PROJECT TITLE :

Performance analysis of Bayesian coalition game-based energy-aware virtual machine migration in vehicular mobile cloud

ABSTRACT:

To provide computing and communication services to mobile clients, vehicular mobile cloud computing has gained ton of attention in recent times. But, one of the largest challenges for the graceful execution of these services during this setting is the intelligent usage of VMs that might be overloaded because of various requests from mobile clients like vehicles and mobile devices to access these services. But, poor utilization of VMs during this environment causes a lot of energy to be wasted. To handle this issue, we have a tendency to propose Bayesian coalition game as-aservice for intelligent context-switching of VMs to support the above outlined services in order to scale back the energy consumption, so that clients will execute their services while not a performance degradation. Within the proposed scheme, we have used the ideas of learning automata (LA) and game theory in which LA are assumed because the players such that each player has a private payoff primarily based upon the energy consumption and cargo on the VM. Players interact with the stochastic atmosphere for taking action like the choice of appropriate VMs and based upon the feedback received from the atmosphere, they update their action chance vector. The performance of the proposed theme is evaluated by using various performance evaluation metrics like context-switching delay, overhead generated, execution time, and energy consumption. The results obtained show that the proposed theme performs well with respect to the aforementioned performance metrics. Specifically, using the proposed theme there's a reduction of ten percent in energy consumption, twelve p.c in network delay, 5 p.c in overhead generation, and 10 percent in execution time.