IEEE Networking Letters最新文献_第3页

Hierarchical Decision Mamba Meets Agentic AI: A Novel Approach for RAN Slicing in 6G 分层决策曼巴与代理人工智能：6G无线局域网切片的新方法

IEEE Networking Letters Pub Date : 2026-01-01 Epub Date: 2026-02-02 DOI: 10.1109/LNET.2026.3660628

Md Arafat Habib;Medhat Elsayed;Majid Bavand;Pedro Enrique Iturria Rivera;Yigit Ozcan;Melike Erol-Kantarci

{"title":"Hierarchical Decision Mamba Meets Agentic AI: A Novel Approach for RAN Slicing in 6G","authors":"Md Arafat Habib;Medhat Elsayed;Majid Bavand;Pedro Enrique Iturria Rivera;Yigit Ozcan;Melike Erol-Kantarci","doi":"10.1109/LNET.2026.3660628","DOIUrl":"https://doi.org/10.1109/LNET.2026.3660628","url":null,"abstract":"Radio Access Network (RAN) slicing enables multiple logical networks to exist on top of the same physical infrastructure by allocating resources to distinct service groups, where radio resource scheduling plays a key role in ensuring compliance with slice-specific Service-Level Agreements (SLAs). Existing configuration-based or intent-driven Reinforcement Learning (RL) approaches usually rely on static mappings and SLA conversions. The current literature does not integrate natural language understanding with coordinated decision-making. To address these limitations, we propose an Agentic AI framework for 6G RAN slicing, driven by a super agent built using Hierarchical Decision Mamba (HDM) controllers and a Large Language Model (LLM). The super agent interprets operator intents and translates them into actionable goals using the LLM, which are used by HDM to coordinate inter-slice, intra-slice, and self-healing agents. Compared to transformer-based and reward-driven baselines, the proposed Agentic AI framework demonstrates consistent improvements across key performance indicators, including higher throughput, improved cell-edge performance, and reduced latency across different slices.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"8 ","pages":"120-124"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147665368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Toward Self-Optimizing 6G Networks Through Network Digital Twin Intelligence: A Real Network Traffic Evaluation 通过网络数字孪生智能实现6G网络的自优化：真实网络流量评估

IEEE Networking Letters Pub Date : 2026-01-01 Epub Date: 2026-02-12 DOI: 10.1109/LNET.2026.3664288

John Sengendo;Fabrizio Granelli

引用次数: 0

Smart Predict and Optimize: A Tutorial on End-to-End Optimization Resource Allocation for IoT Networks 智能预测与优化：物联网网络端到端优化资源分配教程

IF 3.3

IEEE Networking Letters Pub Date : 2026-01-01 Epub Date: 2026-03-25 DOI: 10.1109/LNET.2026.3677356

Xiaoyu Song;Kunsheng Wang;Kwan-Wu Chin;Changlin Yang

{"title":"Smart Predict and Optimize: A Tutorial on End-to-End Optimization Resource Allocation for IoT Networks","authors":"Xiaoyu Song;Kunsheng Wang;Kwan-Wu Chin;Changlin Yang","doi":"10.1109/LNET.2026.3677356","DOIUrl":"https://doi.org/10.1109/LNET.2026.3677356","url":null,"abstract":"The operators and nodes of Internet of things (IoT) networks often perform resource allocation, where they may solve a mathematical program to compute the optimal allocation of resources or decision(s), e.g., energy usage of devices, using sensed data as parameter values. Further, these parameter values may be stored/predicted using a neural network given one or more features, e.g., historical energy arrival rates at nodes. In this respect, to date, there are no IoT specific tutorials or works that focus on the smart predict and optimize (SPO) resource allocation framework. This paper thus fills this gap. Briefly, it shows the workflow of SPO, which involves using a machine learning model and a mathematical program to compute decisions. A key feature of SPO is that unlike prior approaches that only aim to predict the parameter values of a mathematical program, it maps the features of a system to decisions in an end-to-end manner. This paper also outlines various potential IoT applications that would benefit from SPO. It then presents a case study where SPO is used to decide task offloading from a device that has to contend with other users in a WiFi network. Lastly, it outlines some future research directions.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"8 ","pages":"253-257"},"PeriodicalIF":3.3,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148442700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Wireless Broadcast Gossip for Decentralized Drone Swarms: Success Probability, Contraction, and Optimal Aloha 分散无人机群的无线广播八卦：成功概率、收缩和最优Aloha

