Data centres are key to high availability and around the clock access to information. As the number of data centres increases to satisfy the demand for data, so does their energy consumption. This thesis is a case study of the data centres located in the Node Pole region in the North of Sweden. It aims to look at aspects of both the energy supply of Norrbotten and the actual technologies used by the data centres to utilise this energy supply. Using a literature review to gather primary data, the first research question analyses the energy supply of Norrbotten, investigating its specificities through energy security theories, particularly looking through the aspects of availability, accessibility and affordability. The second question examines the Node Pole’s implementation response to the specific energy supply of the North of Sweden, and whether this response is efficient and sustainable, using the four Rs theory and the Energy Efficiency Directive (EED). The results of the analysis show that the North of Sweden is currently in a privileged position: the energy produced in Norrbotten benefits from high availability criteria, is in oversupply, and thanks to the prevalence of hydropower and wind power in the energy mix, is very low in GHG emissions. The Swedish grid is reliable and robust, and Norbotten is no exception to that rule, providing the Node Pole with an accessible “plug and play” module to the electricity grid. In addition, the recent tax rebate aimed at the data centre industry means that the energy is affordable, more so in fact than in many other European countries. This assessment makes for a favourable breeding ground for data centres in the region from an energy security perspective. Meanwhile, the Node Pole data centres use ground-breaking cooling technologies consisting of airside cooling combined with adiabatic pads for humidity control (no separate humidification system), simple air filtration facilities (thanks to the outstanding air quality of the area),  and aerodynamic architectural premises layouts for better flow, reducing the cooling costs by increasing the efficiency of the overall air conditioning system. This technology is paired with innovative power distribution solutions (non-standard voltage and less UPS batteries), thereby considerably reducing the electricity consumption again and the waste of energy caused by voltage conversion. Combining the auspicious energy offerings of the Norrbotten region with the ingenious practical implementations of the data centres thus unleashes a new potential for more efficient and sustainable data centres.

Information and communications technology (ICT) is an important part in today’s society and around 60% of the world's population are connected to the internet. Processing and storing ICT data corresponds to approximately 1% of the global electricity demand. Locations that store ICT data produce a lot of heat that needs to be cooled, and the cooling systems stand for up to 40% of the total energy used in ICT-centre locations. Investigating the efficiency of the cooling in ICT-centres is important to make the whole ICT-centre more energy efficient, and possibly saving operational costs. Unwanted operational behaviour in the cooling system can be analysed by using unsupervised machine learning and clustering of data. The purpose of this thesis is to characterise cooling patterns, using K-means clustering, in two water-cooled ICT rooms. The rooms are located at Ericsson’s facilities in Linköping Sweden. This will be fulfilled answering the research questions: RQ1. What is the cooling power per m2 delivered by the cooling equipment in the two different ICT rooms at Ericsson?  RQ2. What operational patterns can be found using a suitable clustering algorithm to process and compare data for LCP at two ICT-rooms?   RQ3. Based on information from RQ1 and patterns from RQ2 what undesired operational behaviours can be identified for the cooling system? The K-means clustering is applied to time series data collected during the year of 2022 which include temperatures of water and air; electric power and cooling power; as well as waterflow in the system. The two rooms use Liquid Cooling Packages (LCP)s, also known as in-row cooling units, and room 1 (R1) also include computer room air handlers (CRAHs). K-means clusters each observation into a group that share characteristics and represent different operating scenarios. The elbow-method is used to determine the number of clusters, it created four clusters for R1 and three clusters for room 2 (R2).  Results show that the operational patterns differ between R1 and R2. The cooling power produced per m2 is 1.36 kW/m2 for R1 and 2.14 kW/m2 for R2. Cooling power per m3 is 0.39 kW/m3 for R1 and 0.61 kW/m3 for R2. Undesirable operational behaviours were identified through clustering and visual representation of the data. Some LCPs operate very differently even when sharing the same hot aisle. There are disturbances such as air flow and setpoints that create these differences, which results in that some LCPs operate with high cooling power and others that operate with low cooling power. The cluster with the highest cooling power is cluster 4 and 3 for R1 and R2 respectively. Cluster 2 has the lowest cooling power in R1 and R2. For LCPs operating in cluster 2 where waterflow mostly at 0 l/min and therefore where not contributing to the cooling of the rooms. Lastly, the supplied electrical power and produced cooling power match in R1 but do not in R2. Implying that heat leave the rooms by other means than via the cooling system or faulty measurements. There is a possibility to investigate this further. Water in R1 and R2 is found to, at occasions, exit the room with temperature below the ambient room temperature. It is also concluded that the method functions to identify unwanted operational behaviours, knowledge that can be used to improve ICT operations.  To summarize, undesired operational behaviours can be identified using the unsupervised machine learning technique K-means clustering.

