):306-308.ZENG Hong,WU Suni.User image and precision marketing on account of big data in Weibo[J].Modern Economic Information,2016(16):306-308.
[6]王文璐.基于用户大数据的海尔集团线上精准营销研究[D].哈尔滨:东北农业大学,2015.
[7]戴恒宇.基于数据挖掘技术的移动运营商用户投诉数据研究[D].南京:南京大学,2016.
[8]张占清,刘岩,田海亭,等.用电信息采集系统运行监控提升技术[J].广东电力,2016,29(10):69-74.ZHANG Zhanqing,LIU Yan,TIAN Haiting,et al.Improvement technology for operation monitoring of electric information acquisition system[J].Guangdong Electric Power,2016,29(10):69-74.
[9]王璟,杨德昌,李锰,等.配电网大数据技术分析与典型应用案例[J].电网技术,2015,39(11):3114-3121.WANG Jing,YANG Dechang,LI Meng,et al.Analysis of big data technology in power distribution system and typical applications[J].Power System Technology,2015,39(11):3114-3121.
[10]尤毅,刘东,钟清,等.多时间尺度下基于主动配电网的分布式电源协调控制[J].电力系统自动化,2014,38(9):192-198,203.YOU Yi,LIU Dong,ZHONG Qing,et al.Multi-time scale coordinated control of distributed generators based on active distribution network[J].Automation of Electric Power Systems,2014,38(9):192-198,203.
[11]朱朝阳,王继业,邓春宇.电力大数据平台研究与设计[J].电力信息与通信技术,2015,13(6):1-7.ZHU Chaoyang,WANG Jiye,DENG Chunyu.Research and design of electric power big data platform[J].Electric Power Information and Communication Technology,2015,13(6):1-7.
[12]孟祥君,季知祥,杨祎.智能电网大数据平台及其关键技术研究[J].供用电,2015,32(8):19-24.MENG Xiangjun,JI Zhixiang,YANG Yi.Research on big data platform and its key technologies in smart grid[J].Distribution&Utilization,2015,32(8):19-24.
[13]华煌圣,甘霖,伍竹林,等.基于物联网技术的能源互联网数据支撑平台[J].供用电,2018,35(1):40-45.HUA Huangsheng,GAN Lin,WU Zhulin,et al.Data platform of energy Internet based on techniques of Internet of things[J].Distribution&Utilization,2018,35(1):40-45.
[14]郑翔,赵凤展,杨仁刚,等.基于大数据的低压配电网无功运行评价体系[J].电网技术,2017,41(1):272-278.ZHENG Xiang,ZHAO Fengzhan,YANG Rengang,et al.An evaluation system to reactive power operation in LV distribution network based on big data[J].Power System Technology,2017,41(1):272-278.
[15]李刚,刘燕,宋雨,等.基于信息融合的电力大数据可视化预处理方法[J].广东电力,2016,29(12):10-14.LI Gang,LIU Yan,SONG Yu,et al.Visualization pretreatment method for electric power big data based on information fusion[J].Guangdong Electric Power,2016,29(12):10-14.
[16]沈玉玲,吕燕,陈瑞峰.基于大数据技术的电力用户行为分析及应用现状[J].电气自动化,2016,38(3):50-52.SHEN Yuling,LYU Yan,CHEN Ruifeng.Power user behavior analysis and application status based on big data technology[J].Electrical Automation,2016,38(3):50-52.
[17]夏坊.基于多时间尺度的主动配电网多目标能量优化调度研究[D].贵阳:贵州大学,2017.
[18]WANG Y,CHEN Q X,KANG C Q,et al.Load profiling and its application to demand response:A review[J].Tsinghua Science and Technology,2015,20(2):117-129.
[19]傅军,许鑫,罗迪,等.电力用户行为画像构建技术研究[J].电气应用,2018,37(13):18-23.
[20]郑苗苗,吉根林.DK-Means:分布式聚类算法K-Dmeans的改进[J].计算机研究与发展,2007,44(z2):84-88.ZHENG Miaomiao,JI Genlin.DK-means-an improved distributed clustering algorithm[J].Journal of Computer Research and Development,2007,44(z2):84-88.
[21]王成亮,郑海雁.基于模糊聚类的电力客户用电行为模式画像[J].电测与仪表,2018,55(18):77-81.WANG Chengliang,ZHENG Haiyan.A portrait of electricity consumption behavior mode of power users based on fuzzy clustering[J].Electrical Measurement&Instrumentation,2018,55(18):77-81.
[22]李东东,王博伦,刘洋.用户侧用电需求响应行为研究[J].供用电,2018,35(4):14-19.LI Dongdong,WANG Bolun,LIU Yang.User demand response behavior research[J].Distribution&Utilization,2018,35(4):14-19.
[23]AL-JARRAH O Y,AL-HAMMADI Y,YOO P D,et al.Multilayered clustering for power consumption profiling in smart grids[J].IEEE Access,2017(5):18459-18468.
[2]李映坤.大数据背景下用户画像的统计方法实践研究[D].北京:首都经济贸易大学,2016.
[3]王庆福.贝叶斯网络在用户兴趣模型构建中的研究[J].无线互联科技,2016(12):101-102.WANG Qingfu.Research on user interest model construction based on Bayes network[J].Wireless Internet Technology,2016(12):101-102.