IF 3.3

IEEE Networking Letters Pub Date : 2026-01-01 Epub Date: 2026-03-13 DOI: 10.1109/LNET.2026.3693104

Ali Khalesi

引用次数: 0

An Empirical Quality of Service Analysis of Networked MicroGrids 网络化微电网服务质量实证分析

IF 3.3

IEEE Networking Letters Pub Date : 2026-01-01 Epub Date: 2026-03-09 DOI: 10.1109/LNET.2026.3672287

Yasin Emir Kutlu;Ruairí de Fréin

{"title":"An Empirical Quality of Service Analysis of Networked MicroGrids","authors":"Yasin Emir Kutlu;Ruairí de Fréin","doi":"10.1109/LNET.2026.3672287","DOIUrl":"https://doi.org/10.1109/LNET.2026.3672287","url":null,"abstract":"Quality of Service (QoS) degradation of Networked MicroGrids (NMG) control data impacts system performance. Modern communication networks are essential for control data transmission for NMGs. The dynamic nature of these communication networks, driven by variable traffic loads such as neighbourhood area network video traffic, presents challenges to satisfying QoS targets. This makes achieving acceptable convergence times for effective NMG performance difficult. Prior research on NMG control data was conducted primarily through Hardware-In-The-Loop (HIL) simulations or with constant background traffic. We assess the impact of Video-Streaming (VS) traffic on the QoS of NMG control data using a real hardware NMG testbed which is constructed using 500 W Direct Current (DC) power sources and a Layer-3 network consisting of Cisco 4331 Integrated Services Routers (ISR), which is representative of a neighbourhood area NMG deployment. We evaluate the output power convergence times of the NMGs against the 10-second open loop signal response time requirement in IEEE 1547-2018. The experiments show that when real communication and power network equipment is used the mean convergence times for the output power signal are 2.7 times longer than the established requirement, and that instantaneous power losses exceed 50%. These results underscore the need to better manage neighbourhood area communication networks to ensure acceptable QoS of NMG control packets.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"8 ","pages":"209-213"},"PeriodicalIF":3.3,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11426959","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148491476","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Change Point and Anomaly-Aware QoT Forecasting Framework for Proactive Network Management 主动网络管理的变化点和异常感知QoT预测框架

IF 3.3

IEEE Networking Letters Pub Date : 2026-01-01 Epub Date: 2026-03-07 DOI: 10.1109/LNET.2026.3691249

Sandra Aladin;Lena Wosinska;Christine Tremblay

引用次数: 0

Lossy Compression of Cellular Network KPIs 蜂窝网络kpi的有损压缩

IF 3.3

IEEE Networking Letters Pub Date : 2026-01-01 Epub Date: 2026-06-24 DOI: 10.1109/LNET.2026.3706814

Andrea Pimpinella;Fabio Palmese;Alessandro E. C. Redondi

{"title":"Lossy Compression of Cellular Network KPIs","authors":"Andrea Pimpinella;Fabio Palmese;Alessandro E. C. Redondi","doi":"10.1109/LNET.2026.3706814","DOIUrl":"https://doi.org/10.1109/LNET.2026.3706814","url":null,"abstract":"Network Key Performance Indicators (KPIs) are a fundamental component of mobile cellular network monitoring and optimization. Their massive volume, resulting from fine-grained measurements collected across many cells over long time horizons, poses significant challenges for storage, transport, and large-scale analysis. In this letter, we show that common cellular KPIs can be efficiently compressed using standard lossy compression schemes based on prediction, quantization, and entropy coding, achieving substantial reductions in reporting overhead. Focusing on traffic volume KPIs, we first characterize their intrinsic compressibility through a rate–distortion analysis, showing that signal-to-noise ratios around 30 dB can be achieved using only 3–4 bits per sample, corresponding to an 8–<inline-formula> <tex-math>$10times $ </tex-math></inline-formula> reduction with respect to 32-bit floating-point representations. We then assess the impact of KPI compression on representative downstream analytics tasks. Our results show that aggregation across cells mitigates quantization errors and that prediction accuracy is unaffected beyond a moderate reporting rate. These findings indicate that KPI compression is feasible and transparent to network-level analytics in cellular systems.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"8 ","pages":"354-357"},"PeriodicalIF":3.3,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148836885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

