Latency-Aware Service Placement using Neural Combinatorial Optimisers for Edge--Cloud Systems

2026-06-24

AI Summary

This work addresses the NP-hard combinatorial optimization problem of microservice deployment for latency-sensitive IoT applications in edge–cloud systems by proposing the EP-NCO framework. EP-NCO is the first to introduce neural combinatorial optimization to service placement, employing a dual-graph representation to model both infrastructure and application topologies. It integrates graph neural networks with reinforcement learning to jointly optimize execution latency, communication latency, and bandwidth sharing. Experimental results demonstrate that EP-NCO reduces total response time by 46%–50% compared to metaheuristic approaches such as genetic algorithms and achieves a 25%–35% improvement over ablation baselines. Furthermore, the framework supports efficient online inference at scale, handling hundreds of infrastructure nodes and thousands of concurrent applications.

Abstract

The growth of Internet of Things (IoT) applications and latency-sensitive services has increased the demand for efficient service placement across compute continuum platforms, such as edge--cloud systems. Modern applications are decomposed into interdependent microservices deployed over heterogeneous infrastructures, making placement under resource and network constraints an intractable NP-hard combinatorial optimisation problem. This study proposes a latency-aware Edge Placement Neural Combinatorial Optimiser (EP-NCO), a learning-based framework for service placement in compute continuum platforms. EP-NCO employs a dual-graph model to capture resource relationships and service dependencies within both computing infrastructure and application structure. Graph neural networks (GNNs) learn structural embeddings of infrastructure nodes and service components, whereas reinforcement learning policies construct feasible placements that account for execution latency, communication link delays, and bandwidth-sharing effects. Extensive simulations across multiple system scales demonstrate that EP-NCO consistently achieves high-quality placement decisions, reducing the total service response time by 46%--50% compared with metaheuristics (genetic algorithm and particle swarm optimisation) and by 25%--35% compared with controlled RL ablation baselines. Once trained, EP-NCO enables fast online inference, making it a practical solution for dynamic large-scale edge--cloud environments with hundreds of computing nodes, hosting thousands of applications, which is significantly beyond the capability of current scheduling systems.

Problem

• service placement
• edge-cloud systems
• latency-aware
• combinatorial optimisation
• microservices

Innovation

• Neural Combinatorial Optimisation
• Service Placement
• Edge-Cloud Systems
• Graph Neural Networks
• Reinforcement Learning