Energy Efficiency in Future Home Environments: A Distributed Approach

Abstract

In this paper, a new architecture for sharing resources amongst horne environments is proposed. Our approach goes far beyond traditional systems for distributed virtualization like Planetlab or Grid computing, since it relies on complete decentralization in a peer-to-peer Iike manner, and above all, aims at energy efficiency. Energy metrics are defined, which have to bc optimized by the system. The system itself uses virtualization to transparently move tasks from one horne to another in order to optimally utilize the existing computing power. An overview of our proposed architecture is presented as weil as an analytical evaluation of the possible energy savings in a distributcd example scenario where computers share downloads.

Network Virtualization in Future Home Environments

“…In contrast, the VHE proposed in this paper realizes a home centric view on the network, where virtualization is the clue to aggregate and consolidate distributed hardware resources. This understanding of a virtualization based VHE architecture was already introduced in [3] and deepened with more simulation results in [5]. An economic model for fostering fair resource sharing was presented in [4].…”

“…The VHE architecture approach as it was introduced in [3,4,5,6] enables the energy-efficient sharing of hardware resources amongst home networks. The main goal of the architecture is to achieve a consolidation of load (e.g.…”

“…Simulation results concerning VHE have already been shown in [3,4,5,6]. The simulation itself is a discrete event simulation built with the general purpose programming language Java.…”

“…Following energy-saving concepts of data-centers, an energy-efficient Virtual Home Environment (VHE) architecture is suggested and evaluated in [3,4,5,6] and presented in Section 3. Energy wastage in data centers is mainly caused by underutilized hardware.…”

“…Furthermore, network virtualization approaches are evaluated by simulation. Initial simulations and evaluations of the suggested VHE architecture have already been shown in [3,4,5]. In this paper, the simulation is extended by network virtualization.…”