Multi-objective application placement in fog computing using graph neural network-based reinforcement learning

2026-05-14

AI Summary

This work addresses the multi-objective application placement problem in fog computing by proposing a dual Actor-Critic framework that integrates graph neural networks with deep reinforcement learning. The approach explicitly models service dependencies as a graph structure and embeds this representation into a multi-objective reinforcement learning process to jointly optimize resource constraints, service dependencies, and performance metrics through a globally coordinated deployment strategy. Experimental results demonstrate that the proposed method generates a Pareto-optimal solution set comparable to that of genetic algorithms within milliseconds, significantly improving computational efficiency over conventional hour-scale approaches while prioritizing the proper placement of highly interdependent services.

Abstract

We propose a framework designed to tackle a multi-objective optimization challenge related to the placement of applications in fog computing, employing a deep reinforcement learning (DRL) approach. Unlike other optimization techniques, such as integer linear programming or genetic algorithms, DRL models are applied in real time to solve similar problem situations after training. Our model comprises a learning process featuring a graph neural network and two actor-critics, providing a holistic perspective on the priorities concerning interconnected services that constitute an application. The learning model incorporates the relationships between services as a crucial factor in placement decisions: Services with higher dependencies take precedence in location selection. Our experimental investigation involves illustrative cases where we compare our results with baseline strategies and genetic algorithms. We observed a comparable Pareto set with negligible execution times, measured in the order of milliseconds, in contrast to the hours required by alternative approaches.

Problem

• multi-objective optimization
• application placement
• fog computing
• service dependencies
• graph neural network

Innovation

• graph neural network
• reinforcement learning
• fog computing
• multi-objective optimization
• application placement