Industrial Time-Sensitive Networking (TSN) provides deterministic mechanisms for real-time and reliable flow transmission. Increasing attention has been paid to efficient scheduling for time-sensitive flows with stringent requirements such as ultra-low latency and jitter. In TSN, the fine-grained traffic shaping protocol, cyclic queuing and forwarding (CQF), eliminates uncertain delay and frame loss via traffic timing in and out of queues. However, it inevitably causes high scheduling complexity. Moreover, complexity is quite sensitive to flow attributes and network scale. The problem stems in part from the lack of an attribute mining mechanism in existing frame-based scheduling. For time-critical industrial networks with large-scale complex flows, a so-called hyper-flow graph based scheduling scheme is proposed to improve the scheduling scalability in terms of schedulability, scheduling efficiency and latency & jitter. The hyper-flow graph is built by aggregating similar flow sets as hyper-flow nodes and designing a hierarchical scheduling framework. The flow attribute-sensitive scheduling information is embedded into the condensed maximal cliques, and reverse maps them precisely to congestion flow portions for re-scheduling. Its parallel scheduling reduces network scale induced complexity. Further, this scheme is designed in its entirety as a comprehensive scheduling algorithm GH2. It improves the three criteria of scalability along a Pareto front. Extensive simulation studies demonstrate its superiority. Notably, GH2 is verified its scheduling stability with a runtime of less than 100 ms for 1000 flows and near 1/190 of the SOTA FITS method for 3000 flows.
{"title":"Scalable Scheduling for Industrial Time-Sensitive Networking: A Hyper-Flow Graph-Based Scheme","authors":"Yanzhou Zhang;Cailian Chen;Qimin Xu;Shouliang Wang;Lei Xu;Xinping Guan","doi":"10.1109/TNET.2024.3433599","DOIUrl":"10.1109/TNET.2024.3433599","url":null,"abstract":"Industrial Time-Sensitive Networking (TSN) provides deterministic mechanisms for real-time and reliable flow transmission. Increasing attention has been paid to efficient scheduling for time-sensitive flows with stringent requirements such as ultra-low latency and jitter. In TSN, the fine-grained traffic shaping protocol, cyclic queuing and forwarding (CQF), eliminates uncertain delay and frame loss via traffic timing in and out of queues. However, it inevitably causes high scheduling complexity. Moreover, complexity is quite sensitive to flow attributes and network scale. The problem stems in part from the lack of an attribute mining mechanism in existing frame-based scheduling. For time-critical industrial networks with large-scale complex flows, a so-called hyper-flow graph based scheduling scheme is proposed to improve the scheduling scalability in terms of schedulability, scheduling efficiency and latency & jitter. The hyper-flow graph is built by aggregating similar flow sets as hyper-flow nodes and designing a hierarchical scheduling framework. The flow attribute-sensitive scheduling information is embedded into the condensed maximal cliques, and reverse maps them precisely to congestion flow portions for re-scheduling. Its parallel scheduling reduces network scale induced complexity. Further, this scheme is designed in its entirety as a comprehensive scheduling algorithm GH2. It improves the three criteria of scalability along a Pareto front. Extensive simulation studies demonstrate its superiority. Notably, GH2 is verified its scheduling stability with a runtime of less than 100 ms for 1000 flows and near 1/190 of the SOTA FITS method for 3000 flows.","PeriodicalId":13443,"journal":{"name":"IEEE/ACM Transactions on Networking","volume":"32 6","pages":"4810-4825"},"PeriodicalIF":3.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141881003","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2024-07-30DOI: 10.1109/TNET.2024.3422089
Jinlei Lin;Chenglong Li;Wenwen Gong;Guanglei Song;Linna Fan;Zhiliang Wang;Jiahai Yang
IP geolocation is essential for various location-aware Internet applications. High-quality IP geolocation landmarks play a decisive role in IP geolocation accuracy. However, the previous research works focusing on mining landmarks from the Internet are hampered by limited quantity, poor coverage, and insufficient landmark quality. In this paper, we present a new framework called ProbeGeo to mine high-quality landmarks automatically. We divide landmarks into common landmarks and probe landmarks, providing systematic mining methods based on online retrieval and web content. ProbeGeo expands traditional common landmarks by taking advantage of the exposure of multiple IoT (Internet of Things) devices on the Internet, mining them based on search engines and webpage contents. Common landmarks, consisting of multi-type devices, significantly improve landmark quantity and coverage. Furthermore, ProbeGeo establishes a methodology for acquiring new probe landmarks from Internet VPs (Vantage Points) webpages, extracting geographical locations from heterogeneous webpages and utilizing active probe functions. Probe landmarks enhance landmark quality and functions, bringing new geolocation frameworks and breaking through the geolocation accuracy bottleneck. We develop the ProbeGeo as a continuously running system and conduct real-world experiments to validate its efficacy. Our results show that ProbeGeo can detect 89,849 high-quality landmarks, including 6,874 probe landmarks and 82,975 common landmarks. ProbeGeo landmarks are about 10x more than existing work, distributed in 181 countries and 7,094 cities. ProbeGeo landmarks cover more than 8 types of devices, and more than 60% of them remain stable over one month. Moreover, the landmark accuracy of more than 58% of ProbeGeo landmarks is above street level, which has not been achieved in previous works. ProbeGeo can provide geolocation services with higher landmark accuracy and broader coverage by correlating a large scale of landmarks.