Rapid growth of digitalization has urged Data Centres (DC) to be more energy efficient by recovering waste heat from server racks that would otherwise be wasted. This techno-economic study is focused on upgrading low temperature waste heat from typical Air-Cooled DC for District Heating Network (DHN) market in Stockholm region. The methodology is carried out by four system configurations that are experimented with different historical electricity data, impacts of climate change with simulated weather data, and variations in DHN temperature as the heat supply scenario development. The results show that DC configuration with combination of both free-cooling and waste heat recovery can foster techno-economic benefits by reducing cooling consumption by 55.6%, compared to DC configuration with free-cooling only; and further lowering Power Usage Effectiveness (PUE) from 1.95 to 1.52. Lifecycle Operational Expenditure (LCO) has also been used as the economic indicator to represent the maximum initial investment that data centre should accept when deciding to recover the waste heat to the DHN. Moreover, the new technical Key Performance Indicators (KPIs) were introduced to support the decision-making in the supply of recovered waste heat to DHN. The electricity price was further identified to have greater impact than the effect of climate change for the overall techno-economic performance. On one specific hand, heat supply with Price-Limit scenario concluded that 40.18% of available waste heat from DC is not profitable should it be injected to DHN in the case of low electricity price. In the case when the electricity price is high, the amount of waste heat not injected to DHN increases to 58.57%. / <p>The thesis defense presentation was held digitally on Zoom on June 19th 2023 at 09.00 CEST</p>

Model-Based Systems Engineering (MBSE) is a formal method that is used to support analysis, design, independent verification, and validation inherent in the development of software and hardware systems. MBSE applications are present in many areas of our daily lives, including manufacturing, robotics, healthcare, automation, etc. However, despite their rapid and sustainable growth during the last few years, the MBSE methods themselves are quite far away from perfect. There are some current problems, which resist more rapid penetration of MBSE systems in their development. One of them is that currently the majority of MBSE systems are vendor dependent and, as a result, they have poor compatibility with each other. Furthermore, currently, there is a gap between the design of a digital model and a control model of an engineering system. Currently, this problem is usually solved by involving two or more groups of engineers, where each of these groups works on their own problems. All this costs companies additional engineering time and, as a result, development costs. Therefore new, and more sophisticated approaches for the generation of MBSEs are needed in order to overwhelm the challenges highlighted above. In order to narrow the field of study and better concentrate on specific problems, smart power distribution systems have been chosen as the main research object for this dissertation. Thus, in this work, the author introduces Model-Integrated Systems Engineering (MISE), as the MBSE sub-discipline. Here and later in this paper, the author will refer to MISE as the main area of interest. Also, the author uses the term DigitalTwin to refer to the multilayered structure of a complex distributed automation system consisting of three layers, namely:– the static machine-readable information about the infrastructure of the smart energy system,– the simulation model layer,– the distributed control layer for the investigated smart energy system. In general, two new transformation approaches for automatic MISE generation are discussed in the scope of this dissertation, namely:1. Transformation of the System Configuration Design (SCD) files of an electric system(presented in IEC 61850) into the corresponding SIMULINK model.2. Transformation of specification files of electronic components into corresponding OPC UA information model.All discussed approaches are implemented in the form of a program code that is publicly available on the Internet. The IEC 61850 and OPC UA standards are considered key components of the current dissertation. IEC 61850 is an international standard covering different sides of smart energy distribution systems including communication protocols for diverse equipment in a substation, including protection, control, and measurement equipment, as well as intelligent electronic devices (IEDs). Information Modeling OPC UA is a platform-independent service-oriented architecture that combines the concepts of semantic modeling. First, the structure of the IEC 61850 standard is discussed, as well as its potential benefits for the MISE of smart power distribution systems in terms of the automatic transformation of the information model. Next, the architecture of the electrical system (the SCD file) of the electrical vehicle (EV) charging station (CS) is proposed as an example. The aim is to design a mechanism for the automatic transformation of MISE in two domains, namely:- Physical model of the electrical system itself,- Automatically build a communication channel between the digital replica (the model) of the electrical system and the virtual energy management system (EMS). Thus, this work aims to contribute to the design and virtual commissioning of Digital Twin systems, as well as to improve the interoperability between IEC 61850 compliant systems and electric vehicle charging stations (paper C explains that in more detail). Finally, by narrowing down the scope of the investigation to one specific electrical device, a new approach for converting integrated circuit (IC) specification files of an electric system into an OPC UA information model is discussed. The designed transformation algorithm is based on the directed graphs theory (paper D explains that in more detail). The purpose of this work is to highlight and contribute to the problems of the MISE analysis solutions.  In summary, the work presented in this dissertation raises questions about interoperability between different standards, the problems of converting the IEC 61850 information model into MISE, verification of the generated MISE compared to the original IEC 61850 information model, and the problems of forming an information model OPC UA.

Today’s society already requires a great connectivity network. This need will only increase in the future, and EDGE data centres are concepts meeting this future need, where the computational power is deployed close to the end user. They are defined, in this thesis, as a concept including different nodes, or data centres, located in proximity connected and participating in the market as one entity. The electricity grid in the Nordics is also a complex system. Many types of interactions with the grid exist and depend on the type of stakeholder. One collection of such interactions is ancillary services, which refer to different types of measures that maintain a reliable grid and electricity system. Electricity consumers within the grid network have the potential to interact and participate in these different functions. In this thesis, the participation of data centres, or EDGE data centres in ancillary services market, is studied. This thesis modelled different scenarios of an EDGE data centre with the grid network. Scenario 1 looked into self-consumption; scenario 2 looked into spot trading; scenario 3 looked into the FCR-N market; scenario 4 looked into the FCR-D markets; and scenario 5 looked into the combination of self-consumption and the FCR-D markets. It is observed from the results that scenario 4 generated the most favourable economic benefits. The results in relation to the price areas (zones in Sweden) were varied for the results. The price area SE4 gave better results for scenarios 1, 2, and 5 as compared to others. The best price area for scenarios 3 and 4 was from the SE1 zone. It is observed from the results that the potential benefit of the different ancillary markets exist and are at times favourable. Hence, there lies a future potential for the participation of EDGE networks in the electricity market thereby generating benefits for the data centres as well as stability for the grid. / Dagens samhälle kräver redan ett bra nätverk för uppkoppling. Detta behov kommer bara att öka i framtiden, och EDGE:s datacenter är koncept som uppfyller detta framtida behov, där datakraften placeras nära slutanvändaren. De definieras i denna avhandling som ett koncept som omfattar olika noder, eller servrar, som är placerade i närheten av varandra och som deltar på marknaden som en enhet. Elnätet i Norden är också ett komplext system. Det finns många olika typer av interaktioner med elnätet som beror på vilken typ av aktör det är fråga om. En samling av sådana interaktioner är stödtjänster, som avser olika typer av åtgärder som upprätthåller ett tillförlitligt nät och elsystem. Elkonsumenter inom elnätet har möjlighet att interagera och delta i dessa olika funktioner. I den här avhandlingen undersöks datacentraler, eller EDGE-datacenter, som deltar. I denna avhandling har olika scenarier för EDGE-datacenter modellerats i förhållande till elnätet. I scenario 1 undersöktes självkonsumtion, i scenario 2 spothandel, i scenario 3 FCR-N-marknaden, i scenario 4 FCR-D-marknader och i scenario 5 en kombination av självkonsumtion och FCR-D-marknader. I korthet gav scenario 4 de mest gynnsamma ekonomiska fördelarna. De potentiella miljöfördelarna diskuteras och kan inte lika lätt kvantifieras. Resultaten i förhållande till prisområdena varierade för resultaten. Prisområde SE4 gav de bästa resultaten för scenario 1 och 2 samt 5. Det bästa prisområdet för scenario 3 och 4 var SE1. Det framgår tydligt av denna avhandling att de potentiella fördelarna med de olika stödmarknaderna finns och att de vid vissa tillfällen är mycket gynnsamma med tanke på de höga lagringskostnaderna. EDGE-nätverkens framtida potentiella deltagande ger positiva resultat i både ekonomiska och miljömässiga termer.

