{"title":"Modeling Super-Lightweight Cellular Traffic Prediction via Multiservice and Multimodal Feature Fusion Network","authors":"Yingqi Li;Mingxiang Hao;Xiaochuan Sun;Haijun Zhang","doi":"10.1109/LNET.2023.3329744","DOIUrl":"10.1109/LNET.2023.3329744","url":null,"abstract":"Cellular Traffic Prediction has proven to be a key enabler towards automatic network management. However, to pursue performance improvement, the existing studies mainly focus on developing complex deep neural network models, which suffer from extensive computation cost and large model size inevitably. Such models are quite difficult to be deployed on resource-constrained devices. In this letter, we propose a multiservice and multimodal feature fusion network for super-lightweight cellular network traffic prediction, namely \u0000<inline-formula> <tex-math>$m^{2}FFNet$ </tex-math></inline-formula>\u0000, to address the issue. Briefly speaking, such a network consists of a duel feature extraction channel based on grouped 3D convolution for capturing multiservice feature and multimodal feature (yielded from wavelet transform decomposition), respectively. Simulation results demonstrate that our proposal can achieve comparable prediction accuracy as the state-of-the-art deep learning methods, meanwhile obtaining much less computation burden with rather few model size.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 1","pages":"16-20"},"PeriodicalIF":0.0,"publicationDate":"2023-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134889870","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}
Sonu Rathi;Jorge F. Schmidt;Udo Schilcher;Siddhartha S. Borkotoky
{"title":"Energy-Aware Relaying in Dense LoRa Networks With Heterogeneous Batteries","authors":"Sonu Rathi;Jorge F. Schmidt;Udo Schilcher;Siddhartha S. Borkotoky","doi":"10.1109/LNET.2023.3329030","DOIUrl":"10.1109/LNET.2023.3329030","url":null,"abstract":"We propose a relaying scheme for a LoRa network’s uplink, where some end devices (EDs) overhear and relay messages from other EDs. The scheme’s salient feature is that it allows the EDs to adjust their relaying behavior according to their energy status, such that EDs with higher energy reserves perform more forwarding. This prevents early depletion of batteries at the low-energy forwarders, while still achieving high reliability levels. The network is divided into tiers. Any ED in a given tier can relay message from any other ED in certain other tier; this eliminates the need for complicated relay-selection procedures. No synchronization requirement is imposed on the EDs. We demonstrate large reductions in the loss rate with just 10% of the EDs acting as relays, operating within 1% duty cycle.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 1","pages":"41-45"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135362165","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}
{"title":"Energy Sustainability in Dense Radio Access Networks via High Altitude Platform Stations","authors":"Maryam Salamatmoghadasi;Amir Mehrabian;Halim Yanikomeroglus","doi":"10.1109/LNET.2023.3328918","DOIUrl":"10.1109/LNET.2023.3328918","url":null,"abstract":"The growing demand for radio access networks (RANs) driven by advanced wireless technology and the ever-increasing mobile traffic, faces significant energy consumption challenges that threaten sustainability. To address this, an architecture referring to the vertical heterogeneous network (vHetNet) has recently been proposed. Our study seeks to enhance network operations in terms of energy efficiency and sustainability by examining a vHetNet configuration, comprising a high altitude platform station (HAPS) acting as a super macro base station (SMBS), along with a macro base station (MBS) and a set of small base stations (SBSs) in a densely populated area. By intelligently managing SBSs’ sleep mode and employing HAPS’s potentials and additional capacity, our approach aims to minimize vHetNet energy consumption. The proposed method dynamically determines which SBSs to switch off based on the traffic load of SBSs, MBS, and HAPS. This innovative approach offers a flexible and promising solution to enhance network sustainability, energy efficiency, and capacity utilization without compromising the user quality-of-service (QoS). We show that our proposed method offers a scalable solution with comparable performance to exhaustive search (ES) as the optimal solution in terms of energy efficiency. Furthermore, incorporating HAPS, significantly improves grid power consumption, compared to having no offloading, reducing it by 30% for a large number of SBSs.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 1","pages":"21-25"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135362157","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}