{"title":"ProbeGeo: A Comprehensive Landmark Mining Framework Based on Web Content","authors":"Jinlei Lin;Chenglong Li;Wenwen Gong;Guanglei Song;Linna Fan;Zhiliang Wang;Jiahai Yang","doi":"10.1109/TNET.2024.3422089","DOIUrl":"10.1109/TNET.2024.3422089","url":null,"abstract":"IP geolocation is essential for various location-aware Internet applications. High-quality IP geolocation landmarks play a decisive role in IP geolocation accuracy. However, the previous research works focusing on mining landmarks from the Internet are hampered by limited quantity, poor coverage, and insufficient landmark quality. In this paper, we present a new framework called ProbeGeo to mine high-quality landmarks automatically. We divide landmarks into common landmarks and probe landmarks, providing systematic mining methods based on online retrieval and web content. ProbeGeo expands traditional common landmarks by taking advantage of the exposure of multiple IoT (Internet of Things) devices on the Internet, mining them based on search engines and webpage contents. Common landmarks, consisting of multi-type devices, significantly improve landmark quantity and coverage. Furthermore, ProbeGeo establishes a methodology for acquiring new probe landmarks from Internet VPs (Vantage Points) webpages, extracting geographical locations from heterogeneous webpages and utilizing active probe functions. Probe landmarks enhance landmark quality and functions, bringing new geolocation frameworks and breaking through the geolocation accuracy bottleneck. We develop the ProbeGeo as a continuously running system and conduct real-world experiments to validate its efficacy. Our results show that ProbeGeo can detect 89,849 high-quality landmarks, including 6,874 probe landmarks and 82,975 common landmarks. ProbeGeo landmarks are about 10x more than existing work, distributed in 181 countries and 7,094 cities. ProbeGeo landmarks cover more than 8 types of devices, and more than 60% of them remain stable over one month. Moreover, the landmark accuracy of more than 58% of ProbeGeo landmarks is above street level, which has not been achieved in previous works. ProbeGeo can provide geolocation services with higher landmark accuracy and broader coverage by correlating a large scale of landmarks.","PeriodicalId":13443,"journal":{"name":"IEEE/ACM Transactions on Networking","volume":"32 5","pages":"4398-4413"},"PeriodicalIF":3.0,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141862856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper investigates the $(k,k)$ fork-join scheduling scheme on a system of n parallel servers comprising both slow and fast servers. Tasks arriving in the system are divided into k sub-tasks and assigned to a random set of k servers, where each task can be assigned independently to a distinct slow or fast server with selection probability $p_{s}$ or $1-p_{s}$ , respectively. Our analysis demonstrates that the joint distribution of the stationary workload across any set of k queues becomes asymptotically independent as the number of servers n grows, with k scaling as $oleft ({{n^{frac {1}{4}}}}right)$ . Under asymptotic independence, the limiting mean task completion time can be expressed as an integral. However, it is analytically challenging to compute the optimal selection probability $p_{s}^{ast } $ that minimizes this integral. To address this, we provide an upper bound on the limiting mean task completion time and identify the selection probability $hat {p}_{s}$ that minimizes this bound. We validate that this selection probability $hat {p}_{s}$ yields a near-optimal performance through numerical experiments.
