Cloud service reliability modelling and optimal task scheduling

Cloud computing enables service sharing in a massive scale via network access to a pool of configurable computing resources. It has to allocate resources adaptively for tasks and applications to be executed effectively and reliably in a large scale, highly heterogeneous environment. Resource allocation in cloud computing is an NP-hard problem. In this study, the authors conduct a reliability analysis of cloud services by applying a Markov-based method. They formulate the cloud scheduling problem as a multi-objective optimisation problem with constraints in terms of reliability, makespan, and flowtime. Furthermore, they propose a genetic algorithm-based chaotic ant swarm (GA-CAS) algorithm, in which four operators and natural selection are applied, to solve this constrained multi-objective optimisation problem. Simulation results have demonstrated that GA-CAS generally speeds up convergence and outperforms other meta-heuristic approaches.