Pub Date : 2023-07-10DOI: 10.1109/LANMAN58293.2023.10189415
Sudhanshu Naithani, C. Sreenan, A. Zahran
Cable networks are embracing Distributed Access Architectures (DAA) that push traditionally centralized network functions to the network edge. While this shift offers higher data rates, it complicates the management and configuration of the network by having functions distributed in remote nodes. Separately, SDN has evolved for enabling programmable networks of distributed switches, managed in a logically centralized manner. This paper presents an evolutionary path for SDN-based cable DAA that can overcome the aforementioned challenges and support new network services. We present an SDN-DAA architecture, implemented in a real DAA remote device, and evaluated using Mininet to demonstrate the operational benefits.
{"title":"SDN-Enabled Distributed Access Architecture Cable Networks","authors":"Sudhanshu Naithani, C. Sreenan, A. Zahran","doi":"10.1109/LANMAN58293.2023.10189415","DOIUrl":"https://doi.org/10.1109/LANMAN58293.2023.10189415","url":null,"abstract":"Cable networks are embracing Distributed Access Architectures (DAA) that push traditionally centralized network functions to the network edge. While this shift offers higher data rates, it complicates the management and configuration of the network by having functions distributed in remote nodes. Separately, SDN has evolved for enabling programmable networks of distributed switches, managed in a logically centralized manner. This paper presents an evolutionary path for SDN-based cable DAA that can overcome the aforementioned challenges and support new network services. We present an SDN-DAA architecture, implemented in a real DAA remote device, and evaluated using Mininet to demonstrate the operational benefits.","PeriodicalId":416011,"journal":{"name":"2023 IEEE 29th International Symposium on Local and Metropolitan Area Networks (LANMAN)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115118183","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 : 2023-07-10DOI: 10.1109/LANMAN58293.2023.10189813
S. Ishikura, M. Yamamoto
BBR has been proposed as a new congestion control algorithm avoiding bufferbloat and is one of the widely used one along with CUBIC in the current Internet. In this paper, we evaluate preliminary performance of BBR when it shares the bottleneck link with CUBIC. Evaluation results reveal that one of the reasons for unfairness between BBR and CUBIC is misestimation of BBR control parameter RTprop. We also reveal that by increase/decrease of RTprop, we can control delivery rate of BBR. Based on these insights, we propose a new BBR algorithm, BAR(BBR with Adjusting RTprop). BAR adjusts RTprop so that BBR obtains fair bandwidth with CUBIC. Our performance evaluation results show that inter-protocol fairness between BBR and CUBIC flows can be significantly improved by BAR with few packet losses.
BBR作为一种新的避免缓冲区膨胀的拥塞控制算法被提出，与CUBIC一起是当前互联网中广泛使用的拥塞控制算法之一。本文对BBR与CUBIC共享瓶颈链路时的性能进行了初步评价。评价结果表明，BBR与CUBIC之间不公平的原因之一是BBR控制参数RTprop估计错误。我们还发现通过增加/减少RTprop可以控制BBR的递送率。基于这些见解，我们提出了一种新的BBR算法，BAR(BBR with adjust RTprop)。BAR调整RTprop，使BBR通过CUBIC获得公平的带宽。我们的性能评估结果表明，BAR可以显著提高BBR流和CUBIC流之间的协议间公平性，并且丢包较少。
{"title":"BAR : BBR with Adjusting RTprop for Inter-Protocol Fairness with CUBIC TCP","authors":"S. Ishikura, M. Yamamoto","doi":"10.1109/LANMAN58293.2023.10189813","DOIUrl":"https://doi.org/10.1109/LANMAN58293.2023.10189813","url":null,"abstract":"BBR has been proposed as a new congestion control algorithm avoiding bufferbloat and is one of the widely used one along with CUBIC in the current Internet. In this paper, we evaluate preliminary performance of BBR when it shares the bottleneck link with CUBIC. Evaluation results reveal that one of the reasons for unfairness between BBR and CUBIC is misestimation of BBR control parameter RTprop. We also reveal that by increase/decrease of RTprop, we can control delivery rate of BBR. Based on these insights, we propose a new BBR algorithm, BAR(BBR with Adjusting RTprop). BAR adjusts RTprop so that BBR obtains fair bandwidth with CUBIC. Our performance evaluation results show that inter-protocol fairness between BBR and CUBIC flows can be significantly improved by BAR with few packet losses.","PeriodicalId":416011,"journal":{"name":"2023 IEEE 29th International Symposium on Local and Metropolitan Area Networks (LANMAN)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116691144","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 : 2023-07-10DOI: 10.1109/LANMAN58293.2023.10189810