{"title":"Analysis of Fork-Join Scheduling on Heterogeneous Parallel Servers","authors":"Moonmoon Mohanty;Gaurav Gautam;Vaneet Aggarwal;Parimal Parag","doi":"10.1109/TNET.2024.3432183","DOIUrl":"10.1109/TNET.2024.3432183","url":null,"abstract":"This paper investigates the \u0000<inline-formula> <tex-math>$(k,k)$ </tex-math></inline-formula>\u0000 fork-join scheduling scheme on a system of n parallel servers comprising both slow and fast servers. Tasks arriving in the system are divided into k sub-tasks and assigned to a random set of k servers, where each task can be assigned independently to a distinct slow or fast server with selection probability \u0000<inline-formula> <tex-math>$p_{s}$ </tex-math></inline-formula>\u0000 or \u0000<inline-formula> <tex-math>$1-p_{s}$ </tex-math></inline-formula>\u0000, respectively. Our analysis demonstrates that the joint distribution of the stationary workload across any set of k queues becomes asymptotically independent as the number of servers n grows, with k scaling as \u0000<inline-formula> <tex-math>$oleft ({{n^{frac {1}{4}}}}right)$ </tex-math></inline-formula>\u0000. Under asymptotic independence, the limiting mean task completion time can be expressed as an integral. However, it is analytically challenging to compute the optimal selection probability \u0000<inline-formula> <tex-math>$p_{s}^{ast } $ </tex-math></inline-formula>\u0000 that minimizes this integral. To address this, we provide an upper bound on the limiting mean task completion time and identify the selection probability \u0000<inline-formula> <tex-math>$hat {p}_{s}$ </tex-math></inline-formula>\u0000 that minimizes this bound. We validate that this selection probability \u0000<inline-formula> <tex-math>$hat {p}_{s}$ </tex-math></inline-formula>\u0000 yields a near-optimal performance through numerical experiments.","PeriodicalId":13443,"journal":{"name":"IEEE/ACM Transactions on Networking","volume":"32 6","pages":"4798-4809"},"PeriodicalIF":3.0,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141862857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2024-07-26DOI: 10.1109/TNET.2024.3432655
Daojing Guo;Khaled Nakhleh;I-Hong Hou;Sastry Kompella;Clement Kam
This paper introduces a new theoretical framework for optimizing second-order behaviors of wireless networks. Unlike existing techniques for network utility maximization, which only consider first-order statistics, this framework models every random process by its mean and temporal variance. The inclusion of temporal variance makes this framework well-suited for modeling Markovian fading wireless channels and emerging network performance metrics such as age-of-information (AoI) and timely-throughput. Using this framework, we sharply characterize the second-order capacity region of wireless access networks. We also propose a simple scheduling policy and prove that it can achieve every interior point in the second-order capacity region. To demonstrate the utility of this framework, we apply it to an unsolved network optimization problem where some clients wish to minimize AoI while others wish to maximize timely-throughput. We show that this framework accurately characterizes AoI and timely-throughput. Moreover, it leads to a tractable scheduling policy that outperforms other existing work.
