Please use this identifier to cite or link to this item:
Title: Power load demand forecasting
Authors: Palaninathan, Aruna Charukesi
Keywords: DRNTU::Engineering
Issue Date: 2016
Abstract: Electricity load demand is the fundamental building block for all utilities planning. In recent years, due to new developments, electricity generation are deregulated and decentralized causing high fluctuations in the power load. The basis of this project is to inspect different state-of-art forecasting methods and to determine their suitability and efficiency in providing precise forecasts. The first phase of the project was focused on the theory and concepts of the various forecasting methods available. In the subsequent phases, models for short-term load demand forecasting was programmed. In this research, 12 models were constructed based on 7 different techniques. The techniques are: neural network, random forest, support vector regression, autoregressive integrated moving average, empirical mode decomposition, ensemble empirical mode decomposition and lastly complete ensemble empirical mode decomposition with adaptive noise. Once the models were built, they were estimated and forecasted for four different time period intervals. Then, performance measures were applied to the forecast and actual value to study the efficiency and accuracy of the model. The results of the models and the creation process of the models were clearly illustrated in the next few sections of this report.
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 
  Restricted Access
Final Year Project Report4.11 MBAdobe PDFView/Open

Page view(s)

Updated on May 10, 2021

Download(s) 50

Updated on May 10, 2021

Google ScholarTM


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