Nowfel Mashnoor, Jay Thom, A. Rouf, S. Sengupta, Batyr Charyyev
The Internet of Things (IoT) introduced new complexities and challenges to computer networks. Due to their simple nature, these devices are more vulnerable to cyber-attacks. Thus it becomes important to identify these devices in a network for network management and detect malicious activities. Network traffic fingerprinting is an essential tool for device identification and anomaly detection, and existing approaches mainly rely on machine learning (ML). However, ML-based approaches require feature selection, hyperparameter tuning, and model retraining to achieve optimum results and be robust to concept drifts observed in a network. To overcome these challenges, in this paper we propose locality-sensitive hashing (LSH) based network traffic fingerprinting. Specifically, we explore design alternatives for the LSH function Nilsimsa and use it to fingerprint network traffic for device identification. We also compared it with ML-based traffic fingerprinting and observed that our method increases the accuracy of state-of-the-art by 12% achieving around 94% accuracy in identifying devices in a network.
{"title":"Locality Sensitive Hashing for Network Traffic Fingerprinting","authors":"Nowfel Mashnoor, Jay Thom, A. Rouf, S. Sengupta, Batyr Charyyev","doi":"10.1109/LANMAN58293.2023.10189810","DOIUrl":"https://doi.org/10.1109/LANMAN58293.2023.10189810","url":null,"abstract":"The Internet of Things (IoT) introduced new complexities and challenges to computer networks. Due to their simple nature, these devices are more vulnerable to cyber-attacks. Thus it becomes important to identify these devices in a network for network management and detect malicious activities. Network traffic fingerprinting is an essential tool for device identification and anomaly detection, and existing approaches mainly rely on machine learning (ML). However, ML-based approaches require feature selection, hyperparameter tuning, and model retraining to achieve optimum results and be robust to concept drifts observed in a network. To overcome these challenges, in this paper we propose locality-sensitive hashing (LSH) based network traffic fingerprinting. Specifically, we explore design alternatives for the LSH function Nilsimsa and use it to fingerprint network traffic for device identification. We also compared it with ML-based traffic fingerprinting and observed that our method increases the accuracy of state-of-the-art by 12% achieving around 94% accuracy in identifying devices in a network.","PeriodicalId":416011,"journal":{"name":"2023 IEEE 29th International Symposium on Local and Metropolitan Area Networks (LANMAN)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127969137","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 : 2023-07-10DOI: 10.1109/LANMAN58293.2023.10189422
Dauren Beisenkhanov, Refik Caglar Kizilirmak, Ikechi Augustine Ukaegbu, T. Baykaş
The growing interest in drone swarms and their applications using wireless communication has resulted in the necessity for innovative network architectures. Drone swarms are subject to highly dynamic network topology, and the low drone density may constrain connectivity and overall network performance. The Delay Tolerant Network (DTN) architecture, which is based on dynamic discovery of neighbouring nodes and relay of data via store-and-forward mechanism, overcomes these challenges. In this study, we develop a DTN simulator for drone swarms using web technologies that operate within the web browser. We employ two commonly used DTN routing algorithms, namely epidemic routing and spray-and-wait routing, for varying numbers of nodes, simulation durations, and maximum allowed copies in the network. We compare these protocols by evaluating performance metrics such as delivery probability, number of hops/copies, and delivery time, through a case study. Additionally, we investigate the influence of the outage probability of the air-to-air channel between nodes.
