Pub Date : 2023-06-09DOI: 10.1109/LNET.2023.3284665
Yi Shi;Maice Costa;Tugba Erpek;Yalin E. Sagduyu
Reinforcement learning (RL) is applied for dynamic admission control and resource allocation in NextG radio access network slicing. When sharing the spectrum with an incumbent user (that dynamically occupies frequency-time blocks), communication and computational resources are allocated to slicing requests, each with priority (weight), throughput, latency, and computational requirements. RL maximizes the total weight of granted requests over time beyond myopic, greedy, random, and first come, first served solutions. As the state-action space grows, Deep Q-network effectively admits requests and allocates resources as a low-complexity solution that is robust to sensing errors in detecting the incumbent user activity.
{"title":"Deep Reinforcement Learning for NextG Radio Access Network Slicing With Spectrum Coexistence","authors":"Yi Shi;Maice Costa;Tugba Erpek;Yalin E. Sagduyu","doi":"10.1109/LNET.2023.3284665","DOIUrl":"https://doi.org/10.1109/LNET.2023.3284665","url":null,"abstract":"Reinforcement learning (RL) is applied for dynamic admission control and resource allocation in NextG radio access network slicing. When sharing the spectrum with an incumbent user (that dynamically occupies frequency-time blocks), communication and computational resources are allocated to slicing requests, each with priority (weight), throughput, latency, and computational requirements. RL maximizes the total weight of granted requests over time beyond myopic, greedy, random, and first come, first served solutions. As the state-action space grows, Deep Q-network effectively admits requests and allocates resources as a low-complexity solution that is robust to sensing errors in detecting the incumbent user activity.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"5 3","pages":"149-153"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49979548","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}
Pub Date : 2023-06-07DOI: 10.1109/LNET.2023.3283936
Turgay Pamuklu;Aisha Syed;W. Sean Kennedy;Melike Erol-Kantarci
Having unmanned aerial vehicles (UAVs) with edge computing capability hover over smart farmlands supports Internet of Things (IoT) devices with low processing capacity and power to accomplish their deadline-sensitive tasks efficiently and economically. In this letter, we propose a graph neural network-based reinforcement learning solution to optimize the task offloading from these IoT devices to the UAVs. We conduct evaluations to show that our approach reduces task deadline violations while also increasing the mission time of the UAVs by optimizing their battery usage. Moreover, the proposed solution has increased robustness to network topology changes and is able to adapt to extreme cases, such as the failure of a UAV.
{"title":"Heterogeneous GNN-RL-Based Task Offloading for UAV-Aided Smart Agriculture","authors":"Turgay Pamuklu;Aisha Syed;W. Sean Kennedy;Melike Erol-Kantarci","doi":"10.1109/LNET.2023.3283936","DOIUrl":"10.1109/LNET.2023.3283936","url":null,"abstract":"Having unmanned aerial vehicles (UAVs) with edge computing capability hover over smart farmlands supports Internet of Things (IoT) devices with low processing capacity and power to accomplish their deadline-sensitive tasks efficiently and economically. In this letter, we propose a graph neural network-based reinforcement learning solution to optimize the task offloading from these IoT devices to the UAVs. We conduct evaluations to show that our approach reduces task deadline violations while also increasing the mission time of the UAVs by optimizing their battery usage. Moreover, the proposed solution has increased robustness to network topology changes and is able to adapt to extreme cases, such as the failure of a UAV.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"5 4","pages":"213-217"},"PeriodicalIF":0.0,"publicationDate":"2023-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79710523","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}
Pub Date : 2023-04-25DOI: 10.1109/LNET.2023.3269818
Yanshi Sun;Zhiguo Ding
Recently, stochastic geometry has been applied to provide tractable performance analysis for low earth orbit (LEO) satellite networks. However, existing works mainly focus on analyzing the “coverage probability”, which provides limited information. To provide more insights, this letter provides a more fine grained analysis on LEO satellite networks modeled by a homogeneous Poisson point process (HPPP). Specifically, the distribution and moments of the conditional coverage probability given the point process are studied. The developed analytical results can provide characterizations on LEO satellite networks, which are not available in existing literature, such as “user fairness” and “what fraction of users can achieve a given transmission reliability”. Simulation results are provided to verify the developed analysis. Numerical results show that, in a dense satellite network, it is beneficial to deploy satellites at low altitude, for the sake of both coverage probability and user fairness.
