Joint Exit Selection and Offloading Decision for Applications Based on Deep Neural Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00378344" target="_blank" >RIV/68407700:21230/24:00378344 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/JIOT.2024.3444898" target="_blank" >https://doi.org/10.1109/JIOT.2024.3444898</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/JIOT.2024.3444898" target="_blank" >10.1109/JIOT.2024.3444898</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Joint Exit Selection and Offloading Decision for Applications Based on Deep Neural Networks

Popis výsledku v původním jazyce

User applications based on the deep neural networks (DNNs), such as object or anomaly detection, image recognition, or language processing, running on computation- and energy-constrained user equipment (UE) can be partially or fully processed in the edge computing servers to reduce a processing time and save an energy in the UE. To further reduce the processing time and the UE's energy consumption, DNN with multiple exit points can be incorporated. In this article, we address the problem of the decision on whether the computation should be offloaded from the UE to the edge computing server or processed locally by the UE and we solve this problem jointly and "on-the-fly" together with DNN exit selection. Since the formulated problem is very complex, we exploit the deep deterministic policy gradient for the exit selection and the offloading decisions (labeled DDPG-EOD) for the DNN-based applications. To this end, we first convert the problem into the Markov decision process, and then, we employ an end-to-end learning via DDPG with the actor-critic architecture. Second, we use a knowledge distillation-based technique to efficiently select the DNN's exit to minimize the delay and energy consumption. Simulation results show that the proposal is highly scalable, converges very quickly, and surpasses the best performing state-of-the-art approach by up to 120% and 100% in terms of the overall DNN processing delay and the energy consumption, respectively.

Název v anglickém jazyce

Joint Exit Selection and Offloading Decision for Applications Based on Deep Neural Networks

Popis výsledku anglicky

User applications based on the deep neural networks (DNNs), such as object or anomaly detection, image recognition, or language processing, running on computation- and energy-constrained user equipment (UE) can be partially or fully processed in the edge computing servers to reduce a processing time and save an energy in the UE. To further reduce the processing time and the UE's energy consumption, DNN with multiple exit points can be incorporated. In this article, we address the problem of the decision on whether the computation should be offloaded from the UE to the edge computing server or processed locally by the UE and we solve this problem jointly and "on-the-fly" together with DNN exit selection. Since the formulated problem is very complex, we exploit the deep deterministic policy gradient for the exit selection and the offloading decisions (labeled DDPG-EOD) for the DNN-based applications. To this end, we first convert the problem into the Markov decision process, and then, we employ an end-to-end learning via DDPG with the actor-critic architecture. Second, we use a knowledge distillation-based technique to efficiently select the DNN's exit to minimize the delay and energy consumption. Simulation results show that the proposal is highly scalable, converges very quickly, and surpasses the best performing state-of-the-art approach by up to 120% and 100% in terms of the overall DNN processing delay and the energy consumption, respectively.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20203 - Telecommunications

Projekt

<a href="/cs/project/LTT20004" target="_blank" >LTT20004: Spolupráce s mezinárodním výzkumným centrem v oblasti digitálních komunikačních systémů</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE Internet of Things Journal

ISSN

2327-4662

e-ISSN

2327-4662

Svazek periodika

11

Číslo periodika v rámci svazku

23

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

15

Strana od-do

38098-38112

Kód UT WoS článku

001360494400013

EID výsledku v databázi Scopus

2-s2.0-85201589229