Network Service Embedding with Multiple Resource Dimensions

Pentelas, Angelos; Papathanail, George; Fotoglou, Ioakeim; Papadimitriou, Panagiotis

doi:10.1109/noms47738.2020.9110440

Cited by 3 publications

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Optimality with respect to SFCP can take numerous forms. For instance, it can be seen through the lens of load balancing [18], throughput maximization [5], latency minimization [3], fault tolerance (reliability) [11], cross-service communication [19], or resource efficiency [20]. Our work does not intend neither to add another problem dimension nor to further explore an existing one; it rather focuses on the investigation of an RL scheme that is more aligned with current system architectures and goals.…”

Section: A Problem Descriptionmentioning

confidence: 99%

Deep Multi-Agent Reinforcement Learning With Minimal Cross-Agent Communication for SFC Partitioning

et al. 2023

View full text Add to dashboard Cite

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.

show abstract