{"title":"A Fine Grained Stochastic Geometry-Based Analysis on LEO Satellite Communication Systems","authors":"Yanshi Sun;Zhiguo Ding","doi":"10.1109/LNET.2023.3269818","DOIUrl":"10.1109/LNET.2023.3269818","url":null,"abstract":"Recently, stochastic geometry has been applied to provide tractable performance analysis for low earth orbit (LEO) satellite networks. However, existing works mainly focus on analyzing the “coverage probability”, which provides limited information. To provide more insights, this letter provides a more fine grained analysis on LEO satellite networks modeled by a homogeneous Poisson point process (HPPP). Specifically, the distribution and moments of the conditional coverage probability given the point process are studied. The developed analytical results can provide characterizations on LEO satellite networks, which are not available in existing literature, such as “user fairness” and “what fraction of users can achieve a given transmission reliability”. Simulation results are provided to verify the developed analysis. Numerical results show that, in a dense satellite network, it is beneficial to deploy satellites at low altitude, for the sake of both coverage probability and user fairness.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"5 4","pages":"237-240"},"PeriodicalIF":0.0,"publicationDate":"2023-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80430930","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}
Pub Date : 2023-04-25DOI: 10.1109/LNET.2023.3269766
Yihang Tao;Jun Wu;Xi Lin;Wu Yang
Digital twin networks (DTN) simulate and predict 6G network behaviors to support innovative 6G services. However, emerging 6G service requests are rapidly growing with dynamic digital twin resource demands, which brings challenges for digital twin resources management with quality of service (QoS) optimization. We propose a novel software-defined DTN architecture with digital twin function virtualization (DTFV) for adaptive 6G service response. Besides, we propose a proximal policy optimization deep reinforcement learning (PPO-DRL) based DTFV resource orchestration algorithm on realizing massive service response quality optimization. Experimental results show that the proposed solution outperforms heuristic digital twin resource management methods.
{"title":"DRL-Driven Digital Twin Function Virtualization for Adaptive Service Response in 6G Networks","authors":"Yihang Tao;Jun Wu;Xi Lin;Wu Yang","doi":"10.1109/LNET.2023.3269766","DOIUrl":"https://doi.org/10.1109/LNET.2023.3269766","url":null,"abstract":"Digital twin networks (DTN) simulate and predict 6G network behaviors to support innovative 6G services. However, emerging 6G service requests are rapidly growing with dynamic digital twin resource demands, which brings challenges for digital twin resources management with quality of service (QoS) optimization. We propose a novel software-defined DTN architecture with digital twin function virtualization (DTFV) for adaptive 6G service response. Besides, we propose a proximal policy optimization deep reinforcement learning (PPO-DRL) based DTFV resource orchestration algorithm on realizing massive service response quality optimization. Experimental results show that the proposed solution outperforms heuristic digital twin resource management methods.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"5 2","pages":"125-129"},"PeriodicalIF":0.0,"publicationDate":"2023-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49978599","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}
Pub Date : 2023-04-21DOI: 10.1109/LNET.2023.3269054
Zhuoyue Chen;Kechao Cai;Jinbei Zhang;Xiangwei Zhu
The current version of QUIC (Quick UDP Internet Connection) does not allow for prioritized bandwidth allocation of multiple streams. In this letter, we propose a novel framework, Performance-oriented Congestion Control Priority (PCC Priority), to support priority-aware bandwidth allocation of QUIC streams. Our framework incorporates stream priorities into the utility function of PCC to allocate bandwidth proportionally according to the stream priorities. We also provide an equilibrium analysis of PCC Priority and prove that it can allocate bandwidth proportionally based on stream priorities. Our ns-3 simulation results show that PCC Priority outperforms the state-of-the-art protocols in adhering to the priority settings of streams in QUIC. In particular, PCC Priority allocates bandwidth to streams at a ratio that is close to the ratio of their priorities and maintains competitive high throughput, low latency, and high loss tolerance.
