Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Live power generation predictions via AI-driven resilient systems in smart microgrids

Wang, Xueyi, Li, Shancang and Iqbal, Muddesar 2024. Live power generation predictions via AI-driven resilient systems in smart microgrids. IEEE Transactions on Consumer Electronics 70 (1) , pp. 3875-3884. 10.1109/TCE.2024.3371256

[thumbnail of TCE_Final.pdf]
Preview
PDF - Accepted Post-Print Version
Download (2MB) | Preview

Abstract

The 5G technology can significantly benefit smart consumer devices powered by microgrids in several ways, enhancing their efficiency, reliability, and overall performance, which play a pivotal role in advancing consumer electronics by providing a more reliable, efficient, and sustainable source of power for these devices. The growing environmental awareness and emergence of new technologies have made smart microgrids a good renewable and resilient power to serve consumer electronics. This work developed a secure AI-driven predictable and resilient power generation system for efficient microgrid energy use and management. Specifically, we first developed an intelligent power generation forecasting model based on a joint distribution of power generation and weather data; then, a resilient eXtreme Gradient Boosting (XGBoost) power generation forecast model was proposed that allows incorporating the weather intermittency in the joint distribution. The scheme has been validated using real-time power generation data together with weather data. The experimental results show that the proposed scheme can provide a more accurate and robust prediction of the microgrid against weather intermittency.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Publisher: Institute of Electrical and Electronics Engineers
ISSN: 0098-3063
Date of First Compliant Deposit: 28 February 2024
Date of Acceptance: 20 February 2024
Last Modified: 07 Jun 2024 15:30
URI: https://orca.cardiff.ac.uk/id/eprint/166597

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics