Modelling And Forecasting Student's Residential Area Electricity Demand Using Statistical Analysis

Said, Siti Hajar (2016) Modelling And Forecasting Student's Residential Area Electricity Demand Using Statistical Analysis. Project Report. UTeM, Melaka, Malaysia. (Submitted)

Text (24 Pages) Modelling And Forecasting Student's Residential Area Electricity Demand Using Statistical Analysis.pdf - Submitted Version Download (440kB)

Abstract

A present a new approach for short-term electricity load demand forecasting. In particular load forecasting is usually made by constructing models on relative information such as climate and previous load demand data. Electricity demand forecasting is a central and integral process for planning periodical operations and facility expansion in the electricity sector. Demand pattern is almost very complex due to the deregulation of energy markets. Therefore, finding an appropriate forecasting model for a specific electricity demand is not an easy task. Although many forecasting methods were developed, none can be generalized for all demand patterns. Therefore, this paper presents a modelling and forecasting student’s residential area electricity demand using statistical analysis. Statistical analysis can be used as a guide to construct electricity demand and select the best models. Several statistical analysis are involved to study the load features and forecasting precision such as moving average and probability plots of load noise. Real daily load data from kilowatt meter are used as a case study. Some results are reported to guide forecasting future needs of this research. The best model was selected is ARIMA model. The best model of ARIMA was chosen by the lowest AIC which is for SU1 is ARIMA (1, 1, 1), for SU2 is ARIMA (1, 3, 4), for SU3 is ARIMA (1, 1, 4), for SU4 is ARIMA (1, 1, 4) and lastly for SU5 is ARIMA (3, 1, 3).

Actions (login required)

View Item