We present MECBench, an extensible benchmarking framework for multi-access edge computing. MECBench is configurable, and can emulate networks with different capabilities and conditions, can scale the generated workloads to mimic a large number of clients, and can generate a range of work-load patterns. MECBench is extensible; it can be extended to change the generated workload, use new datasets, and integrate new applications. MECBench’s implementation includes machine learning and synthetic edge applications.
We demonstrate MECBench’s capabilities through two scenarios: an object detection scheme for drone navigation and a natural language processing application. Our evaluation shows that MECBench can be used to answer complex what-if questions pertaining to design and deployment decisions of MEC platforms and applications. Our evaluation explores the impact of different combinations of applications, hardware, and network conditions, as well as the cost-benefit tradeoff of different designs and configurations.
People
- Omar Naman
- Hala Qadi
- Martin Karsten
- Samer Al-Kiswany
Downloads
Publications
[1] MECBench: A Framework for Benchmarking Multi-Access Edge Computing Platforms
Omar Naman, Hala Qadi, Martin Karsten, Samer Al-Kiswany
IEEE International Conference on Edge Computing (EDGE), 2023.