The purpose of this degree project is to analyze and investigate how digitalization will affect business modeling in the district heating business. The chosen approach to this degree project was an iterative, abductive method, in order to always use a feedback-analysis and to keep the project open for new findings. The interviews were a mix of a structured method and a qualitative approach. With the structured method, the findings from the interviews were similar and regarding the research topic, and the qualitative approach in some open questions led to matters that otherwise would have been unnoticed. The interviews were performed via e-mail, phone and through personal interviews. This degree project concluded that digitalization has an impact on business modeling in district heating. Digitalization will affect some elements in a major way, for example key resources that will be characterized by digitalization. The findings from this work showed that a business model operating in district heating in a time of digitalization should focus on three main parts: economy, environment and easy visualization. An optimization tool should focus on delivering a value that consist of these three, and the remaining elements should together contribute to that value proposition. / Syftet med detta examensarbete är att analysera och undersöka hur digitaliseringen kommer att påverka affärsmodellering inom fjärrvärmebranschen. Det valda tillvägagångssättet för detta examensarbete är en iterativ, abduktiv metod för att hela tiden återkoppla och hålla studien öppen för nya intryck. Intervjuerna är en kombination av strukturerad metod blandad med en kvalitativ ansats. Med den strukturerade metoden blir svaren inom samma ram samtidigt som den kvalitativa aspekten lockar fram svar som annars skulle passera obemärkta. Intervjuerna genomfördes via mail, telefon samt genom personliga intervjuer. Detta examensarbete drar slutsatsen att digitaliseringen kommer påverka affärsmodeller inom fjärrvärme. Digitaliseringen kommer påverka vissa element i större utsträckning som till exempel nyckelresurserser som kommer präglas av digitaliseringen. Upptäckterna från studien visar att en affärsmodell verksam inom fjärrvärme i en tid präglad av digitaliseringen ska fokusera på tre delar: ekonomi, miljö och lättförstådd visualisering. Ett optimeringsverktyg ska fokusera på att leverera ett värde som innehåller dem tre delarna och resterande element ska tillsammans bidra till det värdeerbjudandet.

Nowadays, reducing energy usage as well as reducing environmental impacts due to energy efficiency measurements is very common in the industrial sector. The objective of these measurements is to achieve better sustainable energy systems. Sandvik Materials Technology (SMT) AB, one of the business areas of the enterprise Sandvik AB, is not an exception in that field. The aim of this thesis project is to analyze how to use waste energy from the cooling of a steel plant for an internal district heating (DH) system within the industrial area of SMT AB located in Sandviken, Sweden. In order to reduce the energy use, the economic cost and the environmental impacts within the industrial area. In order to achieve the aim has been studied the heat pump devices as the system to transfer the waste heat from the cooling of the steel plant to the DH system. Therefore, after the introduction to the project (part 1: Introduction) and the explanation of the aim (part 2: Aim, methodology and delimitations), the basics of the heat pumps are studied and explained (part 3: Heat pumps theoretical study). After that, the knowledge acquired in part 3 is applied to define and calculate the heat pump system which fulfill the required objectives achieving the greatest energy, economical and environmental impacts reductions (part 4: Heat pump practical study). The achieved results show that there is a great opportunity to reduce the energy use within the industrial area (until 45300 MWh per year), the economical cost (until 2 millions euros per year) and the 2 CO emissions (until 2.3 millions of 2 CO kg per year1). Therefore, the conclusion is that it must be taken into account to build the heat pump system and also that the effort of finding possible energy efficiency measurements within the industrial sector must be one priority for all the industrial companies, not only because the possible potential economical reductions, but also because of the potential environmental impacts reductions.

Context. Heat load forecasting is an important part of district heating optimization. In particular, energy companies aim at minimizing peak boiler usage, optimizing combined heat and power generation and planning base production. To achieve resource efficiency, the energy companies need to estimate how much energy is required to satisfy the market demand. Objectives. We suggest an online machine learning algorithm for heat load forecasting. Online algorithms are increasingly used due to their computational efficiency and their ability to handle changes of the predictive target variable over time. We extend the implementation of online bagging to make it compatible to regression problems and we use the Fast Incremental Model Trees with Drift Detection (FIMT-DD) as the base model. Finally, we implement and incorporate to the algorithm a mechanism that handles missing values, measurement errors and outliers. Methods. To conduct our experiments, we use two machine learning software applications, namely Waikato Environment for Knowledge Analysis (WEKA) and Massive Online Analysis (MOA). The predictive ability of the suggested algorithm is evaluated on operational data from a part of the Karlshamn District Heating network. We investigate two approaches for aggregating the data from the nodes of the network. The algorithm is evaluated on 100 runs using the repeated measures experimental design. A paired T-test is run to test the hypothesis that the the choice of approach does not have a significant effect on the predictive error of the algorithm. Results. The presented algorithm forecasts the heat load with a mean absolute percentage error of 4.77\%. This means that there is a sufficiently accurate estimation of the actual values of the heat load, which can enable heat suppliers to plan and manage more effectively the heat production. Conclusions. Experimental results show that the presented algorithm can be a viable alternative to state-of-the-art algorithms that are used for heat load forecasting. In addition to its predictive ability, it is memory-efficient and can process data in real time. Robust heat load forecasting is an important part of increased system efficiency within district heating, and the presented algorithm provides a concrete foundation for operational usage of online machine learning algorithms within the domain.

