• Energy Research

The digitalization of the power distribution grid has surged over the past decade. This transformation has given rise to a host of new data-driven applications focused on condition monitoring and predictive maintenance. However, from the perspective of the distribution system operator, there remains uncertainty about what and how digital maintenance processes can be realized. Additionally, the lack of clarity regarding the relative payback of investments makes it difficult to plan investments in digital maintenance systems optimally. The existing literature does not provide a holistic investigation of proactive maintenance applications, specifically the interplay between how data selection, usage, and degree of digitalization impacts the development of proactive maintenance applications. In this paper, we therefore study the chain of design choices linked to the development of proactive maintenance systems, through a scoping review of existing approaches. Thereby, we offer a valuable resource for power distribution system operators in guiding their decision-making and implementation processes. Additionally, it enables us to point out gaps in existing literature, which can inform future studies. Furthermore, we provide an extendable Sankey diagram-based visualization tool, which enables researchers and practitioners alike to further investigate the complex relationships between proactive maintenance design choices. Eventually, we propose a conceptual model for power distribution systems operators to better understand the benefits of digitally enabled proactive maintenance systems, which can aid investment decision-making.

The digitalization of the power distribution grid has surged over the past decade. This transformation has given rise to a host of new data-driven applications focused on condition monitoring and predictive maintenance. However, from the perspective of the distribution system operator, there remains uncertainty about what and how digital maintenance processes can be realized. Additionally, the lack of clarity regarding the relative payback of investments makes it difficult to plan investments in digital maintenance systems optimally. The existing literature does not provide a holistic investigation of proactive maintenance applications, specifically the interplay between how data selection, usage, and degree of digitalization impacts the development of proactive maintenance applications. In this paper, we therefore study the chain of design choices linked to the development of proactive maintenance systems, through a scoping review of existing approaches. Thereby, we offer a valuable resource for power distribution system operators in guiding their decision-making and implementation processes. Additionally, it enables us to point out gaps in existing literature, which can inform future studies. Furthermore, we provide an extendable Sankey diagram-based visualization tool, which enables researchers and practitioners alike to further investigate the complex relationships between proactive maintenance design choices. Eventually, we propose a conceptual model for power distribution systems operators to better understand the benefits of digitally enabled proactive maintenance systems, which can aid investment decision-making.

