Electricity needs to be consumed when it is produced, making sure that supply closely meets demand at all times. To account for the rapidly changing operational status and the need for increasing the flexibility of power systems, financial instruments have been put in place creating markets where electricity is traded as a commodity across different time frames; from months or days to minutes before, or even after, planned delivery. In this work, the focus is placed on the short-term electricity markets and particularly on forecasting the intraday volume-weighted average price of the last three hours of trading of hourly power products. To this end, two state-of-the-art recurrent neural network architectures, namely the Temporal Fusion Transformer and the DeepAR network, are compared against well-established statistical models, such as the Linear Regression, ARX and SARIMAX models, with respect to their forecast accuracy on each of the 24 hourly delivery products. Two different experimental setups are applied, with one utilizing two input features drawn specifically from the findings of relevant literature and the other blindly exploiting all available streams of information in either their raw or aggregated form. All models are trained individually per hourly product per experimental setup to support a fair and decisive comparison, leading to 240 unique model instances being trained in total. Furthermore, the input feature importance is inferred by exploiting the inbuilt attention mechanism of the Temporal Fusion Transformer architecture. Finally, by using various realworld historical market data originating from the Nord Pool power exchange as well as from the Svenska Kraftnät, available up until the day of delivery, it is shown that the statistical models outperform both contemporary neural network architectures, with the latter suffering from the inability to generalize to elevated price levels—which are absent from the training dataset. / El måste förbrukas när den produceras, och se till att utbudet alltid motsvarar efterfrågan. För att ta hänsyn till den snabbt föränderliga operativa statusen och behovet av att öka flexibiliteten i kraftsystemen har finansiella instrument införts för att skapa marknader där el handlas som en vara över olika tidsramar; från månader eller dagar till minuter före, eller till och med efter, planerad leverans. I detta arbete läggs fokus på de kortsiktiga elmarknaderna och särskilt på att prognostisera det intradagsvolymvägda genomsnittspriset för de senaste tre timmarnas handel med timkraftprodukter. För detta ändamål jämförs två toppmoderna återkommande neurala nätverksarkitekturer, nämligen Temporal Fusion Transformer och DeepAR-nätverket, mot väletablerade statistiska modeller, såsom modellerna Linear Regression, ARX och SARIMAX, med avseende på deras prognosnoggrannhet för var och en av 24-timmarsleveransprodukterna. Två olika experimentella uppsättningar tillämpas, där den ena använder två indatafunktioner som hämtats specifikt från resultaten av relevant litteratur och den andra utnyttjar blint alla tillgängliga informationsströmmar i antingen deras råa eller aggregerade form. Alla modeller tränas individuellt per timprodukt per experimentuppställning för att stödja en rättvis och avgörande jämförelse, vilket leder till att 240 unika modellinstanser tränas totalt. Dessutom härleds ingångsfunktionens betydelse genom att utnyttja den inbyggda uppmärksamhetsmekanismen i Temporal Fusion Transformer-arkitekturen. Slutligen, genom att använda olika verkliga historiska marknadsdata från elbörsen Nord Pool såväl som från Svenska Kraftnät, tillgängliga fram till leveransdagen, visas att de statistiska modellerna överträffar både moderna neurala nätverksarkitekturer, med sistnämnda lider av oförmågan att generalisera till förhöjda prisnivåer — som saknas i utbildningsdataset.

This thesis develops and applies methodological approaches for the analysis of intraday markets for electricity which are organised as continuous double auctions. The focus is to improve the understanding of how balancing forecast errors from weather-dependent renewable energy sources influences the outcomes of continuous intraday markets. This is important as it helps to assess how large amounts of renewable capacity can be utilised cost-efficiently and without stressing security of supply. In a first step, the thesis proposes a (non-mathematical) model of a continuous intraday market to show how the direction of the forecast error determines transactions between market participants, how these transactions relate to the formation of prices, and how the market integration of renewables can be improved. In a second step, the thesis provides a foundation for quantitative market analyses by modelling price-setting decisions for power generators and electricity demanders. This makes it possible to show that information on market participants' technical characteristics enables informed predictions of their market behaviour. In a third step, the thesis presents a computer simulation of a continuous intraday market. Implementing the simulation approach for the German power system allows calculation of the costs associated with the uncertain feed-in from renewables.

