Pub Date : 2021-12-01DOI: 10.1109/GLOBECOM46510.2021.9685585
I. Gepko
Complementary sequences (CS) were considered to be used in pairs, although their property to reduce the crest factor in OFDM and MC-CDMA systems employing CS-based spreading is widely known. Their individual properties have hardly ever been studied, with one exception for the Golay sequences. In this paper, we study the individual properties of periodic CS (PCS), which are a superclass of Golay sequences. We show that PCS have remarkable correlation characteristics and unique features at their own, acting as single sequences. Although PCS are somewhat inferior to the Gold and Kasami sequences in terms of peak correlations, they are similar, and sometimes even perform better, in terms of RMS correlation values, and outnumber them by orders of magnitude. The structure of PCS enables efficient processing in applications requiring high data rates. We have also identified the unique feature of PCS which is possibility to use them to construct sets of orthogonal signals that lead to processing advantages of both complementary sequences and cyclic codes.
{"title":"Individual Correlation Properties and Structural Features of Periodic Complementary Sequences","authors":"I. Gepko","doi":"10.1109/GLOBECOM46510.2021.9685585","DOIUrl":"https://doi.org/10.1109/GLOBECOM46510.2021.9685585","url":null,"abstract":"Complementary sequences (CS) were considered to be used in pairs, although their property to reduce the crest factor in OFDM and MC-CDMA systems employing CS-based spreading is widely known. Their individual properties have hardly ever been studied, with one exception for the Golay sequences. In this paper, we study the individual properties of periodic CS (PCS), which are a superclass of Golay sequences. We show that PCS have remarkable correlation characteristics and unique features at their own, acting as single sequences. Although PCS are somewhat inferior to the Gold and Kasami sequences in terms of peak correlations, they are similar, and sometimes even perform better, in terms of RMS correlation values, and outnumber them by orders of magnitude. The structure of PCS enables efficient processing in applications requiring high data rates. We have also identified the unique feature of PCS which is possibility to use them to construct sets of orthogonal signals that lead to processing advantages of both complementary sequences and cyclic codes.","PeriodicalId":200641,"journal":{"name":"2021 IEEE Global Communications Conference (GLOBECOM)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115144302","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 : 2021-12-01DOI: 10.1109/GLOBECOM46510.2021.9685615
Tianyu Liu, Boya Di, Shupeng Wang, Lingyang Song
The federated learning scheme enhances the privacy preservation through avoiding the private data uploading in cloud-edge computing. However, the attacks against the uploaded model updates still cause private data leakage which demotivates the privacy-sensitive participating edge devices. Facing this issue, we aim to design a privacy-preserving incentive mechanism for the federated cloud-edge learning (PFCEL) system such that 1) the edge devices are motivated to actively contribute to the updated model uploading, 2) a trade-off between the private data leakage and the model accuracy is achieved. We formulate the incentive design problem as a three-layer Stackelberg game, where the server-device interaction is further formulated as a contract design problem. Extensive numerical evaluations demonstrate the effectiveness of our designed mechanism in terms of privacy preservation and system utility.
{"title":"A Privacy-Preserving Incentive Mechanism for Federated Cloud-Edge Learning","authors":"Tianyu Liu, Boya Di, Shupeng Wang, Lingyang Song","doi":"10.1109/GLOBECOM46510.2021.9685615","DOIUrl":"https://doi.org/10.1109/GLOBECOM46510.2021.9685615","url":null,"abstract":"The federated learning scheme enhances the privacy preservation through avoiding the private data uploading in cloud-edge computing. However, the attacks against the uploaded model updates still cause private data leakage which demotivates the privacy-sensitive participating edge devices. Facing this issue, we aim to design a privacy-preserving incentive mechanism for the federated cloud-edge learning (PFCEL) system such that 1) the edge devices are motivated to actively contribute to the updated model uploading, 2) a trade-off between the private data leakage and the model accuracy is achieved. We formulate the incentive design problem as a three-layer Stackelberg game, where the server-device interaction is further formulated as a contract design problem. Extensive numerical evaluations demonstrate the effectiveness of our designed mechanism in terms of privacy preservation and system utility.","PeriodicalId":200641,"journal":{"name":"2021 IEEE Global Communications Conference (GLOBECOM)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115151660","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}
This paper addresses a joint radio and computational resources allocation problem for mobile edge computing (MEC) networks. To alleviate the shortage of licensed spectrum resources, computing tasks can be offloaded to the MEC server through not only the licensed channels but also the unlicensed channels, where the adaptive duty-cycle-muting (DCM) mechanism is employed at the user terminals (UTs) to guarantee the fair coexistence with the WiFi networks. Moreover, Stackelberg game formulation is used to build up a decentralized radio and computational resources allocation framework, where the MEC server is modeled as a leader to set the price of the licensed spectrum, while UTs as followers compete for the radio and computational resources as a non-cooperative game. The objective of each UT is to minimize the long-term energy consumption with the guarantee of task buffer stability. Accordingly, we develop a distributed algorithm to achieve the equilibrium solution for the formulated Stackelberg game. Numerical results are presented to demonstrate that the proposed scheme is effective with respect to the reduction on energy consumption of UTs with limited signaling overheads.
