TY - JOUR
T1 - Seek Common while Shelving Differences
T2 - Orchestrating Deep Neural Networks for Edge Service Provisioning
AU - Chen, Lixing
AU - Xu, Jie
N1 - Funding Information:
Manuscript received July 15, 2020; revised September 26, 2020; accepted October 24, 2020. Date of publication November 9, 2020; date of current version December 16, 2020. This work was supported in part by the National Science Foundation under Award ECCS-2033681, Award ECCS-2029858, and Award CNS-2006630 and in part by the Army Research Office under Award W911NF-18-1-0343. (Corresponding author: Lixing Chen.) The authors are with the Department of Electrical and Computer Engineering, University of Miami, Coral Gables, FL 33146 USA (e-mail: lx.chen@miami.edu; jiexu@miami.edu).
Publisher Copyright:
© 1983-2012 IEEE.
PY - 2021/1
Y1 - 2021/1
N2 - Edge computing (EC) platforms, which enable Application Service Providers (ASPs) to deploy applications in close proximity to users, are providing ultra-low latency and location-awareness to a rich portfolio of services. As monetary costs are incurred for renting computing resources on edge servers to enable service provisioning, ASP has to cautiously decide where to deploy the application and how much resources would be needed to deliver satisfactory performance. However, the service provisioning problem exhibits complex correlations with multifarious factors in EC systems, ranging from user behavior to computation offloading, which are difficult to be fully captured by mathematical modeling and also put off traditional machine learning techniques due to the induction of high-dimension state space. The recent success of deep learning (DL) underpins new tools for addressing our problem. While previous works provide valuable insights on applying DL techniques, e.g., distributed DL, deep reinforcement learning (DRL), and multi-agent DL, in EC systems, these techniques cannot solely handle the distributed and heterogeneous nature of EC systems. To address these limitations, we propose a novel framework based on multi-agent DRL, distributed neural network orchestration (N2O), and knowledge distilling. The multi-agent DRL enables edge servers to learn deep neural networks that shelve distinct features learned from local edge sites and hence caters to the heterogeneity of EC systems. N2O coordinates edge servers in a fully distributed manner toward a common goal of maximizing ASP's reward. It requires only local communications during execution and provides provable performance guarantees. The knowledge distilling is further utilized to distill the N2O policy for reducing the communication overhead and stabilizing the decision-making. We also carry out systematic experiments to show the advantages of our method over state-of-the-art alternatives.
AB - Edge computing (EC) platforms, which enable Application Service Providers (ASPs) to deploy applications in close proximity to users, are providing ultra-low latency and location-awareness to a rich portfolio of services. As monetary costs are incurred for renting computing resources on edge servers to enable service provisioning, ASP has to cautiously decide where to deploy the application and how much resources would be needed to deliver satisfactory performance. However, the service provisioning problem exhibits complex correlations with multifarious factors in EC systems, ranging from user behavior to computation offloading, which are difficult to be fully captured by mathematical modeling and also put off traditional machine learning techniques due to the induction of high-dimension state space. The recent success of deep learning (DL) underpins new tools for addressing our problem. While previous works provide valuable insights on applying DL techniques, e.g., distributed DL, deep reinforcement learning (DRL), and multi-agent DL, in EC systems, these techniques cannot solely handle the distributed and heterogeneous nature of EC systems. To address these limitations, we propose a novel framework based on multi-agent DRL, distributed neural network orchestration (N2O), and knowledge distilling. The multi-agent DRL enables edge servers to learn deep neural networks that shelve distinct features learned from local edge sites and hence caters to the heterogeneity of EC systems. N2O coordinates edge servers in a fully distributed manner toward a common goal of maximizing ASP's reward. It requires only local communications during execution and provides provable performance guarantees. The knowledge distilling is further utilized to distill the N2O policy for reducing the communication overhead and stabilizing the decision-making. We also carry out systematic experiments to show the advantages of our method over state-of-the-art alternatives.
KW - Edge computing
KW - deep reinforcement learning
KW - distributed optimization
KW - multi-agent learning
UR - http://www.scopus.com/inward/record.url?scp=85096392010&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85096392010&partnerID=8YFLogxK
U2 - 10.1109/JSAC.2020.3036953
DO - 10.1109/JSAC.2020.3036953
M3 - Article
AN - SCOPUS:85096392010
VL - 39
SP - 251
EP - 264
JO - IEEE Journal on Selected Areas in Communications
JF - IEEE Journal on Selected Areas in Communications
SN - 0733-8716
IS - 1
M1 - 9252961
ER -