This thesis develops and applies methodological approaches for the analysis of intraday markets for electricity which are organised as continuous double auctions. The focus is to improve the understanding of how balancing forecast errors from weather-dependent renewable energy sources influences the outcomes of continuous intraday markets. This is important as it helps to assess how large amounts of renewable capacity can be utilised cost-efficiently and without stressing security of supply. In a first step, the thesis proposes a (non-mathematical) model of a continuous intraday market to show how the direction of the forecast error determines transactions between market participants, how these transactions relate to the formation of prices, and how the market integration of renewables can be improved. In a second step, the thesis provides a foundation for quantitative market analyses by modelling price-setting decisions for power generators and electricity demanders. This makes it possible to show that information on market participants' technical characteristics enables informed predictions of their market behaviour. In a third step, the thesis presents a computer simulation of a continuous intraday market. Implementing the simulation approach for the German power system allows calculation of the costs associated with the uncertain feed-in from renewables.

L’objectif de cette thèse est d’étudier les nouvelles dynamiques et leurs impacts dans le secteur de l'électricité. Elle discute des sujets critiques d’après les perspectives de la macroéconomie, de la configuration structurelle, et de la transition vers des sources d'énergie renouvelables. Plus précisément, trois sujets se dégagent: le lien entre la consommation d'électricité et la croissance économique, les impacts de l'intégration verticale entre les producteurs et les détaillants, et les impacts d'intégration de production d'énergie renouvelable intermittente. En mettant en jeu ces trois sujets, elle tente d’apporter des réponses aux défis principaux de la sécurité d'approvisionnement, de la compétitivité, et de la durabilité du développement énergétique. En donnant de nouvelles orientations dans la recherche sur l’économie de l’énergie, elle servira à éclairer des débats politiques. / The objective of this thesis is to study the new dynamics and their impacts in the electricity sector. It discusses the critical issues from the perspectives of macroeconomics, structural configuration, and a transition to renewable energy sources. More precisely, three topics emerge: the nexus between electricity consumption and economic growth, the impacts of vertical integration between power generators and retailers, and the market impacts and integration issues of intermittent renewable generation. By studying these three topics, it provides answers to the key challenges of supply security, competitiveness and sustainable development in the energy sector. By giving new research directions of energy economics, it serves to inspire related policy debates.

The high penetration of renewable energies (RE) in power systems is increasing the volatile production on the generation side and the presence of distributed energy resources (DER) over the territory. On the other hand, Virtual Power Plants (VPPs) are an aggregation of DER managed as a single entity to promote flexibility services to power systems. Therefore, VPPs are a valid approach to cope with the arising challenges in the power system related to RE penetration. This report defines the concept of a utility-scale VPP, as a tool to stabilize the grid and increase the flexibility capacity in power systems. For this purpose, the report places special emphasis in the use cases that can be developed with a utility-scale VPP. Nevertheless, implementing a utility-scale VPP is a complex procedure, as VPP solutions are highly customizable depending on the scope and the conditions of each project. For this reason, this report analyses the main factors that must be taken into account when implementing a VPP solution. The report concludes that the two most critical factors that define the viability of a VPP project are, first, the energy market design and regulatory framework and second, the technical requirements. These two must always align with the scope of the project and the use cases intended to be developed. Further, other minor factors, including a cost estimate for a VPP solution, are also considered in the report. / Den höga penetrationen av förnybara energier i kraftsystem ökar den flyktiga produktionen på produktionssidan och närvaron av distribuerade energiresurser över territoriet. Å andra sidan är virtuella kraftverk en sammanställning av distribuerade energiresurser som hanteras som en enda enhet för att främja flexibilitetstjänster till kraftsystem. Därför är virtuella kraftverk: er en giltig strategi för att hantera de uppkomna utmaningarna i kraftsystemet relaterat till förnybara energier genomslag. I denna rapport definieras konceptet med en virtuella kraftverk verktygsskala som ett verktyg för att stabilisera nätet och öka flexibilitetskapaciteten i kraftsystem. För detta ändamål lägger rapporten särskild tonvikt på användningsfall som kan utvecklas med en virtuella kraftverk-nytta. Trots det är implementering av en virtuella kraftverknyckelskala en komplex procedur, eftersom virtuella kraftverk-lösningar är mycket anpassningsbara beroende på omfattning och villkor för varje projekt. Av denna anledning analyserar denna rapport de viktigaste faktorerna som måste beaktas vid implementering av en VPP-lösning. Rapporten drar slutsatsen att de två mest kritiska faktorerna som definierar ett virtuella kraftverk projekts livskraft är, dels energimarknadens utformning och regelverk och för det andra de tekniska kraven. Dessa två måste alltid anpassa sig till projektets omfattning och användningsfall som är avsedda att utvecklas. Vidare beaktas även andra mindre faktorer, inklusive en kostnadsuppskattning för en virtuella kraftverk lösning, i rapporten.