{"title":"Task Offloading and Approximate Computing in Solar Powered IoT Networks","authors":"Junfei Zhan;Jiayi Wu;Tengjiao He;Kwan-Wu Chin","doi":"10.1109/LNET.2023.3328893","DOIUrl":"10.1109/LNET.2023.3328893","url":null,"abstract":"This letter considers approximate computing and task offloading in a solar powered Internet of Things (IoT) network. Specifically, it addresses the novel problem of minimizing the energy consumption of IoT devices by either offloading their tasks or executing these tasks in approximate mode. To this end, this letter outlines a novel mixed integer linear program (MILP) that computes the minimum total energy required to execute tasks. It optimizes four key factors: (i) task offloading decision of devices, (ii) use of approximate computing by devices, (iii) channel allocation, and (iv) virtual machine (VM) assignment. Further, it outlines a novel solution that determines these factors using channel gain and energy arrival estimates obtained from digital twins (DTs). The results show that our DT-based solution uses at most 1.62x more energy than MILP.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 1","pages":"26-30"},"PeriodicalIF":0.0,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135263191","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}
{"title":"Intrusion Detection System for MIL-STD-1553 Based on Convolutional Neural Networks With Binary Images and Adaptive Quantization","authors":"Gianmarco Baldini;Kandeepan Sithamparanathan","doi":"10.1109/LNET.2023.3324508","DOIUrl":"10.1109/LNET.2023.3324508","url":null,"abstract":"This letter proposes an Intrusion Detection System (IDS) for the MIL-STD-1553 serial bus protocol, which is used in the aerospace systems. This letter proposes a novel encoding scheme to transform all the traffic data of MIL-STD-1553 including header, payload and time of packet transmission to binary images, which are given as an input to a Convolutional Neural Network (CNN). The encoding scheme is based on a quantization parameter \u0000<inline-formula> <tex-math>$Q_{b}$ </tex-math></inline-formula>\u0000, which must be tuned to support the optimal attack detection performance of the algorithm. Then, this letter proposes a pre-processing adaptive step before the application of CNN to select the optimal value of \u0000<inline-formula> <tex-math>$Q_{b}$ </tex-math></inline-formula>\u0000. The proposed approach is applied on a recently published cybersecurity data set of MIL-STD-1553 traffic, where it achieves a detection accuracy of 99.31%.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 1","pages":"50-54"},"PeriodicalIF":0.0,"publicationDate":"2023-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136301723","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}
{"title":"NB-SSH: NB-IoT-Based Remote SSH Access to UAVs Under Symmetric NAT","authors":"Xiaojun Zhu;Jiao Tang","doi":"10.1109/LNET.2023.3323389","DOIUrl":"10.1109/LNET.2023.3323389","url":null,"abstract":"When NB-IoT is used to monitor UAVs, developers need to access a UAV via SSH (Secure Shell). However, NB-IoT services are sometimes behind symmetric NAT, and NB-IoT modules can only be controlled by specific AT commands, rendering existing NAT traversal software not applicable. This letter proposes NB-SSH, which provides remote SSH service to UAVs that are behind symmetric NAT. NB-SSH has two variants, in one of which the client side does not need to install any software, and in the other the UAV appears to the client as a neighbor. We implement both variants and evaluate them in a real-world environment.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 1","pages":"6-10"},"PeriodicalIF":0.0,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136208338","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}