{"title":"AoI, Timely-Throughput, and Beyond: A Theory of Second-Order Wireless Network Optimization","authors":"Daojing Guo;Khaled Nakhleh;I-Hong Hou;Sastry Kompella;Clement Kam","doi":"10.1109/TNET.2024.3432655","DOIUrl":"10.1109/TNET.2024.3432655","url":null,"abstract":"This paper introduces a new theoretical framework for optimizing second-order behaviors of wireless networks. Unlike existing techniques for network utility maximization, which only consider first-order statistics, this framework models every random process by its mean and temporal variance. The inclusion of temporal variance makes this framework well-suited for modeling Markovian fading wireless channels and emerging network performance metrics such as age-of-information (AoI) and timely-throughput. Using this framework, we sharply characterize the second-order capacity region of wireless access networks. We also propose a simple scheduling policy and prove that it can achieve every interior point in the second-order capacity region. To demonstrate the utility of this framework, we apply it to an unsolved network optimization problem where some clients wish to minimize AoI while others wish to maximize timely-throughput. We show that this framework accurately characterizes AoI and timely-throughput. Moreover, it leads to a tractable scheduling policy that outperforms other existing work.","PeriodicalId":13443,"journal":{"name":"IEEE/ACM Transactions on Networking","volume":"32 6","pages":"4707-4721"},"PeriodicalIF":3.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141775720","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In comparison with upper-layer authentication mechanisms, the tag-based Physical-Layer Authentication (PLA) attracts many research interests because of high security and low complexity. This paper mainly concerns two problems in prior tag-based PLA schemes, where the first one is extra overhead and vulnerability due to the reason that the parameter is broadcasted and the other one is the problem of setting the parameter empirically. Therefore, two new tag-based PLA schemes are proposed to address the above limitations. Specifically, a blind tag-based PLA scheme (BTP) is presented to achieve accurate authentication without knowing the tag parameter of the legitimate transmitter, which not only saves the communication overhead but also improves security. Then, an adaptive blind tag-based PLA scheme (ABTP) is further proposed, which adaptively sets the tag parameter according to the wireless channel state to achieve a better balance among robustness, security, and compatibility. Rigorous theoretical analyses are provided for the two proposed schemes and the prior schemes’ performance comparisons are given. The accuracy of the theoretical analyses is verified through simulation results. At last, the advantages and disadvantages of the two proposed schemes are discussed, and suggestions are given according to different scenarios.
{"title":"Blind Tag-Based Physical-Layer Authentication","authors":"Chen Wang;Mingrui Sha;Wei Xiong;Ning Xie;Rui Mao;Peichang Zhang;Lei Huang","doi":"10.1109/TNET.2024.3430980","DOIUrl":"10.1109/TNET.2024.3430980","url":null,"abstract":"In comparison with upper-layer authentication mechanisms, the tag-based Physical-Layer Authentication (PLA) attracts many research interests because of high security and low complexity. This paper mainly concerns two problems in prior tag-based PLA schemes, where the first one is extra overhead and vulnerability due to the reason that the parameter is broadcasted and the other one is the problem of setting the parameter empirically. Therefore, two new tag-based PLA schemes are proposed to address the above limitations. Specifically, a blind tag-based PLA scheme (BTP) is presented to achieve accurate authentication without knowing the tag parameter of the legitimate transmitter, which not only saves the communication overhead but also improves security. Then, an adaptive blind tag-based PLA scheme (ABTP) is further proposed, which adaptively sets the tag parameter according to the wireless channel state to achieve a better balance among robustness, security, and compatibility. Rigorous theoretical analyses are provided for the two proposed schemes and the prior schemes’ performance comparisons are given. The accuracy of the theoretical analyses is verified through simulation results. At last, the advantages and disadvantages of the two proposed schemes are discussed, and suggestions are given according to different scenarios.","PeriodicalId":13443,"journal":{"name":"IEEE/ACM Transactions on Networking","volume":"32 6","pages":"4735-4748"},"PeriodicalIF":3.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141775721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2024-07-22DOI: 10.1109/TNET.2024.3430989
Hanlin Huang;Xinle Du;Tong Li;Haiyang Wang;Ke Xu;Mowei Wang;Huichen Dai
Converged Ethernet employs Priority-based Flow Control (PFC) to provide a lossless network. However, issues caused by PFC, including victim flow, congestion spreading, and deadlock, impede its large-scale deployment in production systems. The fine-grained experimental observations on switch buffer occupancy find that the root cause of these performance problems is a mismatch of sending rates between end-to-end congestion control and hop-by-hop flow control. Resolving this mismatch requires the switch to provide an additional buffer, which is not supported by the classic dynamic threshold (DT) policy in current shared-buffer commercial switches. In this paper, we propose Selective-PFC (SPFC), a practical buffer management scheme that handles such mismatch. Specifically, SPFC incrementally modifies DT by proactively detecting port traffic and adjusting buffer allocation accordingly to trigger PFC PAUSE frames selectively. Extensive case studies demonstrate that SPFC can reduce the number of PFC PAUSEs on non-bursty ports by up to 69.0%, and reduce the average flow completion time by up to 83.5% for large victim flows.
