Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/47716
Title: Forecasting of solar radiation using fuzzy neural networks
Authors: Seng, Anthony Sunjaya.
Keywords: DRNTU::Engineering::Electrical and electronic engineering::Power electronics
Issue Date: 2011
Abstract: The growing concern of scarcity of fuel and gas has been one of the main reasons for scientists and researchers to develop more effective and efficient alternative energy, like wind, solar, stream energy and nuclear energy. However, this report will only touch on one of the ways to improve the efficiency of using solar energy in generating power as an alternative power supply in power generation systems. One way to improve the efficiency of power generation in the transmission and distribution of power grid system that connects to the solar power generator is to predict the amount of solar power generated by solar panel in each period of time which can range from minute, hour, to day. This is important because by knowing the amount of solar power that can be generated for each day, the amount of power saving from the grid main power supply can be improved. Hence, by predicting the amount of energy generated from the solar panel, the rest of the power needed can be balanced from the main generator. In this report, the ability to predict the amount of solar power generated from a solar panel will be discussed by forecasting the amount of solar radiation using neural network and fuzzy logic algorithm. This report will start with the concept of neural networks, then move on to the concept of fuzzy logic, simulation and finally will end with the discussion of results in this method of prediction.
URI: http://hdl.handle.net/10356/47716
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 
EEEA1131-102.pdf
  Restricted Access
2.85 MBAdobe PDFView/Open

Page view(s) 50

255
checked on Oct 19, 2020

Download(s) 50

23
checked on Oct 19, 2020

Google ScholarTM

Check

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