Digital Communications and Networks最新文献_第10页

Accurate and efficient elephant-flow classification based on co-trained models in evolved software-defined networks 基于协同训练模型的高效象流分类

IF 7.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Digital Communications and Networks

Pub Date : 2025-08-01 DOI: 10.1016/j.dcan.2024.10.017

Ling Xia Liao , Changqing Zhao , Jian Wang , Roy Xiaorong Lai , Steve Drew

Accurate early classification of elephant flows (elephants) is important for network management and resource optimization. Elephant models, mainly based on the byte count of flows, can always achieve high accuracy, but not in a time-efficient manner. The time efficiency becomes even worse when the flows to be classified are sampled by flow entry timeout over Software-Defined Networks (SDNs) to achieve a better resource efficiency. This paper addresses this situation by combining co-training and Reinforcement Learning (RL) to enable a closed-loop classification approach that divides the entire classification process into episodes, each involving two elephant models. One predicts elephants and is retrained by a selection of flows automatically labeled online by the other. RL is used to formulate a reward function that estimates the values of the possible actions based on the current states of both models and further adjusts the ratio of flows to be labeled in each phase. Extensive evaluation based on real traffic traces shows that the proposed approach can stably predict elephants using the packets received in the first 10% of their lifetime with an accuracy of over 80%, and using only about 10% more control channel bandwidth than the baseline over the evolved SDNs.

大象流的准确早期分类对于网络管理和资源优化具有重要意义。大象模型主要基于流的字节数，总是可以达到很高的准确性，但不是时间效率高的方式。当要分类的流通过软件定义网络（sdn）上的流进入超时进行采样以实现更好的资源效率时，时间效率会变得更差。本文通过结合协同训练和强化学习（RL）来解决这种情况，以实现闭环分类方法，将整个分类过程划分为集，每个集涉及两个大象模型。其中一个预测大象，并通过选择由另一个自动在线标记的流进行再训练。RL用于制定奖励函数，该函数基于两个模型的当前状态估计可能行动的值，并进一步调整每个阶段要标记的流的比例。基于真实流量轨迹的广泛评估表明，所提出的方法可以使用大象生命周期前10%收到的数据包来稳定地预测大象，准确率超过80%，并且使用的控制信道带宽仅比进化的sdn的基线多10%左右。

{"title":"Accurate and efficient elephant-flow classification based on co-trained models in evolved software-defined networks","authors":"Ling Xia Liao , Changqing Zhao , Jian Wang , Roy Xiaorong Lai , Steve Drew","doi":"10.1016/j.dcan.2024.10.017","DOIUrl":"10.1016/j.dcan.2024.10.017","url":null,"abstract":"<div><div>Accurate early classification of elephant flows (elephants) is important for network management and resource optimization. Elephant models, mainly based on the byte count of flows, can always achieve high accuracy, but not in a time-efficient manner. The time efficiency becomes even worse when the flows to be classified are sampled by flow entry timeout over Software-Defined Networks (SDNs) to achieve a better resource efficiency. This paper addresses this situation by combining co-training and Reinforcement Learning (RL) to enable a closed-loop classification approach that divides the entire classification process into episodes, each involving two elephant models. One predicts elephants and is retrained by a selection of flows automatically labeled online by the other. RL is used to formulate a reward function that estimates the values of the possible actions based on the current states of both models and further adjusts the ratio of flows to be labeled in each phase. Extensive evaluation based on real traffic traces shows that the proposed approach can stably predict elephants using the packets received in the first 10% of their lifetime with an accuracy of over 80%, and using only about 10% more control channel bandwidth than the baseline over the evolved SDNs.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"11 4","pages":"Pages 1091-1102"},"PeriodicalIF":7.5,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144925895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Energy-saving control strategy for ultra-dense network base stations based on multi-agent reinforcement learning 基于多智能体强化学习的超密集网络基站节能控制策略

IF 7.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Digital Communications and Networks

