Deployment of real-time systems in the cloud environment

Interest in real-time systems has grown considerably over recent years, primarily due to significant increase in the use of smart technologies and latency-sensitive applications such as cloud gaming, audio/video streaming, and smart homes. Significant work has been done on resource mapping in the cloud environment, and a number of promising results have been established accordingly where the focus is mainly on resource provisioning. However, the applicability of cloud computing services for real-time systems generated from smart systems is still in its infancy and remains unexplored, relatively. To address this gap, we propose a model for the smart systems that periodically offload computational workload to the cloud environment where virtual machines are allocated according to rate-monotonic scheduling policy to ensure requests are processed within the associated deadlines. Deadlines of tasks have been relaxed to improve server utilization as well as maintain a level of confidence in the timing constrains. Experimental results are discussed to highlight the applicability of static priority assignment for the workload in the context of virtual machines allocation.