Die vorliegende Arbeit enthält eine statistische Analyse der Gesamtheit öffentlicher Unternehmen in Deutschland und ihrer wirtschaftlichen Lage. Für diese Untersuchung stand eine Datenbank für etwa 9000 öffentliche Unternehmen mit knapp 500 Merkmalen zur Verfügung, die im Wesentlichen den Posten der Jahresabschlüsse und verschiedenen Identifikationsmerkmalen (wie u. a. Unternehmenssitz, Wirtschaftszweig und Rechtsform) entsprechen. Die Analyse umfasst den Zeitraum von 1998 bis 2006. Die extrem umfangreiche Datengrundlage – Jahresabschlussstatistiken öffentlicher Unternehmen – ist für einen Statistiker eine große Versuchung. In der Arbeit wurden Methoden der beschreibenden Statistik und der Jahresabschlussanalyse mit Bilanzkennzahlen angewandt. Vor allem in den letzten zwanzig Jahren wurde die Entwicklung der Gesamtheit öffentlicher Unternehmen durch Wandelprozesse geprägt und von Diskussionen über ihre Leistungsfähigkeit begleitet. Die Dynamik der Gesamtheit öffentlicher Unternehmen zeigt sich v. a. an der Vielfalt ihrer Aufgabenbereiche und Organisationsformen. Daher wurde in dieser Arbeit versucht, zunächst eine Bestandsaufnahme des öffentlichen Unternehmensbereichs durchzuführen. Ein weiteres Ziel war die Beschreibung der Wirtschaftslage öffentlicher Unternehmen im letzten Jahrzehnt, wobei ihre Leistungsfähigkeit in den Vordergrund gestellt wird. Die Leistungsfähigkeit öffentlicher Unternehmen nur über die betriebswirtschaftliche Effizienz zu messen, ist gewiss einseitig und nicht ausreichend. Diese ließ sich aber im Vergleich zur volkswirtschaftlichen oder sozialen Effizienz leichter operationalisieren: Die betriebswirtschaftlichen Effizienzkriterien können gut aus den Jahresabschlüssen abgeleitet werden. Dadurch wird auch ein Vergleich mit privaten Unternehmen in gewissen Grenzen möglich. Die Beschreibung der Wirtschaftslage öffentlicher Unternehmen wurde als Analyse ihrer einzelnen Teillagen (Vermögens-, Finanz- und Ertragslage) strukturiert. Insgesamt unterstreicht die Analyse der Teillagen die enge Verflechtung zwischen öffentlichen Unternehmen und öffentlichen Haushalten. Die vorliegende Untersuchung soll die Forschung auf dem Gebiet der datengetriebenen Statistik, die im Universitätsbereich in letzten Jahren im Vergleich zur modellgetriebenen Statistik oft vernachlässigt wurde, ausweiten. / This monograph deals with state-owned companies in Germany. The study focuses on a statistical analysis of all state-owned companies in Germany and their economic situation. Approximately 9,000 state-owned companies, with nearly 500 characteristical items surveyed for every company, comprise the database for this statistical analysis. The elements examined are firstly the entries of the annual balance sheets. In addition, there are the identifying characteristics, such as the type of industry, the legal form, or the operating location, in the databank. The analysis covers the period from 1998 to 2007. It’s very tantalizing for a statistician to work with the statistics of the annual balance sheets of the state-owned companies in Germany because of the large volumes of data. Both the methods of the descriptive statistics and the financial statement analysis with the balance sheet ratios were applied in this study. Especially over the last twenty years, the changes in the economic sector have led to discussions about the potential performance of the companies. The population dynamics of the state-owned enterprises are seen in the variety of the types of their activities and services and new legal forms. Therefore, the first goal of this analysis was to take an inventory of the German state-owned companies. The second goal of this work was to describe the economic situation of the state-owned companies in the last decade, with the emphasis on their performance. To measure the performance of the state-owned companies using only the economic efficiency as criterion is insufficient. However, the economic efficiency is easy to operationalise compared to, for example, social efficiency, because the ratios of