Pub Date : 2025-08-01 DOI: 10.1016/j.dcan.2024.10.015

Yan Zhen , Litianyi Tao , Dapeng Wu , Tong Tang , Ruyan Wang

Aiming at the problem of mobile data traffic surge in 5G networks, this paper proposes an effective solution combining massive multiple-input multiple-output techniques with Ultra-Dense Network (UDN) and focuses on solving the resulting challenge of increased energy consumption. A base station control algorithm based on Multi-Agent Proximity Policy Optimization (MAPPO) is designed. In the constructed 5G UDN model, each base station is considered as an agent, and the MAPPO algorithm enables inter-base station collaboration and interference management to optimize the network performance. To reduce the extra power consumption due to frequent sleep mode switching of base stations, a sleep mode switching decision algorithm is proposed. The algorithm reduces unnecessary power consumption by evaluating the network state similarity and intelligently adjusting the agent's action strategy. Simulation results show that the proposed algorithm reduces the power consumption by 24.61% compared to the no-sleep strategy and further reduces the power consumption by 5.36% compared to the traditional MAPPO algorithm under the premise of guaranteeing the quality of service of users.

针对5G网络中移动数据流量激增的问题，本文提出了海量多输入多输出技术与超密集网络（Ultra-Dense Network， UDN）相结合的有效解决方案，重点解决由此带来的能耗增加的挑战。设计了一种基于多智能体邻近策略优化（MAPPO）的基站控制算法。在构建的5G UDN模型中，将每个基站视为一个agent，通过MAPPO算法实现基站间协作和干扰管理，优化网络性能。为了减少基站频繁切换休眠模式所带来的额外功耗，提出了一种休眠模式切换决策算法。该算法通过评估网络状态相似度和智能调整agent的动作策略来减少不必要的功耗。仿真结果表明，该算法在保证用户服务质量的前提下，比无睡眠策略功耗降低24.61%，比传统MAPPO算法功耗进一步降低5.36%。

{"title":"Energy-saving control strategy for ultra-dense network base stations based on multi-agent reinforcement learning","authors":"Yan Zhen , Litianyi Tao , Dapeng Wu , Tong Tang , Ruyan Wang","doi":"10.1016/j.dcan.2024.10.015","DOIUrl":"10.1016/j.dcan.2024.10.015","url":null,"abstract":"<div><div>Aiming at the problem of mobile data traffic surge in 5G networks, this paper proposes an effective solution combining massive multiple-input multiple-output techniques with Ultra-Dense Network (UDN) and focuses on solving the resulting challenge of increased energy consumption. A base station control algorithm based on Multi-Agent Proximity Policy Optimization (MAPPO) is designed. In the constructed 5G UDN model, each base station is considered as an agent, and the MAPPO algorithm enables inter-base station collaboration and interference management to optimize the network performance. To reduce the extra power consumption due to frequent sleep mode switching of base stations, a sleep mode switching decision algorithm is proposed. The algorithm reduces unnecessary power consumption by evaluating the network state similarity and intelligently adjusting the agent's action strategy. Simulation results show that the proposed algorithm reduces the power consumption by 24.61% compared to the no-sleep strategy and further reduces the power consumption by 5.36% compared to the traditional MAPPO algorithm under the premise of guaranteeing the quality of service of users.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"11 4","pages":"Pages 1007-1017"},"PeriodicalIF":7.5,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144926835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A deep-learning-based MAC for integrating channel access, rate adaptation, and channel switch 一种基于深度学习的MAC，用于集成信道访问、速率自适应和信道切换

IF 7.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Digital Communications and Networks

Pub Date : 2025-08-01 DOI: 10.1016/j.dcan.2024.10.010

Jiantao Xin , Wei Xu , Bin Cao , Taotao Wang , Shengli Zhang

With increasing density and heterogeneity in unlicensed wireless networks, traditional MAC protocols, such as Carrier Sense Multiple Access with Collision Avoidance (CSMA/CA) in Wi-Fi networks, are experiencing performance degradation. This is manifested in increased collisions and extended backoff times, leading to diminished spectrum efficiency and protocol coordination. Addressing these issues, this paper proposes a deep-learning-based MAC paradigm, dubbed DL-MAC, which leverages spectrum data readily available from energy detection modules in wireless devices to achieve the MAC functionalities of channel access, rate adaptation, and channel switch. First, we utilize DL-MAC to realize a joint design of channel access and rate adaptation. Subsequently, we integrate the capability of channel switching into DL-MAC, enhancing its functionality from single-channel to multi-channel operations. Specifically, the DL-MAC protocol incorporates a Deep Neural Network (DNN) for channel selection and a Recurrent Neural Network (RNN) for the joint design of channel access and rate adaptation. We conducted real-world data collection within the 2.4 GHz frequency band to validate the effectiveness of DL-MAC. Experimental results demonstrate that DL-MAC exhibits significantly superior performance compared to traditional algorithms in both single and multi-channel environments, and also outperforms single-function designs. Additionally, the performance of DL-MAC remains robust, unaffected by channel switch overheads within the evaluation range.

