International Journal of Network Management最新文献

{"title":"Muno: Improved Bandwidth Estimation Scheme in Video Conferencing Using Deep Reinforcement Learning","authors":"Van Tu Nguyen,&nbsp;Sang-Woo Ryu,&nbsp;Kyung-Chan Ko,&nbsp;Jae-Hyoung Yoo,&nbsp;James Won-Ki Hong","doi":"10.1002/nem.2323","DOIUrl":"https://doi.org/10.1002/nem.2323","url":null,"abstract":"<div>\u0000 \u0000 <p>Many studies have used machine learning techniques for bitrate control to improve the quality of experience (QoE) of video streaming applications. However, most of these studies have focused on HTTP adaptive streaming with one-to-one connections. This research examines video conferencing applications that involve real-time, multiparty, and full-duplex communication among participants. In conventional video conferencing systems, a rule-based algorithm is typically employed to estimate the available bandwidth of each participant, and the outcomes are then used to control the video delivery rate to the participant. This paper proposes Muno, a bandwidth prediction framework based on deep reinforcement learning (DRL) for multiparty video conferencing systems. Muno aims to enhance the overall QoE by using DRL to improve bandwidth estimation for each connection. The experimental results indicate that Muno achieves a significantly higher video streaming rate, video resolution, and framerate while lowering delay in highly dynamic networks when compared to the state-of-the-art rule-based algorithms and roughly equivalent streaming rate and delay in stable networks. Moreover, Muno can generalize well to different network conditions which were not included in the training set. We also implemented a high-performance and scalable version of Muno for in-campus deployment.</p>\u0000 </div>","PeriodicalId":14154,"journal":{"name":"International Journal of Network Management","volume":"35 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143113096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Real-Time Encrypted Traffic Classification in Programmable Networks with P4 and Machine Learning","authors":"Aristide Tanyi-Jong Akem,&nbsp;Guillaume Fraysse,&nbsp;Marco Fiore","doi":"10.1002/nem.2320","DOIUrl":"https://doi.org/10.1002/nem.2320","url":null,"abstract":"<p>Network traffic encryption has been on the rise in recent years, making encrypted traffic classification (ETC) an important area of research. Machine learning (ML) methods for ETC are widely regarded as the state of the art. However, most existing solutions either rely on offline ETC based on collected network data or on online ETC with models running in the control plane of software-defined networks, all of which do not run at line rate and would not meet the strict requirements of ultra-low-latency applications in modern networks. This work exploits recent advances in data plane programmability to achieve real-time ETC in programmable switches at line rate, with high throughput and low latency. An extensive analysis is first conducted to show how tree-based models excel in ETC on various datasets. Then, a workflow is proposed for in-switch ETC with tree-based models. The proposed workflow builds on (i) an ETC-aware random forest (RF) modelling process where only features based on packet size and packet arrival times are used and (ii) an encoding of the trained RF model into off-the-shelf P4-programmable switches. The performance of the proposed in-switch ETC solution is evaluated on three use cases based on publicly available encrypted traffic datasets. Experiments are then conducted in a real-world testbed with Intel Tofino switches, in the presence of high-speed background traffic. Results show how the solution achieves high classification accuracy of up to 95<i>%</i> in QUIC traffic classification, with submicrosecond delay while consuming less than 10<i>%</i> on average of the total hardware resources available on the switch.</p>","PeriodicalId":14154,"journal":{"name":"International Journal of Network Management","volume":"35 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/nem.2320","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143113095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Method for Sharing English Education Resources in Multiple Virtual Networks Based on 6G","authors":"Hongliu He","doi":"10.1002/nem.2319","DOIUrl":"https://doi.org/10.1002/nem.2319","url":null,"abstract":"<div>\u0000 \u0000 <p>The rapid advancement of communication technologies, particularly in English language learning, is sharing education with the implementation of sixth-generation (6G) networks, offering immersive and interactive learning experiences. The purpose of the research is to establish an advanced method for sharing English education resources across multiple virtual networks enabled by 6G technology. Traditional resource-sharing systems lack the effectiveness and optimization requirement for large-scale instructional assignments, especially in virtual settings with various user demands. To address this, the