A Multitask Integrated Deep-Learning Probabilistic Prediction for Load Forecasting

Wang, J; Wang, K; Li, Z; Lu, H; Jiang, H; Xing, Q

A Multitask Integrated Deep-Learning Probabilistic Prediction for Load Forecasting

Wang, J Wang, K Li, Z Lu, H

Jiang, H Xing, Q

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE Transactions on Power Systems, 2024, 39, (1), pp. 1240-1250
Issue Date:: 2024-01-01

Closed Access

	Filename	Description	Size
	A_Multitask_Integrated_Deep-Learning_Probabilistic_Prediction_for_Load_Forecasting.pdf	Published version	1.89 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Wang, J
dc.contributor.author	Wang, K
dc.contributor.author	Li, Z
dc.contributor.author	Lu, H https://orcid.org/0000-0001-5655-0237
dc.contributor.author	Jiang, H
dc.contributor.author	Xing, Q
dc.date.accessioned	2024-03-08T00:31:26Z
dc.date.available	2024-03-08T00:31:26Z
dc.date.issued	2024-01-01
dc.identifier.citation	IEEE Transactions on Power Systems, 2024, 39, (1), pp. 1240-1250
dc.identifier.issn	0885-8950
dc.identifier.issn	1558-0679
dc.identifier.uri	http://hdl.handle.net/10453/176326
dc.description.abstract	Spinning reserve without accurate load forecasting can lead to automatic disconnection of critical loads by under-frequency load shedding devices. Such a predicament poses a grave threat to the economic and social welfare of the affected region, and in extreme scenarios, can result in a debilitating grid collapse. However, existing models lack the deep feature extraction capability and cannot accurately predict the uncertainty of electricity demand. Thus, a multitask integrated deep-learning probabilistic prediction with multidimensional feature extraction based on granularity information and quantile regression is explored in this study to solve the insufficient feature extraction problem in probabilistic prediction. In the proposed scheme, we designed a multi-layer feature extraction framework, which information granularity based on fuzzy rough sets to extract time-domain features, multilayer Laplace operators to extract features globally, and quantile regression recurrent neural network variants to extract time context information. In addition, the Pareto integration method is extended to capture better individuals. The experimental results demonstrate that the proposed system can effectively improve deterministic forecasting and uncertainty analysis of electricity demand and manage daily fluctuations.
dc.language	English
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation.ispartof	IEEE Transactions on Power Systems
dc.relation.isbasedon	10.1109/TPWRS.2023.3257353
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0906 Electrical and Electronic Engineering
dc.subject.classification	Energy
dc.subject.classification	4008 Electrical engineering
dc.title	A Multitask Integrated Deep-Learning Probabilistic Prediction for Load Forecasting
dc.type	Journal Article
utslib.citation.volume	39
utslib.for	0906 Electrical and Electronic Engineering
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
dc.date.updated	2024-03-08T00:31:24Z
pubs.issue	1
pubs.publication-status	Published
pubs.volume	39
utslib.citation.issue	1

Abstract:

Spinning reserve without accurate load forecasting can lead to automatic disconnection of critical loads by under-frequency load shedding devices. Such a predicament poses a grave threat to the economic and social welfare of the affected region, and in extreme scenarios, can result in a debilitating grid collapse. However, existing models lack the deep feature extraction capability and cannot accurately predict the uncertainty of electricity demand. Thus, a multitask integrated deep-learning probabilistic prediction with multidimensional feature extraction based on granularity information and quantile regression is explored in this study to solve the insufficient feature extraction problem in probabilistic prediction. In the proposed scheme, we designed a multi-layer feature extraction framework, which information granularity based on fuzzy rough sets to extract time-domain features, multilayer Laplace operators to extract features globally, and quantile regression recurrent neural network variants to extract time context information. In addition, the Pareto integration method is extended to capture better individuals. The experimental results demonstrate that the proposed system can effectively improve deterministic forecasting and uncertainty analysis of electricity demand and manage daily fluctuations.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/176326