Data Fusion Based on Binary Identifier and Improved D-S Theory

doi:10.11985/2021.03.025

Abstract

Abstract:

In recent years, the power grid has vigorously promoted the informatization, with a number of informatization systems, covering various professional fields. It has accumulated a large number of business data and real-time status data. However, the data is scattered in various systems. It is necessary to fully make use of the massive data, to provide effective basis for planning, construction, operation, transformation and user access of power grid. Therefore, data extraction based on binary identifier is researched to achieve less than 50% memory occupation, and data fusion aimed to improve D-S theory is proposed to achieve high-precision matching(the accuracy is improved to more than 85%), so as to optimize operation modes and improve lean management of power grid.

Key words: Multi-source data, missing identification, evidence theory, data fusion

CLC Number:

TM933

FANG Yanqiong, TANG Shengwei, GU Bochuan, DAI Shiyong, YE Xiangqian. Data Fusion Based on Binary Identifier and Improved D-S Theory[J]. Journal of Electrical Engineering, 2021, 16(3): 184-191.

Figures/Tables 12

References 25

[1]	王玉波. 基于基本概率赋值调整的数据融合方法及应用[D]. 大连:大连理工大学, 2010.
	WANG Yubo. Research and application of data fusion based on basic probability assignment function adjusting[D]. Dalian:Dalian University of Technology, 2010.
[2]	欧志新. 变电所非对称电压畸变的自适应数据融合研究[J]. 电气工程学报, 2017, 12(12):26-32.
	OU Zhixin. Research on adaptive data fusion of asymmetrical voltage distortion in substation[J]. Journal of Electrical Engineering, 2017, 12(12):26-32.
[3]	2030WG-IEEE 2030 Smart Grid Interoperability Working Group,IEEE-SASB Coordinating Committees. IEEE Std 2030-2011 IEEE guide for smart grid interoperability of energy technology and information technology operation with the electric power system (EPS),end-use applications,and loads[S]. [2011-09-10]. IEEE, 2011:1-126. DOI: 10.1109/IEEESTD.2011.6018239. doi: 10.1109/IEEESTD.2011.6018239
[4]	曹军威, 万宇鑫, 涂国煜, 等. 智能电网信息系统体系结构研究[J]. 计算机学报, 2013, 36(1):143-167.
	CAO Junwei, WAN Yuxin, TU Guoyu, et al. Information system architecture for smart grids[J]. Chinese Journal of Computers, 2013, 36(1):143-167. doi: 10.3724/SP.J.1016.2013.00143
[5]	宋亚奇, 周国亮, 朱永利. 智能电网大数据处理技术现状与挑战[J]. 电网技术, 2013, 37(4):927-935.
	SONG Yaqi, ZHOU Guoliang, ZHU Yongli. Present status and challenges of big data processing in smart grid[J]. Power System Technology, 2013, 37(4):927-935.
[6]	赵洪山, 田甜. 基于自适应无迹卡尔曼滤波的电力系统动态状态估计[J]. 电网技术, 2014, 38(1):188-192.
	ZHAO Hongshan, TIAN Tian. Dynamic state estimation for power system based on an adaptive unscented Kalman filter[J]. Power System Technology, 2014, 38(1):188-192.
[7]	修春波, 任晓, 李艳晴, 等. 基于卡尔曼滤波的风速序列短期预测方法[J]. 电工技术学报, 2014, 29(2):253-259.
	XIU Chunbo, REN Xiao, LI Yanqing, et al. Short-term prediction method of wind speed series based on Kalman filtering fusion[J]. Transaction of China Electrotechnical Society, 2014, 29(2):253-259.
[8]	魏克新, 陈峭岩. 基于自适应无迹卡尔曼滤波算法的锂离子动力电池状态估计[J]. 中国电机工程学报, 2014, 34(3):445-452.
	WEI Kexin, CHEN Qiaoyan. States estimation of li-ion power batteries based on adaptive unscented Kalman filters[J]. Proceedings of the CSEE, 2014, 34(3):445-452.
[9]	金杉, 崔文, 金志刚. 正态分布的贝叶斯网络火灾数据融合预警研究[J]. 计算机应用研究, 2016, 33(5):1473-1476,1485.
	JIN Shan, CUI Wen, JIN Zhigang. Research on early warning of fire data fusion of Bayesian network based on normal distribution[J]. Application Research of Computers, 2016, 33(5):1473-1476,1485.
[10]	张品, 董为浩, 高大冬. 一种优化的贝叶斯估计多传感器数据融合方法[J]. 传感技术学报, 2014, 27(5):643-648.
