Exploiting Significance of Computations for Energy-Constrained Approximate Computing

Approximate execution is a viable technique for environments with energy constraints, provided that applications are given the mechanisms to produce outputs of the highest possible quality within the available energy budget. This paper introduces a framework for energy-constrained execution with controlled and graceful quality loss. A simple programming model allows developers to structure the computation in different tasks, and to express the relative importance of these tasks for the quality of the end result. For non-significant tasks, the developer can also supply less costly, approximate versions. The target energy consumption for a given execution is specified when the application is launched. A significance-aware runtime system employs an application-specific analytical energy model to decide how many cores to use for the execution, the operating frequency for these cores, as well as the degree of task approximation, so as to maximize the quality of the output while meeting the user-specified energy constraints. Evaluation on a dual-socket 16-core Intel platform using 9 benchmark kernels shows that the proposed framework picks the optimal configuration with high accuracy. Also, a comparison with loop perforation (a well-known compile-time approximation technique), shows that the proposed framework results in significantly higher quality for the same energy budget.

Energy Optimization of Memory Intensive Parallel Workloads

Energy consumption is an important concern in modern multicore processors. The energy consumed by a multicore processor during the execution of an application can be minimized by tuning the hardware state utilizing knobs such as frequency, voltage etc. The existing theoretical work on energy minimization using Global DVFS (Dynamic Voltage and Frequency Scaling), despite being thorough, ignores the time and the energy consumed by the CPU on memory accesses and the dynamic energy consumed by the idle cores. This article presents an analytical energy-performance model for parallel workloads that accounts for the time and the energy consumed by the CPU chip on memory accesses in addition to the time and energy consumed by the CPU on CPU instructions. In addition, the model we present also accounts for the dynamic energy consumed by the idle cores. The existing work on global DVFS for parallel workloads shows that using a single frequency for the entire duration of a parallel application is not energy optimal and that varying the frequency according to the changes in the parallelism of the workload can save energy. We present an analytical framework around our energy-performance model to predict the operating frequencies (that depend upon the amount of parallelism) for global DVFS that minimize the overall CPU energy consumption. We show how the optimal frequencies in our model differ from the optimal frequencies in a model that does not account for memory accesses. We further show how the memory intensity of an application affects the optimal frequencies.

Argamassas funcionais para uma construção sustentável

A aposta na sustentabilidade tem conduzido o mercado da construção a procurar novas soluções técnicas e novos materiais, que por serem mais eficientes, conseguem dar resposta aos requisitos cada vez mais exigentes deste sector. A aplicação dos conceitos de sustentabilidade não se pode restringir a novas construções, tendo que prever também as renovações e a reabilitação de edifícios antigos. Assim, novos materiais que sejam desenvolvidos, devem contemplar todas estas vertentes de utilização. Neste trabalho desenvolveram-se argamassas com novas funcionalidades, que contribuem para melhorar os níveis de sustentabilidade dos edifícios, através da incorporação de nanomateriais para armazenamento de calor latente e degradação de poluentes do ar interior. Estudou-se não só o impacto da incorporação destas nanopartículas no estado fresco e endurecido, mas também o seu desempenho do ponto de vista funcional quando integrados na estrutura da argamassa. É possível obter argamassas com capacidade para armazenar calor latente através da incorporação de um material de mudança de fase. Este material constituído por uma mistura de parafinas, consegue armazenar calor e libertálo posteriormente. As composições desenvolvidas podem ser aplicadas em novos projectos ou na reabilitação de edifícios contribuindo para reduzir o consumo energético, melhorando o conforto térmico no interior. Com a redução da factura energética obtém-se uma efectiva diminuição do impacto ambiental, energético e económico do edifício. Para além do armazenamento de calor latente, também se desenvolveram argamassas capazes de eliminar poluentes do ar interior e, simultaneamente, com capacidade de auto-limpeza. Utilizaram-se nanopartículas de dióxido de titânio como aditivo fotocatalítico, tendo-se analisado o efeito da introdução deste aditivo nas argamassas. As composições testadas demonstraram elevada capacidade fotocatalítica e de auto-limpeza, sem comprometer as suas propriedades no estado endurecido. Ao aplicar estas composições na camada de acabamento interior melhora-se a qualidade do ar no interior das habitações e reduz-se a necessidade de utilização de sistemas de ventilação. As argamassas funcionais contribuem para melhorar os níveis de sustentabilidade da construção, tendo impacto económico e ambiental em todo o ciclo de vida do edifício.