{"title":"Re-Architecting Buffer Management in Lossless Ethernet","authors":"Hanlin Huang;Xinle Du;Tong Li;Haiyang Wang;Ke Xu;Mowei Wang;Huichen Dai","doi":"10.1109/TNET.2024.3430989","DOIUrl":"10.1109/TNET.2024.3430989","url":null,"abstract":"Converged Ethernet employs Priority-based Flow Control (PFC) to provide a lossless network. However, issues caused by PFC, including victim flow, congestion spreading, and deadlock, impede its large-scale deployment in production systems. The fine-grained experimental observations on switch buffer occupancy find that the root cause of these performance problems is a mismatch of sending rates between end-to-end congestion control and hop-by-hop flow control. Resolving this mismatch requires the switch to provide an additional buffer, which is not supported by the classic dynamic threshold (DT) policy in current shared-buffer commercial switches. In this paper, we propose Selective-PFC (SPFC), a practical buffer management scheme that handles such mismatch. Specifically, SPFC incrementally modifies DT by proactively detecting port traffic and adjusting buffer allocation accordingly to trigger PFC PAUSE frames selectively. Extensive case studies demonstrate that SPFC can reduce the number of PFC PAUSEs on non-bursty ports by up to 69.0%, and reduce the average flow completion time by up to 83.5% for large victim flows.","PeriodicalId":13443,"journal":{"name":"IEEE/ACM Transactions on Networking","volume":"32 6","pages":"4749-4764"},"PeriodicalIF":3.0,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141775722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2024-07-19DOI: 10.1109/TNET.2024.3425617
Qingsong Liu;Zhixuan Fang
We consider the task scheduling scenario where the controller activates one from K task types at each time. Each task induces a random completion time, and a reward is obtained only after the task is completed. The statistics of the completion time and the reward distributions of all task types are unknown to the controller. The controller needs to learn to schedule tasks to maximize the accumulated reward within a given time horizon T. Motivated by the practical scenarios, we require the designed policy to satisfy a system throughput constraint. In addition, we introduce the interruption mechanism to terminate ongoing tasks that last longer than certain deadlines. To address this scheduling problem, we model it as an online learning problem with deadline and throughput constraints. Then, we characterize the optimal offline policy and develop efficient online learning algorithms based on the Lyapunov method. We prove that our online learning algorithm achieves an $O(sqrt {T})$ regret and zero constraint violation. We also conduct simulations to evaluate the performance of our developed learning algorithms.
{"title":"Online Task Scheduling and Termination With Throughput Constraint","authors":"Qingsong Liu;Zhixuan Fang","doi":"10.1109/TNET.2024.3425617","DOIUrl":"10.1109/TNET.2024.3425617","url":null,"abstract":"We consider the task scheduling scenario where the controller activates one from K task types at each time. Each task induces a random completion time, and a reward is obtained only after the task is completed. The statistics of the completion time and the reward distributions of all task types are unknown to the controller. The controller needs to learn to schedule tasks to maximize the accumulated reward within a given time horizon T. Motivated by the practical scenarios, we require the designed policy to satisfy a system throughput constraint. In addition, we introduce the interruption mechanism to terminate ongoing tasks that last longer than certain deadlines. To address this scheduling problem, we model it as an online learning problem with deadline and throughput constraints. Then, we characterize the optimal offline policy and develop efficient online learning algorithms based on the Lyapunov method. We prove that our online learning algorithm achieves an \u0000<inline-formula> <tex-math>$O(sqrt {T})$ </tex-math></inline-formula>\u0000 regret and zero constraint violation. We also conduct simulations to evaluate the performance of our developed learning algorithms.","PeriodicalId":13443,"journal":{"name":"IEEE/ACM Transactions on Networking","volume":"32 6","pages":"4629-4643"},"PeriodicalIF":3.0,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141742620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2024-07-18DOI: 10.1109/TNET.2024.3426607
Bo Wang;Muhan Su;Wufan Wang;Kefan Chen;Bingyang Liu;Fengyuan Ren;Mingwei Xu;Jiangchuan Liu;Jianping Wu
To ensure high performance for HTTP adaptive streaming (HAS), it is critical to provide accurate prediction of end-to-end network bandwidth. Low Latency Live Streaming (LLLS), which has been gaining popularity, faces even greater challenges in this regard. Unlike Video-on-Demand (VOD) streaming, which only needs long-term bandwidth prediction and can tolerate some prediction errors, LLLS demands precise short-term bandwidth predictions. These challenges are amplified by the fact that short-term bandwidth experiences both large abrupt changes and uncertain fluctuations. Furthermore, obtaining valid bandwidth measurement samples in LLLS poses difficulties due to the on-off traffic pattern. In this work, we present DeeProphet, a system designed to enhance the performance of LLLS by achieving accurate bandwidth prediction. DeeProphet collects valid bandwidth samples by identifying intervals of packet continuous sending leveraging TCP state information, estimates the segment-level bandwidth robustly by filtering out noisy samples, and predicts both significant changes and uncertain fluctuations in future bandwidth by combining both time series and learning-based models. Experimental results demonstrate that DeeProphet effectively enhances the overall Quality of Experience (QoE) by 39.5% to 464.6% compared to state-of-the-art LLLS Adaptive Bitrate (ABR) algorithms.
