基于加权随机森林算法的空巢电力用户识别方法

doi:10.11959/j.issn.1000-0801.2020249

Abstract

Abstract:

In view of the lack of effective technical means for the identification of empty-nesters by the government and the society,an empty-nesters prow user identification method based on weighted random forest algorithm was proposed.Firstly,some accurate labels of empty-nest users were obtained through questionnaires,and electricity characteristic library was drawn from three aspects:electricity consumption level,electricity consumption fluctuation and electricity consumption trend.Due to the data imbalance between empty-nest and non-empty-nest users,the weighted random forest algorithm was used to improve the data sensitivity phenomenon of machine learning.Finally,the algorithm model was put online in the power company’s acquisition system.The 2 000 unknown users of various types were identified,among which the identification accuracy of empty-nest users was 74.2%.The results show that the identification of empty-nesters from the perspective of electricity consumption can help power grid companies to understand the personalized and differentiated needs of empty-nesters,so as to provide users with more sophisticated services,and also assist the government and society to carry out assistance work.

Key words: empty-nest user identification, weighted random forest algorithm, user electricity characteristic library, data imbalance

CLC Number:

TP181，TP311，F426

Zimeng LU,Jiayi CHEN,Jing LI,Yue XIE,Xinli JIANG,Lei HAN,Qian GUO. An empty-nest power user identification method based on weighted random forest algorithm[J]. Telecommunications Science, 2020, 36(8): 112-121.