	ZHANG Pin, DONG Weihao, GAO Dadong. An optimal method of data fusion for multi-sensors based on Bayesian estimation[J]. Chinese Journal of Sensors and Actuators, 2014, 27(5):643-648.
[11]	杨柳, 杨德友, 张宇时, 等. 基于Copula函数的风-电-热相关性及其潜在不确定性分析[J]. 电气工程学报, 2020, 15(2):47-53.
	YANG Liu, YANG Deyou, ZHANG Yushi, et al. Wind-power-heat correlation and its underlying uncertainty analysis based on Copula function[J]. Journal of Electrical Engineering, 2020, 15(2):47-53.
[12]	陆三兰, 程铭东. 基于D-S证据理论的组合数据融合算法[J]. 微电子学与计算机, 2011, 28(1):95-98.
	LU Sanlan, CHENG Mingdong. Combination of data fusion algorithm based on D-S evidence theory[J]. Microelectronics & Computer, 2011, 28(1):95-98.
[13]	张彦龙, 翟登辉, 许丹, 等. 基于机器学习的换流站故障分析报告智能分类方法[J]. 电气工程学报, 2019, 14(1):83-88.
	ZHANG Yanlong, ZHAI Denghui, XU Dan, et al. Intelligent classify methods based on machine learning for convertor station failure analysis report[J]. Journal of Electrical Engineering, 2019, 14(1):83-88.
[14]	高新华, 严正. 基于主成分聚类分析的智能电网建设综合评价[J]. 电网技术, 2013, 37(8):2238-2243.
	GAO Xinhua, YAN Zheng. Comprehensive assessment of smart grid construction based on principal component analysis and cluster analysis[J]. Power System Technology, 2013, 37(8):2238-2243.
[15]	王骏, 王士同, 邓赵红. 聚类分析研究中的若干问题[J]. 控制与决策, 2012, 27(3):321-328.
	WANG Jun, WANG Shitong, DENG Zhaohong. Survey on challenges in clustering analysis research[J]. Control and Decision, 2012, 27(3):321-328.
[16]	袁曾任. 人工神经元网络及其应用[M]. 北京: 清华大学出版社, 1999.
	YUAN Zengren. Artificial intelligence and its applications[M]. Beijing: Tsinghua University Press, 1999.
[17]	张锋军. 大数据技术研究综述[J]. 通信技术, 2014, 47(11):1240-1248.
	ZHANG Fengjun. Overview on big data technology[J]. Communications Technology, 2014, 47(11):1240-1248.
[18]	张东霞, 苗新, 刘丽平, 等. 智能电网大数据技术发展研究[J]. 中国电机工程学报, 2015, 35(1):2-12.
	ZHANG Dongxia, MIAO Xin, LIU Liping, et al. Research on development strategy for smart grid big data[J]. Proceedings of the CSEE, 2015, 35(1):2-12.
[19]	彭小圣, 邓迪元, 程时杰, 等. 面向智能电网应用的电力大数据关键技术[J]. 中国电机工程学报, 2015, 35(3):503-511.
	PENG Xiaosheng, DENG Diyuan, CHENG Shijie, et al. Key technologies of electric power big data and its application prospects in smart grid[J]. Proceedings of the CSEE, 2015, 35(3):503-511.
[20]	马坤隆. 基于大数据的分布式短期负荷预测方法[D]. 长沙:湖南大学, 2014.
	MA Kunlong. Short term distributed load forecasting method based on big data[D]. Changsha:Hunan University, 2014.
[21]	张素香, 赵丙镇, 王风雨, 等. 海量数据下的电力负荷短期预测[J]. 中国电机工程学报, 2015, 35(1):37-42.
	ZHANG Suxiang, ZHAO Bingzhen, WANG Fengyu, et al. Short-term power load forecasting based on big data[J]. Proceedings of the CSEE, 2015, 35(1):37-42.
[22]	郭创新, 彭明伟, 刘毅. 多数据源信息融合的电网故障诊断新方法[J]. 中国电机工程学报, 2009, 29(31):1-7.
	GUO Chuangxin, PENG Mingwei, LIU Yi. Novel approach for fault diagnosis of the power grid with information fusion of multi-data resources[J]. Proceedings of the CSEE, 2009, 29(31):1-7.
[23]	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.
	WANG Dewen, SUN Zhiwei. Big data analysis and parallel load forecasting of electric power user side[J]. Proceedings of the CSEE, 2015, 35(3):527-537.
[24]	卢志刚, 程慧琳, 冯磊, 等. 基于证据融合理论的多不良数据辨识[J]. 电网技术, 2012, 36(1):123-128.
	LU Zhigang, CHENG Huilin, FENG Lei, et al. Multi bad data identification based on evidence fusion theory[J]. Power System Technology, 2012, 36(1):123-128.
[25]	严英杰, 盛戈皞, 陈玉峰, 等. 基于时间序列分析的输变电设备状态大数据清洗方法[J]. 电力系统自动化, 2015, 39(7):138-144.
	YAN Yingjie, SHENG Gehao, CHEN Yufeng, et al. Cleaning method for big data of power transmission and transformation equipment state based on time sequence analysis[J]. Automation of Electric Power Systems, 2015, 39(7):138-144.