the economic efficiency can be easily derived from the annual balance sheets of the companies. Besides that, using the ratios of the economic efficiency makes the comparison between the state-owned companies and the private ones easier. The description of the economic situation of the state-owned companies is based on the analysis of their assets, as well as their financial and earning positions. Altogether, the analysis of different positions emphasized the interdependence between the state-owned companies and their owners (regional authorities). From the methodological point of view, this study tried to extend research in the field of the data-driven statistics, which has been a neglected topic at universities in the last years when compared to model-driven statistics.

Abstract According to industry estimates, monthly global mobile data traffic will surpass 30.6 exabytes by 2020 and global mobile data traffic will increase nearly eightfold between 2015 and 2020. Most of the mobile data traffic is generated by smartphones, and the total number of smartphones is expected to continue growing by 2020, which results in rapid traffic growth. In addition, the upcoming 5G networks and Internet of Things based communication are estimated to involve a large amount of network traffic. The increase in mobile data traffic and in the number of connected devices poses a challenge to network operators, service providers, and data center operators. If the transmission capacity of the network and the amount of data traffic are not in line with each other, congestion may occur and ultimately the quality of experience degrades. Mobile networks are also becoming more reliant on data centers that provide efficient computing power. However, the energy consumption of data centers has grown in recent years, which is a problem for data center operators. A traditional strategy to overcome these problems is to scale up the resources or by providing more efficient hardware. Resource over-provisioning increases operating and capital expenditures without a guarantee of increased average revenue per user. In addition, the growing complexity and dynamics of communication systems is a challenge for efficient resource management. Intelligent and resilient methods that can efficiently use existing resources by making autonomous decisions without intervention from human administrators are thus needed. The goal of this research is to implement, develop, model, and test algorithms that can enable efficient and energy-aware network resource management in autonomous communications systems. First, an energy-aware algorithm is introduced for high-performance computing data centers to reduce the energy consumption within a single data center and across a federation of data centers. For network access selection in heterogeneous wireless networks, two algorithms are proposed, a client side algorithm that tries to optimize users' quality of experience and a network side algorithm that focuses on optimizing the global resource usage of the network. Finally, for a video service, an algorithm is presented that can enhance the video content delivery in a controllable and resource-efficient way without major changes in the mobile network infrastructure. / Tiivistelmä Langattoman tietoliikenteen nopean kasvun ennustetaan jatkuvan edelleen lähivuosinakin ja alan teollisuuden arvioiden mukaan matkapuhelinliikenteen määrä ylittäisi globaalisti 30,6 eksatavua vuoteen 2020 mennessä. Tämä tarkoittaisi liikennemäärän kahdeksankertaistumista ajanjaksolla 2015–2020. Älypuhelimet tuottavat suurimman osan matkapuhelinliikenteestä, ja älypuhelimien lukumäärän arvioidaan jatkavan kasvuaan vuoteen 2020 saakka, mikä johtaa nopeaan liikenteen kasvuun. Tämän lisäksi arvioidaan, että 5G verkot ja esineiden Internet tuottavat suuren määrän verkkoliikennettä. Matkapuhelinliikenteen ja laitteiden määrän kasvu tuo haasteita verkko-operaattoreille, palvelun tarjoajille, ja datakeskusoperaattoreille. Mikäli verkossa ei ole tarpeeksi siirtokapasiteettia dataliikenteen