ICT as Key Technology against Global Warming

Two IT-system control methods, which realize efficient battery usage for battery-powered IT systems targeting developing countries such as India, are proposed. The proposed methods control the IT equipment and cooling power collaboratively on the basis of a forecast of power outage duration. To quantitatively evaluate these methods, power outages in Bangalore, India, were measured. The proposed methods were evaluated by using this measured power outage data. According to the evaluation results, the proposed methods can improve a measure of battery efficiency, namely, IT-used-energy (Q _t )/battery-used-energy (Q _u ), by 39% compared to that of conventional IT systems.

The incessant need for energy has raised its cost to unexpected heights. In response to this situation, many projects have been started in order to save energy. In this context, the RIDER project tries to identify pathways for providing recommendations to decrease those costs. The main goal of this project is to develop a weak system dependency of energy management framework which could be applied to different systems and various scales. Particularly, our work focuses on proposing generic optimization techniques for energy management systems. Therefore, our supervision system has to follow RIDER requirements and consider the weak system dependency as well as genericity (i.e., a multi-scale applicable solution). In order to improve the thermal comfort level and/or reduce energy costs, RIDER supervision rules allow the computation of the most relevant setpoints to be provided to the energy control system. Since thermal comfort is a subjective multidimensional concept, an interpretable model is introduced. For this, Multi Attribute Utility Theory is introduced in order to make the multidimensional comfort control problem tractable. In fact, the aggregate objective thermal comfort function proposed by literatures; makes control not intuitive. Thus, interpretable and easily tractable control rules must be designed. The control of thermal comfort is directly based on comfort performance and not on the behavioral model of the supervised building. It guarantees as well its weak system dependency as its multi-scale applicability. This model is embedded in a decision support system that supervises the building energy system control.

Buildings are key mediators between human activity and the environment around them, but details of energy usage and activity in buildings is often poorly communicated and understood. ECOS is an Eco-Visualization project that aims to contextualize the energy generation and consumption of a green building in a variety of different climates.

The ECOS project is being developed for a large public interactive space installed in the new Science and Engineering Centre of the Queensland University of Technology that is dedicated to delivering interactive science education content to the public. This paper focuses on how design can develop ICT solutions from large data sets to create meaningful engagement with environmental data.

In this paper, we present three performance and energy case studies of benchmark applications in the OmpSs environment for task based programming. Different parallel and vectorized implementations are evaluated on an Intel^® Core^TMi7-2600 quad-core processor. Using FLOPS/W derived from chip MSR registers, we find AVX code to be clearly most energy efficient in general. The peak on-chip GFLOPS/W rates are: Black-Scholes (BS) 0.89, FFTW 1.38 and Matrix Multiply (MM) 1.97. Experiments cover variable degrees of thread parallelism and different OmpSs task pool scheduling policies. We find that maximum energy efficiency for small and medium sized problems is obtained by limiting the number of parallel threads. Comparison of AVX variants with non-vectorized code shows ≈ 6 − 7 × (BS) and ≈ 3 − 5 × (FFTW) improvements in on-chip energy efficiency, depending on the problem size and degree of multithreading.

We analyze the energy-performance balance of a task-parallel computation of an ILU-based preconditioner for the solution of sparse linear systems on multi-core processors. In particular, we elaborate a theoretical model for the power dissipation, and employ it to explore the effect of the processor power states on the time-power-energy interaction for this calculation. Armed with the insights gained from this study, we then introduce two energy-saving mechanisms which, incorporated into the runtime in charge of the parallel execution of the algorithm, improve energy efficiency by 6.9%, with a negligible impact on performance.

Energy management in large scale distributed systems has an important role to minimize the contribution of Information and Communication Technology (ICT) industry in global CO2 footprint and to decrease the energy cost. Content Distribution Networks (CDNs) are one of the popular large scale distributed systems, in which the client requests are forwarded towards servers and are fulfilled either by surrogate servers or by the origin server, depending upon the contents availability and the CDN redirection policy. In this paper we explore the energy consumption in CDNs using different client redirection policies. We propose a new model to measure energy consumption in the CDN surrogates. The surrogate servers’ utilization is used as a key criteria to measure the consumed energy. We show the impact of minimizing the number of surrogate servers on the energy consumption and on the other performance evaluation parameters in CDNs (e.g. servers utilization, mean response time, byte hit ratio). We also exhibit, how the energy consumption and the other performance evaluation parameters are affected by the change in the number of content requests, i.e. by the traffic load.

Due to the increasing usage of modern IT service centers, energy consumption has been one of the top concerns for administrators. Many indicators have been proposed with different aims at several levels, but what is missing is an approach for presenting them together within meaningful indexes. The goal of this paper is to introduce our approach to support inter-relationships identification for heterogeneous indicators. The presented aggregation framework aims to make indicators comparable through normalization functions and to properly express the indicator relevance within aggregated values. Thus, the normalization deals with four indicators thresholds and the aggregation calculates the indicator violation impact from the system perspective. The approach is demonstrated with GAMES project testbed measured indicators and presented in a dashboard prototype tool.

EC4MACS (European Consortium for Modelling of Air Pollution and Climate Strategies) establishes a suite of modelling tools for a comprehensive integrated assessment of the effectiveness of emission control strategies for air pollutants and greenhouse gases. This assessment brought together expert knowledge in the fields of energy, transport, agriculture, forestry, land use, atmospheric dispersion, health and vegetation impacts, and it developed a coherent outlook into the future options to reduce atmospheric pollution in Europe. In this paper, first we introduce background to the EC4MACS framework, which links well-established sectoral models of the most relevant policy areas. In this context, an ETL package is used to gather extracted information from multiple model data sources. The integrated data are loaded into the GAINS (Greenhouse gas-Air pollution Interactions and Synergies) Data Warehouse. Afterwards, a web service based toolbox is developed to publish EC4MACS key data, which are represented in this paper in term of case studies.

Life Cycle Assessment provides a well-accepted methodology for modelling environmental impacts of human activities. This methodology relies on the decomposition of a studied system into interdependent processes. Several organisations provide processes databases containing several thousands of processes with their interdependency links. The usual work-flow to manage those databases is based on the manipulation of individual processes which turns out to be a very harnessing work. We propose a new work-flow for LCA inventory databases maintenance based on the addition of semantic information to the processes they contained. This method eases considerably the modelling process and also offers a more understandable model of the dependencies links. In this paper, we explain our approach and some key parts of the implementation. We also present a case study based on the U.S. electricity production and an experiment on the scalability of our implementation.