Electricity is an essential good, which can hardly be replaced. It can be produced thanks to a wide rangeof sources, from coal to nuclear, not to mention renewables such as wind and solar. In order to meetdemand at the lowest cost, an optimisation is made on electricity markets between the differentproduction plants. This optimisation mainly relies on the electricity production cost of each technology.In order to include long-term constraints in the short-term optimisation, a so-called use value (oropportunity cost) can be computed and added to the production cost. One long-term constraint thatEDF, the main French electricity producer, is facing is that its gas plants cannot exceed a given numberof operation hours and starts between two maintenances. A specific software, DiMOI, computes usevalues for this double constraint but its parameters needs to be tested in order to improve thecomputation, as it is not thought to work properly.DiMOI relies on dynamic programming and more particularly on an algorithm called Bellman algorithm.The software has been tested with EDF R&D department in order to propose some modellingimprovements. Electricity and gas market prices, together with real plant parameters such as startingcosts, operating costs and yields, were used as inputs for this work, and the results were checkedagainst reality.This study gave some results but they appeared to be invalid. Indeed, an optimisation problem wasdiscovered in DiMOI computing core: on a deterministic context, a study with little degrees of freedomwas giving better profits than a study with more degrees of freedom. This problem origin was notfound precisely with a first investigation, and the R&D team expected the fixing time to be very long.The adaptation of a simpler tool (MaStock) was proposed and made in order to replace DiMOI. Thisproject has thus led to DiMOI giving up and its replacement by MaStock. Time was missing to testcorrectly this tool, and the first study which was made was not completely positive. Further studiesshould be carried out, for instance deterministic ones (using real past data) whose results could becompared to reality.Some complementary studies were made from a fictitious system, in order to study the impact of someparameters when computing use values and operations schedules. The conclusions of these studiesare the little impacts that changes in gas prices and start-up costs parameters have on the global resultsand the importance of an accurate choice in the time periods durations used for the computations.Unfortunately these conclusions might be too specific as they were made on short study periods.Further case studies should be done in order to reach more general conclusions.

The world is right now in a global transition from a fossil fuel dependency towards an electrified society based on green and renewable energy. Investments in power grid capacity are therefore needed to meet the increased future demand which this transition implicates. One part of this is the expansion of intermittent energy sources, such as wind and solar power. Even though these sources have benefits in form of cheap and green energy, they have other characteristics that need to be addressed. Per definition, intermittent power sources cannot produce energy on demand since they are dependent on weather conditions such as wind and sun. This induces a second problem which is that it can be hard to predict the production from intermittent power sources, especially wind, which increases the volatility in the power market. Because of these characteristics, the expansion of wind power has increased the volume traded on the intraday power market. The intermittent energy surge, emphasizes the need of a good trading strategy for balance responsible parties to handle the increased trading volume and volatility. The prupose of this report is to introduce the elements which affect intraday power trading, formulate the fundamentals of a power trading strategy and thereafter explore how predictive models can be used in such a strategy. This includes predicting regulating and intraday market prices using linear regression models, neural networks and LSTM-models. Furthermore, the report highlights underlying properties which affects the predictive power of a prediction model used to forecast wind power production. Regulating prices can be predicted well using both linear regression models and more complex deep learning models based on weather and market data. Both approaches are better than using a simple model based on the latest regulating and market price, since the simple model tends to fall short in a volatile market. Overall, the deep learning models performs the best.  The difference in result when predicting the volume weighted average price on the intraday market, using linear regression and machine learning, are not as substantial. In fact, the linear models tends to outperform the machine learning models in some instaces. The conclusion when analyzing how underlying properties affect wind power prediction models is that how far ahead the model predicts is not the key factor affecting predictive power. Instead, the production volume predicted has a larger effect.

