<i>DeepFogSim</i>: A Toolbox for Execution and Performance Evaluation of the Inference Phase of Conditional Deep Neural Networks with Early Exits Atop Distributed Fog Platforms
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...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/1/377 |
| _version_ | 1797542516897087488 |
|---|---|
| author | Michele Scarpiniti Enzo Baccarelli Alireza Momenzadeh Sima Sarv Ahrabi |
| author_facet | Michele Scarpiniti Enzo Baccarelli Alireza Momenzadeh Sima Sarv Ahrabi |
| author_sort | Michele Scarpiniti |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T13:31:41Z |
| format | Article |
| id | doaj.art-1fa63c03523b4589b17ddb00bd2417df |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T13:31:41Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-1fa63c03523b4589b17ddb00bd2417df2023-11-21T07:47:48ZengMDPI AGApplied Sciences2076-34172021-01-0111137710.3390/app11010377<i>DeepFogSim</i>: A Toolbox for Execution and Performance Evaluation of the Inference Phase of Conditional Deep Neural Networks with Early Exits Atop Distributed Fog PlatformsMichele Scarpiniti0Enzo Baccarelli1Alireza Momenzadeh2Sima Sarv Ahrabi3Department of Information Engineering, Electronics and Telecommunications (DIET), Sapienza University of Rome, Via Eudossiana 18, 00185 Rome, ItalyDepartment of Information Engineering, Electronics and Telecommunications (DIET), Sapienza University of Rome, Via Eudossiana 18, 00185 Rome, ItalyDepartment of Information Engineering, Electronics and Telecommunications (DIET), Sapienza University of Rome, Via Eudossiana 18, 00185 Rome, ItalyDepartment of Information Engineering, Electronics and Telecommunications (DIET), Sapienza University of Rome, Via Eudossiana 18, 00185 Rome, ItalyThe 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.https://www.mdpi.com/2076-3417/11/1/377Conditional Deep Neural Networks with early exitsvirtualized multi-tier fog execution platformsenergy-vs.-inference delay adaptive optimizationperformance modeling and evaluationsimulation toolkits |
| spellingShingle | Michele Scarpiniti Enzo Baccarelli Alireza Momenzadeh Sima Sarv Ahrabi <i>DeepFogSim</i>: A Toolbox for Execution and Performance Evaluation of the Inference Phase of Conditional Deep Neural Networks with Early Exits Atop Distributed Fog Platforms Applied Sciences Conditional Deep Neural Networks with early exits virtualized multi-tier fog execution platforms energy-vs.-inference delay adaptive optimization performance modeling and evaluation simulation toolkits |
| title | <i>DeepFogSim</i>: A Toolbox for Execution and Performance Evaluation of the Inference Phase of Conditional Deep Neural Networks with Early Exits Atop Distributed Fog Platforms |
| title_full | <i>DeepFogSim</i>: A Toolbox for Execution and Performance Evaluation of the Inference Phase of Conditional Deep Neural Networks with Early Exits Atop Distributed Fog Platforms |
| title_fullStr | <i>DeepFogSim</i>: A Toolbox for Execution and Performance Evaluation of the Inference Phase of Conditional Deep Neural Networks with Early Exits Atop Distributed Fog Platforms |
| title_full_unstemmed | <i>DeepFogSim</i>: A Toolbox for Execution and Performance Evaluation of the Inference Phase of Conditional Deep Neural Networks with Early Exits Atop Distributed Fog Platforms |
| title_short | <i>DeepFogSim</i>: A Toolbox for Execution and Performance Evaluation of the Inference Phase of Conditional Deep Neural Networks with Early Exits Atop Distributed Fog Platforms |
| title_sort | i deepfogsim i a toolbox for execution and performance evaluation of the inference phase of conditional deep neural networks with early exits atop distributed fog platforms |
| topic | Conditional Deep Neural Networks with early exits virtualized multi-tier fog execution platforms energy-vs.-inference delay adaptive optimization performance modeling and evaluation simulation toolkits |
| url | https://www.mdpi.com/2076-3417/11/1/377 |
| work_keys_str_mv | AT michelescarpiniti ideepfogsimiatoolboxforexecutionandperformanceevaluationoftheinferencephaseofconditionaldeepneuralnetworkswithearlyexitsatopdistributedfogplatforms AT enzobaccarelli ideepfogsimiatoolboxforexecutionandperformanceevaluationoftheinferencephaseofconditionaldeepneuralnetworkswithearlyexitsatopdistributedfogplatforms AT alirezamomenzadeh ideepfogsimiatoolboxforexecutionandperformanceevaluationoftheinferencephaseofconditionaldeepneuralnetworkswithearlyexitsatopdistributedfogplatforms AT simasarvahrabi ideepfogsimiatoolboxforexecutionandperformanceevaluationoftheinferencephaseofconditionaldeepneuralnetworkswithearlyexitsatopdistributedfogplatforms |