Power and district heating networks constitute critical infrastructures that play central roles in the renewable energy transition of our society. The maintenance practices for many energy distribution network assets have historically been reactive. As the networks age failure becomes more frequent. These failures lead to supply disruptions, decreased reliability and energy efficiency, and economic losses. The central aim of this doctoral thesis is therefore to develop, improve, and demonstrate proactive maintenance technologies for energy distribution networks, effectively increasing technology readiness levels. Energy distribution networks are governed by incomplete and limited failure data for assets whose observability is low. The majority of the contributions of the thesis therefore target these areas specifically. Through a collection of papers, this thesis suggests data representations, modeling approaches, and parameter estimation techniques that enable a shift in maintenance practices from reactive to proactive reliability-centered and predictive maintenance approaches. The common denominator through most of the proposed methods is the use of third-party data to describe assets’ environmental working conditions, feature engineering, and imbalanced learning techniques. Initial contributions focus on data-driven maintenance prioritization for cable replacement planning and planning thermographic inspections of district heating pipes, while later contributions reapply the central concepts for failure rate predictions and riskbased asset-maintenance planning. The use of existing data and metering infrastructure is a requirement for all tools proposed in this thesis. Therefore, the thesis investigates the feasibility of integrating smart meter data into long and short-term proactive maintenance practices.The tools developed throughout the Ph.D. project are applied to and validated on data from several Danish energy distribution systems, showing the practical feasibility of the proposed tools. These results indicate a significant value in transitioning to data-driven reliability-centered maintenance approaches. They also show that asset management procedures may be improved and the models used to attune investments in asset maintenance. Nevertheless, the results also highlight several barriers to the deployment of proactive maintenance approaches in energy distribution systems. Specifically, the relative youth of district heating pipes makes it hard to discern among distributional assumptions regarding the pipes’ time to failure distribution. While the results show that third-party proxy features and feature engineering improve failure predictions, these build on limited data and thus would benefit from validation on bigger and more comprehensive datasets. Additionally, incomplete tracking of time-varying features of the pipes and cables does not allow for detailed modeling of the time-varying effects of these features. Lastly, the use of smart meter data for long and short-term proactive maintenance is challenged by low data collection frequencies and relatively uncongested network conditions in power systems. El- og fjernvarmenetværker udgør kritiske infrastrukturer, der spiller en central rolle i vores samfunds overgang til vedvarende energi. Vedligeholdelsespraksisser for mange energidistributionsnetværker har historisk set været reaktive. Når netværkene ældes, bliver fejl hyppigere. Disse fejl fører til forsyningsafbrydelser, reduceret pålidelighed og energieffektivitet samt økonomiske tab. Det centrale mål med denne ph.d.-afhandling er derfor at udvikle, forbedre og demonstrere proaktive vedligeholdelsesteknologier til energidistributionsnetværker og dermed øge teknologi-parathedsniveauet.Energidistributionsnetværker styres af ufuldstændige og begrænsede fejldata for aktiver med lav observerbarhed. Størstedelen af afhandlingens bidrag er derfor målrettet disse områder specifikt. Gennem en samling af artikler foreslår denne afhandling datarepræsentationer, modelleringsmetoder og parameterestimeringsteknikker, der muliggør et skift i vedligeholdelsespraksisser fra reaktive til proaktive, pålidelighedscentrerede og prædiktive vedligeholdelsesmetoder.Fællesnævneren gennem de fleste af de foreslåede metoder er brugen af tredjepartsdata til at beskrive aktivers miljømæssige arbejdsforhold, feature engineering og ubalancerede læringsteknikker. De indledende bidrag fokuserer på datadrevet vedligeholdelsesprioritering for kabeludskiftningsplanlægning og planlægning af termografiske inspektioner af fjernvarmerør, mens senere bidrag genanvender de centrale koncepter til fejlrateforudsigelser og risikobaseret vedligeholdelsesplanlægning. Brugen af eksisterende data og måleinfrastrukturer er et krav for alle de værktøjer, der foreslås i denne afhandling. Derfor undersøger afhandlingen muligheden for at integrere data fra smarte målere i både langsigtede og kortsigtede proaktive vedligeholdelsespraksisser. De værktøjer, der er udviklet gennem ph.d.-projektet, anvendes på og valideres med data fra flere danske energidistributionssystemer, hvilket viser den praktiske gennemførlighed af de foreslåede værktøjer. Disse resultater indikerer en betydelig værdi i overgangen til datadrevne, pålidelighedscentrerede vedligeholdelsesmetoder. De viser også, at asset management procedurer kan forbedres, og modellerne kan justere investeringsniveauet i aktivernes vedligeholdelse. Resultaterne fremhæver dog også en række barrierer for implementeringen af proaktive vedligeholdelsesmetoder i energidistributionssystemer. Specifikt gør fjernvarmerørenes relative ungdom det svært at skelne mellem distributionsantagelser vedrørende rørenes tid til fejl fordeling. Mens resultaterne viser, at tredjeparts proxy variable samt fremstillede variable forbedrer fejlforudsigelser, bygger disse på begrænsede data og ville derfor have gavn af validering på større og mere omfattende datasæt. Desuden tillader ufuldstændig sporing af tidsvarierende variable for rør og kabler ikke detaljeret modellering af disse variables tidsvarierende effekter. Endelig udfordres brugen af data fra smarte målere til langsigtet og kortsigtet proaktiv vedligeholdelse af lave datainsamlingsfrekvenser og relativt umættede netværksforhold i elsystemer.