This is a report about machine learning in the field of computer science. The problem handled is prediction of energy consumption in district heating systems. Prediction of energy consumption in district heating systems is a delicate problem because of the social behaviours, weather and distribution time that has to be accounted for. One algorithm is introduced and three different experiments are made to determine if the algorithm is useful. The results from the experiments were good. This report differs in approach to the problem then other reports found in this field. The difference is that this report tries to handle social behaviours and looks at a decentralized view of the problem instead of centralized. / Denna rapport är om maskininlärning och hur mna kan använda en maskinlärningsalgoritm för att förutspå konsumption i fjärrvärmenät. Rapporten skiljer sig markant i synsätt jämt emot andra rapporter i ämnet genom att den tittar även på de sociala faktorerna.

To run a district heating system as efficiently as possible correct unit-commitmentdecisions has to be made and in order to make those decisions a good forecast ofheat demand for the coming planning period is necessary. With a high quality forecastthe need for backup power and the risk for a too high production are lowered. Thisthesis takes a neural network approach to load forecasting and aims to provide asimple, yet powerful, tool that can provide accurate load forecasts from existingproduction data without the need for extensive model building.The developed software is tested using real life data from two co-generation plantsand the conclusion is that when the quality of the raw data is good, the software canproduce very good forecasting results.

Le domaine principal de cette thèse s’intéresse aux conséquences du changement climatique et des actions de rénovation dans le bâtiment sur les réseaux urbains de chaleur, ainsi qu’aux performances environnementales de ces derniers afin d’évaluer leur potentiel dans le futur. Dans ce but, deux modèles complémentaires ont été développés :•Un modèle dynamique de prévision de la demande de chaleur d’un bâtiment. Ce modèle repose sur une analogie thermoélectrique et a comme entrées, non exclusivement, des données climatiques et des scénarii de rénovation. Les résultats de ce modèle ont été comparés avec ceux d’un logiciel de référence (Energie Plus) : les erreurs sont acceptables. Ce modèle est générique et peut être utilisé dans différentes zones géographiques à l’échelle du quartier. Il a été appliqué sur des quartiers à Nantes et Lisbonne;•Un modèle d’évaluation environnementale (reposant sur le concept d’empreinte énergétique, éMergie) de réseau urbain de chauffage a été conçu. Ce modèle est générique et permet de tester différentes technologies de production et de distribution de chaleur. Il a été appliqué sur des applications en Suède et en Serbie;Les résultats des différentes applications indiquent que la nouvelle génération des réseaux urbains de chaleur ayant une infrastructure compacte (utilisant des matériaux à faible impact environnemental) et une production de chaleur à base de ressources renouvelables ou assimilées pourraient être une solution porteuse d’avenir. Cependant, pour maintenir la rentabilité de tels projets, la réduction de la consommation de chaleur des clients, conséquence en direct du changement climatique et en indirect des incitations aux rénovations du bâti, devrait être considérée dès la phase de conception, et intégrée dans de nouveaux business-plan afin de maintenir des prix de vente de la chaleur attractifs. / The main scope of this thesis is to assess the impacts of changed weather conditions and building renovation on district heating systems in the future, as well as the environmental performance of such systems within the urban environment, in order to evaluate the potential of district heating in the future. In order to do so, two models were developed:•A dynamic model for heat demand forecast, based on the thermo-electrical analogy, that takes into account weather and building renovation scenarios. The model had a satisfactory precision, and it can be applied on any location for a given number of buildings, which was proved on the example of multiple case studies;•An environmental assessment model (based onemergy theory) for the assessment of district heating systems environmental performance within the urban environment. The approach can be applied on any type of district heating systems, as well as on competitive urban heating technologies, which was proved by the application on multiple systems within the case studies considered;The results from case studies indicate that the new generation of district heating systems with compact infrastructure (made of non-environmentally intensive materials) and renewable heat production could be a solution for providing sustainable heating services to urban environments. However, in order to maintain the feasibility of these projects, potential heat demand reductions caused by the direct and indirect impacts of climate change should be considered during the design phase, along with the development of new business plans in order to maintain relatively low prices of district heating services. Moreover, the difference between these impacts in different climate types should be considered.

