With the advent of information explosion age, larger capacity disk drives are used to store data and powerful devices are used to process big data. As the scale and complexity of computer systems increase, we expect these systems to provide dependable and energy-efficient services and computation. Although hard drives are reliable in general, they are the most commonly replaced hardware components. Disk failures cause data corruption and even data loss, which can significantly affect system performance and financial losses. In this dissertation research, I analyze different manifestations of disk failures in production data centers and explore data mining techniques combined with statistical analysis methods to discover categories of disk failures and their distinctive properties. I use similarity measures to quantify the degradation process of each failure type and derive the degradation signature. The derived degradation signatures are further leveraged to forecast when future disk failures may happen. Meanwhile, this dissertation also studies energy efficiency of high performance computers. Specifically, I characterize the power and energy consumption of Haswell processors which are used in multiple supercomputers, and analyze the power and energy consumption of Legion, a data-centric programming model and runtime system, and Legion applications. We find that power and energy efficiency can be improved significantly by optimizing the settings and runtime scheduling of processors, and Legion runtime performs well for larger-scale computation in terms of power and energy consumption.

About 12% of the greenhouse gas emissions and 40% of the total energy use in the EU derive from the buildings. User behavior, construction, and HVAC systems has a significant impact on a building’s energy use. If a building is to be energy-efficient it is important to understand how all these parameters are connected. This study is motivated by the need to decrease the energy use in buildings to reach the goals of energy use and greenhouse gas emissions.  In this thesis, measurements of indoor climate and electricity use, together with time diaries was used to create input data for an energy simulation model of a retirement home. A parametric study was conducted to simulate how energy demand was affected by changes in five different parameters in an office building. Also, two different energy-efficiency indicators were used to see how indicators can affect the perceived energy-efficiency of buildings. High amount of airing and low electricity use had the most impact on the heating demand in the retirement home, and electricity use had the highest impact on the total energy demand in the office building. The model of the retirement home using data gathered on-site had 24% higher energy use than the model using standard user input data. In the office building, total energy demand for heating and cooling could be lowered with 12-31% by lowering the electricity use with 30% compared to standard user input data. For office buildings the most important thing to lower total energy demand seems to be lowering the electricity use. Using today’s standard user input data does not correspond well to using on-site gathered data in a retirement home and it is therefore important to develop the standard user input data further. The indicator kWh/m2, seems to promote buildings with low occupancy. This could lead to buildings being utilized in an in-efficient way. The indicator kWh/m2 should either be replaced or combined with an indicator that takes occupancy into consideration. / Runt 12% av utsläppen av växthusgaser och 40% av den totala energianvändningen i EU kommer från byggnader. Brukarbeteende, konstruktion och HVAC-system har signifikant påverkan på en byggnads energianvändning. Om en byggnad ska bli så energieffektiv som möjligt är det viktigt att förstå hur dessa parametrar hör ihop. Denna studie motiveras av behovet att minska energianvändning i byggnader för att nå målen för energianvändning och utsläpp av växthusgaser.  I denna avhandling användes mätningar av inomhusklimat och elanvändning, tillsammans med tidsdagböcker, för att skapa indata till en energisimuleringsmodell av ett ålderdomshem. En parameterstudie genomfördes för att simulera hur energibehovet påverkades av ändringar i fem olika parametrar i en kontorsbyggnad. Två olika indikatorer för energieffektivitet användes också, för att se hur olika indikatorer påverkar hur en byggnads energieffektivitet uppfattas. Hög grad av vädring och låg elanvändning hade störst påverkan av energibehovet i ålderdomshemmet, och i kontorsbyggnaden påverkades det totala energibehovet mest av elanvändningen. Modellen av ålderdomshemmet där data insamlad på plats användes hade 24% högre värmebehov än modellen som använde standardiserade brukarindata. Det totala energibehovet för värme och kyla i kontorsbyggnaden kunde sänkas med 12-31% genom att sänka elanvändningen med 30% jämfört med standardiserad brukarindata. Det viktigaste för att få ner det totala energibehovet i kontorsbyggnader verkar vara att sänka elanvändningen. Att använda dagens standardvärden för brukarindata överensstämmer inte väl med att använda data insamlad på plats för ett ålderdomshem. Det är därför viktigt att vidareutveckla standardiserad brukarindata. Indikatorn kWh/m2 verkar främja byggnader med låg beläggning. Detta skulle kunna leda till att byggnader utnyttjas på ett ineffektivt sätt. Indikatorn kWh/m2 skulle därför behöva ersättas eller kombineras med en indikator som även tar byggnadens beläggning i beaktande.