määrää varten, verkko ruuhkautuu ja lopulta palvelukokemus kärsii. Matkapuhelinverkot tulevat myös tulevaisuudessa tarvitsemaan datakeskusten laskentakapasiteettia. Datakeskusten energiankulutus on kuitenkin kasvanut viime vuosina, mikä on ongelma datakeskusoperaattoreille. Perinteinen strategia ongelmien ratkaisemiseksi on lisätä resurssien määrää tai tarjota tehokkaampaa laitteistoa. Resurssien liiallinen lisääminen kasvattaa kuitenkin sekä käyttö- että pääomakustannuksia ilman takuuta siitä, että keskimääräinen myyntitulo per käyttäjä kasvaisi. Tämän lisäksi tietoliikennejärjestelmät ovat monimutkaisia ja dynaamisia järjestelmiä, minkä vuoksi tehokas resurssienhallinta on haastavaa. Tämän vuoksi tarvitaan älykkäitä ja kestäviä metodeja, jotka pystyvät käyttämään olemassa olevia resursseja tehokkaasti tekemällä autonomisia päätöksiä ilman ylläpitäjän väliintuloa. Tämän tutkimuksen tavoitteena on toteuttaa, kehittää, mallintaa, ja testata algoritmeja, jotka mahdollistavat tehokkaan ja energiatietoisen verkkoresurssien hallinnan autonomisissa tietoliikennejärjestelmissä. Tutkimus esittää aluksi supertietokonedatakeskuksiin energiatietoisen algoritmin, jonka avulla voidaan vähentää energiankulutusta yhden datakeskuksen sisällä sekä usean eri datakeskuksen välillä. Verkkoyhteyden valintaan heterogeenisissä langattomissa verkoissa esitetään kaksi algoritmia. Ensimmäinen on käyttäjäkohtainen algoritmi, joka pyrkii optimoimaan yksittäisen käyttäjän palvelukokemusta. Toinen on verkon puolen algoritmi, joka keskittyy optimoimaan verkon kokonaisresurssien käyttöä. Lopuksi esitetään videopalvelulle algoritmi, joka parantaa videosisällön jakoa kontrolloidusti ja resurssitehokkaasti ilman että matkapuhelinverkon infrastruktuurille tarvitaan muutoksia.

This study examines drivers, challenges, and stakeholder perceptions of resource-efficient investments in the Stockholm real estate market under the EU Taxonomy. It is focused on a green activity involving repurposing energy waste and explores its value through a case study. Data collection involved conducting 13 interviews with stakeholders in the banking, valuation, and property owner sectors. Existing literature suggests limited consideration of environmental and social impacts in traditional real estate valuation. Empirical evidence supporting the influence of sustainability on market prices is scarce due to data comparability issues and a lack of standardisation from valuation organisations. This study used a mixed-method approach, combining interviews and a case study. The results found that stakeholders made different adjustments to meet EU Taxonomy criteria. Banks are driving green investments through attractive financing, causing many property owners to adjust accordingly. Valuers had limited awareness of including sustainability values. Property owners viewed green investments as vital for survival, influenced by financiers and tenants. The results from the case study show an increase in property value when investing in an internal mini data centre focused on repurposing waste energy and heat from the servers and utilising the property’s existing infrastructure. This study has concluded that enhancing awareness about the EU Taxonomy in an early stage could lead to the property industry being able to overcome the barriers and adopt sustainable practices better. / Denna studie undersöker de drivkrafter och utmaningar som finns bland intressenter att genomföra resurseffektiva investeringar på fastighetsmarknaden i Stockholm till följd av EU taxonomin. Studien har undersökt gröna investeringsaktiviteter som innefattar omvandling av resurser som spillvärme och spillenergi samt utforskar deras värde genom en fiktiv fallstudie. Datainsamlingen involverade 13 intervjuer med intressenter inom bank-, värderings- och fastighetsägarsektorn. Den befintliga litteraturen tyder på att traditionella fastighetsvärderingar i begränsad utsträckning tar hänsyn till miljöfaktorer, såsom gröna investeringsaktiviteter. Empiriska bevis visar att hållbarhetsinflytandet på