{"title":"Performance Evaluation of DTN Routing Protocols for Drone Swarms Using a Web-Based Simulator","authors":"Dauren Beisenkhanov, Refik Caglar Kizilirmak, Ikechi Augustine Ukaegbu, T. Baykaş","doi":"10.1109/LANMAN58293.2023.10189422","DOIUrl":"https://doi.org/10.1109/LANMAN58293.2023.10189422","url":null,"abstract":"The growing interest in drone swarms and their applications using wireless communication has resulted in the necessity for innovative network architectures. Drone swarms are subject to highly dynamic network topology, and the low drone density may constrain connectivity and overall network performance. The Delay Tolerant Network (DTN) architecture, which is based on dynamic discovery of neighbouring nodes and relay of data via store-and-forward mechanism, overcomes these challenges. In this study, we develop a DTN simulator for drone swarms using web technologies that operate within the web browser. We employ two commonly used DTN routing algorithms, namely epidemic routing and spray-and-wait routing, for varying numbers of nodes, simulation durations, and maximum allowed copies in the network. We compare these protocols by evaluating performance metrics such as delivery probability, number of hops/copies, and delivery time, through a case study. Additionally, we investigate the influence of the outage probability of the air-to-air channel between nodes.","PeriodicalId":416011,"journal":{"name":"2023 IEEE 29th International Symposium on Local and Metropolitan Area Networks (LANMAN)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131574881","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 : 2023-07-10DOI: 10.1109/LANMAN58293.2023.10189418
Shazal Irshad, Ria Thakkar, Eric Rozner, Eric Wustrow
Today, video cameras are ubiquitously deployed. These cameras collect, stream, store, and analyze video footage for a variety of use cases, ranging from surveillance, retail analytics, architectural engineering, and more. At the same time, many citizens are becoming weary of the amount of personal data captured, along with the algorithms and datasets used to process video pipelines. This work investigates how users can opt-out of such pipelines by explicitly providing consent to be recorded. An ideal system should obfuscate or otherwise cleanse non-consenting user data, ideally before a user even enters the video processing pipeline itself. We present a system, called Consent-Box, that enables obfuscation of users without using complex or personally-identifying vision techniques. Instead, a user's location on a video frame is estimated via Wi-Fi localization of a user's mobile device. This estimation allows us to remove individuals from frames before those frames enter complex vision pipelines.
{"title":"You Can't See Me: Providing Privacy in Vision Pipelines via Wi-Fi Localization","authors":"Shazal Irshad, Ria Thakkar, Eric Rozner, Eric Wustrow","doi":"10.1109/LANMAN58293.2023.10189418","DOIUrl":"https://doi.org/10.1109/LANMAN58293.2023.10189418","url":null,"abstract":"Today, video cameras are ubiquitously deployed. These cameras collect, stream, store, and analyze video footage for a variety of use cases, ranging from surveillance, retail analytics, architectural engineering, and more. At the same time, many citizens are becoming weary of the amount of personal data captured, along with the algorithms and datasets used to process video pipelines. This work investigates how users can opt-out of such pipelines by explicitly providing consent to be recorded. An ideal system should obfuscate or otherwise cleanse non-consenting user data, ideally before a user even enters the video processing pipeline itself. We present a system, called Consent-Box, that enables obfuscation of users without using complex or personally-identifying vision techniques. Instead, a user's location on a video frame is estimated via Wi-Fi localization of a user's mobile device. This estimation allows us to remove individuals from frames before those frames enter complex vision pipelines.","PeriodicalId":416011,"journal":{"name":"2023 IEEE 29th International Symposium on Local and Metropolitan Area Networks (LANMAN)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132953968","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 : 2023-07-10DOI: 10.1109/LANMAN58293.2023.10189423
Vasundhara, A. Mandloi, Mehul Patel
The capacity of Elastic Optical Network (EON) to dynamically employ network resources is drawing a lot of interest these days. Access to spectrum resources is challenging for new requests especially when the spectrum is divided into numerous tiny segments. The distribution of spectrum, intelligent and effective routing are two other major EON challenges. In order to allocate contiguous aligned spectrum slots to multiple requests, this includes searching for a certain route. EON seeks to maximize connectivity while utilizing the least amount of spectrum resources possible in this manner. Given that dispersion is a significant physical problem in optical networks, this research investigated a method of spectrum distribution using first random fit (FRF) method. This plan takes dispersion into account while performing the spectrum allocation strategy. This system tends to allocate more connection requests and use spectrum more effectively when using a FRF strategy. This technique employs and assigns the spectrum slot to the longest photonic route starting from the lowest indexed slot using the First Fit algorithm while using a less reliable modulation technique like BPSK. Using a more stable modulation technology (QPSK) in combination with a random fit assignment method, it is possible to utilize the next higher indexed spectrum spot which has a bigger impact on dispersion to the shortest photonic path. Advantage of using a heuristic approach for large scale network can be quantitatively measured in terms of computational efficiency and scalability. Till now, as per our knowledge FRF technique with ILP approach considering dispersion as one of the parameter has not been covered yet. The finding demonstrate that the suggested method outshines the previous distance adaptive and non distance adaptive spectrum allocation schemes in terms of distinct parameters as fragmentation (0.9966), CASR (0.0033), blocking probability (BBP) of 0.048, blocking probability (B.P) and optimality gap of 4.71 % and other parameters.
