| Summary: | The recent introduction of the so-called Conditional Neural Networks (CDNNs) with multiple early exits, executed atop virtualized multi-tier Fog platforms, makes feasible the real-time and energy-efficient execution of analytics required by future Internet applications. However, until now, toolkits for the evaluation of energy-vs.-delay performance of the inference phase of CDNNs executed on such platforms, have not been available. Motivated by these considerations, in this contribution, we present <i>DeepFogSim</i>. It is a MATLAB-supported software toolbox aiming at testing the performance of virtualized technological platforms for the real-time distributed execution of the inference phase of CDNNs with early exits under IoT realms. The main peculiar features of the proposed <i>DeepFogSim</i> toolbox are that: (i) it allows the <i>joint dynamic</i> energy-aware optimization of the Fog-hosted computing-networking resources under <i>hard constraints</i> on the tolerated inference delays; (ii) it allows the <i>repeatable</i> and <i>customizable</i> simulation of the resulting energy-delay performance of the overall Fog execution platform; (iii) it allows the <i>dynamic tracking</i> of the <i>performed resource allocation</i> under time-varying operating conditions and/or failure events; and (iv) it is equipped with a user-friendly <i>Graphic User Interface</i> (GUI) that supports a number of graphic formats for data rendering. Some numerical results give evidence for about the actual capabilities of the proposed <i>DeepFogSim</i> toolbox.
|
|---|