This case study intends to understand and identify perceived barriers and drivers within the housing sector in Östergötland. By deeper understanding of the pre-existing conditions and the perceived barriers and drivers that both limit and enable development, the thesis contributes to the existing literature with extended knowledge. Previous literature within the field along with interviews make up the empirical material analysed in a qualitative exploratory way. This study finds that the importance of different barriers and drivers can vary depending on location and owner-category as well as culture and socio-economic factors. This means that policy and design of drivers also have to be customized accordingly with the different target groups. One can, based on this thesis also conclude that energy and climate development in the housing sector is a slow process that takes time. Regardless the measure or action, nothing changes overnight. This case study has on a regional level begun to identify decisive conditions, barriers and drivers as well as differences within Östergötland, pointing out the direction for future studies and for future policy and action plans.

This paper discusses an architectural anomaly observed on server processors of the AMD Zen microarchitecture: At a specific operating point, increasing the number of active cores reduces system power consumption while increasing performance more than proportionally to the additional cores. The occurrence of the anomaly is rooted in the hardware control loop for energy management and software-independent. Experiments show a connection to the AMD turbo frequency feature Max Core Boost Frequency (MCBF). In less efficient configurations, this feature could be employed from a processor’s perspective, even though it is not necessarily used on any core. Voltage measurements indicate that the availability of MCBF leads to a higher voltage from mainboard voltage regulators, subsequently raising power consumption unnecessarily. We describe the impact of this anomaly on the performance and energy-efficiency of several micro-benchmarks. The reduced power consumption when additional cores are enabled can lead to higher core frequencies and increased per-core-performance. The presented findings can be used to avoid inefficient core configurations and reduce the overall energy-to-solution.

Building design processes are dynamic and complex. The context of a building pro- ject is manifold and depends on the cultural context, climatic conditions and personal design preferences. Many stakeholders may be involved in deciding between a large space of possible designs defined by a set of influential design parameters. Building performance simulation is the state-of-the-art way to provide estimates of the energy and environmental performance of various design alternatives. However, setting up a simulation model can be labour intensive and evaluating it can be com- putationally costly. As a consequence, building simulations often occur towards the end of the design process instead of being an active component in design processes. This observation and the growing availability of machine learning algorithms as an aid to exploring analytical problems has lead to the development of surrogate mo- dels. The idea of surrogate models is to learn from a high-fidelity counterpart, here a building simulation model, by emulating the simulation outputs given the simula- tion inputs. The key advantage is their computational efficiency. They can produce performance estimates for hundreds of thousands of building designs within seconds. This has great potential to innovate the field. Instead of only being able to assess a few specific designs, entire regions of the design space can be explored, or instan- taneous feedback on the sustainability of building can be given to architects during design sessions. This PhD thesis aims to advance the young field of building energy simulation surrogate models. It contributes by: (a) deriving Bayesian surrogate models that are aware of their uncertainties and can warn of large approximation errors; (b) deriving surrogate models that can process large weather data (≈150’000 inputs) and estimate the associated impact on building performance; (c) calibrating a simulation model via fast iterations of surrogate models, and (d) benchmarking the use of surrogate-based calibration against other approaches. / Graduate

