Using a multi-agent system and artificial intelligence for monitoring and improving the cloud performance and security

Abstract Cloud Computing is one of the most intensively developed solutions for large-scale distributed processing. Effective use of such environments, management of their high complexity and ensuring appropriate levels of Quality of Service (QoS) require advanced monitoring systems. Such monitoring systems have to support the scalability, adaptability and reliability of Cloud. Most of existing monitoring systems do not incorporate any Artificial Intelligence (AI) algorithms for supporting the change inside the task stream or environment itself. They focus only on monitoring or enabling the control of the system as a part of a separated service. An effective monitoring system for the Cloud environment should gather information about all stages of tasks processing and should actively control the monitored environment. In this paper, we present a novel Multi-Agent System based Cloud Monitoring (MAS-CM) model that supports the performance and security of tasks gathering, scheduling and execution processes in large-scale service-oriented environments. Such models are explicitly designed to control the performance and security objectives of the environment. In our work, we focus on prevention of unauthorized task injection and modification, optimization of scheduling process and maximization of resource usage. We evaluate the effectiveness of MAS-CM empirically using an evolutionary driven implementation of Independent Batch Scheduler and FastFlow framework. The obtained results demonstrate the effectiveness of the proposed approach and the performance improvement.