A review on distribution system state estimation uncertainty issues using deep learning approaches

Y Raghuvamsi and Kiran Teeparthi

Renewable and Sustainable Energy Reviews, 2023, vol. 187, issue C

Abstract: This study highlights the research works on different uncertainty issues encountered in distribution system state estimation (DSSE). The DSSE plays a crucial role since the increasing use of renewable energy sources enforces the requirement of monitoring and controlling the distribution system for maintaining a resilient and efficient grid. The arrival of advanced intelligent devices together with the proper communication infrastructures has allowed the DSSE to maintain situational awareness of the system. DSSE imparts the solution of system states by processing the measurements received at the distribution management system. However, the uncertainties in the measurement data such as pseudo-measurement modeling, topology identification, and cyber attacks induce inaccurate solutions and convergence issues. In the modern scenario, machine learning (ML) algorithms and deep learning (DL) models are getting huge importance in various power system non-linear applications. In the recent literature, these ML algorithms and DL models have been applied to solve the uncertainty issues in DSSE to get an accurate solution. This study presents the various problems and challenges of DSSE input requirements which include accurate topology identification, observability, and accurate compensation of the measurements against false data injection attacks and denial-of-service attacks. Subsequently, the existing methods for handling the various uncertainty issues and the recent literature about the applicability of emerging ML/DL approaches in DSSE are discussed. Further, this review work highlights the importance of research in the direction of DSSE advancements so that more sophisticated ML/DL approaches can be developed to address DSSE in the future.

Keywords: Distribution system state estimation; Topology identification; Pseudo-measurements; False data injection attacks; Deep learning; Denial-of-service attacks (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S1364032123006093
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:rensus:v:187:y:2023:i:c:s1364032123006093

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/600126/bibliographic
http://www.elsevier. ... 600126/bibliographic

DOI: 10.1016/j.rser.2023.113752

Access Statistics for this article

Renewable and Sustainable Energy Reviews is currently edited by L. Kazmerski

More articles in Renewable and Sustainable Energy Reviews from Elsevier
Bibliographic data for series maintained by Catherine Liu ().