{"title":"Enhancing Low Latency Adaptive Live Streaming Through Precise Bandwidth Prediction","authors":"Bo Wang;Muhan Su;Wufan Wang;Kefan Chen;Bingyang Liu;Fengyuan Ren;Mingwei Xu;Jiangchuan Liu;Jianping Wu","doi":"10.1109/TNET.2024.3426607","DOIUrl":"10.1109/TNET.2024.3426607","url":null,"abstract":"To ensure high performance for HTTP adaptive streaming (HAS), it is critical to provide accurate prediction of end-to-end network bandwidth. Low Latency Live Streaming (LLLS), which has been gaining popularity, faces even greater challenges in this regard. Unlike Video-on-Demand (VOD) streaming, which only needs long-term bandwidth prediction and can tolerate some prediction errors, LLLS demands precise short-term bandwidth predictions. These challenges are amplified by the fact that short-term bandwidth experiences both large abrupt changes and uncertain fluctuations. Furthermore, obtaining valid bandwidth measurement samples in LLLS poses difficulties due to the on-off traffic pattern. In this work, we present DeeProphet, a system designed to enhance the performance of LLLS by achieving accurate bandwidth prediction. DeeProphet collects valid bandwidth samples by identifying intervals of packet continuous sending leveraging TCP state information, estimates the segment-level bandwidth robustly by filtering out noisy samples, and predicts both significant changes and uncertain fluctuations in future bandwidth by combining both time series and learning-based models. Experimental results demonstrate that DeeProphet effectively enhances the overall Quality of Experience (QoE) by 39.5% to 464.6% compared to state-of-the-art LLLS Adaptive Bitrate (ABR) algorithms.","PeriodicalId":13443,"journal":{"name":"IEEE/ACM Transactions on Networking","volume":"32 6","pages":"4676-4691"},"PeriodicalIF":3.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141742622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2024-07-18DOI: 10.1109/TNET.2024.3423673
Su Wang;Roberto Morabito;Seyyedali Hosseinalipour;Mung Chiang;Christopher G. Brinton
The conventional federated learning (FedL) architecture distributes machine learning (ML) across worker devices by having them train local models that are periodically aggregated by a server. FedL ignores two important characteristics of contemporary wireless networks, however: (i) the network may contain heterogeneous communication/computation resources, and (ii) there may be significant overlaps in devices’ local data distributions. In this work, we develop a novel optimization methodology that jointly accounts for these factors via intelligent device sampling complemented by device-to-device (D2D) offloading. Our optimization methodology aims to select the best combination of sampled nodes and data offloading configuration to maximize FedL training accuracy while minimizing data processing and D2D communication resource consumption subject to realistic constraints on the network topology and device capabilities. Theoretical analysis of the D2D offloading subproblem leads to new FedL convergence bounds and an efficient sequential convex optimizer. Using these results, we develop a sampling methodology based on graph convolutional networks (GCNs) which learns the relationship between network attributes, sampled nodes, and D2D data offloading to maximize FedL accuracy. Through evaluation on popular datasets and real-world network measurements from our edge testbed, we find that our methodology outperforms popular device sampling methodologies from literature in terms of ML model performance, data processing overhead, and energy consumption.