月份	理论数量	实际数量	缺失数量	计算结果	二进制结果
2017.09	30	30	0	1.073 7×10⁹	00111111111111111111111111111111
2017.10	31	30	1	-8.193 0×10³	11111111111111111101111111111111
2017.11	30	30	0	1.073 7×10⁹	00111111111111111111111111111111
2017.12	31	31	0	2.147 5×10⁹	01111111111111111111111111111111
2018.01	31	31	0	2.147 5×10⁹	01111111111111111111111111111111
2018.02	28	28	0	2.684 4×10⁸	00001111111111111111111111111111
2018.03	31	31	0	2.147 5×10⁹	01111111111111111111111111111111
2018.04	30	30	0	1.073 7×10⁹	00111111111111111111111111111111
2018.05	31	31	0	2.147 5×10⁹	01111111111111111111111111111111
2018.06	30	30	0	1.073 7×10⁹	00111111111111111111111111111111
2018.07	31	30	1	-1.290 0×10²	11111111111111111111111101111111
2018.08	31	30	1	-8.193 0×10³	11111111111111111101111111111111
2018.09	30	30	0	1.073 7×10⁹	00111111111111111111111111111111
2018.10	31	31	0	2.147 5×10⁹	01111111111111111111111111111111
2018.11	30	29	1	-1.610 6×10⁹	10011111111111111111111111111111
2018.12	31	31	0	2.147 5×10⁹	01111111111111111111111111111111
2019.01	31	31	0	2.147 5×10⁹	01111111111111111111111111111111
2019.02	28	28	0	2.684 4×10⁸	00001111111111111111111111111111
2019.03	31	27	4	-4.194 3×10⁶	11111111101111111111111111111111
2019.04	30	14	16	-1.610 6×10⁹	10011111111111111111011111111100
2019.05	31	0	31	-2.147 5×10⁹	10000000000000000000000000000000
2019.06	30	29	1	-1.073 7×10⁹	10111111111111111111111011111111
2019.07	31	21	10	-1.024 0×10³	11111111111111111111110000000000
2019.08	31	28	3	-1.258 3×10⁷	11111111001111111111111111111111
2019.09	30	20	10	-2.143 3×10⁹	10000000001111111111111110111111
合计	760	681	79	—	—

方法	数据总大小/B	平均大小/B	识别时间/ms
01标识法(本研究方法)	183	13	31.442
缺失时间标识	1 027	41.08	26.623
缺失时间标识+是否缺失标识	10 640	425.6	52.801

方法	时间/ms	匹配成功数量
基于正则式匹配的方法	140	131
字符串相似度方法	20	5(匹配度≥0.5) 76(匹配度≥0.3)

方法	时间/ms	匹配成功数量
基于正则式匹配的方法	124	106
字符串相似度方法	37	9(匹配度≥0.5) 77(匹配度≥0.3)

数据源	数据源1	数据源2	数据源3	数据源4	合计
数据量	34 413	5 739	1 669	5 524	47 345
权重	0.727	0.121	0.035	0.117	1