marknadspriser är bristfälliga på grund av jämförbarhetsproblem med data och brist på standardisering från värderingsorganisationer. Denna studie använde en mixad metod, som kombinerade intervjuer och en fiktiv fallstudie. Studien visade att intressenter gör olika anpassningar för att uppfylla EU:s taxonomikriterier. Bankerna driver gröna investeringar utefter EU taxonomin genom att erbjuda en mer attraktiv finansiering, vilket leder till att många fastighetsägare har sin största drivkraft för hållbarhetsomställningen som finansiering. Värderare visade sig ha en begränsad medvetenhet om hur hållbarhetsvärden ska inkluderas i fastighetsvärderingen. Fastighetsägare såg ocksågröna investeringar som avgörande för överlevnad, påverkade av både finansiärer och hyresgäster. Samtidigt visade resultaten från fallstudien på en ökning av fastighetsvärdet vid investering i ett mini datacenter, fokuserat på att omvandla spillvärme och spillenergi från servrar samtidigt som fastighetens befintliga infrastruktur nyttjas. Slutsatsen har kommit fram till att ökad medvetenhet om EU:s taxonomi i ett tidigt skede kan leda till att fastighetsbranschen bättre kan övervinna de hinder som finns och samtidigt anta hållbara metoder.

This thesis addresses orchestration of servers amongst multiple co-hosted internet services such as e-Banking, e-Auction and e-Retail in hosting centres. The hosting paradigm entails levying fees for hosting third party internet services on servers at guaranteed levels of service performance. The orchestration of server ensemble in hosting centres is considered in the context of maximising the hosting centre's revenue over a lengthy time horizon. The inspiration for the server orchestration approach proposed in this thesis is drawn from nature and generally classed as swarm intelligence, specifically, sophisticated collective behaviour of social insects borne out of primitive interactions amongst members of the group to solve problems beyond the capability of individual members. Consequently, the approach is self-organising, adaptive and robust. A new scheme for server ensemble orchestration is introduced in this thesis. This scheme exploits the many similarities between server orchestration in an internet hosting centre and forager allocation in a honeybee (Apis mellifera) colony. The scheme mimics the way a honeybee colony distributes foragers amongst flower patches to maximise nectar influx, to orchestrate servers amongst hosted internet services to maximise revenue. The scheme is extended by further exploiting inherent feedback loops within the colony to introduce self-tuning and energy-aware server ensemble orchestration. In order to evaluate the new server ensemble orchestration scheme, a collection of server ensemble orchestration methods is developed, including a classical technique that relies on past history to make time varying orchestration decisions and two theoretical techniques that omnisciently make optimal time varying orchestration decisions or an optimal static orchestration decision based on complete knowledge of the future. The efficacy of the new biomimetic scheme is assessed in terms of adaptiveness and versatility. The performance study uses representative classes of internet traffic stream behaviour, service user's behaviour, demand intensity, multiple services co-hosting as well as differentiated hosting fee schedule. The biomimetic orchestration scheme is compared with the classical and the theoretical optimal orchestration techniques in terms of revenue stream. This study reveals that the new server ensemble orchestration approach is adaptive in a widely varying external internet environments. The study also highlights the versatility of the biomimetic approach over the classical technique. The self-tuning scheme improves on the original performance. The energy-aware scheme is able to conserve significant energy with minimal revenue performance degradation. The simulation results also indicate that the new scheme is competitive or better than classical and static methods.

