<?xml version="1.0" encoding="UTF-8"?> <article key="pdf/85" mdate="2008-10-28 00:00:00"> <author>Mohamed Tarek Khadir and Damien Fay and Ahmed Boughrira</author> <title>Day Type Identification for Algerian Electricity Load using Kohonen Maps</title> <pages>3541 - 3545</pages> <year>2008</year> <volume>2</volume> <number>10</number> <journal>International Journal of Electrical and Computer Engineering</journal> <ee>https://publications.waset.org/pdf/85</ee> <url>https://publications.waset.org/vol/22</url> <publisher>World Academy of Science, Engineering and Technology</publisher> <abstract>Short term electricity demand forecasts are required by power utilities for efficient operation of the power grid. In a competitive market environment, suppliers and large consumers also require short term forecasts in order to estimate their energy requirements in advance. Electricity demand is influenced (among other things) by the day of the week, the time of year and special periods andor days such as Ramadhan, all of which must be identified prior to modelling. This identification, known as daytype identification, must be included in the modelling stage either by segmenting the data and modelling each daytype separately or by including the daytype as an input. Daytype identification is the main focus of this paper. A Kohonen map is employed to identify the separate daytypes in Algerian data.</abstract> <index>Open Science Index 22, 2008</index> </article>