随着非授权无线网络的密度和异构性的增加，传统的MAC协议，如Wi-Fi网络中的载波感知避碰多址（CSMA/CA），正在经历性能下降。这表现在碰撞增加和后退时间延长，导致频谱效率和协议协调降低。为了解决这些问题，本文提出了一种基于深度学习的MAC范式，称为DL-MAC，它利用无线设备中能量检测模块中现成的频谱数据来实现信道接入、速率适应和信道切换的MAC功能。首先，我们利用DL-MAC实现信道接入和速率自适应的联合设计。随后，我们将通道切换功能集成到DL-MAC中，增强了其从单通道到多通道操作的功能。具体来说，DL-MAC协议结合了用于信道选择的深度神经网络（DNN）和用于信道接入和速率自适应联合设计的循环神经网络（RNN）。我们在2.4 GHz频段内进行了实际数据收集，以验证DL-MAC的有效性。实验结果表明，与传统算法相比，DL-MAC在单通道和多通道环境下都表现出显著的性能优势，并且优于单功能设计。此外，DL-MAC的性能保持稳健，在评估范围内不受信道交换开销的影响。

{"title":"A deep-learning-based MAC for integrating channel access, rate adaptation, and channel switch","authors":"Jiantao Xin , Wei Xu , Bin Cao , Taotao Wang , Shengli Zhang","doi":"10.1016/j.dcan.2024.10.010","DOIUrl":"10.1016/j.dcan.2024.10.010","url":null,"abstract":"<div><div>With increasing density and heterogeneity in unlicensed wireless networks, traditional MAC protocols, such as Carrier Sense Multiple Access with Collision Avoidance (CSMA/CA) in Wi-Fi networks, are experiencing performance degradation. This is manifested in increased collisions and extended backoff times, leading to diminished spectrum efficiency and protocol coordination. Addressing these issues, this paper proposes a deep-learning-based MAC paradigm, dubbed DL-MAC, which leverages spectrum data readily available from energy detection modules in wireless devices to achieve the MAC functionalities of channel access, rate adaptation, and channel switch. First, we utilize DL-MAC to realize a joint design of channel access and rate adaptation. Subsequently, we integrate the capability of channel switching into DL-MAC, enhancing its functionality from single-channel to multi-channel operations. Specifically, the DL-MAC protocol incorporates a Deep Neural Network (DNN) for channel selection and a Recurrent Neural Network (RNN) for the joint design of channel access and rate adaptation. We conducted real-world data collection within the 2.4 GHz frequency band to validate the effectiveness of DL-MAC. Experimental results demonstrate that DL-MAC exhibits significantly superior performance compared to traditional algorithms in both single and multi-channel environments, and also outperforms single-function designs. Additionally, the performance of DL-MAC remains robust, unaffected by channel switch overheads within the evaluation range.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"11 4","pages":"Pages 1042-1054"},"PeriodicalIF":7.5,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144926841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Generalized spatial modulation detector assisted by reconfigurable intelligent surface based on deep learning 基于深度学习的可重构智能曲面辅助广义空间调制检测器

IF 7.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Digital Communications and Networks

Pub Date : 2025-08-01 DOI: 10.1016/j.dcan.2024.11.015

Chiya Zhang , Qinggeng Huang , Chunlong He , Gaojie Chen , Xingquan Li

Reconfigurable Intelligent Surface (RIS) is regarded as a cutting-edge technology for the development of future wireless communication networks with improved frequency efficiency and reduced energy consumption. This paper proposes an architecture by combining RIS with Generalized Spatial Modulation (GSM) and then presents a Multi-Residual Deep Neural Network (MR-DNN) scheme, where the active antennas and their transmitted constellation symbols are detected by sub-DNNs in the detection block. Simulation results demonstrate that the proposed MR-DNN detection algorithm performs considerably better than the traditional Zero-Forcing (ZF) and the Minimum Mean Squared Error (MMSE) detection algorithms in terms of Bit Error Rate (BER). Moreover, the MR-DNN detection algorithm has less time complexity than the traditional detection algorithms.