Decisions made at the early stage of building and settlement design can greatly influence the energy performance of the built environment. However, the type of feasible design intervention and their impact strong depends on project: if it is a new development or a re-development, whether the setting of the project is urban or rural, etc. Utilizing Bysjöstrand EcoVillage as a case, the aim of this thesis is to improve the energy performance of a new development at its early design stage through the passive and active use of solar energy. The study evaluated the energy saving potential of various passive solar design strategies as well as the solar energy potential of the new development. The steps taken to reduce the energy consumption are focused on the annual heating demand of buildings, since it accounts for more than a half of the total energy consumed by the village. The energy saving potential of the following passive solar design approaches were considered: building siting, building orientation, windows-to-wall ratio (WWR) analysis and insulation thickness optimization from the economic perspective. Furthermore, an assessment of energy generation potential from on-site photovoltaic (PV) systems was conducted. The financial viability of each building’s PV system was also conducted. According to the results, the evaluated passive solar design strategies can reduce the annual heating energy consumption close to 17 %. Regarding onsite energy generation, electricity from roof-installed PV systems can cover over 100% of the annual energy consumption estimated for the residential lighting and equipment within the eco-village. In summary, this study has demonstrated that with the above design considerations a 50 % reduction of energy consumption from the utility grid is possible. This study is useful for architects, energy engineers, and other parties who are involved in residential buildings energy performance optimization.

Världen under åren har haft en ökning av energianvändning som kan leda till stora problem. Anledningen är för att många länder producerar el och värme med resurser som medför stora mängder utsläpp av växthusgaser. Sverige svarade med att införa en lag om att en energikartläggning skall göras minst var fjärde år hos stora företag, så att Sverige kan uppnå ett mål om att energieffektivisera energianvändningen med 50 procent mellan 2003 och 2030. I detta examensarbete har en energikartläggning gjorts på en kontorsbyggnad som är lokaliserad i Mellan Sverige. Syftet var att kartlägga hur el och värme används i byggnaden samt presentera åtgärder för att minska energianvändningen. Resultatet visar att 770 MWh fjärrvärme och totalt 763 MWh el användes år 2019. Varav de största energianvändare i fastigheten är radiatorer, värmebatterier, elapparater och fläktar. Genom att bland annat göra tre energieffektiva åtgärder för ventilation kan upp till 313 000 kr sparas varje år. Åtgärderna är då att installera effektivare värmeväxlare, lägre SFP-tal på fyra av fastighetens luftbehandlingsaggregat samt att ventilationsystem av typen Demand Controlled Ventilation (DCV) används istället för Constant Air volume (CAV). / The world over the years has had an increase in energy use that can lead to major problems. The reason is that many countries produce electricity and heat with resources that cause large amounts of greenhouse gas emissions. Sweden responded by introducing a law that an energy audit must be done at least every four years at large companies, so that Sweden can achieve a goal of making energy use more energy efficient between 2003 and 2030. In this study, an energy audit has been done on an office building located in Central Sweden. The purpose was to map how electricity and heat are used in the building and to present measures to reduce energy use. The results show that 770 MWh of district heating and a total of 763 MWh of electricity were used in 2019. Of which the largest energy users in the property are radiators, heating batteries, electrical appliances and fans. By, among other things, taking three energy-efficient measures for ventilation, up to 313,000 SEK can be saved each year. The measures are then to install more efficient heat exchangers for ventilation, lower SFP numbers on four of the property's air handling units and that ventilation systems of the type Demand Controlled Ventilation (DCV) are used instead of Constant Air volume (CAV).

Decisions made at the early stage of building and settlement design can greatly influence the energy performance of the built environment. However, the type of feasible design intervention and their impact strong depends on project: if it is a new development or a re-development, whether the setting of the project is urban or rural, etc. Utilizing Bysjöstrand EcoVillage as a case, the aim of this thesis is to improve the energy performance of a new development at its early design stage through the passive and active use of solar energy. The study evaluated the energy saving potential of various passive solar design strategies as well as the solar energy potential of the new development. The steps taken to reduce the energy consumption are focused on the annual heating demand of buildings, since it accounts for more than a half of the total energy consumed by the village. The energy saving potential of the following passive solar design approaches were considered: building siting, building orientation, windows-to-wall ratio (WWR) analysis and insulation thickness optimization from the economic perspective. Furthermore, an assessment of energy generation potential from on-site photovoltaic (PV) systems was conducted. The financial viability of each building’s PV system was also conducted. According to the results, the evaluated passive solar design strategies can reduce the annual heating energy consumption close to 17 %. Regarding onsite energy generation, electricity from roof-installed PV systems can cover over 100% of the annual energy consumption estimated for the residential lighting and equipment within the eco-village. In summary, this study has demonstrated that with the above design considerations a 50 % reduction of energy consumption from the utility grid is possible. This study is useful for architects, energy engineers, and other parties who are involved in residential buildings energy performance optimization.