study proposed a novel Dynamic Tunicate Swarm Refined Graph Neural Networks (DTS-RGNN) model to optimize resource allocation and improve the efficiency of resource sharing among educational tasks. The approach uses TSO for resource allocation scalable through 6G technology and GNN for task assignment according to the previous performances and interaction with the students to balance resource utilization. The experimental group performed writing (90%), sharing (91%), listening (85%), and reading (75%), finishing the task in 5.5 s at 1000 GB. Throughput increased by 5.0 GBps and resource utilization efficiency improved to (96%) and student outcomes showed high satisfaction (93%), retention (89%), and engagement (90%). The findings demonstrated the proposed method significantly improves the sharing of online English education resources, promoting more interactive and effective language learning experiences in virtual networks.</p>\u0000 </div>","PeriodicalId":14154,"journal":{"name":"International Journal of Network Management","volume":"35 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143118095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Efficient Workflow Scheduling Using Genetically Modified Golden Jackal Optimization With Recurrent Autoencoder in Cloud Computing","authors":"Saurav Tripathi,&nbsp;Sarsij Tripathi","doi":"10.1002/nem.2318","DOIUrl":"https://doi.org/10.1002/nem.2318","url":null,"abstract":"<div>\u0000 \u0000 <p>In this paper, a novel workflow scheduling framework is proposed using genetically modified golden jackal optimization (GM-GJO) with recurrent autoencoder. An integrated autoencoder and bidirectional gated recurrent unit (iAE-BiGRU) are used to forecast the number of virtual machines (VMs) needed to manage the system's present workload. The following step involves assigning the tasks of several workflows to cloud VMs through the use of the GM-GJO method for multiworkflow scheduling. GM-GJO provides optimal workflow scheduling by considering minimal maximizing utilization rate, minimizing makespan, and minimizing the number of deadline missed workflows. The proposed approach attempts to allocate the best possible set of resources for the workflows based on objectives such as deadline, cost, and quality of service (QoS). Extensive experiments were conducted with the CloudSIM tool, and the performance is evaluated in terms of scheduling length ratio, cost, QoS, etc. The execution time of 513.45 ms is achieved with a Sipht workflow of 30 tasks. When comparing the suggested strategy to the current methodologies, the suggested approach performs better.</p>\u0000 </div>","PeriodicalId":14154,"journal":{"name":"International Journal of Network Management","volume":"35 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142861696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Security Protection Method for Electronic Archives Based on Homomorphic Aggregation Signature Scheme in Mobile Network","authors":"Junwei Li,&nbsp;Huaquan Su,&nbsp;Li Guo,&nbsp;Wanshuo Wang,&nbsp;Yongjiao Yang,&nbsp;You Wen,&nbsp;Kai Li,&nbsp;Pingyan Mo","doi":"10.1002/nem.2316","DOIUrl":"https://doi.org/10.1002/nem.2316","url":null,"abstract":"<div>\u0000 \u0000 <p>Electronic archives are now widely used in many different industries and serve as the primary method of information management and storage because of the rapid growth of information technology and mobile networks. To enhance the security of electronic archives in mobile networks, the research utilizes the federated learning mechanism to design a federated learning model based on homomorphic aggregation cryptographic signature scheme combined with mobile network management. The use of homomorphic encryption technology in the signing process of electronic archives enables the aggregation of multiple electronic file signatures into a single signature without exposing the data of the electronic archives. This reduces the computational and storage requirements for signature verification. At the same time, a secure aggregation signature scheme is used to ensure the integrity and security of the data in the aggregation process. A novel approach is presented in this study, whereby trusted federated learning models are innovatively combined with homomorphic aggregate signature technology. This integration ensures data integrity through aggregate signature schemes. The results showed that, under mobile network management, the longest encryption time of the trusted federated learning model was 52 ms, and the longest decryption time was 44 ms. The accuracy of the optimized learning model reached 97.49%, and the loss value was significantly reduced to 0.09. To summarize, the electronic archive security protection method based on homomorphic aggregation signature scheme effectively improves the archive data protection efficiency and security.