Fire Hawk optimization-enabled deep learning scheme based hybrid cloud container architecture for migrating interoperability based application

Virtualization is an indispensable part of the cloud for the objective of deploying different virtual servers over the same physical layer. However, the increase in the number of applications executing on the repositories results in increased overload due to the adoption of cloud services. Moreover, the migration of applications on the cloud with optimized resource allocation is a herculean task even though it is employed for minimizing the dilemma of allocating resources. In this paper, a Fire Hawk Optimization enabled Deep Learning Scheme (FHOEDLS) is proposed for minimizing the overload and optimizing the resource allocation on the hybrid cloud container architecture for migrating interoperability based applications This FHOEDLS achieves the load prediction through the utilization of deep CNN-GRU-AM model for attaining resource allocation and better migration of applications. It specifically adopted the Fire Hawk Optimization Algorithm (FHOA) for optimizing the parameters that influence the factors that aid in better interoperable application migration with improved resource allocation and minimized overhead. It considered the factors of resource capacity, transmission cost, demand, and predicted load into account during the formulation of the objective function utilized for resource allocation and application migration. The cloud simulation of this FHOEDLS is achieved using a container, Virtual Machine (VM), and Physical Machine (PM). The results of this proposed FHOEDLS confirmed a better resource capability of 0.418 and a minimized load of 0.0061.