Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/129149
Title: SOLAR IRRADIANCE FORECASTING FOR TROPICAL REGIONS USING NOVEL STATISTICAL ANALYSIS AND MACHINE LEARNING
Authors: DONG ZIBO
Keywords: solar, irradiance, forecasting, tropical regions, statistical analysis, machine learning
Issue Date: 12-May-2016
Citation: DONG ZIBO (2016-05-12). SOLAR IRRADIANCE FORECASTING FOR TROPICAL REGIONS USING NOVEL STATISTICAL ANALYSIS AND MACHINE LEARNING. ScholarBank@NUS Repository.
Abstract: To minimize the risk of destabilizing the electricity grid by a sizeable share of solar PV, it is indispensable to forecast the contribution of solar power ahead of time, by 5 minutes, 1 hour, or 1 day in advance, depending on the needs of the grid operation. This would allow the grid operator to take suitable grid management measures, such as up- or downscaling of the power output of other, adjustable generation capacities. However, the forecasting is particular challenging in the tropics due to high solar irradiance variability. The primary goal of this thesis is to develop novel robust irradiance forecasting models for application in the tropics. Several novel models based on statistical time series analysis and machine learning techniques are proposed, including short-term ESSS model, mid-term hybrid ANN/ESSS model, hybrid SOM/SVR/PSO model and spatial-temporal analysis. Superior forecasting accuracy has been achieved by the proposed models.
URI: http://scholarbank.nus.edu.sg/handle/10635/129149
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
thesis.pdf3 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

119
checked on Oct 12, 2018

Download(s)

142
checked on Oct 12, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.