Intelligent Transport Layer for Bandwidth as a Service in Cloud and IoT Applications

Abstract

Cloud and IoT applications employ a wide range of advanced hardware and software techniques. This paper focuses on utilization of network bandwidth, and proposes the concept of "Bandwidth as a Service" (BaaS) between devices in cloud and IoT environments. Conventional controls for bandwidth are discussed, and a novel algorithm is proposed for dynamically shaping bandwidth into percentage groups containing individual transport-level connections. We show that this approach maximizes bandwidth efficiency while maintaining limitations on network resources. An analysis of bandwidth performance between virtual machines is discussed along with a survey of throughput efficiency and improvements within the hypervisor. The performance of the proposed algorithm using both Xen Bridge and Open vSwitch is also discussed and compared. The proposed algorithm can be used as BAAS modules controlled by individual VM tenants in a cloud datacenter, or it can be embedded/tailored within the algorithms proposed in related research work. 2