Analysis of AI Techniques for Orchestrating Edge-Cloud Application Migration

2025-07-14

AI Summary

This study addresses the automated orchestration of application migration in edge–cloud collaborative environments, balancing Quality-of-Service (QoS) guarantees with operational cost optimization. Methodologically, it innovatively models dynamic migration as a Tower-of-Hanoi (ToH)-inspired structured decision problem and establishes a unified state-space classification framework. Building upon this, it systematically compares three mainstream AI paradigms—Markov Decision Processes (MDPs), AI planning, and reinforcement learning—in terms of modeling expressiveness, solution efficiency, and generalizability for migration orchestration. Experimental evaluation quantifies their trade-offs across latency sensitivity, adaptability to heterogeneous resource constraints, and policy interpretability. The results yield theoretically grounded criteria and practical guidelines for selecting and designing intelligent orchestration systems in computing continuum scenarios.

Technology Category

• Planning, Routing, and Scheduling: Planning with Markov Models (MDPs, POMDPs)
• Search and Optimization: Mixed Discrete/Continuous Search
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Application migration in edge-cloud system enables high QoS and cost effective service delivery. However, automatically orchestrating such migration is typically solved with heuristic approaches. Starting from the Markov Decision Process (MDP), in this paper, we identify, analyze and compare selected state-of-the-art Artificial Intelligence (AI) planning and Reinforcement Learning (RL) approaches for solving the class of edge-cloud application migration problems that can be modeled as Towers of Hanoi (ToH) problems. We introduce a new classification based on state space definition and analyze the compared models also through this lense. The aim is to understand available techniques capable of orchestrating such application migration in emerging computing continuum environments.

Problem

• Analyzing AI techniques for edge-cloud application migration orchestration
• Comparing MDP, AI planning, and RL for ToH-modeled migration problems
• Classifying state space approaches for computing continuum environments

Innovation

• Uses MDP for edge-cloud migration modeling
• Compares AI planning and RL techniques
• Introduces new state space classification