One way to conserve energy in cloud data centers is to transition idle servers into a power saving state during periods of low utilization. Dynamic virtual machine (VM) consolidation (VMC) algorithms are proposed to create idle times by periodically repacking VMs on the least number of physical machines (PMs). Existing works mostly apply VMC on top of centralized, hierarchical, or ring-based system topologies which result in poor scalability and/or packing eciency with increasing number of PMs and VMs. In this paper we propose a novel fully decentralized dynamic VMC schema based on an unstructured peer-to-peer (P2P) network of PMs. The proposed schema is validated using three well known VMC algorithms: First-Fit Decreasing (FFD), Sercon, V-MAN, and a novel migration-cost aware ACO-based algorithm. Extensive experiments performed on the Grid'5000 testbed show that once integrated in our fully decentralized VMC schema, traditional VMC algorithms achieve a global packing eciency very close to a centralized system. Moreover, the system remains scalable with increasing number of PMs and VMs. Finally, the migration-cost aware ACO-based algorithm outperforms FFD and Sercon in the number of released PMs and requires less migrations than FFD and V-MAN.

SummaryModeling and simulation play a major role in complex system engineering. In Systems of Systems (SoS) engineering, a special case of complex systems engineering, they help to better understand and identify the side effects associated with the integration of autonomous constituent systems. Simulation is also a way of apprehending the emerging behaviors from this integration. The dynamic and evolving nature of the SoS environment has led us to rely on their most stable part to define them, namely their mission. In this paper, we propose a simulation framework for SoS based on a mission conceptual model. Mission is defined as a set of situations that require reactions. Situations are defined by rules on facts related to the SoS environment. Reactions are defined as orchestrations of services from constituent systems (subsystems) that must be triggered when a situation is identified. We present this simulation approach through a case study on a Telediabet SoS.

International audienceFor billions of people, mobile phones have become essential communication means to produce and share multimedia contents. Most current sharing solutions rely on centralized online solutions, requiring a permanent Internet connectivity, with the consequence of increasing –and sometimes of overloading– the networks of mobile operators. This paper presents an anycast communication model allowing to offload data in wide intermittently-connected hybrid networks, using a peer-to-peer approach. Such networks combine an infrastructure part that relies on fixed equipments with intermittently or partially connected parts formed by mobile devices. This model has been implemented in a middleware platform called Nephila. Simulation results confirm that, with Nephila, thousands of people roaming a medium-size city center can share multimedia contents , using a combination of stable and transient transmission links