Figures/Tables 12

References 25

[7]	李如初, 沈名龙, 彭海棠 . 大数据、云计算在电力工业中的应用[J]. 电信科学, 2018,34(4): 151-155.
	LI R C , SHEN M L , PENG H T . Application of big data and cloud computing in power industry[J]. Telecommunications Science, 2018,34(4): 151-155.
[8]	谷红勋, 杨珂 . 基于大数据的移动用户行为分析系统与应用案例[J]. 电信科学, 2016,32(3): 139-146.
	GU H X , YANG K . Mobile user behavior analysis system and applications based on big data[J]. Telecommunications Science, 2016,32(3): 139-146.
[9]	王志宏, 杨震 . 人工智能技术研究及未来智能化信息服务体系的思考[J]. 电信科学, 2017,33(5): 1-11.
	WANG Z H , YANG Z . Research on artificial intelligence technology and the future intelligent information service architecture[J]. Telecommunications Science, 2017,33(5): 1-11.
[10]	蔡一鸣 . 几种方差概念的比较[J]. 统计与信息论坛, 2008(4): 20-22.
	CAI Y M . Comparison on diverse concepts of variances[J]. Statistics ＆ Information Forum, 2008(4): 20-22.
[11]	张棪, 曹健 . 面向大数据分析的决策树算法[J]. 计算机科学, 2016,43(S1): 374-379,383.
	ZHANG Y , CAO J . Decision tree algorithms for big data analysis[J]. Computer Science 2016,43(S1): 374-379,383.
[12]	孙梦婷, 魏海平, 李星滢 ,等. 利用 CART 分类树分类检测交通拥堵点[J]. 武汉大学学报(信息科学版), 2019(11): 1-10.
	SUN M T,WEI H X , LI X Y , el at . Detection and classification of traffic congestion points using CART classification tree[J]. Geomatics and Information Science of Wuhan University, 2019(11): 1-10.
[1]	翟振武, 陈佳鞠, 李龙 . 2015—2100 年中国人口与老龄化变动趋势[J]. 人口研究, 2017,41(4): 60-71.
	ZHAI Z W , CHEN J J , LI L . Future trends of China’s population and aging:2015—2100[J]. Population Research, 2017,41(4): 60-71.
[13]	刘玉茹, 赵成萍, 臧军 ,等. CART分析及其在故障趋势预测中的应用[J]. 计算机应用, 2017,37(S2): 57-59,73.
	LIU Y R , ZHAO C P , ZANG J ,et al. Analysis of CART regression tree and its application in fault trend forecasting[J]. Journal of Computer Applications, 2017,37(S2): 57-59,73.
[2]	冯先成, 李寒, 周密 ,等. 基于前馈神经网络的智慧城市空巢老人识别[J]. 武汉工程大学学报, 2015,37(10): 33-39.
	FENG X C , LI H , ZHOU M ,et al. Recognition of empty-nest elders in intelligent city based on feedforward neural network[J]. Journal of Wuhan Institute of Technology, 2015,37(10): 33-39.
[14]	XU Z Y , KANG Y , CAO Y ,et al. Man-machine verification of mouse trajectory based on the random forest model[J]. Frontiers of Information Technology ＆ Electronic Engineering, 2019,20(7): 925-929.
[15]	刘亚丽, 李国栋, 刘云 ,等. 基于随机森林的电动汽车充电行为聚类技术研究[J]. 电力工程技术, 2019,38(6): 115-121.
[3]	崔瀚文, 栾石圳南, 李远帆 ,等.空巢老人手机用户的精准识别[J]. 数学建模及其应用, 2014,3(1): 49-62.
	CUI H W , LUAN S Z N , LI Y F ,et al. Accurate identification approach to empty-nester mobile-phone users[J]. Mathematical Modeling and its Applications, 2014,3(1): 49-62.
[15]	LIU Y L , LI G D , LIU Y ,et al. Clustering technology of electric vehicle charging behavior based on random forest[J]. Electric Power Engineering Technology, 2019,38(6): 115-121.
[16]	吴涛, 刘韬, 王斌 . 安徽联通企业级大数据平台构建及应用实践[J]. 电信科学, 2018,34(1): 135-147.
[4]	吴郅君, 殷新博, 陈中 ,等. 基于模糊聚类曲线相似度的负荷用户识别方法[J]. 电力工程技术, 2019,38(3): 151-156.
	WU Z J , YIN X B , CHEN Z ,et al. Identification method of load customers based on similarity of fuzzy clustering curves[J]. Electric Power Engineering Technology, 2019,38(3): 151-156.
[5]	和敬涵, 卢育梓, 陆金耀 ,等. 基于“进化”主成分分析法的用户分类及其应用[J]. 电力建设, 2017,38(3): 101-107.
	HE J H , LU Y Z , LU J Y ,et al. User classification method based on ‘evolution’ PCA and its application[J]. Electric Power Construction, 2017,38(3): 101-107.
[16]	WU T , LIU T , WANG B . Construction and application of Anhui Unicom enterprise big data platform[J]. Telecommunications Science, 2018,34(1): 135-147.
[17]	王铮, 任华, 方燕萍 . 随机森林在运营商大数据补全中的应用[J]. 电信科学, 2016,32(12): 7-12.
	WANG Z , REN H , FANG Y P . Application of random forest in big data completion[J]. Telecommunications Science, 2016,32(11): 7-12.
[18]	王德文, 孙志伟 . 电力用户侧大数据分析与并行负荷预测[J]. 中国电机工程学报, 2015,35(3): 527-537.
[6]	辛苗苗, 张延迟, 解大 . 基于电力大数据的用户用电行为分析研究综述[J]. 电气自动化, 2019,41(1): 1-4,27.
	XIN M M , ZHANG Y C , XIE D . Summary of researches on consumer behavior analysis based on big power data[J]. Electrical Automation, 2019,41(1): 1-4,27.
[18]	WANG D W , SUN Z W . Big data analysis and parallel load forecasting of electric power user side[J]. Proceedings of the CSEE, 2015,35(3): 527-537.
[19]	李艳霞, 柴毅, 胡友强 ,等. 不平衡数据分类方法综述[J]. 控制与决策, 2019,34(4): 673-688.
	LI Y X , CHAI Y , HU Y Q ,et al. Review of imbalanced data classification methods[J]. Control and Decision, 2019,34(4): 673-688.
[20]	张宏莉, 鲁刚 . 分类不平衡协议流的机器学习算法评估与比较[J]. 软件学报, 2012,23(6): 1500-1516.
	ZHANG H L , LU G . Machine learning algorithms for classifying the imbalanced protocol flows:evaluation and comparison[J]. Journal of Software, 2012,23(6): 1500-1516.
[21]	吴成东, 卢紫微, 于晓升 . 基于加权随机森林的图像超分辨率算法研究[J]. 控制与决策, 2019,34(10): 2243-2248.
	WU C D , LU Z W , YU X S . Image super resolution reconstruction algorithm based on weighted random forest[J]. Control and Decision, 2019,34(10): 2243-2248.
[22]	魏正韬, 杨有龙, 白婧 . 基于非平衡数据的随机森林分类算法改进[J]. 重庆大学学报, 2018,41(4): 54-62.
	WEI Z T , YANG Y L , BAI J . An improved random forest algorithm based on unbalanced data[J]. Journal of Chongqing University, 2018,41(4): 54-62.
[23]	彭徵, 王灵矫, 郭华 . 基于随机森林的文本分类并行化[J]. 计算机科学, 2018,45(12): 148-152.
	PENG Z , WANG L J , GUO H . Parallel text categorization of random forest[J]. Computer Science, 2018,45(12): 148-152.
[24]	常玉清, 孙雪婷, 钟林生 ,等. 基于改进随机森林算法的工业过程运行状态评价[J]. 自动化学报, 2019(11): 1-10.
	CHANG Y Q , SUN X T , ZHONG L S ,et al. Industrial operation performance evaluation of industrial processes based on modified random forest[J]. Acta Automatica Sinica, 2019(11): 1-10.
[25]	姜红红, 张涛, 赵新建 ,等. 基于大数据的电力信息网络流量异常检测机制[J]. 电信科学, 2017,33(3): 134-141.
	JIANG H H , ZHANG T , ZHAO X J ,et al. A big data based flow anomaly detection mechanism of electric power information network[J]. Telecommunications Science, 2017,33(3): 134-141.