{"title":"Device Sampling and Resource Optimization for Federated Learning in Cooperative Edge Networks","authors":"Su Wang;Roberto Morabito;Seyyedali Hosseinalipour;Mung Chiang;Christopher G. Brinton","doi":"10.1109/TNET.2024.3423673","DOIUrl":"10.1109/TNET.2024.3423673","url":null,"abstract":"The conventional federated learning (FedL) architecture distributes machine learning (ML) across worker devices by having them train local models that are periodically aggregated by a server. FedL ignores two important characteristics of contemporary wireless networks, however: (i) the network may contain heterogeneous communication/computation resources, and (ii) there may be significant overlaps in devices’ local data distributions. In this work, we develop a novel optimization methodology that jointly accounts for these factors via intelligent device sampling complemented by device-to-device (D2D) offloading. Our optimization methodology aims to select the best combination of sampled nodes and data offloading configuration to maximize FedL training accuracy while minimizing data processing and D2D communication resource consumption subject to realistic constraints on the network topology and device capabilities. Theoretical analysis of the D2D offloading subproblem leads to new FedL convergence bounds and an efficient sequential convex optimizer. Using these results, we develop a sampling methodology based on graph convolutional networks (GCNs) which learns the relationship between network attributes, sampled nodes, and D2D data offloading to maximize FedL accuracy. Through evaluation on popular datasets and real-world network measurements from our edge testbed, we find that our methodology outperforms popular device sampling methodologies from literature in terms of ML model performance, data processing overhead, and energy consumption.","PeriodicalId":13443,"journal":{"name":"IEEE/ACM Transactions on Networking","volume":"32 5","pages":"4365-4381"},"PeriodicalIF":3.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141742621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Collaborative Edge Computing (CEC) is an emerging paradigm that collaborates heterogeneous edge devices as a resource pool to compute DNN inference tasks in proximity such as edge video analytics. Nevertheless, as the key knob to improve network utility in CEC, existing works mainly focus on the workload routing strategies among edge devices with the aim of minimizing the routing cost, remaining an open question for joint workload allocation and routing optimization problem from a system perspective. To this end, this paper presents a holistic, learned optimization for CEC towards maximizing the total network utility in an online manner, even though the utility functions of task input rates are unknown a priori. In particular, we characterize the CEC system in a flow model and formulate an online learning problem in a form of cross-layer optimization. We propose a nested-loop algorithm to solve workload allocation and distributed routing iteratively, using the tools of gradient sampling and online mirror descent. To improve the convergence rate over the nested-loop version, we further devise a single-loop algorithm. Rigorous analysis is provided to show its inherent convexity, efficient convergence, as well as algorithmic optimality. Finally, extensive numerical simulations demonstrate the superior performance of our solutions.
{"title":"Online Optimization of DNN Inference Network Utility in Collaborative Edge Computing","authors":"Rui Li;Tao Ouyang;Liekang Zeng;Guocheng Liao;Zhi Zhou;Xu Chen","doi":"10.1109/TNET.2024.3421356","DOIUrl":"10.1109/TNET.2024.3421356","url":null,"abstract":"Collaborative Edge Computing (CEC) is an emerging paradigm that collaborates heterogeneous edge devices as a resource pool to compute DNN inference tasks in proximity such as edge video analytics. Nevertheless, as the key knob to improve network utility in CEC, existing works mainly focus on the workload routing strategies among edge devices with the aim of minimizing the routing cost, remaining an open question for joint workload allocation and routing optimization problem from a system perspective. To this end, this paper presents a holistic, learned optimization for CEC towards maximizing the total network utility in an online manner, even though the utility functions of task input rates are unknown a priori. In particular, we characterize the CEC system in a flow model and formulate an online learning problem in a form of cross-layer optimization. We propose a nested-loop algorithm to solve workload allocation and distributed routing iteratively, using the tools of gradient sampling and online mirror descent. To improve the convergence rate over the nested-loop version, we further devise a single-loop algorithm. Rigorous analysis is provided to show its inherent convexity, efficient convergence, as well as algorithmic optimality. Finally, extensive numerical simulations demonstrate the superior performance of our solutions.","PeriodicalId":13443,"journal":{"name":"IEEE/ACM Transactions on Networking","volume":"32 5","pages":"4414-4426"},"PeriodicalIF":3.0,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141720151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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：