Managing Renewable Generation Fluctuations
Date
2016-12
Authors
Contributor
Advisor
Department
Instructor
Depositor
Speaker
Researcher
Consultant
Interviewer
Narrator
Transcriber
Annotator
Journal Title
Journal ISSN
Volume Title
Publisher
University of Hawaii at Manoa
Volume
Number/Issue
Starting Page
Ending Page
Alternative Title
Abstract
Energy and power production are essential to daily life. By the year 2030, HECO desires to increase renewable energy production up to 65%. Increasing renewable energy production will help reduce fuel burning to hopefully minimum. However, power produced from solar panels and wind turbines may be insufficient to meet the load conditions. Therefore, spinning reserves, which are back-up power fuel-burning devices, or energy storage systems such as batteries are used to make up for that power deficiency. These main two back-up plans must be very efficient and cost effective to quickly make up for power deficiency when renewable energy production decreases. The first step is to obtain aggregate power data from household appliances. Then, average power and probability curves of these household appliances will help determine the best-fit daily model of power demand and production in areas in Hawaii. The next step inputs this data and daily solar panel power into a complex valued neural network that considers several variables such as solar irradiation, relative humidity, daily air temperature, and sunshine duration. This neural network will learn patterns from this data to make predictions for short-term load forecasting. The aim of this study is to create a short-term load forecasting model with neural networks to demonstrate how much renewable energy is needed daily to power a home. Excess power can be stored in batteries and used when there is insufficient power from renewable energy sources. If there is sufficient power, then the user can live independently off the power grid.
Description
Keywords
Citation
Extent
96 pages
Format
Geographic Location
Time Period
Related To
Related To (URI)
Table of Contents
Rights
All UHM Honors Projects are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission from the copyright owner.
Rights Holder
Local Contexts
Collections
Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.