DNN distributed inference offloading scheme based on transfer reinforcement learning in metro optical networks

With the development of 5G and mobile edge computing, deep neural network (DNN) inference can be distributed at the edge to reduce communication overhead and inference time, namely, DNN distributed inference. DNN distributed inference will pose challenges to the resource allocation problem in metro...

Full description

Saved in:
Bibliographic Details
Published in:Journal of optical communications and networking 2024-09, Vol.16 (9), p.852-867
Main Authors: Yin, Shan, Liu, Lihao, Cai, Mengru, Chai, Yutong, Jiao, Yurong, Duan, Zheng, Li, Yian, Huang, Shanguo
Format: Article
Language:English
Subjects:
Artificial neural networks
Bandwidth
Computation offloading
Deep learning
Edge computing
Inference
Machine learning
Metropolitan area networks
Mobile computing
Multiagent systems
Network latency
Optical communication
Optical fiber networks
Optimization
Resource allocation
Resource management
Servers
Topology
Transfer learning
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the development of 5G and mobile edge computing, deep neural network (DNN) inference can be distributed at the edge to reduce communication overhead and inference time, namely, DNN distributed inference. DNN distributed inference will pose challenges to the resource allocation problem in metro optical networks (MONs). Efficient cooperative allocation of optical communication and computational resources can facilitate high-bandwidth and low-latency applications. However, it also introduces greater complexity to the resource allocation problem. In this study, we propose a joint resource allocation method using high-performance transfer deep reinforcement learning (T-DRL) to maximize network throughput. When the topologies or characteristics of MONs change, T-DRL requires only a small amount of transfer training to re-converge. Considering that the generalizability of conventional methods is inversely related to optimization performance, we develop two deployment schemes (i.e., single-agent and multi-agent) based on the T-DRL method to explore the performance of T-DRL. Simulation results demonstrate that T-DRL greatly reduces the blocking probability and average inference time of DNN inference requests. Besides, the multi-agent scheme can maintain a lower blocking probability of requests in MONs, while the single-agent has a shorter convergence time after network changes.
ISSN:1943-0620
1943-0639
DOI:10.1364/JOCN.533206