Self-Adapting Security Monitoring in Eucalyptus Cloud Environment

Abstract

This paper discusses the importance of virtual machine (VM) scheduling strategies in cloud computing environments for handling the increasing number of tasks due to virtualization and cloud computing technology adoption. The paper evaluates legacy methods and specific VM scheduling algorithms for the Eucalyptus cloud environment and compare existing algorithms using QoS. The paper also presents a self-adapting security monitoring system for cloud infrastructure that takes into account the specific monitoring requirements of each tenant. The system uses Master Adaptation Drivers to convert tenant requirements into configuration settings and the Adaptation Manager to coordinate the adaptation process. The framework ensures security, cost efficiency, and responsiveness to dynamic events in the cloud environment. The paper also presents the need for improvement in the current security monitoring platform to support more types of monitoring devices and cover the consequences of multi-tenant setups. Future work includes incorporating log collectors and aggregators and addressing the needs of a super-tenant in the security monitoring architecture. The equitable sharing of monitoring resources between tenants and the provider should be established with an adjustable threshold mentioned in the SLA. The results of experiments show that Enhanced Round-Robin uses less energy compared to other methods, and the Fusion Method outperforms other techniques by reducing the number of Physical Machines turned on and increasing power efficiency.