Frequently Asked Questions (FAQs)

This section demonstrate the most frequent questions along with their answers

Does Fogify provide workload generators for IoT devices?

No, Fogify only offers emulation at the infrastructure layer. Users are responsible to provide workload generators as containerized services.

How Fogify achieves the mobility of Fog Computing Deployments?

Currently, Fogify provides users the ability to define scenarios for time-scheduled network alterations, so user should provide the network changes that a Fog node will experience at the execution of the experiment.

Where can I find examples of a Fogify deployment?

Currently, we provide an end-to-end example of Fogify usage at the demo repository (https://github.com/UCY-LINC-LAB/fogify-demo). However, we will provide a wide range of applications described with Fogify in near future.

Is the Fogify’s emulation accurate and near to real-world deployments?

According to the emulation accuracy, we compare real deployments and emulated deployments for the same architectures.

Our experiments show the following results:

The emulated computing resources has only a small performance degradation for workloads approaching 100% CPU usage

Fogify achieves near to real-world network link capabilities, with only outliers not captured and a slight overhead in low-latency connections

The emulation results closely follow the real measurements with a 5%-8% deviation of the overall experiment time. The picture illustrates a image recognition algorithm in two deployments. A Cloud-only deployment and an Edge-Cloud deployment.

You can find more information about our experiments in the Fogify’s paper