Please use this identifier to cite or link to this item:
Title: Deep Multi-Agent Reinforcement Learning With Minimal Cross-Agent Communication for SFC Partitioning
Authors: Pentelas, Angelos
De Vleeschauwer, Danny
Chang, Chia-Yu
De Schepper, Koen
Papadimitriou, Panagiotis
Type: Article
Subjects: FRASCATI::Natural sciences::Computer and information sciences
Keywords: Multi-agent reinforcement learning
network function virtualization
self-learning orchestration
Issue Date: 2023
Source: IEEE Access
Volume: 11
First Page: 40384
Last Page: 40398
Abstract: Network Function Virtualization (NFV) decouples network functions from the underlying specialized devices, enabling network processing with higher flexibility and resource efficiency. This promotes the use of virtual network functions (VNFs), which can be grouped to form a service function chain (SFC). A critical challenge in NFV is SFC partitioning (SFCP), which is mathematically expressed as a graph-to-graph mapping problem. Given its NP-hardness, SFCP is commonly solved by approximation methods. Yet, the relevant literature exhibits a gradual shift towards data-driven SFCP frameworks, such as (deep) reinforcement learning (RL). In this article, we initially identify crucial limitations of existing RL-based SFCP approaches. In particular, we argue that most of them stem from the centralized implementation of RL schemes. Therefore, we devise a cooperative deep multi-agent reinforcement learning (DMARL) scheme for decentralized SFCP, which fosters the efficient communication of neighboring agents. Our simulation results (i) demonstrate that DMARL outperforms a state-of-the-art centralized double deep Q -learning algorithm, (ii) unfold the fundamental behaviors learned by the team of agents, (iii) highlight the importance of information exchange between agents, and (iv) showcase the implications stemming from various network topologies on the DMARL efficiency.
ISSN: 2169-3536
Other Identifiers: 10.1109/ACCESS.2023.3269576
Appears in Collections:Department of Applied Informatics

This item is licensed under a Creative Commons License Creative Commons