{"title":"Distributed Resource Management for Licensed and Unlicensed Integrated Mobile Edge Computing","authors":"Xiao Lu, Rui Yin, Chao Chen, Xianfu Chen, Celimuge Wu","doi":"10.1109/GLOBECOM46510.2021.9685757","DOIUrl":"https://doi.org/10.1109/GLOBECOM46510.2021.9685757","url":null,"abstract":"This paper addresses a joint radio and computational resources allocation problem for mobile edge computing (MEC) networks. To alleviate the shortage of licensed spectrum resources, computing tasks can be offloaded to the MEC server through not only the licensed channels but also the unlicensed channels, where the adaptive duty-cycle-muting (DCM) mechanism is employed at the user terminals (UTs) to guarantee the fair coexistence with the WiFi networks. Moreover, Stackelberg game formulation is used to build up a decentralized radio and computational resources allocation framework, where the MEC server is modeled as a leader to set the price of the licensed spectrum, while UTs as followers compete for the radio and computational resources as a non-cooperative game. The objective of each UT is to minimize the long-term energy consumption with the guarantee of task buffer stability. Accordingly, we develop a distributed algorithm to achieve the equilibrium solution for the formulated Stackelberg game. Numerical results are presented to demonstrate that the proposed scheme is effective with respect to the reduction on energy consumption of UTs with limited signaling overheads.","PeriodicalId":200641,"journal":{"name":"2021 IEEE Global Communications Conference (GLOBECOM)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115306596","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 : 2021-12-01DOI: 10.1109/GLOBECOM46510.2021.9685395
C. O. Nnamani, Muhammad R. A. Khandaker, M. Sellathurai
This paper considers the grid formation of an unmanned aerial vehicle (UAV) swarm for maximizing the secrecy rate in the presence of an unknown eavesdropper. In particular, the UAV swarm performs coordinated beamforming onto the null space of the legitimate channel to jam the eavesdropper located at an unknown location. By nulling the channel between the legitimate receiver and the UAV swarm, we obtain an optimal trajectory and jamming power allocation for each UAV enabling wideband single ray beamforming to improve the secrecy rate. Results obtained demonstrate the effectiveness of the proposed UAV-aided jamming scheme as well as the optimal number of UAVs in the swarm necessary to observe a saturation effect in the secrecy rate. We also show the optimal radius of the unknown but constrained location of the eavesdropper.
{"title":"Secrecy Rate Maximization with Gridded UAV Swarm Jamming for passive Eavesdropping","authors":"C. O. Nnamani, Muhammad R. A. Khandaker, M. Sellathurai","doi":"10.1109/GLOBECOM46510.2021.9685395","DOIUrl":"https://doi.org/10.1109/GLOBECOM46510.2021.9685395","url":null,"abstract":"This paper considers the grid formation of an unmanned aerial vehicle (UAV) swarm for maximizing the secrecy rate in the presence of an unknown eavesdropper. In particular, the UAV swarm performs coordinated beamforming onto the null space of the legitimate channel to jam the eavesdropper located at an unknown location. By nulling the channel between the legitimate receiver and the UAV swarm, we obtain an optimal trajectory and jamming power allocation for each UAV enabling wideband single ray beamforming to improve the secrecy rate. Results obtained demonstrate the effectiveness of the proposed UAV-aided jamming scheme as well as the optimal number of UAVs in the swarm necessary to observe a saturation effect in the secrecy rate. We also show the optimal radius of the unknown but constrained location of the eavesdropper.","PeriodicalId":200641,"journal":{"name":"2021 IEEE Global Communications Conference (GLOBECOM)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115623126","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 : 2021-12-01DOI: 10.1109/GLOBECOM46510.2021.9685051
Hamza Ben Ammar, Y. Ghamri-Doudane
In order to face the rise in data consumption and network congestion, caching structures like Content Delivery Networks (CDNs) are being more and more used and integrated into the network infrastructure. Knowing that the capacities of caching resources are most often limited due to their large operational cost, it has become very important that these entities are managed efficiently. Especially, at the caching operations level, the question that arises is what content should be cached or evicted from the cache when it becomes full. Having these in mind, we introduce a lightweight Artificial Intelligence-based caching scheme called Reversed OPT (RevOPT). In our proposal, we use a Long Short-Term Memory (LSTM) encoder-decoder model to learn future requests patterns from the past and exploit its outcome with a Counting Bloom Filter (CBF) structure to manage efficiently the caching decisions and to keep in the cache only contents expected to be reused in the near future. The conducted simulations show promising results of RevOPT in terms of the cache hit ratio compared to existing caching algorithms.
