Скачать или смотреть ZINC 2020 - Optimization of Application Deployment Delay with Efficient Task Scheduling in Cloud...

Optimization of Application Deployment Delay with Efficient Task Scheduling in Cloud-Based Smart Home Platform

Janan joy Rajkumar (Ecole De Technologie Superieure, Canada); Chuan Pham (Kyung Hee University, Korea (South)); Kim Khoa Nguyen (University of Quebec, Canada); Mohamed Cheriet (Ecole de technologie superieure (University of Quebec), Canada)

Smart home platform consists of various technologies, such as sensor networks, Internet of Things (IoT), and cloud computing, etc. In such a platform, home applications are deployed using Software as a Service (SaaS) deployment model. However, this deployment model still has deployment performance issues due to the involvement of a high degree of coordination and mutual dependencies of distributed services built on heterogeneous technologies. In a large scale deployment setup with more number of services, inter and intracommunication links between the coordinated services increase thereby introducing execution delays at service computation, and inter-service communications. Therefore, in this paper, we propose a smart home platform architecture based on Platform as a Service (PaaS) model supporting SaaS deployment model through efficient coordination of the interdependent services. Based on the designed architecture, we model an optimization problem named as Optimized IoT Application Deployment (OIAD) to minimize application deployment time (total execution time). To solve the OIAD problem, this paper proposes a heuristic algorithm to find a near optimal deployment time. The results of our simulation show an improvement in comparison with FCFS (First Come First Serve) and Ramdom execution algorithm under various deployment scenarios and strategies