Cloud-fog based load balancing using shortest remaining time first optimization

Abstract

Micro Grid (MG) integrated with cloud computing to develop an improved Energy Management System (EMS) for end users and utilities. For data processing on cloud new applications are developed. To overcome the overloading on cloud data centers fog computing is integrated. Three-layered framework is proposed in this paper to overcome the load of consumers. First layer is end-user layer which contains clusters of smart buildings. These smart buildings consist smart homes. Each smart home having multiple appliances. Controllers are used to connect with fog. Second and central layer consists of fogs with Virtual Machines (VMs). Fogs receive user requests and forwards that to MG. If the request is out of bound then MG requests to cloud using fog. Third layer contains cloud which consists data centers and utility. For load balancing three different techniques are used. Round Robin (RR), Throttled and Shortest Remaining Time First (SRTF) used to compare results of VMs allocation. Results show that proposed technique performed better cost wise. However, RR and Throttled outperformed SRTF overall. Closest Data Center Service broker policy is used for fog selection.