[ES] Los Sistemas de Distribución de Calor Urbanos (SDCU) son una tecnología madura para el suministro eficiente de calor en las ciudades. En el contexto de la crisis climática y del objetivo de descarbonizar el sector de la calefacción, estos sistemas pueden desempeñar un papel muy importante. En principio, los SDCU existentes actualmente están basados principalmente en el uso de combustibles fósiles, por lo que forman parte del problema. Sin embargo, mediante la integración de plantas de generación de calor renovables, los SDCU pueden ofrecer un gran potencial para apoyar la transición hacia un suministro de calor sin combustibles fósiles. Esta transición se ve dificultada por diversas barreras. Por ejemplo, la necesidad de bajas temperaturas de suministro para que la integración de las plantas renovables de generación de calor sea rentable. Sin embargo, dado que las plantas de generación de calor fósiles existentes no se benefician de una reducción de la temperatura, existe un efecto de bloqueo en los modelos de negocio establecidos. En la investigación actual, la resolución de las barreras se centra en soluciones individuales para cuestiones específicas y en estrategias de calor para un nivel general. Como las barreras están fuertemente interrelacionadas, las empresas de distribución de calor urbano requieren una metodología de transición sistémica para sus actividades específicas en los diferentes ámbitos de planificación y operación. Tras constatar su ausencia en la bibliografía, la presente tesis pretende desarrollar una metodología integral que facilite dicha transición de forma rentable. Para la realización de esta tarea, esta tesis introduce un enfoque de marco que combina conceptos independientes nuevos y existentes, construyéndose sobre una estructura diseñada en los ocho «ámbitos» de interés de los SDCU. Estos ámbitos de los SDCU clasifican las actividades en los diferentes campos de las problemáticas de este tipo de sistemas. Para abordar las actividades de planificación y operación en las empresas de distribución de calor urbano, estas actividades se integran en el nuevo «marco» que se clasifica según los tres ámbitos de los SDCU: «diseño», «planificación operativa» y «operación». Dicho marco resume las actividades relacionadas según los procesos y las vincula mediante mecanismos técnicos y económicos. Estos mecanismos se plantean de forma que todas las actividades se incentiven para facilitar la transición. Se propone una nueva estructura organizativa que permita la introducción de la competencia, al mismo tiempo que el marco asegura la llamada suboptimización, la prevención del abuso de poder en el mercado y la restricción de las inversiones. Además, permite a los productores de calor independientes integrarse en el sistema. Complementariamente, el marco integra las tecnologías más relevantes que ofrecen flexibilidad al sistema para compensar las fluctuaciones de la producción. En esta tesis se ha desarrollado un marco adecuado para aplicar un «paradigma de transición» global a los SDCU existentes o futuros. Además, puede ser utilizado por los responsables políticos o municipales para mejorar las condiciones legales existentes y las estrategias locales de calor en relación con un sistema global. La tesis recomienda seguir investigando para la implementación del marco y una evaluación cuantitativa de la introducción de la competencia en los SDCU. / [CA] Els Sistemes de Distribució de Calor Urbans (SDCU) són una tecnologia madura per a la provisió eficient de calor a les ciutats. En el context de la crisi climàtica i de l'objectiu de descarbonitzar el sector de la calefacció, aquests sistemes poden exercir un paper molt important. En principi, els SDCU existents actualment estan basats principalment en l'ús de combustibles fòssils, per la qual cosa formen part del problema. No obstant això, mitjançant la integració de plantes de generació de calor renovables, els SDCU poden oferir un gran potencial per a donar suport a la transició cap a una provisió de calor sense combustibles fòssils. Aquesta transició es veu dificultada per diverses barreres. Per exemple, la necessitat de baixes temperatures de subministrament perquè la integració de les plantes renovables de generació de calor siga fructífera. No obstant això, atés que les plantes de generació de calor fòssils existents no es beneficien d'una reducció de la temperatura, existeix un efecte de bloqueig en els models de negoci establits. En la investigació actual, la resolució de les barreres se centra en solucions individuals per a qüestions específiques i en estratègies de calor per a un nivell general. Com les barreres estan fortament interrelacionades, les empreses de distribució de calor urbana requereixen una metodologia de transició sistèmica per a les seues activitats específiques en els diferents àmbits de planificació i operació. Després de constatar la seua absència en la bibliografia, la present tesi pretén desenvolupar una metodologia integral que facilite aquesta