Edge Computing and 5th generation (5G) mobile networks are emerging as the dominating paradigms bridging the compute and connectivity gap between IoT sensing devices and latency-sensitive services. However, experimenting and evaluating IoT services is a daunting task involving the manual configuration and deployment of a mixture of geo-distributed physical and virtual infrastructure with various compute resources and network properties.

In this presentation, we introduce Fogify, an open-source emulation framework designed to help users in evaluating geo-distributed IoT services within Edge Computing and 5G deployments. Fogify takes as input an extended version of a docker-compose file and generates an emulated execution environment. Specifically, users extend docker-compose by describing their compute devices along with their geo-positions and trajectories, network characteristics and 5G infrastructure components, "what-if" scenarios, and so on. Fogify translates the description into a virtualized execution environment by allocating resources as isolated containerized processes, provisions network connectivity among entities, configures the infrastructure accordingly, and deploys enablers for runtime assessment, emulating the direct behavior of a geo-distributed environment. Lastly, it provides an out-of-the-box monitoring stack for the deployed services and an interactive evaluation interface.

During the presentation, we will highlight how one can model, deploy, and evaluate an application via Fogify, and how Fogify integrates different technologies such as Docker Swarm, cAdvisor & Prometheus, and Jupyter Notebooks to fulfill its promises.