Advanced energy efficient coordinated multi-point transmission for OFDMA

The ever-growing energy consumption in mobile networks stimulated by the expected growth in data tra ffic has provided the impetus for mobile operators to refocus network design, planning and deployment towards reducing the cost per bit, whilst at the same time providing a signifi cant step towards reducing their operational expenditure. As a step towards incorporating cost-eff ective mobile system, 3GPP LTE-Advanced has adopted the coordinated multi-point (CoMP) transmission technique due to its ability to mitigate and manage inter-cell interference (ICI). Using CoMP the cell average and cell edge throughput are boosted. However, there is room for reducing energy consumption further by exploiting the inherent exibility of dynamic resource allocation protocols. To this end packet scheduler plays the central role in determining the overall performance of the 3GPP longterm evolution (LTE) based on packet-switching operation and provide a potential research playground for optimizing energy consumption in future networks. In this thesis we investigate the baseline performance for down link CoMP using traditional scheduling approaches, and subsequently go beyond and propose novel energy e fficient scheduling (EES) strategies that can achieve power-e fficient transmission to the UEs whilst enabling both system energy effi ciency gain and fairness improvement. However, ICI can still be prominent when multiple nodes use common resources with di fferent power levels inside the cell, as in the so called heterogeneous networks (Het- Net) environment. HetNets are comprised of two or more tiers of cells. The rst, or higher tier, is a traditional deployment of cell sites, often referred to in this context as macrocells. The lower tiers are termed small cells, and can appear as microcell, picocells or femtocells. The HetNet has attracted signiffi cant interest by key manufacturers as one of the enablers for high speed data at low cost. Research until now has revealed several key hurdles that must be overcome before HetNets can achieve their full potential: bottlenecks in the backhaul must be alleviated, as well as their seamless interworking with CoMP. In this thesis we explore exactly the latter hurdle, and present innovative ideas on advancing CoMP to work in synergy with HetNet deployment, complemented by a novel resource allocation policy for HetNet tighter interference management. As system level simulator has been used to analyze the proposed algorithm/protocols, and results have concluded that up to 20% energy gain can be observed.

Reliable and energy efficient routing for ad hoc networks

In Mobile Ad hoc NETworks (MANETs), where cooperative behaviour is mandatory, there is a high probability for some nodes to become overloaded with packet forwarding operations in order to support neighbor data exchange. This altruistic behaviour leads to an unbalanced load in the network in terms of traffic and energy consumption. In such scenarios, mobile nodes can benefit from the use of energy efficient and traffic fitting routing protocol that better suits the limited battery capacity and throughput limitation of the network. This PhD work focuses on proposing energy efficient and load balanced routing protocols for ad hoc networks. Where most of the existing routing protocols simply consider the path length metric when choosing the best route between a source and a destination node, in our proposed mechanism, nodes are able to find several routes for each pair of source and destination nodes and select the best route according to energy and traffic parameters, effectively extending the lifespan of the network. Our results show that by applying this novel mechanism, current flat ad hoc routing protocols can achieve higher energy efficiency and load balancing. Also, due to the broadcast nature of the wireless channels in ad hoc networks, other technique such as Network Coding (NC) looks promising for energy efficiency. NC can reduce the number of transmissions, number of re-transmissions, and increase the data transfer rate that directly translates to energy efficiency. However, due to the need to access foreign nodes for coding and forwarding packets, NC needs a mitigation technique against unauthorized accesses and packet corruption. Therefore, we proposed different mechanisms for handling these security attacks by, in particular by serially concatenating codes to support reliability in ad hoc network. As a solution to this problem, we explored a new security framework that proposes an additional degree of protection against eavesdropping attackers based on using concatenated encoding. Therefore, malicious intermediate nodes will find it computationally intractable to decode the transitive packets. We also adopted another code that uses Luby Transform (LT) as a pre-coding code for NC. Primarily being designed for security applications, this code enables the sink nodes to recover corrupted packets even in the presence of byzantine attacks.

Improving energy efficiency in the road freight transport sector: the application of a vehicle approach

Several approaches can be used to analyse performance, energy consumption and CO2 emissions in freight transport. In this paper we define and apply a vehicle-oriented, bottom up survey approach, the so called ‘vehicle approach’, in contrast to a ‘supply chain approach’. The main objective of the approach is to assess the impacts of various freight transport operations on efficiency and energy use. We apply the approach, comparing official statistics on freight transport and energy efficiency in Britain and France. Results on freight intensity, vehicle utilisation, fuel use, fuel efficiency and CO2 intensity are compared for the two countries. The results indicate comparable levels of operational and fuel efficiency in road freight transport operations in the two countries. Issues that can be addressed with the vehicle approach include: the impacts of technology innovations and logistics decisions implemented in freight companies, and the quantification of the effect of policy measures on fuel use at the national level.