L'informatique en nuage (Cloud Computing) a émergé comme un nouveau paradigme pour offrir des ressources informatiques à la demande et pour externaliser des infrastructures logicielles et matérielles. Le Cloud Computing est rapidement et fondamentalement en train de révolutionner la façon dont les services informatiques sont mis à disposition et gérés. Ces services peuvent être demandés à partir d'un ou plusieurs fournisseurs de Cloud d'où le besoin de la mise en réseau entre les composants des services informatiques distribués dans des emplacements géographiquement répartis. Les utilisateurs du Cloud veulent aussi déployer et instancier facilement leurs ressources entre les différentes plateformes hétérogènes de Cloud Computing. Les fournisseurs de Cloud assurent la mise à disposition des ressources de calcul sous forme des machines virtuelles à leurs utilisateurs. Par contre, ces clients veulent aussi la mise en réseau entre leurs ressources virtuelles. En plus, ils veulent non seulement contrôler et gérer leurs applications, mais aussi contrôler la connectivité réseau et déployer des fonctions et des services de réseaux complexes dans leurs infrastructures virtuelles dédiées. Les besoins des utilisateurs avaient évolué au-delà d'avoir une simple machine virtuelle à l'acquisition de ressources et de services virtuels complexes, flexibles, élastiques et intelligents. L'objectif de cette thèse est de permettre le placement et l'instanciation des ressources complexes dans des infrastructures de Cloud distribués tout en permettant aux utilisateurs le contrôle et la gestion de leurs ressources. En plus, notre objectif est d'assurer la convergence entre les services de cloud et de réseau. Pour atteindre ces objectifs, cette thèse propose des algorithmes de mapping d'infrastructures virtuelles dans les centres de données et dans le réseau tout en respectant les exigences des utilisateurs. Avec l'apparition du Cloud Computing, les réseaux traditionnels sont étendus et renforcés avec des réseaux logiciels reposant sur la virtualisation des ressources et des fonctions réseaux. En plus, le nouveau paradigme d'architecture réseau (SDN : Software Defined Networks) est particulièrement pertinent car il vise à offrir la programmation du réseau et à découpler, dans un équipement réseau, la partie plan de données de la partie plan de contrôle. Dans ce contexte, la première partie de la thèse propose des algorithmes optimaux (exacts) et heuristiques de placement pour trouver le meilleur mapping entre les demandes des utilisateurs et les infrastructures sous-jacentes, tout en respectant les exigences exprimées dans les demandes. Cela inclut des contraintes de localisation permettant de placer une partie des ressources virtuelles dans le même nœud physique. Ces contraintes assurent aussi le placement des ressources dans des nœuds distincts. Les algorithmes proposés assurent le placement simultané des nœuds et des liens virtuels sur l'infrastructure physique. Nous avons proposé aussi un algorithme heuristique afin d'accélérer le temps de résolution et de réduire la complexité du problème. L'approche proposée se base sur la technique de décomposition des graphes et la technique de couplage des graphes bipartis. Dans la troisième partie de la thèse, nous proposons un cadriciel open source (framework) permettant d'assurer la mise en réseau dynamique entre des ressources Cloud distribués et l'instanciation des fonctions réseau dans l'infrastructure virtuelle de l'utilisateur. Ce cadriciel permettra de déployer et d'activer les composants réseaux afin de mettre en place les demandes des utilisateurs. Cette solution se base sur un gestionnaire des ressources réseaux "Cloud Network Gateway Manager" et des passerelles logicielles permettant d'établir la connectivité dynamique et à la demande entre des ressources cloud et réseau [...] / Cloud computing has rapidly emerged as a successful paradigm for providing IT infrastructure, resources and services on a pay-per-use basis over the past few years. As, the wider adoption of Cloud and virtualization technologies has led to the establishment of large scale data centers that consume excessive energy and have significant carbon footprints, energy efficiency is becoming increasingly important for data centers and Cloud. Today data centers energy consumption represents 3 percent of all global electricity production and is estimated to further rise in the future. This thesis presents new models and algorithms for energy efficient resource allocation in Cloud data centers. The first goal of this work is to propose, develop and evaluate optimization algorithms of resource allocation for traditional Infrastructutre as a Service (IaaS) architectures. The approach is Virtual Machine (VM) based and enables on-demand and dynamic resource scheduling while reducing power consumption of the data center. This initial objective is extended to deal with the new trends in Cloud services through a new model and optimization algorithms of energy efficient resource allocation for hybrid IaaS-PaaS Cloud providers. The solution is generic enough to support different type of virtualization technologies, enables both on-demand and advanced resource provisioning to deal with dynamic resource scheduling and fill the gap between IaaS and PaaS services and create a single continuum of services for Cloud users. Consequently, in the thesis, we first present a survey of the state of the art on energy efficient resource allocation in cloud environments. Next, we propose a bin packing based approach for energy efficient resource allocation for classical IaaS. We formulate the problem of energy efficient resource allocation as a bin-packing model and propose an exact energy aware algorithm based on integer linear program (ILP) for initial resource allocation. To deal with dynamic resource consolidation, an exact ILP algorithm for dynamic VM reallocation is also proposed. This algorithm is based on VM migration and aims at constantly optimizing energy efficiency at service departures. A heuristic method based on the best-fit algorithm has also been adapted to the problem. Finally, we present a graph-coloring based approach for energy efficient resource allocation in the hybrid IaaS-PaaS providers context. This approach relies on a new graph coloring based model that supports both VM and container virtualization and provides on-demand as well as advanced resource reservation. We propose and develop an exact Pre-coloring algorithm for initial/static resource allocation while maximizing energy efficiency. A heuristic Pre-coloring algorithm for initial resource allocation is also proposed to scale with problem size. To adapt reservations over time and improve further energy efficiency, we introduce two heuristic Re-coloring algorithms for dynamic resource reallocation. Our solutions are generic, robust and flexible and the experimental evaluation shows that both proposed approaches lead to significant energy savings while meeting the users' requirements

