Please use this identifier to cite or link to this item:
Title: Extreme learning machines on PV generation regression
Authors: Chin, Ken Liang Koon
Keywords: DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
Issue Date: 2015
Abstract: Most countries in the world rely heavily on coal, oil and natural gas for its energy. But they are non-renewable and is currently depleting from its finite resources. This also led to the huge increase of their cost over the years. In contrast, renewable energy are constantly replenished and will never run out. This is why the world is interested in harnessing solar energy as its potential is immense and having environmental advantages. In this project, solar power is the subject of research. As the technology of solar energy advance, higher efficiency and power quality of photovoltaic (PV) power output is being studied. One of the ways is to provide accurate prediction continuously to PV power plants as fast as possible so it will balance its energy dispatch. Forecasting algorithm such as Artificial Neural Network (ANN), Support Vector Machine (SVM) and Multiple Linear Regression (MLR) algorithms were being used. The introduction of Extreme Learning Machines (ELM) algorithms have overwhelming by the learning speed and accuracy. Several methods of ELM are used to find the one who gives the best accuracy at the fastest speed.
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 
  Restricted Access
Extreme Learning Machines on PV Generation Regression1.56 MBAdobe PDFView/Open

Page view(s)

Updated on Jul 18, 2024

Download(s) 50

Updated on Jul 18, 2024

Google ScholarTM


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