Pub Date : 2024-08-06DOI: 10.1109/TNSM.2024.3439472
Bong-Hwan Oh
The advent of Programming Protocol-independent Packet Processors (P4) enables the programmability of data planes, which provides not only further flexibility but also the possibility of the emergence of new features. With programmable data planes, network monitoring functionalities can be evolved beyond the conventional mechanism of Software-Defined Networks (SDN) which is polling-based monitoring based on OpenFlow. Although the polling-based method is easy and simple to collect monitoring information, it can cause substantial monitoring overhead on both the controller side and the switch side. Unlike the OpenFlow-based SDN which has one option to collect pre-defined information using the polling-based method, monitoring performance can be improved by applying new monitoring approaches based on P4. In this paper, a novel mechanism referred to as P4-based Proactive Monitoring (PPM) is proposed in order to enhance the efficiency of monitoring collection operations. PPM scheme adopts a proactive approach which allows programmable switches to proactively forward monitoring information to the controller after the controller enables PPM. The measurement results show that PPM can not only enhance the efficiency of collecting monitoring information by applying a proactive mechanism but also minimize the general monitoring overhead compared to the polling-based method.
{"title":"P4-Based Proactive Monitoring Scheme in Software-Defined Networks","authors":"Bong-Hwan Oh","doi":"10.1109/TNSM.2024.3439472","DOIUrl":"10.1109/TNSM.2024.3439472","url":null,"abstract":"The advent of Programming Protocol-independent Packet Processors (P4) enables the programmability of data planes, which provides not only further flexibility but also the possibility of the emergence of new features. With programmable data planes, network monitoring functionalities can be evolved beyond the conventional mechanism of Software-Defined Networks (SDN) which is polling-based monitoring based on OpenFlow. Although the polling-based method is easy and simple to collect monitoring information, it can cause substantial monitoring overhead on both the controller side and the switch side. Unlike the OpenFlow-based SDN which has one option to collect pre-defined information using the polling-based method, monitoring performance can be improved by applying new monitoring approaches based on P4. In this paper, a novel mechanism referred to as P4-based Proactive Monitoring (PPM) is proposed in order to enhance the efficiency of monitoring collection operations. PPM scheme adopts a proactive approach which allows programmable switches to proactively forward monitoring information to the controller after the controller enables PPM. The measurement results show that PPM can not only enhance the efficiency of collecting monitoring information by applying a proactive mechanism but also minimize the general monitoring overhead compared to the polling-based method.","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"21 5","pages":"5781-5794"},"PeriodicalIF":4.7,"publicationDate":"2024-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141969888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-06DOI: 10.1109/tnsm.2024.3438828
Kaustabha Ray
{"title":"Context-Aware Fault Classification for Multi-Access Edge Computing","authors":"Kaustabha Ray","doi":"10.1109/tnsm.2024.3438828","DOIUrl":"https://doi.org/10.1109/tnsm.2024.3438828","url":null,"abstract":"","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"24 1","pages":""},"PeriodicalIF":5.3,"publicationDate":"2024-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141946472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"5G Service Function Chain Provisioning: A Deep Reinforcement Learning-Based Framework","authors":"Thinh Duy Tran, Brigitte Jaumard, Quang Huy Duong, Kim-Khoa Nguyen","doi":"10.1109/tnsm.2024.3438438","DOIUrl":"https://doi.org/10.1109/tnsm.2024.3438438","url":null,"abstract":"","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"9 1","pages":""},"PeriodicalIF":5.3,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141946473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-02DOI: 10.1109/tnsm.2024.3436677
Katalin Hajdú-Szücs, Péter Vaderna, Zsófia Kallus, Péter Kersch, János Márk Szalai-Gindl, Sándor Laki
