A proactive resource allocation method based on adaptive prediction of resource requests in cloud computing

Abstract With the development of big data and artificial intelligence, cloud resource requests present more complex features, such as being sudden, arriving in batches diverse, which cause allocation to lag far behind an unbalanced utilization that wastes resources. To solve this issue, paper proposes a proactive method based on adaptive prediction computing. Specifically, first runs test improves accuracy requests, then, it builds multiobjective optimization model, alleviates latency balances utilizations different types resources physical machine. Furthermore, evolutionary algorithm, Nondominated Sorting Genetic Algorithm with Elite Strategy (NSGA-II), is improved further reduce time by accelerating solution speed model. The experimental results show realizes balanced between CPU memory reduces at least 43% (10 threads) compared Improved Strength Pareto Evolutionary algorithm (SPEA2) NSGA-II methods.