可重构智能表面（RIS）被认为是未来无线通信网络发展的前沿技术，具有提高频率效率和降低能耗的特点。本文提出了一种将RIS与广义空间调制（GSM）相结合的结构，并在此基础上提出了一种多残差深度神经网络（MR-DNN）方案，该方案通过检测块中的子dnn检测有源天线及其发射星座符号。仿真结果表明，提出的MR-DNN检测算法在误码率（BER）方面明显优于传统的零强迫（Zero-Forcing， ZF）和最小均方误差（Minimum Mean Squared Error， MMSE）检测算法。此外，MR-DNN检测算法比传统检测算法具有更低的时间复杂度。

引用次数: 0

Interest-aware joint caching, computing, and communication optimization for mobile VR delivery in MEC networks MEC网络中移动VR传输的兴趣感知联合缓存、计算和通信优化

IF 7.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Digital Communications and Networks

Pub Date : 2025-08-01 DOI: 10.1016/j.dcan.2024.10.018

Baojie Fu , Tong Tang , Dapeng Wu , Ruyan Wang

In the upcoming B5G/6G era, Virtual Reality (VR) over wireless has become a typical application, which is an inevitable trend in the development of video. However, in immersive and interactive VR experiences, VR services typically exhibit high delay, while simultaneously posing challenges for the energy consumption of local devices. To address these issues, this paper aims to improve the performance of VR service in the edge-terminal cooperative system. Specifically, we formulate a joint Caching, Computing, and Communication (3C) VR service policy problem by optimizing the weighted sum of the total VR delivery delay and the energy consumption of local devices. To design the optimal VR service policy, the optimization problem is decoupled into three independent subproblems to be solved separately. To improve the caching efficiency within the network, a Bert-based user interest analysis method is first proposed to accurately characterize the content request behavior. Based on this, a service cost minimum-maximization problem is formulated under the consideration of performance fairness among users. Then, the joint caching and computing scheme is derived for each user with a given allocation of communication resources while a bisection-based communication scheme is acquired with the given information on the joint caching and computing policy. With alternative optimization, an optimal policy for joint 3C based on user interest can be finally obtained. Simulation results are presented to demonstrate the superiority of the proposed user interest-aware caching scheme and the effectiveness of the joint 3C optimization policy while considering user fairness. Our code is available at https://github.com/mrfuqaq1108/Interest-Aware-Joint-3C-Optimization.

在即将到来的B5G/6G时代，基于无线的虚拟现实（VR）已经成为一种典型的应用，这是视频发展的必然趋势。然而，在沉浸式和交互式VR体验中，VR服务通常具有高延迟，同时对本地设备的能耗提出了挑战。针对这些问题，本文旨在提高边缘终端协同系统中虚拟现实服务的性能。具体而言，我们通过优化VR总交付延迟和本地设备能耗的加权和，制定了一个联合缓存、计算和通信（3C） VR服务策略问题。为了设计最优的虚拟现实服务策略，将优化问题解耦为三个独立的子问题分别求解。为了提高网络内的缓存效率，首先提出了一种基于bert的用户兴趣分析方法来准确表征内容请求行为。在此基础上，提出了考虑用户间性能公平性的服务成本最小最大化问题。然后，在给定通信资源分配的情况下，推导出每个用户的联合缓存和计算方案，并利用给定的联合缓存和计算策略信息获得基于切分的通信方案。通过备选优化，最终得到基于用户兴趣的联合3C最优策略。仿真结果证明了所提出的用户兴趣感知缓存方案的优越性，以及在考虑用户公平性的情况下联合3C优化策略的有效性。我们的代码可在https://github.com/mrfuqaq1108/Interest-Aware-Joint-3C-Optimization上获得。