{"title":"RevOPT: An LSTM-based Efficient Caching Strategy for CDN","authors":"Hamza Ben Ammar, Y. Ghamri-Doudane","doi":"10.1109/GLOBECOM46510.2021.9685051","DOIUrl":"https://doi.org/10.1109/GLOBECOM46510.2021.9685051","url":null,"abstract":"In order to face the rise in data consumption and network congestion, caching structures like Content Delivery Networks (CDNs) are being more and more used and integrated into the network infrastructure. Knowing that the capacities of caching resources are most often limited due to their large operational cost, it has become very important that these entities are managed efficiently. Especially, at the caching operations level, the question that arises is what content should be cached or evicted from the cache when it becomes full. Having these in mind, we introduce a lightweight Artificial Intelligence-based caching scheme called Reversed OPT (RevOPT). In our proposal, we use a Long Short-Term Memory (LSTM) encoder-decoder model to learn future requests patterns from the past and exploit its outcome with a Counting Bloom Filter (CBF) structure to manage efficiently the caching decisions and to keep in the cache only contents expected to be reused in the near future. The conducted simulations show promising results of RevOPT in terms of the cache hit ratio compared to existing caching algorithms.","PeriodicalId":200641,"journal":{"name":"2021 IEEE Global Communications Conference (GLOBECOM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123043826","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 : 2021-12-01DOI: 10.1109/GLOBECOM46510.2021.9685264
Jeongmin Chae, U. Mitra, Songnam Hong
Fully decentralized online learning with multiple kernels (named FDOMKL) is studied, where each node in a network learns a sequence of global functions in an online fashion without the control of a central server. Every node finds the best global function only using information from its one-hop neighboring nodes via online alternating direction method of multipliers (ADMM) and the network-wise Hedge algorithm. The learning framework for an individual node is based on kernel learning and the proposed algorithm successfully harness multi-kernel method to find the best common function over the entire network. To the best of our knowledge, this is the first work that proposes a fully-decentralized online learning algorithm based on multiple kernels. The proposed FDOMKL preserves privacy by maintaining the local data at the edge nodes and exchanging model parameters only. We prove that FDOMKL achieves a sublinear regret bound compared with the best kernel function in hindsight under certain assumptions. In addition, numerical tests on real time-series datasets demonstrate the superiority of the proposed algorithm in terms of learning accuracy and network consistency compared to state-of-the-art single kernel methods.
{"title":"Fully-Decentralized Multi-Kernel Online Learning over Networks","authors":"Jeongmin Chae, U. Mitra, Songnam Hong","doi":"10.1109/GLOBECOM46510.2021.9685264","DOIUrl":"https://doi.org/10.1109/GLOBECOM46510.2021.9685264","url":null,"abstract":"Fully decentralized online learning with multiple kernels (named FDOMKL) is studied, where each node in a network learns a sequence of global functions in an online fashion without the control of a central server. Every node finds the best global function only using information from its one-hop neighboring nodes via online alternating direction method of multipliers (ADMM) and the network-wise Hedge algorithm. The learning framework for an individual node is based on kernel learning and the proposed algorithm successfully harness multi-kernel method to find the best common function over the entire network. To the best of our knowledge, this is the first work that proposes a fully-decentralized online learning algorithm based on multiple kernels. The proposed FDOMKL preserves privacy by maintaining the local data at the edge nodes and exchanging model parameters only. We prove that FDOMKL achieves a sublinear regret bound compared with the best kernel function in hindsight under certain assumptions. In addition, numerical tests on real time-series datasets demonstrate the superiority of the proposed algorithm in terms of learning accuracy and network consistency compared to state-of-the-art single kernel methods.","PeriodicalId":200641,"journal":{"name":"2021 IEEE Global Communications Conference (GLOBECOM)","volume":"4320 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114646853","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 : 2021-12-01DOI: 10.1109/GLOBECOM46510.2021.9685633
M. Rashid, M. Naraghi-Pour
We consider downlink channel estimation in massive multiple input multiple output (MIMO) systems using a Bayesian compressive sensing (BCS) approach. BCS exploits the sparse structure of the channel in the angular domain in order to reduce the pilot overhead. Due to limited local scattering, the massive MIMO channel has a block-sparse representation in the angular domain. Thus, we use a conditionally independent and identically distributed spike-and-slab prior to model the sparse vector coefficients representing the channel and a Markov prior to model its support. An expectation propagation (EP) algorithm is developed to approximate the intractable joint posterior distribution on the sparse vector and its support with a distribution from an exponential family. The unknown model parameters which are required by EP, are estimated using the expectation maximization (EM) algorithm. The proposed combination of EM and EP algorithms is reminiscent of variational EM and is referred to as EM-EP. The approximated distribution is then used for estimating the massive MIMO channel. Simulation results show that our proposed EM-EP algorithm outperforms several recently-proposed algorithms in channel estimation.