Power and district heating networks constitute critical infrastructures that play central roles in the renewable energy transition of our society. The maintenance practices for many energy distribution network assets have historically been reactive. As the networks age failure becomes more frequent. These failures lead to supply disruptions, decreased reliability and energy efficiency, and economic losses. The central aim of this doctoral thesis is therefore to develop, improve, and demonstrate proactive maintenance technologies for energy distribution networks, effectively increasing technology readiness levels. Energy distribution networks are governed by incomplete and limited failure data for assets whose observability is low. The majority of the contributions of the thesis therefore target these areas specifically. Through a collection of papers, this thesis suggests data representations, modeling approaches, and parameter estimation techniques that enable a shift in maintenance practices from reactive to proactive reliability-centered and predictive maintenance approaches. The common denominator through most of the proposed methods is the use of third-party data to describe assets’ environmental working conditions, feature engineering, and imbalanced learning techniques. Initial contributions focus on data-driven maintenance prioritization for cable replacement planning and planning thermographic inspections of district heating pipes, while later contributions reapply the central concepts for failure rate predictions and riskbased asset-maintenance planning. The use of existing data and metering infrastructure is a requirement for all tools proposed in this thesis. Therefore, the thesis investigates the feasibility of integrating smart meter data into long and short-term proactive maintenance practices.The tools developed throughout the Ph.D. project are applied to and validated on data from several Danish energy distribution systems, showing the practical feasibility of the proposed tools. These results indicate a significant value in transitioning to data-driven reliability-centered maintenance approaches. They also show that asset management procedures may be improved and the models used to attune investments in asset maintenance. Nevertheless, the results also highlight several barriers to the deployment of proactive maintenance approaches in energy distribution systems. Specifically, the relative youth of district heating pipes makes it hard to discern among distributional assumptions regarding the pipes’ time to failure distribution. While the results show that third-party proxy features and feature engineering improve failure predictions, these build on limited data and thus would benefit from validation on bigger and more comprehensive datasets. Additionally, incomplete tracking of time-varying features of the pipes and cables does not allow for detailed modeling of the time-varying effects of these features. Lastly, the use of smart meter data for long and short-term proactive maintenance is challenged by low data collection frequencies and relatively uncongested network conditions in power systems. El- og fjernvarmenetværker udgør kritiske infrastrukturer, der spiller en central rolle i vores samfunds overgang til vedvarende energi. Vedligeholdelsespraksisser for mange energidistributionsnetværker har historisk set været reaktive. Når netværkene ældes, bliver fejl hyppigere. Disse fejl fører til forsyningsafbrydelser, reduceret pålidelighed og energieffektivitet samt økonomiske tab. Det centrale mål med denne ph.d.-afhandling er derfor at udvikle, forbedre og demonstrere proaktive vedligeholdelsesteknologier til energidistributionsnetværker og dermed øge teknologi-parathedsniveauet.Energidistributionsnetværker styres af ufuldstændige og begrænsede fejldata for aktiver med lav observerbarhed. Størstedelen af afhandlingens bidrag er derfor målrettet disse områder specifikt. Gennem en samling af artikler foreslår denne afhandling datarepræsentationer, modelleringsmetoder og parameterestimeringsteknikker, der muliggør et skift i vedligeholdelsespraksisser fra reaktive til proaktive, pålidelighedscentrerede og prædiktive vedligeholdelsesmetoder.Fællesnævneren gennem de fleste af de foreslåede metoder er brugen af tredjepartsdata til at beskrive aktivers miljømæssige arbejdsforhold, feature engineering og ubalancerede læringsteknikker. De indledende bidrag fokuserer på datadrevet vedligeholdelsesprioritering for kabeludskiftningsplanlægning og planlægning af termografiske inspektioner af fjernvarmerør, mens senere bidrag genanvender de centrale koncepter til fejlrateforudsigelser og risikobaseret vedligeholdelsesplanlægning. Brugen af eksisterende data og måleinfrastrukturer er et krav for alle de værktøjer, der foreslås i denne afhandling. Derfor undersøger afhandlingen muligheden for at integrere data fra smarte målere i både langsigtede og kortsigtede proaktive vedligeholdelsespraksisser. De værktøjer, der er udviklet gennem ph.d.-projektet, anvendes på og valideres med data fra flere danske energidistributionssystemer, hvilket viser den praktiske gennemførlighed af de foreslåede værktøjer. Disse resultater indikerer en betydelig værdi i overgangen til datadrevne, pålidelighedscentrerede vedligeholdelsesmetoder. De viser også, at asset management procedurer kan forbedres, og modellerne kan justere investeringsniveauet i aktivernes vedligeholdelse. Resultaterne fremhæver dog også en række barrierer for implementeringen af proaktive vedligeholdelsesmetoder i energidistributionssystemer. Specifikt gør fjernvarmerørenes relative ungdom det svært at skelne mellem distributionsantagelser vedrørende rørenes tid til fejl fordeling. Mens resultaterne viser, at tredjeparts proxy variable samt fremstillede variable forbedrer fejlforudsigelser, bygger disse på begrænsede data og ville derfor have gavn af validering på større og mere omfattende datasæt. Desuden tillader ufuldstændig sporing af tidsvarierende variable for rør og kabler ikke detaljeret modellering af disse variables tidsvarierende effekter. Endelig udfordres brugen af data fra smarte målere til langsigtet og kortsigtet proaktiv vedligeholdelse af lave datainsamlingsfrekvenser og relativt umættede netværksforhold i elsystemer.

The transition towards sustainable practices and a reliable electricity grid accommodates the rising electrification of the heating and transportation sectors. Aging, environmental factors, and operational conditions of electrical grid infrastructure contribute to a higher likelihood of faults. This leads to a reduced level of reliability, emphasizing the importance of renewing electrical grid infrastructure, particularly underground cables. Optimally replacing cables is essential, taking into account various factors like reducing the fault probability, minimizing the cost of power outages, and enhancing reliability within the budgetary constraint. This paper introduces an innovative methodology to predictive asset management for replacing underground cables using multi-objective optimization approach. Three objective functions are formulated: number of replaced cables, cost of power outages, and interruption-related index, which is determined through metrics like SAIFI, SAIDI, and ASIDI. These objectives are modeled as mixed-integer programming creating a multi-objective optimization problem, which is addressed using the epsilon-constraint approach. The optimization model identifies the cables that should be replaced within the budget constraint, aiming to optimize the objectives. The effectiveness of this approach is assessed using a real Danish distribution grid. The findings indicate that, compared to methods based on the cable age, fault vulnerability, and risk assessment, the proposed method demonstrates superior performance in terms of reliability metrics and power outage cost.

