An Energy-Aware Agent-Based Resource Allocation Using Targeted Load Balancer for Improving Quality of Service in Cloud Environment

Abstract

Abstract In order to manage the load on dispersed data centers and cut down on energy established on time usage, agent-based resource allocation is given attention. Using a targeted load balancer (TLB), we suggest an energy-aware agent-based resource allocation in this research to enhance quality of service in a cloud setting. This agent is first set up to keep track of the resource load resulting from the request that has been assigned a job. Cloud watch also keeps an eye on energy levels to determine the typical payload size of resource execution. The TLB establishes new instance state to assign the resource based on the payload weight. To shorten the execution time, the dynamic hyper switching model develops a balancing mechanism. The suggested system achieves high performance in resource management by creating load balancer that is efficiently targeted to cut down on computation time and cost depending on energy levels. In comparison to existing techniques, the suggested parallelized homogeneous job in the cloud environment produces greater performance up to 95.5% while maintaining the time execution utilizing switching state of execution. This maintains the reduced CPU consumption, which dependent on the lowering of temporal complexity.