Modelling Daily Load Profiles In The Utility Of Malaysia

This paper presents a statistical framework for the modelling of daily load profiles. Data of short term load profiles in the utility of Malaysia with the reading recorded every half an hour was used for this study. The daily plot and analysis of average maximum demand and minimum demand was done in order to choose the best statistical distribution to be fit this data. Analysis shows that the average maximum load, minimum load and average load consumption are vary for every seven days. The frequency distribution plots of the data reveal different pattern for different days. Based on these, the normal distribution, log-normal distribution and Weibull distribution was fit to the data. Maximum likelihood method was used to estimate parameters in these distributions. The assessments of the best distribution are by using numerical method, namely the mean square error (MSE) and normal absolute error (NAE). Result shows that the load consumption for each seven day can be model using different statistical distributions. Hence results from this study can be used to forecast the daily load consumption using confidence interval method.