ELECTRICITY FORECASTING FOR SMALL SCALE POWER SYSTEM USING ARTIFICIAL NEURAL NETWORK

Short-term load forecast is an essential part of electric power system planning and
operation. For this project, the main focus will be on the Gas District Cooling Plant (GDC)
which acts as the primary source of energy for Universiti Teknologi PETRONAS (UTP).
This project is looking into weekly forecast of the electricity production for the GDC plant
using Artificial Neural Network Approach. This forecasting method will be very useful to
support plant operation as the trending of load demand for an educational centre such as
UTP is very much dependent on the university activities itself. The project involve
MATLAB program for the STLF with Artificial Neural Network prediction model. The
obtained results showed that introducing Multilayer Perceptron (MLP) Neural Network
architecture improve the prediction significantly by obtaining a very small value of Mean
Absolute Percent Error (MAPE). Besides that, by getting the smaller value of MAPE, it
represents higher forecast accuracy of the model itself. The report consists of an
introduction, problem statement, objectives, literature review and methodology used to solve
the problem. It further looks into the obtained results with consistent discussion.