transició de manera profitosa. Per a la realització d'aquesta tasca, aquesta tesi introdueix un enfocament de marc que combina conceptes independents nous i existents, construint-se sobre una estructura dissenyada en els huit «àmbits» d'interés dels SDCU. Aquests àmbits dels SDCU classifiquen les activitats en els diferents camps de les problemàtiques d'aquest tipus de sistemes. Per a abordar les activitats de planificació i operació en les empreses de distribució de calor urbana, aquestes activitats s'integren en el nou «marc» que es classifica segons els tres àmbits dels SDCU: «disseny», «planificació operativa» i «operació». Aquest marc resumeix les activitats relacionades segons els processos i les vincula mitjançant mecanismes tècnics i econòmics. Aquests mecanismes es plantegen de manera que totes les activitats s'incentiven per a facilitar la transició. Es proposa una nova estructura organitzativa que permeta la introducció de la competència, al mateix temps que el marc assegura l'anomenada suboptimització, la prevenció de l'abús de poder en el mercat i la restricció de les inversions. A més, permet als productors de calor independents integrar-se en el sistema. Complementàriament, el marc integra les tecnologies més rellevants que ofereixen flexibilitat al sistema per a compensar les fluctuacions de la producció. En aquesta tesi s'ha desenvolupat un marc adequat per a aplicar un «paradigma de transició» global als SDCU existents o futurs. A més, pot ser utilitzat pels responsables polítics o municipals per a millorar les condicions legals existents i les estratègies locals de calor en relació amb un sistema global. La tesi recomana continuar investigant per a la implementació del marc i una avaluació quantitativa de la introducció de la competència en els SDCU. / [EN] District heating systems (DHSs) are a mature technology for an efficient heat supply in cities. In the context of the climate crisis and the related goal of a decarbonized heating sector, DHSs play an ambivalent role. As existing DHSs are mostly based on fossil fuels, they are part of the problem. However, as they can also integrate renewable heating plants, DHSs offer a great potential to support the transition towards a fossil-free heat supply. This transition is hindered by several barriers. For example, low supply temperatures are needed for the economically efficient integration of renewable heating plants. However, since existing fossil heating plants marginally benefit from a reduction of the temperature, a lock-in effect to the established business models exists. In the current research, resolving the barriers is focused either on individual solutions for specific issues or on heat strategies for a general level. Since the barriers are strongly interrelated, district heating (DH) companies require a systemic transition methodology for their specific activities in the different fields of planning and operation. Since such a transition methodology is identified as lacking in the literature, this thesis aims to develop a comprehensive methodology that facilitates the transition in an economically efficient way. To develop such a transition methodology, this thesis introduces a framework approach that combines new and existing independent concepts and that is built on a newly developed structure of eight "DH scopes." These DH scopes classify the activities in the different fields of DH concerns. To address the planning and operation activities in DH companies, these activities are integrated into the new "framework" that is classified according to the three DH scopes "design," "operative planning," and "operation." The framework summarizes the related activities according to processes and links them using technical and economic mechanisms. These mechanisms are considered in such a way that all activities are incentivized to facilitate the transition. A new organizational structure is proposed that allows for the introduction of competition while the framework secures so-called suboptimization, abuse of market power, or investment restraint. Independent heat producers are integrated in a system-serving way. The framework integrates the relevant technologies that offer flexibility to the system to compensate for fluctuation in production. In this thesis, a framework is devised that is suitable for implementing a comprehensive "transition paradigm" to existing or future DHSs. Further, it can be used by policymakers or municipalities to improve existing legal conditions and local heat strategies in relation to a comprehensive overall system. The thesis recommends further investigation for the implementation of the framework and a quantitative evaluation of the introduction of competition to DHSs. / Lorenzen, P. (2022). A Comprehensive Framework and Associated Methodology for the Design, Operative Planning, and Operation of District Heating Systems to Facilitate the Transition Towards a Fully Renewable Heat Supply [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/185882