{"title":"Interest-aware joint caching, computing, and communication optimization for mobile VR delivery in MEC networks","authors":"Baojie Fu , Tong Tang , Dapeng Wu , Ruyan Wang","doi":"10.1016/j.dcan.2024.10.018","DOIUrl":"10.1016/j.dcan.2024.10.018","url":null,"abstract":"<div><div>In the upcoming B5G/6G era, Virtual Reality (VR) over wireless has become a typical application, which is an inevitable trend in the development of video. However, in immersive and interactive VR experiences, VR services typically exhibit high delay, while simultaneously posing challenges for the energy consumption of local devices. To address these issues, this paper aims to improve the performance of VR service in the edge-terminal cooperative system. Specifically, we formulate a joint Caching, Computing, and Communication (3C) VR service policy problem by optimizing the weighted sum of the total VR delivery delay and the energy consumption of local devices. To design the optimal VR service policy, the optimization problem is decoupled into three independent subproblems to be solved separately. To improve the caching efficiency within the network, a Bert-based user interest analysis method is first proposed to accurately characterize the content request behavior. Based on this, a service cost minimum-maximization problem is formulated under the consideration of performance fairness among users. Then, the joint caching and computing scheme is derived for each user with a given allocation of communication resources while a bisection-based communication scheme is acquired with the given information on the joint caching and computing policy. With alternative optimization, an optimal policy for joint 3C based on user interest can be finally obtained. Simulation results are presented to demonstrate the superiority of the proposed user interest-aware caching scheme and the effectiveness of the joint 3C optimization policy while considering user fairness. Our code is available at <span><span>https://github.com/mrfuqaq1108/Interest-Aware-Joint-3C-Optimization</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"11 4","pages":"Pages 1103-1113"},"PeriodicalIF":7.5,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144925843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing generalized receive spatial modulation by symbol-level precoding: Design guidelines with or without intelligent reflecting surfaces 通过符号级预编码增强广义接收空间调制：有或没有智能反射面的设计指南

IF 7.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Digital Communications and Networks

Pub Date : 2025-08-01 DOI: 10.1016/j.dcan.2025.01.003

Lei Zhang , Miaowen Wen , Qiang Li , Guangyuan Zheng , Lixia Xiao

Existing Generalized Receive Spatial Modulation (GRSM) with Symbol-Level Precoding (SLP) forces the received signals (excluding noise) at unintended antennas to be zero, which restricts the generation of strong constructive interference to intended receive antennas and thus limits the performance improvement over conventional GRSM with Zero-Forcing (ZF) precoding. In this paper, we propose a novel GRSM-SLP scheme that relaxes the zero receive power constraint and achieves superior performance by integrating Intelligent Reflecting Surfaces (IRSs). Specifically, our advanced GRSM-RSLP jointly exploits SLP at the transmitter and passive beamforming at the IRS to maximize the power difference between intended and unintended receive antennas, where the received signals at unintended antennas are relaxed to lie in a sphere centered at origin with a preset radius that depends on the Signal-to-Noise Ratio (SNR) value. The precoding matrix and passive beamforming vectors are optimized alternately by considering both phase shift keying and quadrature amplitude modulation signaling. It is worth emphasizing that GRSM-RSLP is a universal solution, also applicable to systems without IRS, although it performs better in IRS-assisted systems. We finally conduct extensive simulations to prove the superiority of GRSM-RSLP over GRSM-ZF and GRSM-SLP. Simulation results show that the performance of GRSM-RSLP is significantly influenced by the number of unintended antennas, and the larger the number, the better its performance. In the best-case scenario, GRSM-RSLP can achieve SNR gains of up to 10.5 dB and 12.5 dB over GRSM-SLP and GRSM-ZF, respectively.

现有的带有符号级预编码（SLP）的广义接收空间调制（GRSM）将非预期天线处的接收信号（不含噪声）强制为零，这限制了对预期接收天线产生强建设性干扰，从而限制了采用零强制（ZF）预编码的GRSM性能的提高。在本文中，我们提出了一种新的GRSM-SLP方案，该方案放松了零接收功率约束，并通过集成智能反射面（IRSs）来获得优越的性能。具体来说，我们先进的GRSM-RSLP联合利用发射器处的SLP和IRS处的无源波束形成来最大限度地提高预期和非预期接收天线之间的功率差，其中非预期天线处的接收信号被放松到以原点为中心的球体中，该球体的半径取决于信噪比（SNR）值。通过相移键控和正交调幅信号交替优化预编码矩阵和无源波束形成矢量。值得强调的是，GRSM-RSLP是一个通用的解决方案，也适用于没有IRS的系统，尽管它在IRS辅助系统中表现更好。最后，我们进行了大量的仿真，以证明GRSM-RSLP优于GRSM-ZF和GRSM-SLP。仿真结果表明，GRSM-RSLP的性能受非预期天线数量的影响较大，且非预期天线数量越大，其性能越好。在最佳情况下，与GRSM-SLP和GRSM-ZF相比，GRSM-RSLP的信噪比增益分别可达10.5 dB和12.5 dB。