Metrics

Recommended 0

No Suggested Reading articles found!

用电特征指标	维数
全年用电量最大值、最小值及差值	D₁~D₃
季度用电最大值、最小值及差值	D₄~D₆
月用电最大值、最小值及差值	D₇~D₉
年用电平均值	D₁₀
每季度用电平均值	D₁₁~D₁₄
全年用电标准差、离散系数	D₁₅~D₁₆
每季度用电标准差最大值、最小值及比值	D₁₇~D₁₉
每季度用电离散系数最大值、最小值及比值	D₂₀~D₂₂
每月用电标准差最大值、最小值及比值	D₂₃~D₂₅
每月用电离散系数最大值、最小值及比值	D₂₆~D₂₈
季度用电之差均值和比值的最大值、最小值	D₂₉~D₃₂
月用电之差均值和比值的最大值、最小值	D₃₃~D₃₆

预测	空巢	非空巢
空巢	TP	FP
非空巢	FN	TN

	非空巢	空巢	总和
训练集	3 055	465	3 520
测试集	1 521	213	1 734
总和	4 576	678	5 254

	α	精确率	召回率
A	0.595	67.1%	67.1%
B	0.912	93.4%	14.2%

An empty-nest power user identification method based on weighted random forest algorithm

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 25

Related Articles 11

Metrics

Recommended 0

[1]	Yibo CHEN, Zhijin ZHAO. Intelligent anti-jamming decision algorithm of bivariate frequency hopping pattern based on ET-PPO [J]. Telecommunications Science, 2022, 38(11): 86-95.
[2]	Wen QIAO, Xiaozheng WANG, Zhenqiang SUN, Gan REN, Yunxin LIU, Aidong YANG, Peng WANG, Da WANG, Xiaozhou YE, Ye OUYANG. A pilot study of Telco’s next generation IT architecture evolution: business function virtualization (BFV) [J]. Telecommunications Science, 2022, 38(6): 143-155.
[3]	Wenjun ZHU, Sining WANG, Xiaoxin GAO, Qian ZHENG. Load forecasting based on knowledge flow and transfer learning [J]. Telecommunications Science, 2022, 38(5): 114-123.
[4]	Mingwei ZHU. AI engineering technology solutions in network intelligence [J]. Telecommunications Science, 2022, 38(2): 157-165.
[5]	Zishan LIU,Qiang CHENG,Bo LV. A survey on key technologies of privacy protection for machine learning [J]. Telecommunications Science, 2020, 36(11): 18-27.
[6]	Ye OUYANG,Aidong YANG,Fanyu MENG. A game theory-assisted machine learning methodology for subscriber churn behaviors detection [J]. Telecommunications Science, 2020, 36(6): 79-89.
[7]	Yingzhao ZHU. Review on heterogeneous transfer learning [J]. Telecommunications Science, 2020, 36(3): 100-110.
[8]	Feng ZHOU,Bing WANG. Application practice of base station inspection based on AI [J]. Telecommunications Science, 2018, 34(12): 102-109.
[9]	Ru NIE. Improved large data spectral clustering algorithm based on sampling subspace constraint [J]. Telecommunications Science, 2018, 34(11): 41-47.
[10]	Yuxiang ZHAO,Guangyue LU,Hanglong WANG,Siwei LI. A prediction algorithm of telecom customer churn based on Bayesian network parameters learning under incomplete data [J]. Telecommunications Science, 2018, 34(1): 52-60.
[11]	Chuangchuang LI,Guangyue LU,Hanglong WANG. SVM classifier for telecom user arrears based on boundary samples-based under-sampling approaches [J]. Telecommunications Science, 2017, 33(9): 85-91.