Denna uppsats tar sitt avstamp från en gammal rapport vid namn ”Samkörning mellan värmepumpar och fjärrvärme. – Bostadsrättsföreningen Bogården” från 2008. Denna rapport behandlar en undercentral vari det fanns risk för spridning av legionellabakterier. Rapporten från 2008 mynnade ut i åtgärdsförslag som togs i beaktande av Brf. Bogården och insatser genomfördes senare av SWECO i form av en nyprojektering av hela anläggningen. Följden av detta blev att undercentralen 2012 byggdes om helt och hållet och nya styr- och reglerflöden inrättades. I detta arbete presenteras en bred bild av energiläget i världen och i Sverige för att sedan rikta fokus ner till Gävle och undercentralen i Brf. Bogården. I denna studie så genomfördes flertalet observationstillfällen där noteringar gjordes för att se hur anläggningen och dess styr- och reglerflöden tedde sig. Bieffekten av besöken bestod av upptäckter som på ett eller annat sätt påverkade anläggningen i sin helhet. Det som upptäcktes var att undercentralen inte styr och regleras enligt projekteringen, retur- och framledningstemperaturer var för höga och att värmepumparnas drifttider absolut inte var enligt funktionsbeskrivningen. Dessa styr- och reglerfel gör så att Bogården måste köpa in mer fjärrvärme än vad som behövs vilket leder till mer kostnader än nödvändigt. / This paper takes its starting point from an old report named ”Samkörning mellan värmepumpar och fjärrvärme. – Bostadsrättsföreningen Bogården” from the year 2008. This report discusses a sub-station where there was a risk of proliferation of legionella bacteria. The 2008 report resulted in action proposals that were taken into account by tenant Bogården and thereafter efforts were implemented by SWECO in the form of a new projection of the entire sub-stationed facility. What happened next was that the sub- center was rebuilt completely in 2012 and a new management control settings were put into use. In this work, a broad picture of the energy situation in the world and in Sweden is presented, and after that the paper shifts focus on Gävle and the sub-center of tenant Bogården. In this study, many observation visits were made and during these notes were made to see how the plant and its control and regulatory flows occurred. The side effect of the visits consisted of discoveries that in one way or another affected the plant. What was discovered was that the sub-central did not control and regulate according to the design, the return and outflow temperatures in the radiator circuit were way too high and the heat pump operating hours were not at all according to the functional description that was provided to aid this report. These controls and regulate errors forces the tenant Bogården to buy more district heating than needed, which leads to more costs than necessary.

District heating systems could help manage the expected increase of volatility on the Nordic electricity market by starting a combined heat and power production plant (CHP) instead of a heat only production plant when electricity prices are expected to be high. Fortum Värme is interested in adjusting the production planning of their district heating system more towards high electricity prices and in their system there is a peak load CHP unit that could be utilised for this purpose. The economic potential of starting the CHP, instead of a heat only production unit, when profitable was approximated for 2013-2016. Three machine learning classification algorithms, Support vector machine (SVM), Naive Bayes and an ensemble of decision trees were implemented and compared with the purpose of predicting price spikes in price area SE3, where Fortum Värme operates, and to assist production planning. The results show that the SVM model achieved highest performance and could be useful in production planning towards high electricity prices. The results also show a potential profit of adjusting production planning. A potential that might increase if the electricity market becomes more volatile.

The isolated evaluation of companies is not sufficient to analyze economic performance of particular enterprises. The performance of the company has to be assessed in relation to the relevant segment and to other companies. The importance of inter-company comparison based on financial analysis is enlarged by the need to increase efficiency and to maintain competitiveness. The aim of this thesis is to identify the determinants of performance of companies, which operate in the district heating segment. The aim is achieved by application of different methods of inter-company comparison. The particular emphasis is placed on the type of used fuel (the most significant cost for district heating companies). Appropriate indicators for evaluation of the economic performance are selected from a wide range of financial analysis indicators. The selection is subject to interests of the parent company.

If new build nuclear reactors are built in the UK they will provide a large low carbon thermal resource that can be recovered for heating services through heat networks (district heating). There are however questions about the geographic location of nuclear sites relative to heating demand and public/user interpretations of a potentially controversial technology to consider. This thesis includes three research themes that explore these issues. The first is an assessment of potential non-technical barriers to nuclear heat network development. The second is a focus group approach to studying local resident responses to nuclear heat network technology both as potential users, and as public groups. The third theme considers the technical potential for a heat network connecting the Hartlepool nuclear site to local heating demand centres. The research finds that there is potential for nuclear heat networks to take 70,000 existing users off the natural gas in the Hartlepool area. Following series of expert interviews it finds no non-technical barriers that would be unique to nuclear heat networks as opposed to other heat network types. It also suggests that the technology could be acceptable to local residents if it is framed as a local resource that benefits the local area. These findings indicate that there could be similar potential at Heysham and Oldbury nuclear sites.