Jul 2026· Annual International Computer Software and Applications Conference· pp. 1353-1362· 1 citation· 49 references
Abstract
Wireless Mesh Networks (WMNs) are essential for many Internet of Things (IoT) applications, such as industrial automation, environmental monitoring, and smart cities. Today, configuring a WMN to meet its stringent performance requirements remains a significant challenge due to dynamic real-world wireless conditions and operating environments. The simulationto-reality gap in network configuration further complicates the generalization of models trained solely with simulation data, leading to suboptimal performance in physical deployments. To address such challenges, we develop WMN-LLM-DS, a novel framework that integrates Large Language Models (LLMs) for synthetic data generation with domain adaptation techniques to better configure WMNs. Leveraging LLMs, WMN-LLM-DS generates high-quality, diverse synthetic datasets conditioned on realworld constraints, effectively bridging the simulation-to-reality gap and enriching the diversity of training data. WMN-LLM-DS employs a teacher-student architecture to transfer network configuration knowledge learned from simulations to physical deployments, enhanced by custom loss functions to align feature representations across different domains. Experiments conducted on datasets collected from a physical testbed and network simulators demonstrate that WMN-LLM-DS outperforms existing solutions, achieving an improvement of up to 10.8% in prediction accuracy while also exhibiting strong domain generalization capabilities.
It is concluded that the co-design of lightweight, telecom-specific large language models (Telecom-LLMs) and distributed inference mechanisms constitutes a pivotal evolutionary pathway toward realizing endogenous intelligence in future wireless communication systems.
Chunxuan Zhao· Applied and Computational En...· 0 citations
Efficient long-term network evolution is becoming increasingly critical in dense 5G-Advanced and beyond cellular systems, where persistent traffic imbalances and localized congestion pose significant challenges that conventional short-term radio resource management alone cannot fully mitigate. This paper proposes a digital twin (DT)-enabled non-real-time (NRT) network evolution framework integrated with a large language model (LLM). Within this architecture, the digital twin provides a high-fidelity, controllable environment for evaluating infrastructure actions, while the LLM serves as a strategic orchestration engine that recommends cost-efficient network upgrades based on observed network states. Unlike traditional optimization methods that require exhaustive mathematical reformulations for each specific scenario, the proposed framework leverages the reasoning capabilities of LLMs to interpret operator objectives and constraints in natural language, generating structured evolution plans. The considered NRT action space encompasses antenna upgrades, bandwidth expansion, and new base station (BS) deployment. A techno-economic formulation is introduced to jointly evaluate load reduction performance and overall economic expenditure. Numerical results in a dense cellular scenario demonstrate that the framework effectively reduces peak resource utilization and provides diverse, coordinated evolution strategies tailored to varying network conditions.
Yukai Wang, Janghee Woo, G. Hahm et al.· International Conference on...· 0 citations
As Software-Defined Networking (SDN) and Network Function Virtualization (NFV) enabled networks scale in size and complexity, monitoring and managing Service Function Chains (SFCs) under stringent latency and resource constraints becomes increasingly challenging. Although Deep Reinforcement Learning (DRL) is widely applied to SFC provisioning and Virtual Network Function (VNF) placement, enhanced network state monitoring is crucial to capture unexpected network conditions and guide DRL agents toward more adaptive decisions. In this context, Language Models (LMs) enable flexible, natural-language (NL)–based, query-driven network monitoring; however, directly processing complex multi-metric NL queries is computationally expensive and error-prone. This paper proposes an end-to-end (E2E) edge-based query translation pipeline that decomposes multi-metric NL queries into simpler single-metric sub-queries. Query decomposition is performed using a retrieval-augmented language model (RAG-LLM) and compared with a lightweight rule-based decomposition baseline. The resulting sub-queries are translated into Structured Query Language (SQL) using FLAN-T5. A cloud-only baseline, which directly translates NL queries to SQL without decomposition, is also evaluated. The results show that the rule-based edge pipeline achieves the lowest latency, reducing E2E latency by up to 78% compared to RAG-LLM and 18% compared to cloud execution under high workloads. Under increasing arrival rates for the largest workload, the rule-based edge pipeline maintains superior performance over cloud, reducing total E2E latency by 57% at $\lambda = 0.8$ . While RAG-LLM provides greater flexibility for unseen query patterns, both edge-based approaches achieve 100% NL2SQL accuracy with zero decomposition failures, outperforming the cloud-only baseline (95% accuracy).
Parisa Fard Moshiri, Xinyu Zhu, Poonam Lohan et al.· IEEE Transactions on Network...· 0 citations
Results confirm that reinforcement learning–based resource allocation provides a scalable and effective solution for IoT networks, particularly in environments characterized by large state spaces, dynamic network conditions, and stochastic traffic patterns.
L. Hoang, Van-Tam Hoang, Huu-Huy Ngo· International journal of Com...· 1 citation
The telecommunication industry in India is undergoing a structural change, with the deployment of the 5G network, the widespread deployment of smart devices for the Digital India initiative and the need for ultra-low latencies, high-speed services for smart cities, healthcare, agriculture and industrial automation. Traditional network management methods, which are mostly based on static configuration and human intervention are increasingly proving to be insufficient for the scale, diversity and dynamism of these networks. This paper introduces an Artificial Intelligence (AI) centric network management framework that combines 5G radio access and core capabilities, Software-Defined Networking (SDN) for centralized and programmable control and Multi-access Edge Computing (MEC) for localized and low latency processing. This framework includes a traffic prediction module (based on Long Short-Term Memory (LSTM)) and a resource orchestration engine (Deep Q-Network (DQN)), both of which allow for closed-loop self-optimizing network actions. Mininet-WiFi and Ryu SDN controller were used to simulate a representative Indian metropolitan network topology and assess the proposed framework in comparison to a baseline configuration with conventional SDN. Experimental results show significant gains in end-to-end latency (53.3 %), throughput (53.2 %), jitter (60.7 %), packet loss (72.4 %) and resource-utilization efficiency (42.6 %). The results indicate that 5G-SDN-edge continuum orchestration can positively impact the Quality of Service (QoS) in India-specific use cases such as dense urban areas and rural areas with limited infrastructure. The paper also elaborates the deployment challenges pertinent to the Indian context like spectrum availability, fiber backhaul penetration, cost of edge infrastructure, and regulatory considerations, while proposing the directions for future research like federated learning in orchestrating with privacy constraints and upcoming 6G research initiatives.
Praveen Kumar, S. Hashmi, Preeti Singhwal et al.· International journal of com...· 0 citations
This article outlines the fundamental principles of the dual-layer OTA model and introduces the adaptive BH mechanism designed for time-varying topologies, aiming to provide insights for the evolution of ubiquitous non-terrestrial intelligence.
Zhendong Li, Shaojie Wang, Zhou Su et al.· 0 citations