{"title":"A Novel First Random Fit (FRF): Dispersion Aware Approach using Heuristic and ILP in Elastic Optical Network (EON)","authors":"Vasundhara, A. Mandloi, Mehul Patel","doi":"10.1109/LANMAN58293.2023.10189423","DOIUrl":"https://doi.org/10.1109/LANMAN58293.2023.10189423","url":null,"abstract":"The capacity of Elastic Optical Network (EON) to dynamically employ network resources is drawing a lot of interest these days. Access to spectrum resources is challenging for new requests especially when the spectrum is divided into numerous tiny segments. The distribution of spectrum, intelligent and effective routing are two other major EON challenges. In order to allocate contiguous aligned spectrum slots to multiple requests, this includes searching for a certain route. EON seeks to maximize connectivity while utilizing the least amount of spectrum resources possible in this manner. Given that dispersion is a significant physical problem in optical networks, this research investigated a method of spectrum distribution using first random fit (FRF) method. This plan takes dispersion into account while performing the spectrum allocation strategy. This system tends to allocate more connection requests and use spectrum more effectively when using a FRF strategy. This technique employs and assigns the spectrum slot to the longest photonic route starting from the lowest indexed slot using the First Fit algorithm while using a less reliable modulation technique like BPSK. Using a more stable modulation technology (QPSK) in combination with a random fit assignment method, it is possible to utilize the next higher indexed spectrum spot which has a bigger impact on dispersion to the shortest photonic path. Advantage of using a heuristic approach for large scale network can be quantitatively measured in terms of computational efficiency and scalability. Till now, as per our knowledge FRF technique with ILP approach considering dispersion as one of the parameter has not been covered yet. The finding demonstrate that the suggested method outshines the previous distance adaptive and non distance adaptive spectrum allocation schemes in terms of distinct parameters as fragmentation (0.9966), CASR (0.0033), blocking probability (BBP) of 0.048, blocking probability (B.P) and optimality gap of 4.71 % and other parameters.","PeriodicalId":416011,"journal":{"name":"2023 IEEE 29th International Symposium on Local and Metropolitan Area Networks (LANMAN)","volume":"281 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131901868","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 : 2023-07-10DOI: 10.1109/LANMAN58293.2023.10189811
Adil Kucherbayev, Refik Caglar Kizilirmak
In this work, we evaluate the two most common routing protocols of Delay Tolerant Networks (DTNs), opportunistic and scheduled routing, for vehicular networks. We compare the feasibility of these routing protocols in terms of packet delivery ratio, delivery time, and network load using a miniature vehicular network. The mobile nodes in the network are equipped with a radio transceiver such that they exchange the data packets according to the chosen routing protocol. We observe that scheduled routing can decrease the traffic load significantly as compared to opportunistic routing, however, this comes at the cost of requiring nodes to have a contact plan.
