cs.NI papers | Gist.Science

Arterial Network Traffic State Prediction with Connected Vehicle Data: An Abnormality-Aware Spatiotemporal Network

This paper proposes a novel framework for predicting arterial traffic states using real-world connected vehicle data, featuring a two-stage traffic state extraction method and an Abnormality-aware Spatiotemporal Graph Convolution Network (AASTGCN) that effectively handles both normal and abnormal traffic conditions by separately modeling them with a dual-expert architecture and a gated-fusion mechanism.

Lei Han, Mohamed Abdel-Aty, Yang-Jun Joo2026-03-06💻 cs

Data-Driven Optimization of Multi-Generational Cellular Networks: A Performance Classification Framework for Strategic Infrastructure Management

This paper leverages a multi-generational cellular network dataset from OpenCelliD to analyze deployment patterns and utilization metrics, offering a strategic framework for Mobile Network Operators to optimize infrastructure, identify cost-saving opportunities, and guide targeted LTE upgrades in underserved regions.

Maryam Sabahat, M. Umar Khan2026-03-06💻 cs

When Scaling Fails: Network and Fabric Effects on Distributed GPU Training Performance

This paper presents an empirical study demonstrating that network topology, congestion dynamics, and GPU locality often cause unpredictable scaling failures in distributed GPU training, urging system builders to adopt specific diagnostic principles to address these overlooked fabric-level bottlenecks.

Dinesh Gopalan, Ratul Ali2026-03-06💻 cs

How segmented is my network?

This paper introduces "segmentedness," a statistically principled metric defined as the fraction of disallowed node-pair communications, and provides a normalized estimator with a 95% confidence interval that requires only 97 uniformly sampled node pairs to accurately measure network segmentation across various models and real-world datasets.

Rohit Dube2026-03-06💻 cs

MEC Task Offloading in AIoT: A User-Centric DRL Model Splitting Inference Scheme

This paper proposes a user-centric deep reinforcement learning framework, specifically a UCMS_MADDPG-based offloading algorithm, to optimize model splitting inference in AIoT-enabled mobile edge computing by jointly addressing resource allocation, server selection, and task offloading to minimize execution delay and energy consumption under dynamic constraints.

Weixi Li, Rongzuo Guo, Yuning Wang + 1 more2026-03-06💻 cs

Handover Delay Minimization in Non-Terrestrial Networks: Impact of Open RAN Functional Splits

This paper investigates the impact of Open RAN functional splits and beam configurations on handover performance in non-terrestrial networks, demonstrating that placing the gNB onboard LEO satellites maximizes user availability to approximately 95.4% by minimizing handover delays compared to other split options.

Siva Satya Sri Ganesh Seeram, Luca Feltrin, Mustafa Ozger + 2 more2026-03-06💻 cs

Wall-Street: An Intelligent Vehicular Surface for Reliable mmWave Handover

Wall-Street is a vehicle-mounted intelligent surface that enhances mmWave connectivity for high-speed users by steering signals into the vehicle, enabling seamless neighbor-cell searches, and facilitating reliable make-before-break handovers, resulting in significant throughput improvements and latency reductions compared to standard schemes.

Kun Woo Cho, Prasanthi Maddala, Ivan Seskar + 1 more2026-03-06💻 cs

Multi-Channel Operation for the Release 2 of ETSI Cooperative Intelligent Transport Systems

This paper provides a comprehensive review of the new ETSI Release 2 multi-channel operation (MCO) specifications for Cooperative Intelligent Transport Systems, detailing the extended architecture, illustrating future use cases, and identifying open research issues to address the growing data traffic demands of advanced V2X applications.

Alessandro Bazzi, Miguel Sepulcre, Quentin Delooz + 5 more2026-03-06💻 cs

Performance Analysis of IEEE 802.11p Preamble Insertion in C-V2X Sidelink Signals for Co-Channel Coexistence

This paper proposes and evaluates a mitigation strategy for co-channel interference between IEEE 802.11p and LTE-V2X Mode 4 by inserting an 802.11p preamble into LTE-V2X transmissions, demonstrating through analysis and simulations that this approach effectively reduces collisions and improves performance across various traffic densities, particularly when combined with congestion control mechanisms.

Alessandro Bazzi, Stefania Bartoletti, Alberto Zanella + 1 more2026-03-06💻 cs

Quantum Algorithms for Network Signal Coordination

This paper presents and validates quantum algorithms based on Grover's search that solve the NP-complete Network Signal Coordination (NSC) problem and its robust variants, achieving quadratic speedups and maintaining efficiency even when the solution space fraction decays polynomially with network size.

