POSEIDON : Efficient Function Placement at the Edge using Deep Reinforcement Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jain, Prakhar, Singhal, Prakhar, Pandey, Divyansh, Quattrocchi, Giovanni, Vaidhyanathan, Karthik
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912192932085760
author Jain, Prakhar
Singhal, Prakhar
Pandey, Divyansh
Quattrocchi, Giovanni
Vaidhyanathan, Karthik
author_facet Jain, Prakhar
Singhal, Prakhar
Pandey, Divyansh
Quattrocchi, Giovanni
Vaidhyanathan, Karthik
contents Edge computing allows for reduced latency and operational costs compared to centralized cloud systems. In this context, serverless functions are emerging as a lightweight and effective paradigm for managing computational tasks on edge infrastructures. However, the placement of such functions in constrained edge nodes remains an open challenge. On one hand, it is key to minimize network delays and optimize resource consumption; on the other hand, decisions must be made in a timely manner due to the highly dynamic nature of edge environments. In this paper, we propose POSEIDON, a solution based on Deep Reinforcement Learning for the efficient placement of functions at the edge. POSEIDON leverages Proximal Policy Optimization (PPO) to place functions across a distributed network of nodes under highly dynamic workloads. A comprehensive empirical evaluation demonstrates that POSEIDON significantly reduces execution time, network delay, and resource consumption compared to state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11879
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle POSEIDON : Efficient Function Placement at the Edge using Deep Reinforcement Learning
Jain, Prakhar
Singhal, Prakhar
Pandey, Divyansh
Quattrocchi, Giovanni
Vaidhyanathan, Karthik
Distributed, Parallel, and Cluster Computing
Edge computing allows for reduced latency and operational costs compared to centralized cloud systems. In this context, serverless functions are emerging as a lightweight and effective paradigm for managing computational tasks on edge infrastructures. However, the placement of such functions in constrained edge nodes remains an open challenge. On one hand, it is key to minimize network delays and optimize resource consumption; on the other hand, decisions must be made in a timely manner due to the highly dynamic nature of edge environments. In this paper, we propose POSEIDON, a solution based on Deep Reinforcement Learning for the efficient placement of functions at the edge. POSEIDON leverages Proximal Policy Optimization (PPO) to place functions across a distributed network of nodes under highly dynamic workloads. A comprehensive empirical evaluation demonstrates that POSEIDON significantly reduces execution time, network delay, and resource consumption compared to state-of-the-art methods.
title POSEIDON : Efficient Function Placement at the Edge using Deep Reinforcement Learning
topic Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2410.11879