{"title":"Ensemble Graph Attention Networks for Cellular Network Analytics: From Model Creation to Explainability","authors":"Katalin Hajdú-Szücs, Péter Vaderna, Zsófia Kallus, Péter Kersch, János Márk Szalai-Gindl, Sándor Laki","doi":"10.1109/tnsm.2024.3436677","DOIUrl":"https://doi.org/10.1109/tnsm.2024.3436677","url":null,"abstract":"","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"215 1","pages":""},"PeriodicalIF":5.3,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141880634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-02DOI: 10.1109/TNSM.2024.3436942
Shunwai Zhang;Lulu Song;Rongfang Song
We consider a robust energy-efficient reconfigurable intelligent surface (RIS)-aided multi-antenna decode-and-forward (DF) relay cooperative multiple-input multiple-output (MIMO). Although RIS and relay share some similarities in common, they have fundamental differences and can indeed complement each other. Due to the passive characteristic of RIS, it is much challenging to obtain the perfect channel state information (CSI) and the channel estimation error (CEE) is inevitable in practice. Taking into account the imperfect CSI, we formulate the robust energy efficiency (EE) optimization problems under the bounded CEE and statistical CEE models, where the precoding matrices at the source and relay, and the passive beamforming at the RIS in two slots are jointly designed. At first, the original problems under two CEE models are transformed into deterministic forms with the help of S-procedure and Bernstein-type Inequality, respectively. Subsequently, the reformulated problems are solved by the alternating optimization (AO)-based Dinkelbach algorithm in an iterative manner. Particularly, for the passive beamforming subproblem, the semi-definite relaxation (SDR) method and penalty concave-convex procedure (PCCP) method are utilized to deal with the rank-one constraint. Numerical simulations demonstrate that the EE performance of the considered scheme obviously outperforms the benchmarks. Simulation results also show the superiorities of the robust EE optimization compared with the non-robust optimization.
我们考虑的是一种稳健的高能效可重构智能表面（RIS）辅助多天线解码前向（DF）中继合作多输入多输出（MIMO）。尽管可重构智能表面和中继有一些共同之处，但它们也有本质区别，而且确实可以相互补充。由于 RIS 的被动特性，要获得完美的信道状态信息（CSI）非常困难，信道估计误差（CEE）在实际应用中不可避免。考虑到不完美的 CSI，我们提出了有界 CEE 模型和统计 CEE 模型下的鲁棒能效（EE）优化问题，其中源端和中继端的预编码矩阵以及两个时隙内 RIS 的无源波束成形是共同设计的。首先，借助 S 过程和伯恩斯坦式不等式，分别将两种 CEE 模型下的原始问题转化为确定性问题。随后，采用基于交替优化（AO）的丁克尔巴赫算法，以迭代的方式解决重新表述的问题。特别是在无源波束成形子问题中，采用了半有限松弛（SDR）方法和惩罚凹凸过程（PCCP）方法来处理秩一约束。数值模拟表明，所考虑方案的 EE 性能明显优于基准方案。仿真结果还显示了鲁棒 EE 优化与非鲁棒优化相比的优越性。
{"title":"Robust Energy-Efficient RIS-Aided Multi-Antenna DF Relay Cooperative MIMO","authors":"Shunwai Zhang;Lulu Song;Rongfang Song","doi":"10.1109/TNSM.2024.3436942","DOIUrl":"10.1109/TNSM.2024.3436942","url":null,"abstract":"We consider a robust energy-efficient reconfigurable intelligent surface (RIS)-aided multi-antenna decode-and-forward (DF) relay cooperative multiple-input multiple-output (MIMO). Although RIS and relay share some similarities in common, they have fundamental differences and can indeed complement each other. Due to the passive characteristic of RIS, it is much challenging to obtain the perfect channel state information (CSI) and the channel estimation error (CEE) is inevitable in practice. Taking into account the imperfect CSI, we formulate the robust energy efficiency (EE) optimization problems under the bounded CEE and statistical CEE models, where the precoding matrices at the source and relay, and the passive beamforming at the RIS in two slots are jointly designed. At first, the original problems under two CEE models are transformed into deterministic forms with the help of S-procedure and Bernstein-type Inequality, respectively. Subsequently, the reformulated problems are solved by the alternating optimization (AO)-based Dinkelbach algorithm in an iterative manner. Particularly, for the passive beamforming subproblem, the semi-definite relaxation (SDR) method and penalty concave-convex procedure (PCCP) method are utilized to deal with the rank-one constraint. Numerical simulations demonstrate that the EE performance of the considered scheme obviously outperforms the benchmarks. Simulation results also show the superiorities of the robust EE optimization compared with the non-robust optimization.","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"21 5","pages":"5063-5075"},"PeriodicalIF":4.7,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141880561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-01DOI: 10.1109/tnsm.2024.3436887
Yuhan Su, Yuchen Lin, Sicong Liu, Minghui Liwang, Xinqin Liao, Tingzhu Wu, Zhong Chen, Xianbin Wang