</p>\u0000 </div>","PeriodicalId":14154,"journal":{"name":"International Journal of Network Management","volume":"35 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142861454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"REMEDIATE: Improving Network and Middlebox Resilience With Virtualisation","authors":"Lyn Hill,&nbsp;Charalampos Rotsos,&nbsp;Chris Edwards,&nbsp;David Hutchison","doi":"10.1002/nem.2317","DOIUrl":"https://doi.org/10.1002/nem.2317","url":null,"abstract":"<p>The increasing demand for low-latency, high-bandwidth connectivity has introduced novel challenges to delivering strong resilience guarantees in production network environments. Closed hardware platforms, known as middleboxes, that lack visibility and support for state retention remain a key challenge for continuous service delivery during network failures. These middleboxes rarely employ recovery mechanisms of their own, inspiring renewed interest in the field of NFV in recent years due to this gap within the industry. The increasing availability of VNF capabilities in modern infrastructures offers an opportunity to exploit the flexibility of software and use hybrid architectures to improve resilience. REMEDIATE is a high-availability service that propagates state between unmodified hardware middleboxes and backup PNF or VNF appliances. The platform utilises targeted packet mirroring to allow network devices to organically construct equivalent state and thus allow an easy transition between hardware and software. To demonstrate its viability, we have evaluated REMEDIATE against a wide range of common hardware middlebox use cases built using multiple open-source packet processing frameworks. Results show upwards of 90% matching state with no observable delay to normal traffic or impact on its functionality.</p>","PeriodicalId":14154,"journal":{"name":"International Journal of Network Management","volume":"35 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2024-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/nem.2317","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142764090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spectrum Allocation in 5G and Beyond Intelligent Ubiquitous Networks","authors":"Banoth Ravi,&nbsp;Utkarsh Verma","doi":"10.1002/nem.2315","DOIUrl":"https://doi.org/10.1002/nem.2315","url":null,"abstract":"<div>\u0000 \u0000 <p>Effective spectrum allocation in 5G and beyond intelligent ubiquitous networks is vital for predicting future frequency band needs and ensuring optimal network performance. As wireless communication evolves from 4G to 5G and beyond, it has brought about remarkable advancements in speed and connectivity. However, with the growing demand for higher data rates and increased network capacity, new challenges in managing and utilizing network frequencies have emerged. Accurately forecasting spectrum requirements is critical to addressing these challenges. This research explores how machine learning (ML) plays a pivotal role in optimizing network performance through intelligent decision-making, predictive analysis, and adaptive management of network resources. By leveraging ML algorithms, networks can autonomously self-optimize in real time, adjusting to changing conditions and improving performance in 5G and beyond. The effectiveness of our approach was demonstrated through an extensive case study, which showed that it not only meets spectrum requirements in various environments but also significantly reduces energy consumption by pinpointing the appropriate spectrum range for each location. These results underscore the approach's potential for enhancing spectrum management in future networks, offering a scalable and efficient solution to the challenges facing 5G and beyond.</p>\u0000 </div>","PeriodicalId":14154,"journal":{"name":"International Journal of Network Management","volume":"35 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142758077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intent-Based Network Configuration Using Large Language Models","authors":"Nguyen Tu,&nbsp;Sukhyun Nam,&nbsp;James Won-Ki Hong","doi":"10.1002/nem.2313","DOIUrl":"https://doi.org/10.1002/nem.2313","url":null,"abstract":"<div>\u0000 \u0000 <p>The increasing scale and complexity of network infrastructure present a huge challenge for network operators and administrators in performing network configuration and management tasks. Intent-based networking has emerged as a solution to simplify the configuration and management of networks. However, one of the most difficult tasks of intent-based networking is correctly translating high-level natural language intents into low-level network configurations. In this paper, we propose a general and effective approach to perform the network intent translation task using large language models with fine-tuning, dynamic in-context learning, and continuous learning. Fine-tuning allows a pretrained large language model to perform better on a specific task. In-context learning enables large language models to learn from the examples provided along with the actual intent. Continuous learning allows the system to improve overtime with new user intents. To demonstrate the feasibility of our approach, we present and evaluate it with two use cases: network formal specification translation and network function virtualization configuration. Our evaluation shows that with the proposed approach, we can achieve high intent translation accuracy as well as fast processing times using small large language models that can run on a single consumer-grade GPU.