{"title":"Block-Sparse Channel Estimation in Massive MIMO Systems by Expectation Propagation","authors":"M. Rashid, M. Naraghi-Pour","doi":"10.1109/GLOBECOM46510.2021.9685633","DOIUrl":"https://doi.org/10.1109/GLOBECOM46510.2021.9685633","url":null,"abstract":"We consider downlink channel estimation in massive multiple input multiple output (MIMO) systems using a Bayesian compressive sensing (BCS) approach. BCS exploits the sparse structure of the channel in the angular domain in order to reduce the pilot overhead. Due to limited local scattering, the massive MIMO channel has a block-sparse representation in the angular domain. Thus, we use a conditionally independent and identically distributed spike-and-slab prior to model the sparse vector coefficients representing the channel and a Markov prior to model its support. An expectation propagation (EP) algorithm is developed to approximate the intractable joint posterior distribution on the sparse vector and its support with a distribution from an exponential family. The unknown model parameters which are required by EP, are estimated using the expectation maximization (EM) algorithm. The proposed combination of EM and EP algorithms is reminiscent of variational EM and is referred to as EM-EP. The approximated distribution is then used for estimating the massive MIMO channel. Simulation results show that our proposed EM-EP algorithm outperforms several recently-proposed algorithms in channel estimation.","PeriodicalId":200641,"journal":{"name":"2021 IEEE Global Communications Conference (GLOBECOM)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124271614","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 : 2021-12-01DOI: 10.1109/GLOBECOM46510.2021.9685355
Pengfei Wang, Boya Di, Lingyang Song
In this paper, we investigate the traffic-sensitive multi-layer low Earth orbit (LEO) satellite-terrestrial network. Massive terrestrial user access to the core network is realized via the backhaul supported by multi-layer LEO satellites. The ultra-dense satellite topology enables a promising solution for the high-capacity backhaul data transmission for terrestrial users. Jointly considering the backhaul capacity requirement and traffic dynamics of terrestrial satellite terminals, we analyze their average backhaul capacity using both stochastic geometry and queueing theory. Aiming to minimize the total required satellite number for fulfilling the backhaul capacity and seamless global coverage requirements, we propose a multi-layer LEO satellite constellation deployment scheme considering the satellite mobility. Simulation results verify the backhaul capacity analysis and the advantage of multi-layer constellation for saving satellites. The optimized multi-layer LEO satellite constellation with any coverage requirement and traffic rate is presented.
{"title":"Multi-layer LEO Satellite Constellation Design for Seamless Global Coverage","authors":"Pengfei Wang, Boya Di, Lingyang Song","doi":"10.1109/GLOBECOM46510.2021.9685355","DOIUrl":"https://doi.org/10.1109/GLOBECOM46510.2021.9685355","url":null,"abstract":"In this paper, we investigate the traffic-sensitive multi-layer low Earth orbit (LEO) satellite-terrestrial network. Massive terrestrial user access to the core network is realized via the backhaul supported by multi-layer LEO satellites. The ultra-dense satellite topology enables a promising solution for the high-capacity backhaul data transmission for terrestrial users. Jointly considering the backhaul capacity requirement and traffic dynamics of terrestrial satellite terminals, we analyze their average backhaul capacity using both stochastic geometry and queueing theory. Aiming to minimize the total required satellite number for fulfilling the backhaul capacity and seamless global coverage requirements, we propose a multi-layer LEO satellite constellation deployment scheme considering the satellite mobility. Simulation results verify the backhaul capacity analysis and the advantage of multi-layer constellation for saving satellites. The optimized multi-layer LEO satellite constellation with any coverage requirement and traffic rate is presented.","PeriodicalId":200641,"journal":{"name":"2021 IEEE Global Communications Conference (GLOBECOM)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125236581","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 : 2021-12-01DOI: 10.1109/GLOBECOM46510.2021.9685332
Ligia F. Borges, Michael Taynnan Barros, M. N. Lima
Molecular Communications (MC) networks comprise multiple devices performing coordinated complex tasks, such as detecting types of cancer and smart drug delivery. Signaling-based MC uses molecules as information carriers between signaling cells. In this context, synchronization is jointly paramount and challenging since the system must overcome the limitation of molecular propagation to make sure computationally deprived bio-devices can communicate. On top of that, a multi-user increases this system challenges as possible co-channel interference causes errors or failures. Bio-devices present severe computational and communication limitations, being this last one essentially unidirectional. This paper presents the first synchronization protocol between signaling cells for multi-user MC. Results have shown the convergence time concerning different network sizes from 12 to 60 nodes.