{"title":"PCC Priority: A Priority-Aware Bandwidth Allocation Framework for QUIC","authors":"Zhuoyue Chen;Kechao Cai;Jinbei Zhang;Xiangwei Zhu","doi":"10.1109/LNET.2023.3269054","DOIUrl":"10.1109/LNET.2023.3269054","url":null,"abstract":"The current version of QUIC (Quick UDP Internet Connection) does not allow for prioritized bandwidth allocation of multiple streams. In this letter, we propose a novel framework, Performance-oriented Congestion Control Priority (PCC Priority), to support priority-aware bandwidth allocation of QUIC streams. Our framework incorporates stream priorities into the utility function of PCC to allocate bandwidth proportionally according to the stream priorities. We also provide an equilibrium analysis of PCC Priority and prove that it can allocate bandwidth proportionally based on stream priorities. Our ns-3 simulation results show that PCC Priority outperforms the state-of-the-art protocols in adhering to the priority settings of streams in QUIC. In particular, PCC Priority allocates bandwidth to streams at a ratio that is close to the ratio of their priorities and maintains competitive high throughput, low latency, and high loss tolerance.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"5 4","pages":"279-283"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76513554","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}
Ultra-reliability and low-latency are pivotal requirements of the emerging 6th generation of communication systems (xURLLC). The transition in millimeter-wave (mmWave) technology, from omni-directional to highly directional antennas, has been seen as an enabler for high bandwidth communications, still susceptible to high loss and high latency variation. Classical error recovery approaches cannot close the rising gap between high throughput and low delay in such systems. In this letter, we incorporate effective sliding window network coding solutions in mmWave communications. While legacy systems such as rateless codes improve the delay, cross-layer results show that they do not provide Low Latency Communications (LLC), due to the lossy behaviour of mmWave channel and the lower-layers’ retransmission mechanisms. On the other hand, fixed sliding window random linear network coding (RLNC) is able to achieve LLC, and even better, adaptive sliding window RLNC obtains Ultra-Reliable LLC (URLLC) in mmWave backhaul networks.
{"title":"Sliding Window Network Coding Enables NeXt Generation URLLC Millimeter-Wave Networks","authors":"Eurico Dias;Duarte Raposo;Homa Esfahanizadeh;Alejandro Cohen;Tânia Ferreira;Miguel Luís;Susana Sargento;Muriel Médard","doi":"10.1109/LNET.2023.3269387","DOIUrl":"https://doi.org/10.1109/LNET.2023.3269387","url":null,"abstract":"Ultra-reliability and low-latency are pivotal requirements of the emerging 6th generation of communication systems (xURLLC). The transition in millimeter-wave (mmWave) technology, from omni-directional to highly directional antennas, has been seen as an enabler for high bandwidth communications, still susceptible to high loss and high latency variation. Classical error recovery approaches cannot close the rising gap between high throughput and low delay in such systems. In this letter, we incorporate effective sliding window network coding solutions in mmWave communications. While legacy systems such as rateless codes improve the delay, cross-layer results show that they do not provide Low Latency Communications (LLC), due to the lossy behaviour of mmWave channel and the lower-layers’ retransmission mechanisms. On the other hand, fixed sliding window random linear network coding (RLNC) is able to achieve LLC, and even better, adaptive sliding window RLNC obtains Ultra-Reliable LLC (URLLC) in mmWave backhaul networks.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"5 3","pages":"159-163"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49979550","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}
Pub Date : 2023-04-20DOI: 10.1109/LNET.2023.3268648
Pedro Enrique Iturria-Rivera;Marcel Chenier;Bernard Herscovici;Burak Kantarci;Melike Erol-Kantarci
IEEE 802.11ax introduces several amendments to previous standards with a special interest in spatial reuse (SR) to respond to dense user scenarios with high demanding services. In dynamic scenarios with more than one Access Point, the adjustment of joint Transmission Power (TP) and Clear Channel Assessment (CCA) threshold remains a challenge. With the aim of mitigating Quality of Service (QoS) degradation, we introduce a solution that builds on meta-learning and multi-arm bandits. Simulation results show that the proposed solution can adapt with an average of 1250 fewer environment steps and 72% average improvement in terms of fairness and starvation than a transfer learning baseline.
