Performance and Security Aware Distributed Service Placement in Fog Computing

2026-01-03

arXiv.org

AI Summary

This work addresses the challenge of service placement in fog computing, where heterogeneous resources, dynamic workloads, and diverse security requirements make it difficult to simultaneously optimize performance and security—a trade-off often overlooked by existing approaches. To this end, the authors propose SPA-DDRL, a distributed deep reinforcement learning framework that jointly optimizes response time and security compliance. The framework introduces a novel three-tier security scoring mechanism—encompassing configuration-, capability-, and control-level assessments—and employs a distributed broker-learner architecture enhanced with LSTM networks, prioritized experience replay, and off-policy correction for efficient multi-objective optimization. Experimental results under real-world IoT workloads demonstrate that SPA-DDRL reduces response time by 16.3%, accelerates convergence by 33%, and consistently generates feasible, security-compliant solutions across varying system scales, significantly outperforming current baselines.

Technology Category

• Search and Optimization: Distributed Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

The rapid proliferation of IoT applications has intensified the demand for efficient and secure service placement in Fog computing. However, heterogeneous resources, dynamic workloads, and diverse security requirements make optimal service placement highly challenging. Most solutions focus primarily on performance metrics while overlooking the security implications of deployment decisions. This paper proposes a Security and Performance-Aware Distributed Deep Reinforcement Learning (SPA-DDRL) framework for joint optimization of service response time and security compliance in Fog computing. The problem is formulated as a weighted multi-objective optimization task, minimizing latency while maximizing a security score derived from the security capabilities of Fog nodes. The security score features a new three-tier hierarchy, where configuration-level checks verify proper settings, capability-level assessments evaluate the resource security features, and control-level evaluations enforce stringent policies, thereby ensuring compliant solutions that align with performance objectives. SPA-DDRL adopts a distributed broker-learner architecture where multiple brokers perform autonomous service-placement decisions and a centralized learner coordinates global policy optimization through shared prioritized experiences. It integrates three key improvements, including Long Short-Term Memory networks, Prioritized Experience Replay, and off-policy correction mechanisms to improve the agent's performance. Experiments based on real IoT workloads show that SPA-DDRL significantly improves both service response time and placement security compared to current approaches, achieving a 16.3% improvement in response time and a 33% faster convergence rate. It also maintains consistent, feasible, security-compliant solutions across all system scales, while baseline techniques fail or show performance degradation.

Problem

• Fog Computing
• Service Placement
• Security Compliance
• Performance Optimization
• IoT Applications

Innovation

• Security-aware service placement
• Distributed deep reinforcement learning
• Multi-objective optimization
• Fog computing
• Prioritized experience replay