{"title":"A Synchronization Protocol for Multi-User Cell Signaling-Based Molecular Communication","authors":"Ligia F. Borges, Michael Taynnan Barros, M. N. Lima","doi":"10.1109/GLOBECOM46510.2021.9685332","DOIUrl":"https://doi.org/10.1109/GLOBECOM46510.2021.9685332","url":null,"abstract":"Molecular Communications (MC) networks comprise multiple devices performing coordinated complex tasks, such as detecting types of cancer and smart drug delivery. Signaling-based MC uses molecules as information carriers between signaling cells. In this context, synchronization is jointly paramount and challenging since the system must overcome the limitation of molecular propagation to make sure computationally deprived bio-devices can communicate. On top of that, a multi-user increases this system challenges as possible co-channel interference causes errors or failures. Bio-devices present severe computational and communication limitations, being this last one essentially unidirectional. This paper presents the first synchronization protocol between signaling cells for multi-user MC. Results have shown the convergence time concerning different network sizes from 12 to 60 nodes.","PeriodicalId":200641,"journal":{"name":"2021 IEEE Global Communications Conference (GLOBECOM)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116764366","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 : 2021-12-01DOI: 10.1109/GLOBECOM46510.2021.9685792
Zeyu Luan, Lie Lu, Qing Li, Yong Jiang
Segment Routing (SR) provides Traffic Engineering (TE) with Explicit Path Control (EPC) by steering data flows passing through a list of SR routers along a desired path. However, large-scale migration from a pure IP network to a full SR one requires prohibitive hardware replacement and software update. Therefore, network operators prefer to upgrade a subset of IP routers into SR routers during a transitional period. This paper proposes EPC-TE to optimize TE performance in hybrid IP/SR networks where partially deployed SR routers coexist with legacy IP routers. We propose a concept of key nodes to achieve EPC over desired paths and a criterion to select which IP routers to upgrade first under a pre-defined upgrading ratio. EPC-TE leverages Deep Reinforcement Learning (DRL) to inference the optimal traffic splitting ratio across multiple controllable paths between source-destination pairs. EPC-TE can achieve comparable TE performance as a full SR network with an upgrading ratio less than 30%. Extensive experimental results with real-world topologies show that EPC-TE significantly outperforms other baseline TE solutions in minimizing maximum link utilization.
{"title":"EPC-TE: Explicit Path Control in Traffic Engineering with Deep Reinforcement Learning","authors":"Zeyu Luan, Lie Lu, Qing Li, Yong Jiang","doi":"10.1109/GLOBECOM46510.2021.9685792","DOIUrl":"https://doi.org/10.1109/GLOBECOM46510.2021.9685792","url":null,"abstract":"Segment Routing (SR) provides Traffic Engineering (TE) with Explicit Path Control (EPC) by steering data flows passing through a list of SR routers along a desired path. However, large-scale migration from a pure IP network to a full SR one requires prohibitive hardware replacement and software update. Therefore, network operators prefer to upgrade a subset of IP routers into SR routers during a transitional period. This paper proposes EPC-TE to optimize TE performance in hybrid IP/SR networks where partially deployed SR routers coexist with legacy IP routers. We propose a concept of key nodes to achieve EPC over desired paths and a criterion to select which IP routers to upgrade first under a pre-defined upgrading ratio. EPC-TE leverages Deep Reinforcement Learning (DRL) to inference the optimal traffic splitting ratio across multiple controllable paths between source-destination pairs. EPC-TE can achieve comparable TE performance as a full SR network with an upgrading ratio less than 30%. Extensive experimental results with real-world topologies show that EPC-TE significantly outperforms other baseline TE solutions in minimizing maximum link utilization.","PeriodicalId":200641,"journal":{"name":"2021 IEEE Global Communications Conference (GLOBECOM)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117124418","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：