{"title":"Coexistence of Hybrid VLC-RF and Wi-Fi for Indoor Wireless Communication Systems: An Intelligent Approach","authors":"Yuhan Su, Yuchen Lin, Sicong Liu, Minghui Liwang, Xinqin Liao, Tingzhu Wu, Zhong Chen, Xianbin Wang","doi":"10.1109/tnsm.2024.3436887","DOIUrl":"https://doi.org/10.1109/tnsm.2024.3436887","url":null,"abstract":"","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"1 1","pages":""},"PeriodicalIF":5.3,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141887054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-01DOI: 10.1109/TNSM.2024.3437217
Mahdieh Ahmadi;Arash Moayyedi;Muhammad Sulaiman;Mohammad A. Salahuddin;Raouf Boutaba;Aladdin Saleh
The virtualization and distribution of 5G Radio Access Network (RAN) functions across radio unit (RU), distributed unit (DU), and centralized unit (CU) in conjunction with multi-access edge computing (MEC) enable the creation of network slices tailored for various applications with distinct quality of service (QoS) demands. Nonetheless, given the dynamic nature of slice requests and limited network resources, optimizing long-term revenue for infrastructure providers (InPs) through real-time admission and embedding of slice requests poses a significant challenge. Prior works have employed Deep Reinforcement Learning (DRL) to address this issue, but these approaches require re-training with the slightest topology changes due to node/link failure or overlook the joint consideration of slice admission and embedding problems. This paper proposes a novel method, utilizing multi-agent DRL and Graph Attention Networks (GATs), to overcome these limitations. Specifically, we develop topology-independent admission and slicing agents that are scalable and generalizable across diverse metropolitan networks. Results demonstrate substantial revenue gains-up to 35.2% compared to heuristics and 19.5% when compared to other DRL-based methods. Moreover, our approach showcases robust performance in different network failure scenarios and substrate networks not seen during training without the need for re-training or re-tuning. Additionally, we bring interpretability by analyzing attention maps, which enables InPs to identify network bottlenecks, increase capacity at critical nodes, and gain a clear understanding of the model decision-making process.
{"title":"Generalizable 5G RAN/MEC Slicing and Admission Control for Reliable Network Operation","authors":"Mahdieh Ahmadi;Arash Moayyedi;Muhammad Sulaiman;Mohammad A. Salahuddin;Raouf Boutaba;Aladdin Saleh","doi":"10.1109/TNSM.2024.3437217","DOIUrl":"10.1109/TNSM.2024.3437217","url":null,"abstract":"The virtualization and distribution of 5G Radio Access Network (RAN) functions across radio unit (RU), distributed unit (DU), and centralized unit (CU) in conjunction with multi-access edge computing (MEC) enable the creation of network slices tailored for various applications with distinct quality of service (QoS) demands. Nonetheless, given the dynamic nature of slice requests and limited network resources, optimizing long-term revenue for infrastructure providers (InPs) through real-time admission and embedding of slice requests poses a significant challenge. Prior works have employed Deep Reinforcement Learning (DRL) to address this issue, but these approaches require re-training with the slightest topology changes due to node/link failure or overlook the joint consideration of slice admission and embedding problems. This paper proposes a novel method, utilizing multi-agent DRL and Graph Attention Networks (GATs), to overcome these limitations. Specifically, we develop topology-independent admission and slicing agents that are scalable and generalizable across diverse metropolitan networks. Results demonstrate substantial revenue gains-up to 35.2% compared to heuristics and 19.5% when compared to other DRL-based methods. Moreover, our approach showcases robust performance in different network failure scenarios and substrate networks not seen during training without the need for re-training or re-tuning. Additionally, we bring interpretability by analyzing attention maps, which enables InPs to identify network bottlenecks, increase capacity at critical nodes, and gain a clear understanding of the model decision-making process.","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"21 5","pages":"5384-5399"},"PeriodicalIF":4.7,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141880559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-01DOI: 10.1109/TNSM.2024.3436674