Energy efficiency and greenhouse gas emissions of different supply chains: a comparison of French, UK and Belgian cases

Freight transportation system is critical to economic activity but it carries significant environmental costs, notably GHG emissions and climate change : energy use and corresponding CO2 emissions is increasing faster in freight transport than in other sectors and this increase is primarily the result of increased trade. This paper compares the transport activities, associated energy consumption and CO2 emissions of different supply chains for a range of products in three countries: Belgium, France and United Kingdom. Among the products considered are furniture and ‘fruits & vegetables’. For each of these products, different supply chains, involving more or less transport activity and associated energy consumption are analysed in each country. The comparison highlights some of the main factors that influence GHG emissions for different supply chains and illustrates how they vary according to product and country of final distribution. In more detail, the paper addresses the main differences between the supply chains of these products namely, the origin of their sourcing, the logistical organisation between production and retail and different types of retail outlet. The origin of the sourcing impact is mainly related to distance. The impact of the logistical organisation between raw material and retail on GHG emissions is linked to the mode and vehicle choice and to the load factor. As for retail, the consumer trip emissions, between his home and the retail outlet, are also an important part of the whole supply chain emissions. It is worthwhile to notice that our goal in this project is to consider the whole supply chain, from production to consumption. Therefore a particular focus is put on the mobility behaviours of consumers purchasing the studied products during their shopping and dropping back home activities related to these products. Especially a web based survey has been conducted and the gathered results offer an opportunity for drawing a more detailed picture of the associated CO2 emissions. This paper uses the results of an ongoing research on supply chain energy efficiency, funded by ADEME (the French Energy Agency) through the French program on transport research (PREDIT). This research is based on a comprehensive review of the various approaches to quantifying the environmental impacts of supply chains together with data collection from a range of organisations including manufacturers, retailers and transport companies. We will first present the developed methodologies, then the results corresponding to each studied product will be described. A discussion of the potential application of the research approach to the wider debate about the environmental impact of freight transport and the scope for GHG emissions reduction targets to be achieved will be included.

O que se diz quando se pensa em energia? Reflexões sobre o tema da energia a partir das representações dos jovens e dos professores de uma escola secundária

A importância da eficiência energética em edifícios de uso coletivo através do aperfeiçoamento das práticas de conservação e da implementação de novas tecnologias, enfatiza o papel que a mudança de comportamentos associados ao uso e à conservação de energia detém na melhoria desta eficiência. Mas como contribuir para a alteração de comportamentos sem antes conhecer os sentidos e significados sociais atribuídos à energia? Considerando que este conhecimento é fulcral para a alteração de comportamentos, recorre-se aos resultados de um inquérito por questionário sobre o uso de energia desenvolvido com alunos e professores de uma escola secundária de Lisboa recentemente intervencionada, para caracterizar as representações sociais da energia destes dois grupos (cf. projeto Net Zero Energy School - Reaching the Community – FCT/MIT Portugal). A primeira pergunta do questionário solicitava aos inquiridos que indicassem as primeiras três palavras que lhes vinham à ideia quando pensavam em energia. A maioria dos alunos associou a palavra “energia” às energias renováveis e à luz, e os professores à ambiente e sustentabilidade energética, às questões de natureza económica e de consumo. Explora-se aqui os aspetos centrais e periféricos das representações da energia na explicitação dos sentidos e significados atribuídos a energia e discutem-se as questões fundamentais a considerar no âmbito da mudança de comportamentos de uso e conservação de energia numa dada comunidade escolar.

Energy efficiency and greenhouse gas emissions of different supply chains: a comparison of French, UK and Belgian cases

