A task assignment algorithm based on particle swarm optimization and simulated annealing in Ad-hoc mobile cloud

An Ad-hoc mobile cloud can be constructed upon local devices, where devices work together and share resources. However, the deployment of Ad-hoc mobile cloud is hindered by the limitation of mobile devices, such as storage capacities and relatively short battery lives. To overcome such problem, this paper proposes a task assignment algorithm based on particle swarm optimization and simulated annealing (PSO-SA) in Ad-hoc mobile cloud. The main contribution of our work is considering the fairness of resource utilization of all devices and total energy consumption of all devices under the constraint of time delay. We also combine particle swarm optimization and simulated annealing to avoid falling into local optimal solution and guarantee the convergence speed. PSO-SA is used to make the decision for task assignment to achieve two main objectives which include minimizing total energy consumption and balancing the fairness of resource utilization of all devices. Through the simulation, it is shown that compared with other population-based optimization algorithms PSO-SA has less energy consumption and the result of PSO-SA can be close to the optimal solution.