IOSR Journal of Electrical and Electronics Engineering (IOSR-JEEE) e-ISSN: 2278-1676,p-ISSN: 2320-3331, Volume 11, Issue 1 Ver. III (Jan. – Feb. 2016), PP 72-81 www.iosrjournals.org DOI: 10.9790/1676-11137281 www.iosrjournals.org 72 | Page Short-Term Load Forecasting Using The Time Series And Artificial Neural Network Methods Isaac Samuel 1 , Tolulope Ojewola 1 ,Ayokunle Awelewa 1 ,Peter Amaize 1 1 (Electrical &Information Engineering Department, College of Engineering/ Covenant University, Nigeria) Abstract: Forecasting of electrical load is very crucial to the effective and efficient operation of any power system. This is achieved by obtaining the most accurate forecast which help in minimizing the risk in decision making and reducesthe costs of operating the power plant. Therefore, the comparative study of time series and artificial neural network methods for short term load forecasting is carried out in this paper using real time load data of Covenant University,withthe moving average, exponential smoothing (time series method) and the Artificial Neural Network (ANN) models. The work was done for the day-to-day operation of the soon-to-be- completed power station of the university. For each of the methods, models were developed for the load forecast. The Artificial Neural Network proved to be the best forecast method when the results are compared in terms of error measurementswith amean absolutedeviation(MAD) having 0.225, mean squared error (MSE) having 0.095 and the mean absolute percent error(MAPE)having 8.25. Keywords:Artificial neural network, Error measurement, Exponential smoothing, Load forecasting, Moving average. I. Introduction A power system serves a major function of supplying its customers, (large and small) with economical and reliableelectrical energy as much as possible. For adequate electricity to be supplied to the customers, their load demand must be known[1], [2]. The process of making these evaluations of future demand of load is called ‘Load forecasting’. Load forecasting is the projection of electrical load that will be required by a certain geographical area considering previous electrical load usage in the said area [3].Loadforecasting helps to make vital decisions concerning the system, therefore, load forecasting is very crucial for successful effective and efficient operation of any energy system. If the system load forecast is overestimated, the system may overcommit the generation of powerwhich will inadvertently lead to costly operation of the power system. On the other hand, if the system load forecast is underestimated, the reliability and security of the system may be compromised, resulting in power interruptions and customer dissatisfaction [1]. The time period in which the forecast is carried out is fundamental to the results and use of the forecast. Short-term forecast, which spans a period of one hour to one week, helps to provide a great saving potential for economic and secured operation of power system, medium-term forecast, which ranges from a week to a year, concerns with scheduling of fuel supply and maintenance operation and long-term forecast and is from a year upwards, is useful for planning operations [3]. This paper focuses on the short term load forecasting (STLF) which is used for prompt load scheduling and determines the most economic load dispatch with operational constraints and policies, environmental and equipment limitations [4]. Over the years, different methods have been developed and improved upon to forecast load demands.These methods of load forecasting are classified into two categories: classical approaches and artificial intelligence (AI) based techniques. Classical approaches are based on various statistical modeling methods.These approaches forecast future values of the load by using a mathematical combination of previous values of the load and other variable such as weather data. This includes the use of regression exponential smoothing, Box-Jenkins, autoregressive integrated moving average (ARIMA) models and Kalman filters. Recently several researchers have studied the use of artificial neural networks (ANNs) models and Fuzzy neural networks (FNNs) models for load forecasting[4]. This paper is organized as follows. Section II briefly discusses electrical load forecasting, while section III,presents the methods used to carry out the load forecasting, and in section IV results are discussed. Section V concludes the paper. II. Electrical Load Forecasting There is a need for the development of models for electrical load forecasting. The models to be developed depend on the relative information about the past load data available and how long into the future the forecast will be. Forecasting models merely identify patterns in the load data being analyzed and use these patternsto forecast what will be the future load.Load forecasting holds a lot of benefits for electric power system