{"title":"Implementation of Opportunistic and Scheduled Routing Algorithms for DTN based Vehicular Networks","authors":"Adil Kucherbayev, Refik Caglar Kizilirmak","doi":"10.1109/LANMAN58293.2023.10189811","DOIUrl":"https://doi.org/10.1109/LANMAN58293.2023.10189811","url":null,"abstract":"In this work, we evaluate the two most common routing protocols of Delay Tolerant Networks (DTNs), opportunistic and scheduled routing, for vehicular networks. We compare the feasibility of these routing protocols in terms of packet delivery ratio, delivery time, and network load using a miniature vehicular network. The mobile nodes in the network are equipped with a radio transceiver such that they exchange the data packets according to the chosen routing protocol. We observe that scheduled routing can decrease the traffic load significantly as compared to opportunistic routing, however, this comes at the cost of requiring nodes to have a contact plan.","PeriodicalId":416011,"journal":{"name":"2023 IEEE 29th International Symposium on Local and Metropolitan Area Networks (LANMAN)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133901460","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 : 2023-07-10DOI: 10.1109/LANMAN58293.2023.10189809
Nehal Baganal Krishna, David Munstein, Amr Rizk
Load balancers in distributed caching systems face a fundamental trade-off between networking and caching performance metrics. The first comprises how the network traffic of object requests and replies is balanced on the different links to/from the cache servers while the second denotes cache hit rates and response times. In a nutshell, the root of this trade-off lies in the combination of the skewed popularity and dynamic nature of incoming object requests as well as whether the load balancing function is agnostic to the caching application or not. In this paper, we present Lethe, a network data-plane load balancer for distributed Time-to-Live (TTL) caching. We con-sider TTL caching as it separates the object dynamics but still performs equivalently to many classical caching algorithms (e.g. LRU) under appropriate TTL parametrization. Lethe segregates the cache objects based on the pattern of the incoming requests and efficiently places objects in cache servers to balance the network traffic without sacrificing the caching system hit rate. We implement Lethe in P4 and experimentally show that it improves the average response time and cache hit rate as compared to application-agnostic load balancing even for a skewed and dynamically changing workload.
{"title":"LETHE: Combined Time-to-Live Caching and Load Balancing on the Network Data Plane","authors":"Nehal Baganal Krishna, David Munstein, Amr Rizk","doi":"10.1109/LANMAN58293.2023.10189809","DOIUrl":"https://doi.org/10.1109/LANMAN58293.2023.10189809","url":null,"abstract":"Load balancers in distributed caching systems face a fundamental trade-off between networking and caching performance metrics. The first comprises how the network traffic of object requests and replies is balanced on the different links to/from the cache servers while the second denotes cache hit rates and response times. In a nutshell, the root of this trade-off lies in the combination of the skewed popularity and dynamic nature of incoming object requests as well as whether the load balancing function is agnostic to the caching application or not. In this paper, we present Lethe, a network data-plane load balancer for distributed Time-to-Live (TTL) caching. We con-sider TTL caching as it separates the object dynamics but still performs equivalently to many classical caching algorithms (e.g. LRU) under appropriate TTL parametrization. Lethe segregates the cache objects based on the pattern of the incoming requests and efficiently places objects in cache servers to balance the network traffic without sacrificing the caching system hit rate. We implement Lethe in P4 and experimentally show that it improves the average response time and cache hit rate as compared to application-agnostic load balancing even for a skewed and dynamically changing workload.","PeriodicalId":416011,"journal":{"name":"2023 IEEE 29th International Symposium on Local and Metropolitan Area Networks (LANMAN)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123676386","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 : 2023-07-10DOI: 10.1109/LANMAN58293.2023.10189421
Sergi Rene, G. Pavlou, Onur Ascigil
Hybrid Information-Centric Networking (hICN) is an incrementally-deployable information-centric networking architecture that is built on top of IPv6. In hICN, application-level identifiers are directly used to route interest packets (i.e., request for content) to fetch a copy of the desired content/data from any location. However, following the Internet Protocol conventions that require storing pre-computed routing/forwarding state for all prefixes in the routers raises scalability concerns, especially at the inter-domain level. Here we consider instead the other extreme; i.e. on-demand routing computation for content name prefixes when interest packets arrive at the router. Following this approach, we propose a centralized routing service within a domain that keeps a mapping between hICN name prefixes and locators (i.e., routable addresses) to hICN routers. Once a locator is received, an hICN router forwards an interest packet towards the intended destination using segment routing. We evaluated the proposed solution through a real testbed implementation in order to demonstrate that the performance is equivalent to typical hICN forwarding, while offering a scalability solution.
