Please use this identifier to cite or link to this item:
Title: Interval forecasting of renewable power generation
Authors: Seah, Mun Ting
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2019
Abstract: Purpose: The aim of this project is to implement a program to develop an accurate prediction interval model using interval forecasting method to better estimate the solar irradiance and solar output power generated in the future. Brief Description of Project: Forecasting plays a major role in assisting system operators to make valuable decision and ensure safe and reliability of the power systems. Furthermore, better scheduling of generation is achieved, reducing cost of operation. Hence, it is vital to have an accurate prediction model so that actions can be taken to manage intermittency and ensuring robust operation of the power systems. The algorithm that is used to implement in this project includes gradient boosting and extreme gradient boosting. Furthermore, feature importance is also incorporated to enhance performance of the model. Conclusion & Future Works: Further analysis and improvements can be made to the model which would enhance the model performance. The following future works that can be implemented are grid search, improvement in interval score and exploring better forecasting approaches in the literature. At the end of the day, interval forecasting of power generated would not only affect the operators but also everyone. Therefore, it is crucial to develop and enhance forecasting models to better prepare for the growing demand ahead and ensuring a balance in system and supply reliability.
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 
Final report Submission_seah mun ting_lib.pdf
  Restricted Access
FYP Final Report4.19 MBAdobe PDFView/Open

Page view(s)

Updated on Nov 30, 2020

Download(s) 50

Updated on Nov 30, 2020

Google ScholarTM


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