An implementation of artificial neural network (ANN) based on load demand forecasting for UiTM building / Mohd Najib Mohd Hussain

• Main Author: Mohd Hussain, Mohd Najib
• Format: Thesis
• Language: English
• Published: 2003
• Subjects: Back propagation (Artificial intelligence)
• Online Access: https://ir.uitm.edu.my/id/eprint/77934/1/77934.pdf; https://ir.uitm.edu.my/id/eprint/77934/
• Institution: Universiti Teknologi Mara

This project report presents the application of Artificial Neural network (ANN), as one of the modern technologies based on artificial intelligence, for short term load forecasting in distribution system of UiTM building. ANN models are based on the activity in the human brain such as learning, generalization, recognition, and complex control [ 1]. First, a literature survey was conducted on the subject. Most of the reported models are based on the so-called Multi-Layer Perceptron (MLP) network. The ANN have the ability to respond to input stimuli and for learn to adapt to the environment by use a Multi-layer Perceptron (MLP) network as a network to identify the assumed relation between the future load and the earlier load [2]. Several models were developed and tested on the real load data of a UiTM electric utility by using a MLP network to identify the assumed relation between the future load and the earlier load including day, time, activity and temperature as inputs for the system.