A Method for Load Balancing and Energy Optimization in Cloud Computing Virtual Machine Scheduling

In today's world, cloud computing delivers the payable on demand resources like platform, application, software, and infrastructure as a service. Because it has a variety of advantages, such as adaptability, scalability, dependability, capability, safety, swiftness, and all-time supportability, it is quite popular in all over the world. In this research, proposes a Load-balanced and Energy Optimization method (user to server) in Cloud Computing (LEOCC). The user sends the request to the core switch, where first check if the service is available in the core switch (check the load of each core switch) and if not then forward the request to the next level of switch, the aggregator switch. Here also measure the load of each aggregator switch and select a lightly loaded switch for the service request, which forwards the request to the next level for access switch while the service is unavailable. The same load and service are checked in the access layer switch also, if the requested service is unavailable, it is forwarded to a lightly loaded server for response generation and sent to the user via the reverse path. Otherwise, the response is sent by the access switch. The performance measured by average energy consumption, load, average delay, data received and task handling by virtual machine. The results of LEOCC are compared with various scheduling approaches, i.e., round robin, random, and dens. Finally, LEOCC provides better load balancing and energy optimization in cloud computing as compared to other approaches.