{"title":"Enhancing generalized receive spatial modulation by symbol-level precoding: Design guidelines with or without intelligent reflecting surfaces","authors":"Lei Zhang , Miaowen Wen , Qiang Li , Guangyuan Zheng , Lixia Xiao","doi":"10.1016/j.dcan.2025.01.003","DOIUrl":"10.1016/j.dcan.2025.01.003","url":null,"abstract":"<div><div>Existing Generalized Receive Spatial Modulation (GRSM) with Symbol-Level Precoding (SLP) forces the received signals (excluding noise) at unintended antennas to be zero, which restricts the generation of strong constructive interference to intended receive antennas and thus limits the performance improvement over conventional GRSM with Zero-Forcing (ZF) precoding. In this paper, we propose a novel GRSM-SLP scheme that relaxes the zero receive power constraint and achieves superior performance by integrating Intelligent Reflecting Surfaces (IRSs). Specifically, our advanced GRSM-RSLP jointly exploits SLP at the transmitter and passive beamforming at the IRS to maximize the power difference between intended and unintended receive antennas, where the received signals at unintended antennas are relaxed to lie in a sphere centered at origin with a preset radius that depends on the Signal-to-Noise Ratio (SNR) value. The precoding matrix and passive beamforming vectors are optimized alternately by considering both phase shift keying and quadrature amplitude modulation signaling. It is worth emphasizing that GRSM-RSLP is a universal solution, also applicable to systems without IRS, although it performs better in IRS-assisted systems. We finally conduct extensive simulations to prove the superiority of GRSM-RSLP over GRSM-ZF and GRSM-SLP. Simulation results show that the performance of GRSM-RSLP is significantly influenced by the number of unintended antennas, and the larger the number, the better its performance. In the best-case scenario, GRSM-RSLP can achieve SNR gains of up to 10.5 dB and 12.5 dB over GRSM-SLP and GRSM-ZF, respectively.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"11 4","pages":"Pages 1262-1270"},"PeriodicalIF":7.5,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144926717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Performance analysis of RIS-assisted dual-hop mixed FSO-RF UAV communication systems ris辅助双跳混合FSO-RF无人机通信系统性能分析

IF 7.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Digital Communications and Networks

Pub Date : 2025-08-01 DOI: 10.1016/j.dcan.2025.02.001

Donghyun Kim , Hwi Sung Park , Bang Chul Jung

In this paper, we investigate a Reconfigurable Intelligent Surface (RIS)-assisted Free-Space Optics–Radio Frequency (FSO–RF) mixed dual-hop communication system for Unmanned Aerial Vehicles (UAVs). In the first hop, a source UAV transmits data to a relay UAV using the FSO technique. In the second hop, the relay UAV forwards data to a destination Mobile Station (MS) via an RF channel, with the RIS enhancing coverage and performance. The relay UAV operates in a Decode-and-Forward (DF) mode. As the main contribution, we provide a mathematical performance analysis of the RIS-assisted FSO–RF mixed dual-hop UAV system, evaluating outage probability, Bit-Error Rate (BER), and average capacity. The analysis accounts for factors such as atmospheric attenuation, turbulence, geometric losses, and link interruptions caused by UAV hovering behaviors. To the best of our knowledge, this is the first theoretical investigation of RIS-assisted FSO–RF mixed dual-hop UAV communication systems. Our analytical results show strong agreement with Monte Carlo simulation outcomes. Furthermore, simulation results demonstrate that RIS significantly enhances the performance of UAV-aided mixed RF/FSO systems, although performance saturation is observed due to uncertainties stemming from UAV hovering behavior.

