Electrical and Computer Engineering ETDs

Publication Date

Spring 4-7-2022

Abstract

Due to the increasing use of photovoltaic systems, power grids are vulnerable to the projection of shadows from moving clouds. An intra-hour solar forecast provides power grids with the capability of automatically controlling the dispatch of energy, reducing the additional cost for a guaranteed, reliable supply of energy (i.e., energy storage). This dissertation introduces a novel sky imager consisting of a long-wave radiometric infrared camera and a visible light camera with a fisheye lens. The imager is mounted on a solar tracker to maintain the Sun in the center of the images throughout the day, reducing the scattering effect produced by the Sun's direct radiation. Features of the cloud dynamics are analyzed to compute the probability of the Sun intercepting air parcels in the sky images. Probabilistic and deterministic multi-task intra-hour solar forecasting algorithms are introduced, based on kernel and deep learning methods, to increase the penetration of photovoltaic systems in power grids.

Keywords

computer vision, deep learning, kernel learning, machine learning, sky imaging, solar forecasting.

Sponsors

King Felipe VI Endowed Chair of the University of New Mexico, and the National Science Foundation (NSF) Established Program to Stimulate Competitive Research (EPSCoR) grant number OIA-175720

Document Type

Dissertation

Language

English

Degree Name

Electrical Engineering

Level of Degree

Doctoral

Department Name

Electrical and Computer Engineering

First Committee Member (Chair)

Prof. Manel Martínez-Ramón

Second Committee Member

Prof. Ramiro Jordan

Third Committee Member

Prof. Trilce Estrada

Third Advisor

Prof. Manel Martínez-Ramón

Fourth Committee Member

Prof. Ali Bidram

Share

COinS