Electricity has overtime become one of the most important forms of energy to man. One of the key concerns of the electricity industry for planning and strategic purposes is the quantity of electricity consumed. To this end it has become vital over the years for accurate and efficient mechanisms to model and predict electricity consumption patterns. This paper presents an efficient electricity consumption model for North Cyprus. The designed model is based on using a back propagation neural network. This supervised neural model has as its inputs key economic and seasonal indicators, which to a large extent influence every nation's electricity consumption including North Cyprus. The output of the system is total electricity consumed per year. The system was developed using economic and social indicators of the North Cyprus State Planning Organization (SPO) over the past 32 years, and the obtained experimental results indicate that neural networks can be effectively used for automatic modelling of electricity consumption, provided their input training and validation information are meaningful.
Financed by the National Centre for Research and Development under grant No. SP/I/1/77065/10 by the strategic scientific research and experimental development program:
SYNAT - “Interdisciplinary System for Interactive Scientific and Scientific-Technical Information”.