Hierarchical Multi-Agent Optimization for Resource Allocation in Cloud Computing

In cloud computing, an important concern is to allocate the available resources of service nodes requested tasks on demand and make objective function optimum, i.e., maximizing resource utilization, payoffs bandwidth. This paper proposes a hierarchical multi-agent optimization (HMAO) algorithm in order maximize utilization bandwidth cost minimum for computing. The proposed HMAO combination genetic (GA) (MAO) algorithm. With improved GA implemented find set that are used deploy tasks. A decentralized-based MAO presented minimize cost. We study effect key parameters by Taguchi method evaluate performance results. When compared with fast elitist non-dominated sorting (NSGA-II) algorithm, simulation results demonstrate more effective than existing solutions solve problem allocation large number Furthermore, we provide comparison first-fit greedy approach on-line allocation.