SOMETIME: Software defined network-basec Available Bandwidth measurement in MONROE

Abstract

Mobile Broadband (MBB) access networks are becoming more and more used worldwide, and the devices adopted to access them are increasing in number and complexity (smartphones, mobile hotspots, vehicular infotainment systems). The highly dynamic nature of such scenarios calls for continuous monitoring and measurement of the network, and possibly cross-layer management of network applications. A recent shift in network management, Software-Defined Networking (SDN), is a promising tool to manage such evolved scenario, characterized by constraints due to HW, virtualization, and data plans. In this paper, we present the fundamental ideas and the first findings that underpin the SOMETIME research project, that aims at implementing active measurements leveraging the features provided by SDN technologies. Several platforms and tools are being presented to investigate separately MBB and SDN: we consider as a reference testbed the MONROE platform, a system offering in-the-field MBB experimenting facilities. We adopt MONROE as an use case to highlight the main issues and challenges raised by the SOMETIME vision, investigating the feasibility of SDN-based active measurements for MBB. In more details, we assess the impact of SDN on performance of active measurements, namely Available Bandwidth (ABw) estimation, an end-to-end network metric characterizing the spare capacity on a path. We also report preliminary results on achievable throughput as a first root-cause analysis for poor performance in estimating ABw in MBB scenarios. The preliminary results confirm the expected difficulties in ABw estimation over MBB but also validate the feasibility of SDN-based approaches and suggest future directions for SDN-based enhancement of ABw estimation.