{"title":"Meta-Bandit: Spatial Reuse Adaptation via Meta-Learning in Distributed Wi-Fi 802.11ax","authors":"Pedro Enrique Iturria-Rivera;Marcel Chenier;Bernard Herscovici;Burak Kantarci;Melike Erol-Kantarci","doi":"10.1109/LNET.2023.3268648","DOIUrl":"10.1109/LNET.2023.3268648","url":null,"abstract":"IEEE 802.11ax introduces several amendments to previous standards with a special interest in spatial reuse (SR) to respond to dense user scenarios with high demanding services. In dynamic scenarios with more than one Access Point, the adjustment of joint Transmission Power (TP) and Clear Channel Assessment (CCA) threshold remains a challenge. With the aim of mitigating Quality of Service (QoS) degradation, we introduce a solution that builds on meta-learning and multi-arm bandits. Simulation results show that the proposed solution can adapt with an average of 1250 fewer environment steps and 72% average improvement in terms of fairness and starvation than a transfer learning baseline.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"5 4","pages":"179-183"},"PeriodicalIF":0.0,"publicationDate":"2023-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10105943","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79033937","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}
Pub Date : 2023-04-14DOI: 10.1109/LNET.2023.3267122
Haruto Taka;Takeru Inoue;Eiji Oki
A Clos network is well known as a switching network structure that can achieve a strict-sense non-blocking condition. However, the non-blocking condition is too restrictive to increase the switching capacity of Clos network under the constraint of the limited number of switches. This letter proposes a Clos network design model that guarantees an admissible blocking probability to increase the switching capacity. The proposed design model achieves a larger switching capacity in a practical time than the conventional design model that satisfies the strict-sense non-blocking condition, while guaranteeing an admissible blocking probability.
{"title":"Design of Twisted and Folded-Clos Network With Guaranteeing Admissible Blocking Probability","authors":"Haruto Taka;Takeru Inoue;Eiji Oki","doi":"10.1109/LNET.2023.3267122","DOIUrl":"10.1109/LNET.2023.3267122","url":null,"abstract":"A Clos network is well known as a switching network structure that can achieve a strict-sense non-blocking condition. However, the non-blocking condition is too restrictive to increase the switching capacity of Clos network under the constraint of the limited number of switches. This letter proposes a Clos network design model that guarantees an admissible blocking probability to increase the switching capacity. The proposed design model achieves a larger switching capacity in a practical time than the conventional design model that satisfies the strict-sense non-blocking condition, while guaranteeing an admissible blocking probability.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"5 4","pages":"265-269"},"PeriodicalIF":0.0,"publicationDate":"2023-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88769133","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}
Pub Date : 2023-04-13DOI: 10.1109/LNET.2023.3266863
Paul Schwenteck;Giang T. Nguyen;Holger Boche;Wolfgang Kellerer;Frank H. P. Fitzek
The first release of 5G technology is being rolled out worldwide. In parallel, 3GPP is constantly adding new features to upcoming releases covering well-known use cases. This raises the questions i) when will 6G be introduced?, ii) how can 6G be motivated for the stakeholders, and iii) what are the 6G use cases? In this letter, we present the perspective of these stakeholders, namely the network operators, manufacturers, and verticals, identifying potential 5G shortcomings and the remaining 6G solution space. We will highlight the Metaverse as the enabler for 6G addressing omnipresent daily challenges and the upcoming energy problem.
{"title":"6G Perspective of Mobile Network Operators, Manufacturers, and Verticals","authors":"Paul Schwenteck;Giang T. Nguyen;Holger Boche;Wolfgang Kellerer;Frank H. P. Fitzek","doi":"10.1109/LNET.2023.3266863","DOIUrl":"https://doi.org/10.1109/LNET.2023.3266863","url":null,"abstract":"The first release of 5G technology is being rolled out worldwide. In parallel, 3GPP is constantly adding new features to upcoming releases covering well-known use cases. This raises the questions i) when will 6G be introduced?, ii) how can 6G be motivated for the stakeholders, and iii) what are the 6G use cases? In this letter, we present the perspective of these stakeholders, namely the network operators, manufacturers, and verticals, identifying potential 5G shortcomings and the remaining 6G solution space. We will highlight the Metaverse as the enabler for 6G addressing omnipresent daily challenges and the upcoming energy problem.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"5 3","pages":"169-172"},"PeriodicalIF":0.0,"publicationDate":"2023-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/8253410/10261392/10102280.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49979552","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}
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：