SUMMARY REMARKS & TESTBEDS
MECPerf is a tool that provides an open interface to gather application-and network-level measurements about the performance of a Mobile Edge Computing (MEC) infrastructure and the applications that are deployed on top of it. In this project, we will run experiments on the NITOS testbed to validate MECPerf in a close-to-production environment. The validation will focus on two main aspects: 1)operability on real-world networks with wireless links and multiple access technologies, and 2)assessment f MECPerf and identification of possible performance bottlenecks. Experiments will be run in multiple operational scenarios, collecting passive and active measurements, also involving an underlying SDN infrastructure. MECPerf runs on a basic implementation of ETSI MEC, which will be made available to the scientific and industrial community as open-source software.
- MECPerf: An Application-Level Tool for Estimating the Network Performance in Edge Computing Environments (PDF – link)
Edge computing is an emerging architecture in 5G networks where computing power is provided at the edge of the fixed network, to be as close as possible to the end users. Computation offloading, better communication latency, and reduction of traffic in the core network are just some of the possible benefits. However, the Quality of Experience (QoE) depends significantly on the network performance of the user device towards the edge server vs. cloud server, which is not known a priori and may generally change very fast, especially in heterogeneous, dense, and mobile deployments. Building on the emergence of standard interfaces for the installation and operation of thirdparty edge applications in a mobile network, such as the MultiAccess Edge Computing (MEC) under standardization at the European Telecommunications Standards Institute (ETSI), we propose MECPerf, a tool for user-driven network performance measurements. Bandwidth and latency on different network segments are measured and stored in a central repository, from where they can be analyzed, e.g., by application and service providers without access to the underlying network management services, for run-time resource optimization.
- Measurement-driven design and runtime optimization in edge computing: Methodology and tools (PDF – link)
Edge computing is projected to become the dominant form of cloud computing in the future because of the significant advantages it brings to both users (less latency, higher throughput) and telecom operators (less Internet traffic, more local management). However, to fully unlock its potential at scale, system designers and automated optimization systems alike will have to monitor closely the dynamics of both processing and communication facilities. Especially the latter is often neglected in current systems since network performance in cloud computing plays only a minor role. In this paper, we propose the architecture of MECPerf, which is a solution to collect network measurements in a live edge computing domain, to be collected for offline provisioning analysis and simulations, or to be provided in real-time for on-line system optimization. MECPerf has been validated in a realistic testbed funded by the European Commission (Fed4Fire+), and we describe here a summary of the results, which are fully available as open data and through a Python library to expedite their utilization. This is demonstrated via a use case involving the optimization of a system parameter for migrating clients in a federated edge computing system adopting the GSMA platform operator concept.