Background: In the cloud environment, satisfaction of service level agreement (SLA) is the prime objective. It can be achieved by providing services in minimum time in an efficient manner at the lowest cost by efficiently utilizing the resources. This will create a win-win situation for both consumer and service provider. Through literature analysis, it has been found that the procedure of resource optimization is quite costly and time-consuming. Objective: The research aim is to design and develop an efficient load-balancing technique for the satisfaction of service level agreement and the utilization of resources in an efficient manner. Methods: To achieve this, authors have proposed a new load-balancing algorithm named eB-GAP by picking the best features from Bacterial Foraging, Genetic, Particle-Swarm, and Ant-Colony algorithm. Based on the availability of resources and load on a virtual machine, a fitness value is assigned to all virtual machines. Results: A newly arrived task is mapped with the fittest virtual machine. Whenever a new task is mapped or left the system, the fitness value of the virtual machine is updated. In this manner, the system achieves the satisfaction of service level agreement, the balance of the load, and efficient utilization of resources. To test the proposed approach, the authors have used the real-time cloud environment of amazon web service. In this, waiting time, completion time, execution time, throughput, and cost have been computed in a real-time environment.

Cost is the backbone of any business model to sustain and growth in the competitive business market. Considering this, higher energy consumption may affect the operational cost of any industry. Cloud computing is one of the most popular IT business model for service provider and its users. It is observed in many research, that the average cost of the services are highly dependent upon the run time and power consumption. More power consumption effect the environmental things as well. In this review, more than 100 research articles are considered to evaluate the energy consumption methods, issues and challenges from 2009 to 2021. Based on the study, the energy-aware load balancing methods are classified into four major clusters. The most cited methods are compared based on method used, platform where it is deployed, different evaluation parameters like cost, run time, Virtual Machine utilization, Service-level-agreement violation rate, and Quality-of-service QoS. The result of this review is presented as open research issues and challenges for forthcoming research.