{"title":"Scalable Content-centric Routing for Hybrid ICN","authors":"Sergi Rene, G. Pavlou, Onur Ascigil","doi":"10.1109/LANMAN58293.2023.10189421","DOIUrl":"https://doi.org/10.1109/LANMAN58293.2023.10189421","url":null,"abstract":"Hybrid Information-Centric Networking (hICN) is an incrementally-deployable information-centric networking architecture that is built on top of IPv6. In hICN, application-level identifiers are directly used to route interest packets (i.e., request for content) to fetch a copy of the desired content/data from any location. However, following the Internet Protocol conventions that require storing pre-computed routing/forwarding state for all prefixes in the routers raises scalability concerns, especially at the inter-domain level. Here we consider instead the other extreme; i.e. on-demand routing computation for content name prefixes when interest packets arrive at the router. Following this approach, we propose a centralized routing service within a domain that keeps a mapping between hICN name prefixes and locators (i.e., routable addresses) to hICN routers. Once a locator is received, an hICN router forwards an interest packet towards the intended destination using segment routing. We evaluated the proposed solution through a real testbed implementation in order to demonstrate that the performance is equivalent to typical hICN forwarding, while offering a scalability solution.","PeriodicalId":416011,"journal":{"name":"2023 IEEE 29th International Symposium on Local and Metropolitan Area Networks (LANMAN)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126047686","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 : 2023-07-10DOI: 10.1109/LANMAN58293.2023.10189426
Alp Berke Ardic, H. Seferoglu, S. Rouayheb, Erdem Koyuncu
Random walk learning (RWL) has recently gained a lot of attention thanks to its potential for reducing communication and computation over edge networks in a decentralized fashion. In RWL, each node in a graph updates a global model with its local data, selects one of its neighbors randomly, and sends the updated global model. The selected neighbor becomes a newly activated node, so it updates the global model using its local data. This continues until convergence. Despite its promise, RWL has two challenges: (i) training time is long, and (ii) nodes should have the complete model. Thus, in this paper, we design Random Walking Snakes (RWS), where a set of nodes instead of one node is activated for model update, and each node in the set trains a part of the model. Thanks to model partitioning and parallel processing in the set of activated nodes, RWS reduces both the training time and the amount of the model that needs to be stored. We also design a novel policy that determines the set of activated nodes by taking into account the computing power of nodes. Simulation results show that RWS significantly reduces the convergence time as compared to RWL.
{"title":"Random Walking Snakes for Decentralized Learning at Edge Networks","authors":"Alp Berke Ardic, H. Seferoglu, S. Rouayheb, Erdem Koyuncu","doi":"10.1109/LANMAN58293.2023.10189426","DOIUrl":"https://doi.org/10.1109/LANMAN58293.2023.10189426","url":null,"abstract":"Random walk learning (RWL) has recently gained a lot of attention thanks to its potential for reducing communication and computation over edge networks in a decentralized fashion. In RWL, each node in a graph updates a global model with its local data, selects one of its neighbors randomly, and sends the updated global model. The selected neighbor becomes a newly activated node, so it updates the global model using its local data. This continues until convergence. Despite its promise, RWL has two challenges: (i) training time is long, and (ii) nodes should have the complete model. Thus, in this paper, we design Random Walking Snakes (RWS), where a set of nodes instead of one node is activated for model update, and each node in the set trains a part of the model. Thanks to model partitioning and parallel processing in the set of activated nodes, RWS reduces both the training time and the amount of the model that needs to be stored. We also design a novel policy that determines the set of activated nodes by taking into account the computing power of nodes. Simulation results show that RWS significantly reduces the convergence time as compared to RWL.","PeriodicalId":416011,"journal":{"name":"2023 IEEE 29th International Symposium on Local and Metropolitan Area Networks (LANMAN)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126662128","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}
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：