The transition towards sustainable practices and a reliable electricity grid accommodates the rising electrification of the heating and transportation sectors. Aging, environmental factors, and operational conditions of electrical grid infrastructure contribute to a higher likelihood of faults. This leads to a reduced level of reliability, emphasizing the importance of renewing electrical grid infrastructure, particularly underground cables. Optimally replacing cables is essential, taking into account various factors like reducing the fault probability, minimizing the cost of power outages, and enhancing reliability within the budgetary constraint. This paper introduces an innovative methodology to predictive asset management for replacing underground cables using multi-objective optimization approach. Three objective functions are formulated: number of replaced cables, cost of power outages, and interruption-related index, which is determined through metrics like SAIFI, SAIDI, and ASIDI. These objectives are modeled as mixed-integer programming creating a multi-objective optimization problem, which is addressed using the epsilon-constraint approach. The optimization model identifies the cables that should be replaced within the budget constraint, aiming to optimize the objectives. The effectiveness of this approach is assessed using a real Danish distribution grid. The findings indicate that, compared to methods based on the cable age, fault vulnerability, and risk assessment, the proposed method demonstrates superior performance in terms of reliability metrics and power outage cost.

Aging infrastructure in energy distribution networks, e.g., electrical distribution systems and district heating networks, increases components’ fault vulnerability. This decreases the security of supply and infers large costs on consumers and utilities alike. In this paper, we explore the application of geospatial data processing and machine learning as a means of grasping the complex relationship between pipes’ and cables’ physical working environment and their relative fault vulnerability. The paper presents the application of relative fault vulnerability prediction on a district heating network and an electrical distribution network. A large part of this work revolves around the treatment of data. In this regard, we demonstrate a method to combine geospatial data from different sources, namely environmental data, georeferenced fault observations, and the GIS of the case networks, and how to further augment the data with spatial fault clustering and expert knowledge, injected in the form of rule-based data reconstruction. Additionally, we propose a new data level imbalanced learning technique to handle the scarcity of fault observations. Our resultsconfirm, that our method outperforms traditional data level imbalanced learning techniques i.e., methods that change the data as opposed to changing the model or how it is trained. Our results also show that our model for relative faultvulnerability prediction effectively identifies failure-prone pipes and cables and outperforms age-based vulnerability ranking, which is a current industry practice.

Aging infrastructure in energy distribution networks, e.g., electrical distribution systems and district heating networks, increases components’ fault vulnerability. This decreases the security of supply and infers large costs on consumers and utilities alike. In this paper, we explore the application of geospatial data processing and machine learning as a means of grasping the complex relationship between pipes’ and cables’ physical working environment and their relative fault vulnerability. The paper presents the application of relative fault vulnerability prediction on a district heating network and an electrical distribution network. A large part of this work revolves around the treatment of data. In this regard, we demonstrate a method to combine geospatial data from different sources, namely environmental data, georeferenced fault observations, and the GIS of the case networks, and how to further augment the data with spatial fault clustering and expert knowledge, injected in the form of rule-based data reconstruction. Additionally, we propose a new data level imbalanced learning technique to handle the scarcity of fault observations. Our resultsconfirm, that our method outperforms traditional data level imbalanced learning techniques i.e., methods that change the data as opposed to changing the model or how it is trained. Our results also show that our model for relative faultvulnerability prediction effectively identifies failure-prone pipes and cables and outperforms age-based vulnerability ranking, which is a current industry practice.

AbstractNon-convex scheduling of energy production allows for more complex models that better describe the physical nature of the energy production system. Solutions to non-convex optimization problems can only be guaranteed to be local optima. For this reason, there is a need for methodologies that consistently provide low-cost solutions to the non-convex optimal scheduling problem. In this study, a novel Monte Carlo Tree Search initialization method for branch and bound solvers is proposed for the production planning of a combined heat and power unit with thermal heat storage in a district heating system. The optimization problem is formulated as a non-convex mixed-integer program, which is incorporated in a sliding time window framework. Here, the proposed initialization method offers lower-cost production planning compared to random initialization for larger time windows. For the test case, the proposed method lowers the yearly operational cost by more than 2,000,000 DKK per year. The method is one step in the direction of more reliable non-convex optimization that allows for more complex models of energy systems.