Jul 2026· 2026 6th International Conference on Intelligent Communications and Computing (ICICC)· pp. 222-225· 0 citations· 9 references
Abstract
Managing resilience in wireless ad hoc networks is challenging when the topology, routing paths, and protocol details are not fully observable. We study an online resilience recovery scheduling problem where a controller selects a limited set of nodes each round for monitoring, reconfiguration, protection, or recovery, and only an aggregate network-level feedback is observed. To address the resulting credit assignment issue in combinatorial decisions, we develop (i) an Improved Combinatorial UCB method that estimates node utilities from aggregate rewards, and (ii) a Correlation-Guided UCB method that learns a pairwise node correlation matrix and constructs more effective multi-node recovery sets. We also evaluate a protocolindependent reward based on active-node variation to support partially observable environments. Simulations on Poisson point process wireless ad hoc networks show that the proposed correlation-guided approach consistently improves cumulative service recovery and robustness across network density, size, flow load, and recovery budgets, outperforming independent bandits and centrality-based baselines.
Decentralized wireless collectives including vehicular swarms, IoT clusters, and edge AI networks require communication protocols that maintain robustness under dynamic topologies and heterogeneous link quality. While Random Linear Network Coding (RLNC) provides algebraic resilience against packet erasures, its performance degrades significantly when peers exhibit diverse channel conditions. This paper presents Adaptive Peer Clustering with Hierarchical RLNC (APC-RLNC), a system that dynamically groups peers by exponentially weighted moving average (EWMA) reliability metrics and applies multi-tier network coding within and across clusters. We formalize the clustering optimization problem, derive closed-form decoding probability bounds for Markov erasure channels, and prove O(sqrt(T)) regret for online reconfiguration under the Follow-the-Regularized-Leader (FTRL) framework. Our implementation includes both a high-fidelity network simulator and a proof-of-concept testbed deployment on Jetson Nano edge devices. Evaluation across diverse scenarios including high-mobility vehicular networks, burst-error channels, and adversarial interference demonstrates 5.2-9.8 percentage-point packet delivery ratio (PDR) improvements, 10-23% latency reductions, and up to 30% higher node retention compared to state-of-the-art baselines. The system exhibits linear scalability to 500+ nodes and maintains real-time reconfiguration overhead below 3%. APC-RLNC establishes adaptive clustering as a foundational primitive for AI-native 6G wireless systems.
Future sixth-generation (6G)-oriented networks require programmable control that can adapt routing to latency and congestion without unsafe online exploration. This study evaluates offline multi-agent deep deterministic policy gradient (MADDPG) with behavior-adjusted training rewards for latency-aware path control in software-defined networking (SDN). Each traffic pair is modeled as an agent selecting one of three retained candidate paths, while centralized critics learn coordinated decisions from topology-specific Ryu–Mininet transition datasets. Nine policies are compared using ten paired seeds on fat-tree, mesh-grid, and WAN-corridors topologies under a deployed utilization–latency weighting of 0.60/0.40, together with flow-completion, latency, congestion, architectural-comparison, sensitivity, robustness, statistical, and controller-overhead analyses. The utilization-aware path heuristic achieves the strongest overall reward ranking. MADDPG is the strongest learned policy on fat-tree, is not significantly outperformed by any evaluated policy on mesh-grid, and remains statistically tied with completion-matched policies on WAN-corridors. Behavior adjustment is topology-dependent rather than uniformly beneficial. The exported policy requires approximately 52μs per joint decision, whereas complete control-loop timing is dominated by network-statistics polling. These results support offline multi-agent SDN control as a competitive, low-overhead option when interpreted jointly with topology structure, flow completion, and strong heuristic baselines.
A. Kyzyrkanov, Y. Nurakhov, Zhenis Otarbay et al.· Technologies· 0 citations
Wireless Sensor Networks (WSNs) require precise time synchronization to ensure coordinated monitoring operations and data coherence across distributed multi-agent systems. Consensus-based protocols offer a robust, fully distributed solution for synchronizing clock offsets and frequencies by leveraging local information exchange. The convergence speed of such algorithms is heavily dependent on the algebraic connectivity of the network graph, structurally quantified by the second smallest eigenvalue of the graph’s Laplacian matrix. This paper investigates the reduction of convergence time in WSNs by strategically introducing a single dynamic node to an existing network topology. Three distinct criteria for determining the connections of the new node are proposed and mathematically analyzed: an exhaustive search for optimal positioning, a maximum degree constraint approach, and a Twin criterion that emulates the topology of an existing node. Numerical simulations establish that maximizing the second eigenvalue significantly accelerates synchronization. Furthermore, the integration of optimal node placement strategies provides a comprehensive framework for optimizing both resource cost and convergence speed.
F. Lamonaca, L. D’Alfonso· International Conference on...· 0 citations
This work introduces TANGCO (Topology-Aware Neural Graph-Guided Capacity Optimization), which uses a graph neural network policy trained through the cascade simulator with policy-gradient learning and a heuristic anchor to allocate a fixed capacity budget across nodes to resist cascades under local load redistribution.
This paper proposes a simulation-based dynamic message packing framework that enables runtime MPS selection based on queue occupancy and inter-participant distance while preserving the standard TDMA structure and waveform and provides a practical, standards-compliant runtime optimization for Link 16 systems.
F. Abut, Mehmet Kızıldağ· IEEE Access· 0 citations
Next-generation wireless networks must maintain reliable operation under abrupt and severe disruptions, particularly in ultra-reliable low-latency communication (URLLC) scenarios where strict time constraints dominate system design. This work addresses network resilience from a time-centric perspective by explicitly integrating finite blocklength (FBL) communication, thereby exposing transmission duration as a controllable resource for system recovery. To this end, we propose a unified cross-layer framework that jointly couples queue dynamics, rate adaptation, and blocklength optimization, enabling the system to actively absorb, adapt to, and recover from diverse resilience events. To systematically evaluate these mechanisms, we introduce an interpretable resilience metric that decomposes disruption impact into absorption loss, adaptation efficiency, and recovery behavior, enabling a direct and intuitive assessment of system resilience. Building on this framework, we develop a three-stage alternating optimization approach that jointly optimizes PHY-layer parameters, including beamforming, reconfigurable intelligent surface (RIS) phase shifts, and blocklength, revealing the importance of time-aware resource allocation in the FBL regime. Numerical results demonstrate strong resilience performance under repeated channel disruptions and AI-driven traffic surges, highlighting the effectiveness of cross-layer resource adaptation. Finally, the proposed resilience metric enables an intuitive and consistent comparison of resilience performance across different approaches and disruption types, while revealing their respective strengths and limitations.
K. Weinberger, Aydin Sezgin, Mehdi Bennis· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
