Secure Resource Allocation via Constrained Deep Reinforcement Learning

2025-01-20

AI Summary

To address security vulnerabilities, low energy efficiency, and difficulties in coordinating multiple constraints for task offloading and resource allocation in serverless-based multi-cloud edge computing—driven by 6G and IoT—this paper proposes SARMTO, a deep reinforcement learning framework with a constrained action space. SARMTO innovatively integrates an adaptive security mechanism with a constraint-aware Markov decision process (MDP) to jointly optimize security, energy efficiency, and system cost. Evaluated under diverse workloads, varying data scales, and heterogeneous multi-access edge computing (MEC) capacities, SARMTO reduces system cost by 40%, improves energy efficiency by 41.5%, and significantly enhances operational stability compared to state-of-the-art approaches. By enabling scalable, dynamic, and security-critical resource management in resource-constrained edge environments, SARMTO establishes a novel paradigm for intelligent edge resource orchestration.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The proliferation of Internet of Things (IoT) devices and the advent of 6G technologies have introduced computationally intensive tasks that often surpass the processing capabilities of user devices. Efficient and secure resource allocation in serverless multi-cloud edge computing environments is essential for supporting these demands and advancing distributed computing. However, existing solutions frequently struggle with the complexity of multi-cloud infrastructures, robust security integration, and effective application of traditional deep reinforcement learning (DRL) techniques under system constraints. To address these challenges, we present SARMTO, a novel framework that integrates an action-constrained DRL model. SARMTO dynamically balances resource allocation, task offloading, security, and performance by utilizing a Markov decision process formulation, an adaptive security mechanism, and sophisticated optimization techniques. Extensive simulations across varying scenarios, including different task loads, data sizes, and MEC capacities, show that SARMTO consistently outperforms five baseline approaches, achieving up to a 40% reduction in system costs and a 41.5% improvement in energy efficiency over state-of-the-art methods. These enhancements highlight SARMTO's potential to revolutionize resource management in intricate distributed computing environments, opening the door to more efficient and secure IoT and edge computing applications.

Problem

• Resource Allocation
• Multi-cloud Systems
• Security and Efficiency

Innovation

• SARMTO
• Deep Learning with Action Constraints
• Multi-cloud and Edge Computing Resource Allocation