Data centers are major contributors to the emission of carbon dioxide to the atmosphere, and this contribution is expected to increase in the following years. This has encouraged the development of techniques to reduce the energy consumption and the environmental footprint of data centers. Whereas some of these techniques have succeeded to reduce the energy consumption of the hardware equipment of data centers (including IT, cooling, and power supply systems), we claim that sustainable data centers will be only possible if the problem is faced by means of a holistic approach that includes not only the aforementioned techniques but also intelligent and unifying solutions that enable a synergistic and energy-aware management of data centers.
In this paper, we propose a comprehensive strategy to reduce the carbon footprint of data centers that uses the energy as a driver of their management procedures. In addition, we present a holistic management architecture for sustainable data centers that implements the aforementioned strategy, and we propose design guidelines to accomplish each step of the proposed strategy, referring to related achievements and enumerating the main challenges that must be still solved.
In microgrids, the integration of distributed energy resources (DERs) in the residential sector can improve power reliability, and potentially reduce power demands and carbon emissions. Improving the utilization of renewable energy in households is a critical challenge for DERs. In this regard, renewable power sharing is one of the possible solutions to tackle this problem. Even though this solution has attracted significant attention recently, most of the proposed power sharing frameworks focus more on centralized schemes. In contrast, in this paper, the performance of a proposed distributed power sharing framework is investigated. The problem is formulated as a repeated game between households in a microgrid. In this game, each household decides to cooperate and borrow/lend some amount of renewable power from/to a neighboring household, or to defect and purchase the entire demands from the main grid based on a payoff function. The Nash equilibrium of this game is characterized and the effect of the strategies taken by the households on the system is analyzed. We conduct an extensive evaluation using real demand data from 12 households of different sizes and power consumption profiles in Stockholm. Numerical results indicate that cooperation is beneficial from both an economical and environmental perspective and that households can achieve cost savings up to 20 %.
As a result of the rapid growth of Cloud Computing, several Cloud middleware solutions for the creation and automated management of virtual appliances have been released. Generally, these solutions offer some predefined scheduling policies to manage the provider infrastructure, but additional tuning of the policies is often needed to fully align their behavior with the provider interests. However, current middleware solutions do not offer ways to do this without stopping and recompiling the middleware. This paper proposes a solution that separates scheduling policies from the managers that interpret them, to allow the behavior of the management system to be changed without re-coding the managers. In this way, the middleware can adapt to changing requirements by disabling policies or replacing old policies with new ones without shutting down the system. We propose a new policy language for the definition of management policies and we enable the EMOTIVE Cloud middleware to use these policies by integrating in the middleware the needed policy management framework for parsing and generating code on demand. We demonstrate with real experiments that our policy management framework mimics the expressiveness of scheduling policies in real Cloud middleware and provides more expressiveness if needed. The overhead of the policy management framework is low, but its performance degrades, especially in large datacenters, due to the low scalability of the EMOTIVE monitoring solution.
A set of wireless mobile terminals, which cooperate by routing packets to each other creates a Mobile Ad-hoc Network (MANET). MANETs are continuing to grow their interest in research environment and they are attracting attention for their potential use in several fields such as collaborative computing and disaster recovery environments. Considering mobility of the terminals, the topology changes rapidly and routing becomes a key process for operation of MANETs. In this paper, we analyze the performance of Better Approach To MANET (BATMAN) routing protocol in an outdoor bridge environment considering mobility and vertical communication. We implement two scenarios on our testbed and evaluate the performance in terms of throughput and packetloss.
During last decade more and more old people live alone and the number of old people that need medical care is increased. The lack of doctors and the increase of the medical cost is becoming a big problem. Therefore, IT-based information systems should be implemented to help solve this problem. In this paper, we present the experimental results and evaluation of the SmartBox stimulation device for medical applications using a P2P system which is based on JXTA-Overlay. The SmartBox is integrated with our P2P system as a useful tool for monitoring and controlling patients activities. We found by experimental results that by SmartBox we can check the patient's situation. We carried out experiments with a patient in the bed and changed the temperature of the room. From the experimental results, we conclude that the use of SmartBox is an effective way for medical applications.