An Enhanced Short-term Forecasting of Wind Generating Resources based on Edge Computing in Jeju Carbon-Free Islands

Date

2024-01-03

Contributor

Advisor

Department

Instructor

Depositor

Speaker

Researcher

Consultant

Interviewer

Narrator

Transcriber

Annotator

Journal Title

Journal ISSN

Volume Title

Publisher

Volume

Number/Issue

Starting Page

2926

Ending Page

Alternative Title

Abstract

As the Internet-of-Things makes various types of sensing possible, edge computing has been developed to collect, store, and analyze vast amounts of data. It is becoming a great resource for future industries because unlike in cloud systems, large amounts of data can be processed efficiently and immediately near the source. After comparing the characteristics of cloud computing and edge computing techniques, SCADA systems in various countries were analyzed. Lastly, in this study, we propose an SLA architecture for wind power output forecast which uses data collected from edge computing. To validate the proposed method, we analyzed empirical data obtained from Korea wind farm based on ARIMAX and Monte-Carlo simulations and found that the NMAE (Normalized MAE) value for the forecasting period was about 2%. Therefore, this study focuses on increasing the flexibility of the distribution grid and look forward to deploying this architecture to energy management systems in South Korea.

Description

Keywords

Distributed, Renewable, and Mobile Resources, analog-ensemble model, edge computing, kriging-based spatial modeling, short-term wind power forecasting, statistical learning analysis

Citation

Extent

10 pages

Format

Geographic Location

Time Period

Related To

Proceedings of the 57th Hawaii International Conference on System Sciences

Related To (URI)

Table of Contents

Rights

Attribution-NonCommercial-NoDerivatives 4.0 International

Rights Holder

Local Contexts

Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.