本文研究了一种用于无人机的可重构智能表面（RIS）辅助自由空间光学-射频（FSO-RF）混合双跳通信系统。在第一跳中，源无人机使用FSO技术向中继无人机传输数据。在第二跳中，中继无人机通过射频信道将数据转发到目标移动站（MS）， RIS增强了覆盖范围和性能。中继无人机以解码和转发（DF）模式操作。作为主要贡献，我们提供了ris辅助FSO-RF混合双跳无人机系统的数学性能分析，评估了中断概率，误码率（BER）和平均容量。该分析考虑了由无人机悬停行为引起的大气衰减、湍流、几何损失和链路中断等因素。据我们所知，这是ris辅助FSO-RF混合双跳无人机通信系统的第一个理论研究。我们的分析结果与蒙特卡罗模拟结果非常吻合。此外，仿真结果表明，RIS显著提高了无人机辅助混合RF/FSO系统的性能，尽管由于无人机悬停行为的不确定性导致性能饱和。

{"title":"Performance analysis of RIS-assisted dual-hop mixed FSO-RF UAV communication systems","authors":"Donghyun Kim , Hwi Sung Park , Bang Chul Jung","doi":"10.1016/j.dcan.2025.02.001","DOIUrl":"10.1016/j.dcan.2025.02.001","url":null,"abstract":"<div><div>In this paper, we investigate a Reconfigurable Intelligent Surface (RIS)-assisted Free-Space Optics–Radio Frequency (FSO–RF) mixed dual-hop communication system for Unmanned Aerial Vehicles (UAVs). In the first hop, a source UAV transmits data to a relay UAV using the FSO technique. In the second hop, the relay UAV forwards data to a destination Mobile Station (MS) via an RF channel, with the RIS enhancing coverage and performance. The relay UAV operates in a Decode-and-Forward (DF) mode. As the main contribution, we provide a mathematical performance analysis of the RIS-assisted FSO–RF mixed dual-hop UAV system, evaluating outage probability, Bit-Error Rate (BER), and average capacity. The analysis accounts for factors such as atmospheric attenuation, turbulence, geometric losses, and link interruptions caused by UAV hovering behaviors. To the best of our knowledge, this is the first theoretical investigation of RIS-assisted FSO–RF mixed dual-hop UAV communication systems. Our analytical results show strong agreement with Monte Carlo simulation outcomes. Furthermore, simulation results demonstrate that RIS significantly enhances the performance of UAV-aided mixed RF/FSO systems, although performance saturation is observed due to uncertainties stemming from UAV hovering behavior.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"11 4","pages":"Pages 1271-1279"},"PeriodicalIF":7.5,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144926718","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Environment-aware streaming media transmission method in high-speed mobile networks 高速移动网络中环境感知流媒体传输方法

IF 7.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Digital Communications and Networks

Pub Date : 2025-08-01 DOI: 10.1016/j.dcan.2025.03.007

Jia Guo, Jinqi Zhu, Xiang Li, Bowen Sun, Qian Gao, Weijia Feng

With technological advancements, high-speed rail has emerged as a prevalent mode of transportation. During travel, passengers exhibit a growing demand for streaming media services. However, the high-speed mobile networks environment poses challenges, including frequent base station handoffs, which significantly degrade wireless network transmission performance. Improving transmission efficiency in high-speed mobile networks and optimizing spatiotemporal wireless resource allocation to enhance passengers' media experiences are key research priorities. To address these issues, we propose an Adaptive Cross-Layer Optimization Transmission Method with Environment Awareness (ACOTM-EA) tailored for high-speed rail streaming media. Within this framework, we develop a channel quality prediction model utilizing Kalman filtering and an algorithm to identify packet loss causes. Additionally, we introduce a proactive base station handoff strategy to minimize handoff-related disruptions and optimize resource distribution across adjacent base stations. Moreover, this study presents a wireless resource allocation approach based on an enhanced genetic algorithm, coupled with an adaptive bitrate selection mechanism, to maximize passenger Quality of Experience (QoE). To evaluate the proposed method, we designed a simulation experiment and compared ACOTM-EA with established algorithms. Results indicate that ACOTM-EA improves throughput by 11% and enhances passengers' media experience by 5%.

随着科技的进步，高速铁路已经成为一种普遍的交通方式。在旅行中，乘客对流媒体服务的需求日益增长。然而，高速移动网络环境带来了挑战，包括频繁的基站切换，这大大降低了无线网络的传输性能。提高高速移动网络的传输效率，优化无线资源的时空分配，以增强乘客的媒体体验是研究的重点。为了解决这些问题，我们提出了一种针对高铁流媒体的环境意识自适应跨层优化传输方法（ACOTM-EA）。在这个框架内，我们开发了一个信道质量预测模型，利用卡尔曼滤波和一种算法来识别数据包丢失的原因。此外，我们引入了一种主动的基站切换策略，以最大限度地减少与切换相关的中断，并优化相邻基站之间的资源分配。此外，本研究提出了一种基于增强型遗传算法的无线资源分配方法，结合自适应比特率选择机制，以最大限度地提高乘客体验质量（QoE）。为了评估所提出的方法，我们设计了一个仿真实验，并将ACOTM-EA与已有算法进行了比较。结果表明，ACOTM-EA提高了11%的吞吐量，提高了5%的乘客媒体体验。

