Analysis of demand and consumption of electricity using auto-regressive time series processCESS.

Abstract

Electricity is a special commodity which is difficult to store. Production and consumption have to be equal every time. For this reason, it is necessary to know the quantity of electricity produced and consumed .Basically 'all players in the electricity sector need to know past and future development of consumption and production. There are several prediction methods most of which work with data from previous periods given that it follows a historical trend. Analysis of such data can be used to create a suitable model for understanding the conditions and relationships which affects the development of such values. With such a model one can predict the future development with certain accuracy. Developing an accurate forecast model for the amount of power consumed' will include such factors as time of day, day of the year and weather among others. Based upon these factors, current models use neural network approach to forecast in the very near future. In this research study, we will use AR approach to forecast consumption of electricity. Reliable forecast of electricity' consumption represents a starting point in policy development and improvement of production and distribution. This paper introduces the technique of time series to forecast electricity consumption .This work utilizes data from Maasai Mara University, a public university in Kenya from 2009 to 20 I3.The variables considered in this research include electricity consumption for different months over the years. The resultant model will be tested by the use of historical data obtained from Maasai Mara University