Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/68098
Title: | Solar irradiance forecasting | Authors: | Chng, Shu Yan | Keywords: | DRNTU::Engineering::Electrical and electronic engineering | Issue Date: | 2016 | Abstract: | In recent years, due to increased electricity consumption globally, there has been a drastic increase in carbon dioxide emissions caused by generation of electricity which heavily contributes to global warming. Therefore environmentally friendly alternatives such as the use of renewable energy has been widely adopted in an effort to slow down global warming as well as reduce the dependency on fossil fuels to generate electricity. Reliability in power systems is an important aspect, thus to effectively use PV for power generation, forecasting of solar irradiance is essential. Accurate forecasting of solar irradiance can be used to predict the power output of solar PV system or smart grids to optimise its operation and improve system reliability. The purpose of this project is to study different short term hour solar irradiance forecasting methods and to evaluate the prediction accuracy by comparing error measures mean absolute error and root mean squared error. This report focuses mainly on the implementation of three machine learning forecasting methods, ANN feedforward neural network, SVM regression and random forest. Based on the three methods, random forest has proven to be the effective as well as easiest to implement compared to feedforward neural network (FNN) and support vector regression (SVR). | URI: | http://hdl.handle.net/10356/68098 | 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 | Size | Format | |
---|---|---|---|---|
FYP Report_Chng Shu Yan.pdf Restricted Access | 3.21 MB | Adobe PDF | View/Open |
Page view(s)
314
Updated on Mar 28, 2024
Download(s) 50
37
Updated on Mar 28, 2024
Google ScholarTM
Check
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.