Performance optimization for cyber foraging network via dynamic spectrum allocation

Recently, cyber foraging has been proposed to reduce the application response time and to save energy for the mobile hosts by offloading the resource-demanding tasks to the surrogates via wireless networks. However, communication overheads are further aggravated in the cyber foraging network (CFN), where multi-hosts share the same spectrum to offload tasks. Therefore, it is important for the CFN to properly allocate the spectrum to multi-hosts to improve the network performance. In this paper, we deeply discuss the challenging issue of the dynamic spectrum allocation for the infrastructure-based CFN, and aim to minimize the total completion time of the multiple remote tasks offloaded by mobile hosts with the constraints that the task completion time of each remote task is less than a preset threshold. Firstly, a system-level workflow is proposed to handle the requests of offloading tasks for mobile hosts. Then, we formulate the optimization problem of the dynamic spectrum allocation for the infrastructure-based CFN. We propose an algorithm to test the feasibility of satisfying the task completion time constraint for each remote task simultaneously. Moreover, we derive an optimal solution of the dynamic spectrum allocation. Conducted simulation results show the validity of the proposed dynamic spectrum allocation algorithm.