NEOL: Multiscale Adaptation of Large Language Models for Network Energy Optimization 网络能量优化的多尺度自适应大语言模型

IEEE Networking Letters Pub Date : 2026-01-01 Epub Date: 2025-11-19 DOI: 10.1109/LNET.2025.3635176

Rushali Rajesh;Kowsik Nandagopan;Dilip Krishnaswamy

{"title":"NEOL: Multiscale Adaptation of Large Language Models for Network Energy Optimization","authors":"Rushali Rajesh;Kowsik Nandagopan;Dilip Krishnaswamy","doi":"10.1109/LNET.2025.3635176","DOIUrl":"https://doi.org/10.1109/LNET.2025.3635176","url":null,"abstract":"Energy conservation and sustainable system development have been key focal points of late globally. In this context, the exploration of energy-efficient strategies within wireless mobile networks has gained significant research interest in recent years. Base stations are among the most power-intensive components of mobile networking systems due to their high-power radio frequency emissions required for extensive coverage. This letter investigates energy-saving approaches in the telecommunications sector through a proactive methodology that predicts network usage patterns. Edge cloud resources can be leveraged for AI model learning based on observed network key performance indicators. Dynamic network edge processing is utilized to enable dynamic network resource management with digital twin model processing to provide the dynamic input context window to an AI inferencing engine. Furthermore, the study finds that Large Language Models (LLMs) that have the ability to process data across different timescales could be leveraged to create a future predicted network resource utilization context window. Our results indicate that such a predicted context window combined with dual threshold monitoring of network utilization can be used to enable dynamic network resource optimization.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"8 ","pages":"179-183"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147665468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Diffusion Policies Reinforcement Learning for Resource Allocation in Open RAN Digital Twin 开放式RAN数字孪生中资源分配的扩散策略强化学习

IEEE Networking Letters Pub Date : 2026-01-01 Epub Date: 2026-01-19 DOI: 10.1109/LNET.2026.3655578

Zhizhou He;Mohammad Shojafar;Chuan Heng Foh;Rahim Tafazolli

{"title":"Diffusion Policies Reinforcement Learning for Resource Allocation in Open RAN Digital Twin","authors":"Zhizhou He;Mohammad Shojafar;Chuan Heng Foh;Rahim Tafazolli","doi":"10.1109/LNET.2026.3655578","DOIUrl":"https://doi.org/10.1109/LNET.2026.3655578","url":null,"abstract":"This letter presents a deterministic diffusion Q-learning scheme for resource allocation in Open Radio Access Network (O-RAN) digital twin systems. The proposed approach jointly optimizes resource allocation for all UEs by formulating Q-values based on the dynamic O-RAN environment. Diffusion policies in Q-learning enhance exploration and smooth policy optimization by leveraging the diffusion process, leading to more robust and efficient learning. To improve computational efficiency, a deterministic diffusion mechanism is introduced to eliminate redundant iteration steps in the forward–reverse diffusion process. Compared to traditional stochastic diffusion models, the proposed method significantly reduces computational complexity while allowing for customizable optimization targets. Simulation results show that the proposed approach improves total throughput by 8.2% over proportional fairness, while matching the performance of classic Q-learning using 7.9% fewer resources. Meanwhile, the proposed model can be easily adapted to various O-RAN scenarios with minimal fine-tuning, leveraging the inherent flexibility of the diffusion-based framework.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"8 ","pages":"164-168"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147665514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Low-Latency Network Design Scheme for Distributed Databases With Application-Specific Access Distributions 具有特定应用访问分布的分布式数据库的低延迟网络设计方案

IF 3.3

IEEE Networking Letters Pub Date : 2026-01-01 Epub Date: 2026-07-16 DOI: 10.1109/LNET.2026.3714008

Hiroki Hori;Akio Kawabata

引用次数: 0