Md. Masuduzzaman;Tariq Rahim;Anik Islam;Soo Young Shin
This study proposes an intelligent approach to identifying an injured soldier on blockchain-integrated Internet-of-Battlefield Things (IoBT) employing unmanned aerial vehicles (UAVs). The intelligent approach combines a unique deep learning (DL) model with a smartwatch-based heart-rate (HR) data collection technique. Different activation functions (i.e., MISH and Leaky rectified linear unit) are used in the proposed DL model to enhance the identification task by extracting the in-depth features from the images. Furthermore, a smart-watch-based HR data analyzing technique is introduced to confirm the injury of a soldier. However, due to the UAV’s low battery capacity, the identification task is offloaded to the neighboring edge computing server to improve system performance. Moreover, to restrict the access of registered IoT devices (e.g., UAV, smartwatch, etc.) and protect the sensitive data leakage on IoBT, a blockchain-integrated access control (ACL) mechanism is utilized. Detailed experimental results are provided for the proposed DL model that outperforms existing DL models. Besides, implementing a smartwatch-based HR data analysis technique for the soldiers improves the outcome of the proposed DL model. To provide a fine-grained data protection mechanism in the proposed system, a private blockchain-based ACL management policy is constructed utilizing hyperledger, and various assessment metrics have been scrutinized.
{"title":"UAV-Employed Intelligent Approach to Identify Injured Soldier on Blockchain-Integrated Internet of Battlefield Things","authors":"Md. Masuduzzaman;Tariq Rahim;Anik Islam;Soo Young Shin","doi":"10.1109/TNSM.2024.3436674","DOIUrl":"10.1109/TNSM.2024.3436674","url":null,"abstract":"This study proposes an intelligent approach to identifying an injured soldier on blockchain-integrated Internet-of-Battlefield Things (IoBT) employing unmanned aerial vehicles (UAVs). The intelligent approach combines a unique deep learning (DL) model with a smartwatch-based heart-rate (HR) data collection technique. Different activation functions (i.e., MISH and Leaky rectified linear unit) are used in the proposed DL model to enhance the identification task by extracting the in-depth features from the images. Furthermore, a smart-watch-based HR data analyzing technique is introduced to confirm the injury of a soldier. However, due to the UAV’s low battery capacity, the identification task is offloaded to the neighboring edge computing server to improve system performance. Moreover, to restrict the access of registered IoT devices (e.g., UAV, smartwatch, etc.) and protect the sensitive data leakage on IoBT, a blockchain-integrated access control (ACL) mechanism is utilized. Detailed experimental results are provided for the proposed DL model that outperforms existing DL models. Besides, implementing a smartwatch-based HR data analysis technique for the soldiers improves the outcome of the proposed DL model. To provide a fine-grained data protection mechanism in the proposed system, a private blockchain-based ACL management policy is constructed utilizing hyperledger, and various assessment metrics have been scrutinized.","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"21 5","pages":"5197-5214"},"PeriodicalIF":4.7,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141880635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-01DOI: 10.1109/tnsm.2024.3437165
Bita Fatemipour, Zhe Zhang, Marc St-Hilaire
{"title":"A Survey on Replica Transfer Optimization Schemes in Geographically Distributed Data Centers","authors":"Bita Fatemipour, Zhe Zhang, Marc St-Hilaire","doi":"10.1109/tnsm.2024.3437165","DOIUrl":"https://doi.org/10.1109/tnsm.2024.3437165","url":null,"abstract":"","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"79 1","pages":""},"PeriodicalIF":5.3,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141880636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-01DOI: 10.1109/tnsm.2024.3435516
Pin-Hsuan Chiang, Shi-Chun Tsai
{"title":"Detection of Malicious Domains With Concept Drift Using Ensemble Learning","authors":"Pin-Hsuan Chiang, Shi-Chun Tsai","doi":"10.1109/tnsm.2024.3435516","DOIUrl":"https://doi.org/10.1109/tnsm.2024.3435516","url":null,"abstract":"","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"373 1","pages":""},"PeriodicalIF":5.3,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141880637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：