Reliability modelling and optimization for microservice‐based cloud application using multi‐agent system

In the process of continuous development Internet Things, cloud computing has been applied in many fields, how to guarantee quality service, such as low latency, high bandwidth, reliability etc., become a challenging problem. This paper proposes method model and optimize for microservice-based applications using multi-agent system (MAS), thus maximizing dynamically scheduling microservices minimize delay within budget. Firstly, dynamic microservice scheme is proposed provide efficient services by MAS. A hierarchical formed predicated Petri net (PrT net) properties constructed are analysed. Secondly, agents have utilized describe essential characteristics applications. The partial critical path (PCP) aims maximize under limitation budget meet user-defined deadline. Finally, PCPRO algorithm environment, which suitable different scientific workflows environment. effectiveness this verified simulation, experiment results show method.