Please use this identifier to cite or link to this item:
Title: Probabilistic forecasting of solar PV power generation
Authors: Du, Ziyao
Keywords: DRNTU::Engineering::Electrical and electronic engineering::Electric power
DRNTU::Engineering::Computer science and engineering::Theory of computation::Analysis of algorithms and problem complexity
Issue Date: 2019
Abstract: The penetration of solar photovoltaic (PV) generation grew fast in recent years based on the situation that the demand for renewable energy increased rapidly. However, because of high intermittency of solar power, the integration of solar PV generation may cause significant challenges to operation and control for power grids. Hence, to predict solar PV generation is a fundamental and important task for power utilities. Probabilistic forecasting, also called interval forecasting is proposed as a more effective method in recent years. Compared with conventional point forecasting method, it shows a better performance on modelling the uncertainty of solar PV generation. Probabilistic forecasting uses a range instead of a single point to represent forecasting results. The bound of range is based on results of point forecasting. In this dissertation project, multiple linear regression (MLR) and radial basis function neural network (RBFNN) are used to build the model for point forecasting. Load consumption data and solar irradiance data are utilized as input features, also the target would need to be predicted in two different models of MLR and RBFNN. Then, prediction intervals (PIs) are produced based on the results of point forecasting by using a nonparametric PIs formation method. Coverage probability and interval scores are used as PIs metrics to evaluate the PIs performance.
Schools: School of Electrical and Electronic Engineering 
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Theses

Files in This Item:
File Description SizeFormat 
Probabilistic Forecasting of Solar PV Power Generation.pdf
  Restricted Access
3.01 MBAdobe PDFView/Open

Page view(s)

Updated on Jun 22, 2024


Updated on Jun 22, 2024

Google ScholarTM


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