Clustering Residential Electricity Consumption: A Case Study

Abstract

Electricity is a crucial need of any modern society for improved lifestyle. Rwanda is a fast growing economy country, with some electricity access rolling out programmes and the country is trying its best to improve the national power grid infrastructure to meets its population power demand and enhance quality of life. Macroeconomic data of expenses on annual electricity consumption from EICV 4 (EICV: Enquête Intégrale sur les Conditions de Vie des ménages (French), Integrated Household and Living Conditions Survey (English)) from National Institute of Statistics of Rwanda (NISR), and price of electricity for residential customers, comprising dataset of 2311 surveyed residential dwellings were clustered by their annual electricity consumption between October 2013 and October 2014 into three groups. Statistical Package for Social Sciences (SPSS version 20), K-means clustering algorithm and Excel Data Analyses Tool results reveal that: (a) 60.2 kWh was the annual electricity consumption per person nationwide, (b) 3395 kWh (dwelling of 5 people) was the highest annual electricity consumption (Huye district, Southern Province), (c) 9.7 kWh (dwelling of 6 occupants) was lowest annual electricity consumption (Bugesera District, Eastern Province), and (d) 278.7 kWh was the average kWh annual energy consumption. K-means clustering algorithm reveals that 93.2% of surveyed dwellings annual electricity consumption was between 9.7 and 582.1 kWh.