{"title":"Twisted and Folded Clos-Network Design Model With Two-Step Blocking Probability Guarantee","authors":"Haruto Taka;Takeru Inoue;Eiji Oki","doi":"10.1109/LNET.2023.3322172","DOIUrl":"10.1109/LNET.2023.3322172","url":null,"abstract":"A data center network often employs a Clos-network structure due to scalability nature. A previous design model analyzed blocking probability to guarantee the quality of Clos network. However, the conditions to guarantee the blocking probability in these models are stringent, which shrinks the switching capacity. This letter proposes a model that relaxes network design constraints to maximize switching capacity while guaranteeing blocking probability in a two-step manner, where the proposed model divides intermediate switches into two groups. Numerical results show that the proposed model achieves a larger switching capacity than a conventional one-step model.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 1","pages":"60-64"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136003853","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}
Davide Borsatti;Gianluca Davoli;Federico Tonini;Walter Cerroni;Carla Raffaelli;Wint Yi Poe;Riccardo Trivisonno
{"title":"Hierarchical Management Algorithms for Highly Reliable Communication in 6G Industrial Environments","authors":"Davide Borsatti;Gianluca Davoli;Federico Tonini;Walter Cerroni;Carla Raffaelli;Wint Yi Poe;Riccardo Trivisonno","doi":"10.1109/LNET.2023.3321630","DOIUrl":"10.1109/LNET.2023.3321630","url":null,"abstract":"This letter explores the challenges of reliable communication in industrial applications, where human and robot collaboration requires highly reliable communication channels. We propose a hierarchical and distributed approach for solving the dynamic selection of resources. We assign distributed entities to portions of the managed working environment and investigate how to deal with users at their borders, proposing a mechanism to balance performance and resource efficiency. We support our analysis with numerical results obtained by simulation. By properly tuning the algorithm parameters, we can reduce energy consumption while satisfying the same reliability requirements.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 1","pages":"36-40"},"PeriodicalIF":0.0,"publicationDate":"2023-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135845796","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}
{"title":"SDN-Based Multicast Traffic Engineering for Radio Telescope Data Networks","authors":"Martin Slabber;Neco Ventura;Joyce Mwangama","doi":"10.1109/LNET.2023.3319965","DOIUrl":"10.1109/LNET.2023.3319965","url":null,"abstract":"Modern radio telescopes utilize IP multicast in their data networks because multicasting offers enhanced flexibility. Telescope data networks carry high volumes of real-time data and need to support network reconfigurability. Hence, they stand to gain from optimized traffic management. Software-Defined Networking (SDN) simplifies and adds dynamism to multicast routing. We reference the MeerKAT radio telescope data network and investigate methods to route the multicast streams in an SDN context. Such route planning is influenced by the telescope control system along with architectural and dynamic (e.g., link or device failure) properties of the network. This letter shows that SDN is a practical option for radio telescope data networks and that the system is flexible, easy to understand, and scalable. Additionally, we present two basic algorithms which can serve as foundational templates for more tailored solutions.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 1","pages":"65-69"},"PeriodicalIF":0.0,"publicationDate":"2023-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135794554","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}
{"title":"Energy and Delay Efficient Fountain-Coded File Transfer Assisted by Unreliable Feedback","authors":"Sonu Rathi;Siddhartha S. Borkotoky","doi":"10.1109/LNET.2023.3318790","DOIUrl":"10.1109/LNET.2023.3318790","url":null,"abstract":"We propose a unicast wireless file-transfer scheme based on fountain coding augmented by a feedback mechanism to help the source make near-optimal transmission decisions. By avoiding wasted transmissions that occur in conventional fountain coding due to the delayed reception of feedback messages, the proposed scheme provides large reductions in the energy expenditure, while keeping the delivery latency very close to its minimum achievable value and avoiding excessive computational overhead. The scheme is robust against feedback message losses and imperfect estimates of system parameters. We demonstrate up to 85% reduction in the energy expenditure compared to conventional fountain coding and similar reductions in the average delivery latency compared to a state-of-the-art method.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"6 1","pages":"70-74"},"PeriodicalIF":0.0,"publicationDate":"2023-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135699092","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}