Please use this identifier to cite or link to this item:
Title: Electrical load forecasting for buildings in Singapore using adaptive neuro-fuzzy inference system
Authors: Lee, Han Pin
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2018
Abstract: A typical household’s electrical tariff in Singapore are charged on a fixed rate. The users must pay based on the amount of electricity they use without consideration on other factors. It is different when it comes to electricity for the whole building, Electricity retailers will come out with packages to get landlords to commit contracted capacity they project to use and pay a premium should they exceed their agreed contracted capacity. With this setup, the power system infrastructure ensure that the system would be more efficient, in terms of engineering and economic. Therefore, a building's electrical load profiling is important to understand the power usage consumption pattern. Landlord uses such pattern as a guide to form contract with power generation companies. However, any high surge or abnormal usage might cause tenants or landlords to pay for high premium which is not desirable. Many times, landlords or tenants realizes this only when end of the month bills come which is too late. Thus, this project aims to bridge the gap by using prediction using Adaptive Neuro-Fuzzy Inference System of the load and detect any abnormalities before it goes out of hand. Load forecasting adds intelligence to running of building management. When the system flags an irregularity, a notification can be sent to relevant parties. This provides an early warning system to landlord or even tenants
Schools: School of Electrical and Electronic Engineering 
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
Electrical Load Forecasting for Buildings in Singapore Using ANFIS.pdf
  Restricted Access
1.33 MBAdobe PDFView/Open

Page view(s)

Updated on Jun 12, 2024


Updated on Jun 12, 2024

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.