[4]刘海,卢慧,阮金花,等.基于“用户画像”挖掘的精准营销细分模型研究[J].丝绸,2015,52(12):37-42,47.LIU Hai,LU Hui,RUAN Jinhua,et al.Research on precision marketing segmentation model based on mining“persona”[J].Journal of Silk,2015,52(12):37-42,47.
[5]曾鸿,吴苏倪.基于微博的大数据用户画像与精准营销[J].现代经济信息,2016(16):306-308.ZENG Hong,WU Suni.User image and precision marketing on account of big data in Weibo[J].Modern Economic Information,2016(16):306-308.
[6]王文璐.基于用户大数据的海尔集团线上精准营销研究[D].哈尔滨:东北农业大学,2015.
[7]戴恒宇.基于数据挖掘技术的移动运营商用户投诉数据研究[D].南京:南京大学,2016.
[8]张占清,刘岩,田海亭,等.用电信息采集系统运行监控提升技术[J].广东电力,2016,29(10):69-74.ZHANG Zhanqing,LIU Yan,TIAN Haiting,et al.Improvement technology for operation monitoring of electric information acquisition system[J].Guangdong Electric Power,2016,29(10):69-74.
[9]王璟,杨德昌,李锰,等.配电网大数据技术分析与典型应用案例[J].电网技术,2015,39(11):3114-3121.WANG Jing,YANG Dechang,LI Meng,et al.Analysis of big data technology in power distribution system and typical applications[J].Power System Technology,2015,39(11):3114-3121.
[10]尤毅,刘东,钟清,等.多时间尺度下基于主动配电网的分布式电源协调控制[J].电力系统自动化,2014,38(9):192-198,203.YOU Yi,LIU Dong,ZHONG Qing,et al.Multi-time scale coordinated control of distributed generators based on active distribution network[J].Automation of Electric Power Systems,2014,38(9):192-198,203.
[11]朱朝阳,王继业,邓春宇.电力大数据平台研究与设计[J].电力信息与通信技术,2015,13(6):1-7.ZHU Chaoyang,WANG Jiye,DENG Chunyu.Research and design of electric power big data platform[J].Electric Power Information and Communication Technology,2015,13(6):1-7.
[12]孟祥君,季知祥,杨祎.智能电网大数据平台及其关键技术研究[J].供用电,2015,32(8):19-24.MENG Xiangjun,JI Zhixiang,YANG Yi.Research on big data platform and its key technologies in smart grid[J].Distribution&Utilization,2015,32(8):19-24.
[13]华煌圣,甘霖,伍竹林,等.基于物联网技术的能源互联网数据支撑平台[J].供用电,2018,35(1):40-45.HUA Huangsheng,GAN Lin,WU Zhulin,et al.Data platform of energy Internet based on techniques of Internet of things[J].Distribution&Utilization,2018,35(1):40-45.
[14]郑翔,赵凤展,杨仁刚,等.基于大数据的低压配电网无功运行评价体系[J].电网技术,2017,41(1):272-278.ZHENG Xiang,ZHAO Fengzhan,YANG Rengang,et al.An evaluation system to reactive power operation in LV distribution network based on big data[J].Power System Technology,2017,41(1):272-278.
[15]李刚,刘燕,宋雨,等.基于信息融合的电力大数据可视化预处理方法[J].广东电力,2016,29(12):10-14.LI Gang,LIU Yan,SONG Yu,et al.Visualization pretreatment method for electric power big data based on information fusion[J].Guangdong Electric Power,2016,29(12):10-14.
[16]沈玉玲,吕燕,陈瑞峰.基于大数据技术的电力用户行为分析及应用现状[J].电气自动化,2016,38(3):50-52.SHEN Yuling,LYU Yan,CHEN Ruifeng.Power user behavior analysis and application status based on big data technology[J].Electrical Automation,2016,38(3):50-52.
[17]夏坊.基于多时间尺度的主动配电网多目标能量优化调度研究[D].贵阳:贵州大学,2017.
[18]WANG Y,CHEN Q X,KANG C Q,et al.Load profiling and its application to demand response:A review[J].Tsinghua Science and Technology,2015,20(2):117-129.
[19]傅军,许鑫,罗迪,等.电力用户行为画像构建技术研究[J].电气应用,2018,37(13):18-23.
[20]郑苗苗,吉根林.DK-Means:分布式聚类算法K-Dmeans的改进[J].计算机研究与发展,2007,44(z2):84-88.ZHENG Miaomiao,JI Genlin.DK-means-an improved distributed clustering algorithm[J].Journal of Computer Research and Development,2007,44(z2):84-88.
[21]王成亮,郑海雁.基于模糊聚类的电力客户用电行为模式画像[J].电测与仪表,2018,55(18):77-81.WANG Chengliang,ZHENG Haiyan.A portrait of electricity consumption behavior mode of power users based on fuzzy clustering[J].Electrical Measurement&Instrumentation,2018,55(18):77-81.
[22]李东东,王博伦,刘洋.用户侧用电需求响应行为研究[J].供用电,2018,35(4):14-19.LI Dongdong,WANG Bolun,LIU Yang.User demand response behavior research[J].Distribution&Utilization,2018,35(4):14-19.
[23]AL-JARRAH O Y,AL-HAMMADI Y,YOO P D,et al.Multilayered clustering for power consumption profiling in smart grids[J].IEEE Access,2017(5):18459-18468.