Energy benchmarking and disclosure policies exist in several local and state governments to manage the energy consumption of existing buildings and encourage energy efficient retrofits and upgrades, yet little is known about whether these efforts have improved overall energy efficiency. The purpose of this repeated-measures study was to examine the influence of New York City's (NYC's) Benchmarking Law (LL84) on the energy performance of the city's existing commercial buildings through investigating whether the energy performance of the city's existing commercial buildings significantly improved after the implementation of this policy. The study was based on Ostrom's institutional analysis and development framework. Paired-sample t tests were performed to statistically analyze the annually disclosed energy benchmarking data for 1,072 of NYC's existing commercial buildings that were benchmarked in both 2011 and 2016. Compared to 2011, the study results revealed statistically significant improvements in the energy performance of NYC's commercial buildings by 2016. On average, their site energy use intensity (EUI) significantly reduced by 5%, source EUI significantly decreased by 10%, greenhouse gas emissions significantly dropped by 12%, and ENERGY STAR performance rating significantly improved by 5%. However, these improvements were primarily achieved in 2012, 1 year after the city's energy benchmarking data were publicly disclosed. Additional measures should be considered to maintain continuous energy savings and greenhouse gas mitigation patterns. Positive social change implications include the potential to promote energy-efficient upgrades and inspire the adoption of sustainable building concepts.