</p>\u0000 </div>","PeriodicalId":14154,"journal":{"name":"International Journal of Network Management","volume":"35 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142707785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MSC: A Unique Chameleon Hash-Based Off-Chain Storage Framework for Metaverse Applications","authors":"Chenxi Xiong,&nbsp;Ting Yang,&nbsp;Gang Mao","doi":"10.1002/nem.2314","DOIUrl":"https://doi.org/10.1002/nem.2314","url":null,"abstract":"<p>Blockchain has evolved into a secure and trustworthy environment for decentralized applications, offering the advantages of tamper-resistant, while simultaneously introducing on-chain overhead issues. The development of metaverse related smart contracts on blockchain has given rise to a compelling research inquiry concerning the secure reduction of on-chain storage overhead. In this research, the Metaverse Off-chain Storage Framework based on Chameleon hash (MSC), a unique framework for decentralized system based on chameleon hash, supports code or stored data updates without changing on-chain data is presented. The index of decentralized applications' data is calculated using the Chameleon hash to ensure that the index remains unchanged during the data modification process. Simultaneously, data can be stored outside of the blockchain with proper authentication mechanisms in place. The experimental results have shown that MSC exhibits reduced on-chain storage requirements when compared to similar frameworks. Furthermore, MSC significantly reduced overhead as compared to the direct storage of data within a smart contract.</p>","PeriodicalId":14154,"journal":{"name":"International Journal of Network Management","volume":"35 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/nem.2314","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143114889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SentinelGuard Pro: Deploying Cutting-Edge FusionNet for Unerring Detection and Enforcement of Wrong Parking Incidents","authors":"Vankadhara Rajyalakshmi,&nbsp;Kuruva Lakshmanna","doi":"10.1002/nem.2310","DOIUrl":"https://doi.org/10.1002/nem.2310","url":null,"abstract":"<div>\u0000 \u0000 <p>Wrong parking incidents pose a pervasive challenge in urban environments, disrupting the smooth flow of traffic, compromising safety and contributing to various logistical issues. Unauthorized parking occurs when vehicles are parked in locations not designated for such purposes, leading to a myriad of problems for both authorities and the general public. This research introduces a pioneering approach to confront the persistent challenge of unauthorized parking incidents in urban environments. The study focuses on harnessing the advanced capabilities of the FusionNet model to enhance the accuracy of license plate detection. This paper introduces the YOLO v8 Model, a deep learning architecture designed to enhance urban parking management by accurately detecting vehicles parked in unauthorized slots. The objective is to enhance parking management efficiency by accurately detecting vehicles and their occupancy status in designated parking areas. The methodology begins with data collection and preprocessing of images of parking spaces, followed by the training of YOLO v8 to identify vehicles and parking spaces in real time. Leveraging a diverse dataset encompassing various parking scenarios, including instances of unauthorized parking, the model achieves an accuracy of 98.50% in identifying vehicles outside designated areas. This model segments characters from detected license plates, enabling the accurate extraction of alphanumeric information associated with each vehicle. The integrated system provides timely identification of parking violations and facilitates effective enforcement actions through captured license plate data. Results demonstrate the model's effectiveness in real-world scenarios, showcasing its potential for improving urban safety and efficiency. The implementation of FusionNet in the Python programming language, the proposed solution aims to streamline parking management, improve compliance with parking regulations and enhance overall urban mobility., with robust precision 96.17%, specificity 97.42% and sensitivity 96.19%, surpassing other MobileNet, CNN, ANN, DNN and EfficientNet models.</p>\u0000 </div>","PeriodicalId":14154,"journal":{"name":"International Journal of Network Management","volume":"35 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2024-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142724245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}