Vinayak Dixit, Richard Pech2026-03-06⚛️ quant-ph

Bitcoin Under Stress: Measuring Infrastructure Resilience 2014-2025

This paper presents the first longitudinal study (2014–2025) of Bitcoin's physical infrastructure resilience, demonstrating through a novel 4-layer multiplex model that while targeted cable attacks pose significant risks, the network's clearnet and TOR-based overlay structures exhibit high robustness against random submarine cable failures, with empirical data showing that 87% of historical faults caused minimal node impact.

Wenbin Wu, Alexander Neumueller2026-03-05💻 cs

Measuring Round-Trip Response Latencies Under Asymmetric Routing

This paper introduces PIRATE, a passive measurement technique that estimates client-side response latencies by analyzing causal request pairs in encrypted traffic, demonstrating high accuracy and the ability to significantly reduce tail latencies when integrated with load balancers.

Bhavana Vannarth Shobhana, Yen-lin Chien, Jonathan Diamant + 3 more2026-03-05💻 cs

Scalable Interference Graph Learning for Low-Latency Wi-Fi Networks using Hashing-based Evolution Strategy

This paper proposes a scalable interference graph learning framework that combines an evolution strategy with deep hashing to efficiently optimize RTWT slot assignments for low-latency Wi-Fi 7 networks, significantly improving slot efficiency, reducing packet loss, and accelerating training and inference times in dense environments.

Zhouyou Gu, Jihong Park, Jinho Choi2026-03-05💻 cs

A Constrained RL Approach for Cost-Efficient Delivery of Latency-Sensitive Applications

This paper proposes a constrained deep reinforcement learning (CDRL) approach formulated as a constrained Markov decision process to minimize resource allocation costs while ensuring strict per-packet delay requirements for latency-sensitive applications, outperforming existing stochastic optimization methods in both reliability and cost-efficiency.

Ozan Aygün, Vincenzo Norman Vitale, Antonia M. Tulino + 3 more2026-03-05🤖 cs.LG

Selecting Offline Reinforcement Learning Algorithms for Stochastic Network Control

This paper evaluates various offline reinforcement learning algorithms within a stochastic telecom environment and finds that Conservative Q-Learning offers the most robust policies for network control, while sequence-based methods serve as competitive alternatives when high-quality trajectory data is abundant.

Nicolas Helson, Pegah Alizadeh, Anastasios Giovanidis2026-03-05🤖 cs.AI

Agentic Peer-to-Peer Networks: From Content Distribution to Capability and Action Sharing

This paper proposes a plane-based reference architecture and a tiered verification spectrum to enable secure, intent-aware discovery and execution of heterogeneous capabilities within Agentic Peer-to-Peer networks, demonstrating through simulation that this approach significantly improves workflow success while maintaining low latency and overhead.

Taotao Wang, Lizhao You, Jingwen Tong + 2 more2026-03-05🤖 cs.AI

Chimera: Neuro-Symbolic Attention Primitives for Trustworthy Dataplane Intelligence

Chimera is a neuro-symbolic framework that enables trustworthy, line-rate traffic analysis on programmable dataplanes by mapping attention-based neural computations and symbolic constraints onto hardware primitives to achieve high-fidelity inference within strict resource limits.

Rong Fu, Xiaowen Ma, Kun Liu + 9 more2026-03-05🤖 cs.AI

Space-O-RAN: Enabling Intelligent, Open, and Interoperable Non Terrestrial Networks in 6G

This paper introduces Space-O-RAN, a distributed control architecture that extends Open RAN principles to satellite constellations by deploying lightweight onboard applications and hierarchical coordination via SpaceRIC and terrestrial SMO to enable intelligent, autonomous, and interoperable Non-Terrestrial Networks for 6G.

Eduardo Baena, Paolo Testolina, Michele Polese + 3 more2026-03-05🤖 cs.AI

Simulation of a Heterogeneous Quantum Network

This paper presents an open-source, hardware-faithful simulation framework built on SeQUeNCe that models heterogeneous quantum networks combining Ytterbium atoms and superconducting qubits to analyze rate-fidelity trade-offs and identify unique system bottlenecks.

Hayden Miller, Caitao Zhan, Michael Bishof + 4 more2026-03-05⚛️ quant-ph

Optimizing Orbital Parameters of Satellites for a Global Quantum Network

This paper demonstrates that black-box optimization frameworks, specifically Bayesian Optimization and Genetic Algorithms, can effectively optimize satellite orbital inclinations and allocations to significantly maximize entanglement generation rates in global quantum networks compared to naive constellation designs.

Athul Ashok, Owen DePoint, Jackson MacDonald + 2 more2026-03-03⚛️ quant-ph

← Previous Next →