Resilient Packet Forwarding: A Reinforcement Learning Approach to Routing in Gaussian Interconnected Networks with Clustered Faults

2025-12-23

AI Summary

To address the sharp degradation in communication reliability caused by clustered faults—such as hotspots and physical damage—that follow a Gaussian distribution in Gaussian-interconnected networks (e.g., NoCs/WSNs), this paper proposes the first fault-aware reinforcement learning routing paradigm tailored for Gaussian integer topologies. Our method innovatively introduces a fault-proximity penalizing reward function, integrated within the Proximal Policy Optimization (PPO) framework, and incorporates Gaussian integer network modeling, fault-distribution-aware state encoding, and localized topology observation to enable dynamic avoidance of non-uniform fault regions. Experimental results demonstrate that, under 40% fault density, our approach achieves a packet delivery ratio (PDR) of 0.95—44% higher than greedy routing; at 20% low traffic load, PDR reaches 0.57, a 33% improvement. These results confirm substantial gains in congestion robustness and fault resilience.

Technology Category

Planning, Routing, and Scheduling: Replanning and Plan RepairIntelligent Robots: Learning & Optimization for ROBSearch and Optimization: Learning to Search

Application Category

Responsible Web: Human-perceived consequences of algorithmic deployment on the webGraph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphsSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

As Network-on-Chip (NoC) and Wireless Sensor Network architectures continue to scale, the topology of the underlying network becomes a critical factor in performance. Gaussian Interconnected Networks based on the arithmetic of Gaussian integers, offer attractive properties regarding diameter and symmetry. Despite their attractive theoretical properties, adaptive routing techniques in these networks are vulnerable to node and link faults, leading to rapid degradation in communication reliability. Node failures (particularly those following Gaussian distributions, such as thermal hotspots or physical damage clusters) pose severe challenges to traditional deterministic routing. This paper proposes a fault-aware Reinforcement Learning (RL) routing scheme tailored for Gaussian Interconnected Networks. By utilizing a PPO (Proximal Policy Optimization) agent with a specific reward structure designed to penalize fault proximity, the system dynamically learns to bypass faulty regions. We compare our proposed RL-based routing protocol against a greedy adaptive shortest-path routing algorithm. Experimental results demonstrate that the RL agent significantly outperforms the adaptive routing sustaining a Packet Delivery Ratio (PDR) of 0.95 at 40% fault density compared to 0.66 for the greedy. Furthermore, the RL approach exhibits effective delivery rates compared to the greedy adaptive routing, particularly under low network load of 20% at 0.57 vs. 0.43, showing greater proficiency in managing congestion, validating its efficacy in stochastic, fault-prone topologies

Problem

• Develops a fault-aware RL routing scheme for Gaussian Interconnected Networks
• Addresses performance degradation from clustered node and link faults
• Improves packet delivery by dynamically learning to bypass faulty regions

Innovation

• Reinforcement Learning routing for Gaussian networks
• PPO agent with fault-proximity penalty reward structure
• Dynamically learns to bypass faulty regions