kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Addressing Data Deficiencies in Outage Reports: A Qualitative and Machine Learning Approach
KTH, School of Electrical Engineering and Computer Science (EECS), Electrical Engineering, Electric Power and Energy Systems.ORCID iD: 0000-0002-6745-4918
KTH, School of Electrical Engineering and Computer Science (EECS), Electrical Engineering, Electromagnetic Engineering and Fusion Science.ORCID iD: 0000-0002-2964-7233
2024 (English)Conference paper (Other academic)
Abstract [en]

This study investigates outage statistics in the Swedish power system. More specifically, this paper delves into the critical analysis and enhancement of data quality, focusing on inconsistencies and missing values, i.e. unknown outage causes and unidentified faulty equipment. By carefully examining the data, noticeable gaps and deficiencies are revealed. Thus, a format for improving outage reporting using a database with 3 relations (outage summary, outage breakdown and customer breakdown) is proposed. In addition to a qualitative analysis of the data, various machine learning algorithms are explored and tested for their capability to predict the unknown values within the dataset, thereby offering a twofold solution: enhancing the accuracy of outage data and facilitating deeper, more accurate analytical capabilities. The findings and proposals within this work not only illuminate the current challenges within outage data management but also pave the way for more robust, data-driven decision-making in outage management and policy formation. 

Place, publisher, year, edition, pages
Paris, 2024.
Keywords [en]
Data analysis, Power outages, Machine learning, Decision-making, Data processing, Technical reports
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electrical Engineering
Identifiers
URN: urn:nbn:se:kth:diva-342705OAI: oai:DiVA.org:kth-342705DiVA, id: diva2:1831801
Conference
2024 Power Systems Computation Conference (PSCC), Paris, France
Funder
SweGRIDS - Swedish Centre for Smart Grids and Energy Storage, CP26Swedish Energy Agency
Note

QC 20240130

Available from: 2024-01-26 Created: 2024-01-26 Last updated: 2024-01-30Bibliographically approved
In thesis
1. Security of Electricity Supply in Power Systems: Establishing a Global Framework for Assessing Power System Health and Analyzing Outage Statistics in Sweden
Open this publication in new window or tab >>Security of Electricity Supply in Power Systems: Establishing a Global Framework for Assessing Power System Health and Analyzing Outage Statistics in Sweden
2024 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

The primary objective of this thesis is to enhance the security of electricity supply by providing a holistic perspective and introducing a comprehensive framework for assessing power system health. This novel approach aims for a thorough evaluation of the system’s overall performance and well-being, using the physical dimensions of the security of supply as the foundation for a power system health index. 

After establishing the theoretical framework, relevant and available data is collected in order to analyze and understand the system’s performance. By analyzing outage statistics in Sweden, the research identifies specific trends and performance metrics that can be further investigated and segmented according to various criteria. The insights gained from this research can, in turn, be used to inform proactive maintenance strategies and capacity planning, ultimately mitigating the risks of outages and ensuring a more reliable electricity supply. 

Outage statistics are furthermore analyzed from the aspect of data quality, focusing on inconsistencies and missing values in the outage reports, i.e. unknown outage causes and unidentified faulty equipment. By carefully examining the data, noticeable gaps and deficiencies are revealed. Thus, a format for improving outage reporting using a database with 3 relations (outage summary, outage breakdown and customer breakdown) is proposed. In addition to a qualitative analysis of the data, various machine learning algorithms are explored and tested for their capability to predict the unknown values within the dataset, thereby offering a twofold solution: enhancing the accuracy of outage data and facilitating deeper, more accurate analytical capabilities. The findings and proposals within this work highlight the current challenges within outage data management and also lay the groundwork for a more comprehensive, data-driven approach in outage management and policy development. 

Abstract [sv]

Det primära syftet med denna avhandling är att förbättra elförsörjningstryggheten genom att tillhandahålla ett holistiskt perspektiv och införa ett heltäckande ram- verk för att bedöma kraftsystemets hälsa. Detta nya tillvägagångssätt syftar till en grundlig utvärdering av systemets övergripande prestanda och välbefinnande, med hjälp av de fysiska dimensionerna av försörjningstryggheten som grunden för ett hälsoindex för kraftsystemet. 

Efter att ha upprättat det teoretiska ramverket samlas relevant och tillgäng- lig data in för att analysera och förstå systemets prestanda. Genom att analysera avbrottsstatistik i Sverige identifierar forskningen specifika trender och prestations- mått som kan undersökas ytterligare och segmenteras enligt olika kriterier. Insik- terna från denna forskning kan i sin tur användas för att informera om proaktiva underhållsstrategier och kapacitetsplanering, för att i slutändan minska riskerna för avbrott och säkerställa en mer tillförlitlig elförsörjning. 

Avbrottsstatistiken analyseras vidare ur aspekten datakvalitet, med fokus på inkonsekvenser och saknade värden i avbrottsrapporterna, det vill säga okända av- brottsorsaker och oidentifierad felaktig utrustning. Genom att noggrant granska uppgifterna avslöjas märkbara luckor och brister. Därför föreslås ett format för att förbättra avbrottsrapporteringen med hjälp av en databas med 3 relationer (avbrottsöversikt, avbrottsuppdelning och kunduppdelning). Förutom en kvalitativ analys av data, utforskas och testas olika maskininlärningsalgoritmer med avseen- de på deras förmåga att förutsäga de okända värdena i datamängden, och erbjuder därmed en tvåfaldig lösning: förbättrar avbrottsdatans noggrannhet och underlättar djupare, mer exakta analytiska möjligheter. Resultaten och förslagen inom detta arbete belyser de nuvarande utmaningarna inom hantering av avbrottsdata och lägger också grunden för ett mer omfattande, datadrivet tillvägagångssätt inom avbrottshantering och policyutveckling. 

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2024. p. 56
Series
TRITA-EECS-AVL ; 2024:11
Keywords
security of electricity supply, power system health, outage statistics, data analysis
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Electrical Engineering
Identifiers
urn:nbn:se:kth:diva-342706 (URN)978-91-8040-824-0 (ISBN)
Public defence
2024-02-19, https://kth-se.zoom.us/j/68367508107, Kollegiesalen, Brinellvägen 6, Stockholm, 13:00 (English)
Opponent
Supervisors
Funder
SweGRIDS - Swedish Centre for Smart Grids and Energy Storage, CP26
Note

QC 20240129

Available from: 2024-01-29 Created: 2024-01-29 Last updated: 2024-02-05Bibliographically approved

Open Access in DiVA

fulltext(562 kB)39 downloads
File information
File name FULLTEXT01.pdfFile size 562 kBChecksum SHA-512
00ef81ddaac3ea1bd8742410882af362153c9ae28ed7113baae66b380d0d6e695af17e93b45de9acee3709319ea0d232ca79b8efd1d7ebff8ddd522cea473088
Type fulltextMimetype application/pdf

Authority records

Duvnjak Zarkovic, SanjaWeiss, XavierHilber, Patrik

Search in DiVA

By author/editor
Duvnjak Zarkovic, SanjaWeiss, XavierHilber, Patrik
By organisation
Electric Power and Energy SystemsElectromagnetic Engineering and Fusion Science
Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 39 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 144 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf