Electricity Consumption Modeling and Medium-Term Forecasting Based on Grouped Grey Model, GGM(1,1)

被引:0
作者
Getanda, Vincent B. [1 ]
Kihato, Peter K. [1 ]
Hinga, Peterson K. [1 ]
Oya, Hidetoshi [2 ]
机构
[1] Jomo Kenyatta Univ Agr & Technol, Dept Elect & Elect Engn, Sch Elect Elect & Informat Engn, Nairobi, Kenya
[2] Tokyo City Univ, Dept Comp Sci, Tokyo, Japan
来源
2020 IEEE PES & IAS POWERAFRICA CONFERENCE | 2020年
关键词
Electricity; forecasting; grey-model; grouping; modeling; PREDICTION;
D O I
暂无
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Global electricity consumption in any developing sector is increasing faster than expected and energy demand forecasting is vital for sound-sustainable energy supply-demand management. Consequently, developing accurate electricity demand forecasting models is inevitable. In this paper we propose the Grouped Grey Model (GGM(1,1)) in modeling medium-term forecasting of electricity consumption. GGM(1,1) is subjected to electricity consumption data scenario to ascertain its ability and applicability in time series data forecasting. In addition, analysis of an empirical example validates data grouping techniques in improving the accuracy of the original grey model. Hence the accuracy of the prediction on electricity consumption is improved due to data grouping techniques. The proposed model can improve energy forecasting performance for future energy plans of management in producing and distributing power. Moreover, it can enhance smart grid benefits.
引用
收藏
页数:5
相关论文
共 16 条
[1]  
Chen Z., 2012, SYSTEMS ENG PROCEDIA, V5, P179, DOI DOI 10.1016/J.SEPRO.2012.04.029
[2]  
Deng Julong, 1989, Journal of Grey Systems, V1, P1
[3]  
Getanda Vincent B., 2017, Proceedings of the IASTED International Conference on Modeling, Identification and Control (MIC 2017), P39, DOI 10.2316/P.2017.848-016
[4]   DATA GROUPING TECHNIQUES' PERFORMANCE ANALYSIS IN GM(1,1)'s PREDICTION ACCURACY IMPROVEMENT FOR FORECASTING TRAFFIC PARAMETERS [J].
Getanda, Vincent B. ;
Oya, Hidetoshi ;
Kubo, Tomohiro ;
Sato, Yosuke .
MECHATRONIC SYSTEMS AND CONTROL, 2020, 48 (01) :25-34
[5]   An overview of energy demand forecasting methods published in 2005–2015 [J].
Ghalehkhondabi I. ;
Ardjmand E. ;
Weckman G.R. ;
Young W.A., II .
Energy Systems, 2017, 8 (02) :411-447
[6]  
Jun D., 2018, AM J ELECT POWER ENE, V7, P42, DOI DOI 10.11648/J.EPES.20180704.11
[7]   Electric Energy Consumption Prediction by Deep Learning with State Explainable Autoencoder [J].
Kim, Jin-Young ;
Cho, Sung-Bae .
ENERGIES, 2019, 12 (04)
[8]   Building Energy Consumption Prediction: An Extreme Deep Learning Approach [J].
Li, Chengdong ;
Ding, Zixiang ;
Zhao, Dongbin ;
Yi, Jianqiang ;
Zhang, Guiqing .
ENERGIES, 2017, 10 (10)
[9]   Forecasting Electricity Consumption Using an Improved Grey Prediction Model [J].
Li, Kai ;
Zhang, Tao .
INFORMATION, 2018, 9 (08)
[10]   Semi-random partitioning of data into training and test sets in granular computing context [J].
Liu H. ;
Cocea M. .
Granular Computing, 2017, 2 (04) :357-386