Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Graph Neural Networks and Reinforcement Learning for Proactive Application Image Placement

Antonios Makris, Theodoros Theodoropoulos, Evangelos Psomakelis, Emanuele Carlini, Matteo Mordacchini, Patrizio Dazzi, Konstantinos Tserpes

TL;DR

This work tackles proactive image placement in the Cloud-Edge continuum by formulating the problem as a Minimum Vertex Cover (MVC) and evaluating alternative MVC-inspired models (Set Cover, Linear Optimization). It introduces GNOSIS, a hybrid approach that fuses Graph Neural Networks with actor-critic reinforcement learning to learn effective MVC-based placement strategies for edge networks. Empirical results across diverse topologies show GNOSIS delivers superior placement quality (lower cost and smaller vertex covers) at the expense of longer execution times, illustrating a practical trade-off for dynamic edge environments. The method provides a scalable, topology-aware framework for proactive deployment of microservice images, with implications for reduced transfer latency and improved responsiveness in next-generation applications.

Abstract

The shift from Cloud Computing to a Cloud-Edge continuum presents new opportunities and challenges for data-intensive and interactive applications. Edge computing has garnered a lot of attention from both industry and academia in recent years, emerging as a key enabler for meeting the increasingly strict demands of Next Generation applications. In Edge computing the computations are placed closer to the end-users, to facilitate low-latency and high-bandwidth applications and services. However, the distributed, dynamic, and heterogeneous nature of Edge computing, presents a significant challenge for service placement. A critical aspect of Edge computing involves managing the placement of applications within the network system to minimize each application's runtime, considering the resources available on system devices and the capabilities of the system's network. The placement of application images must be proactively planned to minimize image tranfer time, and meet the strict demands of the applications. In this regard, this paper proposes an approach for proactive image placement that combines Graph Neural Networks and actor-critic Reinforcement Learning, which is evaluated empirically and compared against various solutions. The findings indicate that although the proposed approach may result in longer execution times in certain scenarios, it consistently achieves superior outcomes in terms of application placement.

Graph Neural Networks and Reinforcement Learning for Proactive Application Image Placement

TL;DR

This work tackles proactive image placement in the Cloud-Edge continuum by formulating the problem as a Minimum Vertex Cover (MVC) and evaluating alternative MVC-inspired models (Set Cover, Linear Optimization). It introduces GNOSIS, a hybrid approach that fuses Graph Neural Networks with actor-critic reinforcement learning to learn effective MVC-based placement strategies for edge networks. Empirical results across diverse topologies show GNOSIS delivers superior placement quality (lower cost and smaller vertex covers) at the expense of longer execution times, illustrating a practical trade-off for dynamic edge environments. The method provides a scalable, topology-aware framework for proactive deployment of microservice images, with implications for reduced transfer latency and improved responsiveness in next-generation applications.

Abstract

The shift from Cloud Computing to a Cloud-Edge continuum presents new opportunities and challenges for data-intensive and interactive applications. Edge computing has garnered a lot of attention from both industry and academia in recent years, emerging as a key enabler for meeting the increasingly strict demands of Next Generation applications. In Edge computing the computations are placed closer to the end-users, to facilitate low-latency and high-bandwidth applications and services. However, the distributed, dynamic, and heterogeneous nature of Edge computing, presents a significant challenge for service placement. A critical aspect of Edge computing involves managing the placement of applications within the network system to minimize each application's runtime, considering the resources available on system devices and the capabilities of the system's network. The placement of application images must be proactively planned to minimize image tranfer time, and meet the strict demands of the applications. In this regard, this paper proposes an approach for proactive image placement that combines Graph Neural Networks and actor-critic Reinforcement Learning, which is evaluated empirically and compared against various solutions. The findings indicate that although the proposed approach may result in longer execution times in certain scenarios, it consistently achieves superior outcomes in terms of application placement.
Paper Structure (18 sections, 8 equations, 3 figures, 2 tables, 1 algorithm)

This paper contains 18 sections, 8 equations, 3 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Problem Formulation
  4. Minimum Vertex Cover and Proactive Image Placement
  5. Set Cover
  6. Linear Optimization
  7. Algorithmic Approaches to Minimum Vertex Cover Problem
  8. Approximation
  9. Greedy
  10. Genetic
  11. The GNOSIS Approach
  12. Graph Neural Networks
  13. The Actor-Critic Algorithm
  14. Graph Neural Networks & Deep Reinforcement Learning for Combinatorial Optimization
  15. Experimental Evaluation
  16. ...and 3 more sections

Figures (3)

  • Figure 1: Execution time of each algorithm for the different network topologies
  • Figure 2: Cost function of each algorithm for the different network topologies (the lower the better)
  • Figure 3: Vertex Cover set of each algorithm for the different network topologies