Freight transportation system is critical to economic activity but it carries significant environmental costs, notably GHG emissions and climate change : energy use and corresponding CO2 emissions is increasing faster in freight transport than in other sectors and this increase is primarily the result of increased trade. This paper compares the transport activities, associated energy consumption and CO2 emissions of different supply chains for a range of products in three countries: Belgium, France and United Kingdom. Among the products considered are furniture and fruits & vegetables. For each of these products, different supply chains, involving more or less transport activity and associated energy consumption are analysed in each country. The comparison highlights some of the main factors that influence GHG emissions for different supply chains and illustrates how they vary according to product and country of final distribution. In more detail, the paper addresses the main differences between the supply chains of these products namely, the origin of their sourcing, the logistical organisation between production and retail and different types of retail outlet. The origin of the sourcing impact is mainly related to distance. The impact of the logistical organisation between raw material and retail on GHG emissions is linked to the mode and vehicle choice and to the load factor. As for retail, the consumer trip emissions, between his home and the retail outlet, are also an important part of the whole supply chain emissions. It is worthwhile to notice that our goal in this project is to consider the whole supply chain, from production to consumption. Therefore a particular focus is put on the mobility behaviours of consumers purchasing the studied products during their shopping and dropping back home activities related to these products. Especially a web based survey has been conducted and the gathered results offer an opportunity for drawing a more detailed picture of the associated CO2 emissions. This paper uses the results of an ongoing research on supply chain energy efficiency, funded by ADEME (the French Energy Agency) through the French program on transport research (PREDIT). This research is based on a comprehensive review of the various approaches to quantifying the environmental impacts of supply chains together with data collection from a range of organisations including manufacturers, retailers and transport companies. We will first present the developed methodologies, then the results corresponding to each studied product will be described. A discussion of the potential application of the research approach to the wider debate about the environmental impact of freight transport and the scope for GHG emissions reduction targets to be achieved will be included.

Impact of energy-using product policies

Energy-using products (EuPs), such as domestic appliances, audio-visual and ICT equipment contribute significantly to CO2 emissions, both in the domestic and non-domestic sectors. Policies that encourage the use of more energy efficient products can therefore generate significant reductions in overall energy consumption and hence, CO2 emissions. To the extent that these policies cause an increase the average production cost of EuPs, they may impose economic costs on producers, or on consumers, or on both. In this theoretical paper, an adaptation of a simple vertical product differentiation model – in which products are characterised in terms of their quality and their energy consumption – is used to analyse the impact of the different EuP polices on product innovation and to assess the resultant economic impacts on producers and consumers. It is shown that whereas the imposition of a binding product standard for energy efficiency unambiguously reduces aggregate profit and increases the average market price in the absence of any learning effects, the introduction or strengthening of demand-side measures (such as energy labelling) may reduce, or increase, aggregate profit. Even in the case where the overall impact is unambiguously negative, the effects of product innovation and learning can be in either direction.

Product innovation and the costs of energy-using product policies

Energy-using Products (EuPs) contribute significantly to the United Kingdom’s CO2 emissions, both in the domestic and non-domestic sectors. Policies that encourage the use of more energy efficient products (such as minimum performance standards, energy labelling, enhanced capital allowances, etc.) can therefore generate significant reductions in overall energy consumption and hence, CO2 emissions. While these policies can impose costs on the producers and consumers of these products in the short run, the process of product innovation may reduce the magnitude of these costs over time. If this is the case, then it is important that the impacts of innovation are taken into account in policy impact assessments. Previous studies have found considerable evidence of experience curve effects for EuP categories (e.g. refrigerators, televisions, etc.), with learning rates of around 20% for both average unit costs and average prices; similar to those found for energy supply technologies. Moreover, the decline in production costs has been accompanied by a significant improvement in the energy efficiency of EuPs. Building on these findings and the results of an empirical analysis of UK sales data for a range of product categories, this paper sets out an analytic framework for assessing the impact of EuP policy interventions on consumers and producers which takes explicit account of the product innovation process. The impact of the product innovation process can be seen in the continuous evolution of the energy class profiles of EuP categories over time; with higher energy classes (e.g. A, A+, etc.) entering the market and increasing their market share, while lower classes (e.g. E, F, etc.) lose share and then leave the market. Furthermore, the average prices of individual energy classes have declined over their respective lives, while new classes have typically entered the market at successively lower “launch prices”. Based on two underlying assumptions regarding the shapes of the “lifecycle profiles” for the relative sales and the relative average mark-ups of individual energy classes, a simple simulation model is developed that can replicate the observed market dynamics in terms of the evolution of market shares and average prices. The model is used to assess the effect of two alternative EuP policy interventions – a minimum energy performance standard and an energy-labelling scheme – on the average unit cost trajectory and the average price trajectory of a typical EuP category, and hence the financial impacts on producers and consumers.

Energy-aware Workflow Scheduling and Fuzzy Logic Based Capacity Provisioning in Cloud Environment

Thesis (Master's)--University of Washington, 2015

Convergência para NZEB de um edifício classificado

Dissertação para obtenção do grau de Mestre em Engenharia Civil na Área de Edificações

NZEB e os novos revestimentos

Dissertação de natureza científica para obtenção do grau de Mestre em Engenharia Civil na Área de Especialização de Edificações

Relatório de estágio em gabinete de engenharia na componente de climatização

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia Mecânica com Especialização em Energia, Climatização e Refrigeração