This Green IT case study commissioned by Försäkringskassan (FK), the Swedish National Social Insurance Agency, quantifies the environmental performance of the IT infrastructure (IT-IS) in use during 2010 in a lifecycle perspective. Adopting a system view in Green IT analysis can mitigate risks of problem shifts. IT-IS concerns the equipment that enables office automation and external web application services. The size of the FK IT-IS is in the order of 300 branch offices with 14000 pc’s, 2100 printers and a 1 MW data centre hosting 1200 servers, 5 Petabyte of central data storage and serving about 80 key business applications. The carbon footprint of the FK IT-IS in 2010 accounts to 6.5 kiloton CO2-equivalents. The total environmental impact is calculated across 18 themes and expressed as a single indicator eco score amounting to 822.000 ReCiPe points. The contribution of capital goods is large with 44% of the carbon footprint and 47% of the eco score linked to emissions embedded in material equipment. The environmental effects from distributed IT deployed at local office sites, dominate at two thirds of the total FK IT-IS impacts. Important drivers in the local office sites category are the relatively short economic life span of pc equipment and the significant volume of paper consumed in printing activities. Within the data centre category, operational processes dominate the environmental impacts and are linked to intensive power use. In comparison to industry benchmark scores, the data centre infrastructure energy efficiency (DCiE) is relatively low at 57%, or 59% when credited for waste heat utilisation. Airflow containment measures in computer rooms are identified for efficiency improvement. Enhanced airflow controls also act as a prerequisite to better leverage opportunities for free cooling present at the location in northern Europe.  With regards to the data centre hosted IT, environmental impacts linked to storage services dominate and remarkably exceed those of servers. / Denna fallstudie inom Grön IT på uppdrag av Försäkringskassan (FK) kvantifierar IT-infrastrukturens (IT-IS) miljöprestanda i ett livscykelperspektiv under 2010. Att införa ett systemperspektiv inom Grön IT analys kan lindra riskerna av problemväxling. IT-IS avser utrustning som möjliggör kontorsautomatisering och externa webbapplikationer. FK IT-IS omfattar 300 kontor med 14,000 datorer, 2,100 skrivare och ett 1 MW datacenter med 1,200 servrar, 5 Petabyte central datalagring och 80 huvudsakliga applikationer. Koldioxidavtrycket av det totala FK IT-IS utgör 6,5 kiloton CO2-ekvivalenter för 2010 . Den totala miljöpåverkan är beräknad över 18 miljöteman och anger som en enda indikator ekobetyget på 822,000 ReCiPe poäng . Kapitalvaror bidrar stort, med hela 44% av koldioxidutsläppen och 47% av ekobetyget kan härledas till inbäddade utsläpp i material utrustning. Miljöeffekterna av de lokala kontorens IT dominerar med två tredjedelar av den totala FK IT-IS miljöpåverkan. Viktiga faktorer i kategorin lokala kontor är kapitalvarornas relativt korta ekonomiska livslängd samt de betydande volymer av skrivarpapper som används.   Inom datacenterkategorin domineras miljöpåverkan av de operativa processerna som är kopplade till intensiv el förbrukning. I jämförelse med branschstandarden är energieffektiviteten av datacentrets infrastruktur (DCiE) relativt låg, med 57%, alternativt 59% när användandet av spillvärme inräknas. Luftflöde inneslutningsåtgärder i datorsalar identifieras för effektivisering. Förbättrad luftflödesinneslutning i datahallarna är identifierad som en energieffektivisering. Den förbättrade luftflödeskontrollen är också ett krav för att bättre kunna utnyttja möjligheterna för fri kyla som finns i Norra Europa.  Med avseende på datacentrets IT, domineras miljökonsekvenserna kopplade till lagringstjänster och överstiger anmärkningsvärt effekterna från servrarna. / Miljöutredning Grön IT på Försäkringskassan - examensarbeten