{"title":"Environment-aware streaming media transmission method in high-speed mobile networks","authors":"Jia Guo, Jinqi Zhu, Xiang Li, Bowen Sun, Qian Gao, Weijia Feng","doi":"10.1016/j.dcan.2025.03.007","DOIUrl":"10.1016/j.dcan.2025.03.007","url":null,"abstract":"<div><div>With technological advancements, high-speed rail has emerged as a prevalent mode of transportation. During travel, passengers exhibit a growing demand for streaming media services. However, the high-speed mobile networks environment poses challenges, including frequent base station handoffs, which significantly degrade wireless network transmission performance. Improving transmission efficiency in high-speed mobile networks and optimizing spatiotemporal wireless resource allocation to enhance passengers' media experiences are key research priorities. To address these issues, we propose an Adaptive Cross-Layer Optimization Transmission Method with Environment Awareness (ACOTM-EA) tailored for high-speed rail streaming media. Within this framework, we develop a channel quality prediction model utilizing Kalman filtering and an algorithm to identify packet loss causes. Additionally, we introduce a proactive base station handoff strategy to minimize handoff-related disruptions and optimize resource distribution across adjacent base stations. Moreover, this study presents a wireless resource allocation approach based on an enhanced genetic algorithm, coupled with an adaptive bitrate selection mechanism, to maximize passenger Quality of Experience (QoE). To evaluate the proposed method, we designed a simulation experiment and compared ACOTM-EA with established algorithms. Results indicate that ACOTM-EA improves throughput by 11% and enhances passengers' media experience by 5%.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"11 4","pages":"Pages 992-1006"},"PeriodicalIF":7.5,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144926834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A knowledge graph-based reinforcement learning approach for cooperative caching in MEC-enabled heterogeneous networks 基于知识图的异构网络协同缓存强化学习方法

IF 7.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Digital Communications and Networks

Pub Date : 2025-08-01 DOI: 10.1016/j.dcan.2024.12.006

Dan Wang, Yalu Bai, Bin Song

Existing wireless networks are flooded with video data transmissions, and the demand for high-speed and low-latency video services continues to surge. This has brought with it challenges to networks in the form of congestion as well as the need for more resources and more dedicated caching schemes. Recently, Multi-access Edge Computing (MEC)-enabled heterogeneous networks, which leverage edge caches for proximity delivery, have emerged as a promising solution to all of these problems. Designing an effective edge caching scheme is critical to its success, however, in the face of limited resources. We propose a novel Knowledge Graph (KG)-based Dueling Deep Q-Network (KG-DDQN) for cooperative caching in MEC-enabled heterogeneous networks. The KG-DDQN scheme leverages a KG to uncover video relations, providing valuable insights into user preferences for the caching scheme. Specifically, the KG guides the selection of related videos as caching candidates (i.e., actions in the DDQN), thus providing a rich reference for implementing a personalized caching scheme while also improving the decision efficiency of the DDQN. Extensive simulation results validate the convergence effectiveness of the KG-DDQN, and it also outperforms baselines regarding cache hit rate and service delay.

现有的无线网络充斥着视频数据传输，对高速和低延迟视频服务的需求持续激增。这给网络带来了拥堵的挑战，也需要更多的资源和更专用的缓存方案。最近，支持多访问边缘计算（MEC）的异构网络，利用边缘缓存进行近距离传输，已经成为解决所有这些问题的有希望的解决方案。然而，在资源有限的情况下，设计一个有效的边缘缓存方案是其成功的关键。我们提出了一种新的基于知识图（KG）的Dueling Deep Q-Network (KG- ddqn)，用于支持mec的异构网络中的协同缓存。KG- ddqn方案利用KG来发现视频关系，为用户对缓存方案的偏好提供有价值的见解。具体来说，KG指导选择相关视频作为缓存候选（即DDQN中的动作），从而为实现个性化缓存方案提供了丰富的参考，同时也提高了DDQN的决策效率。大量的仿真结果验证了KG-DDQN的收敛有效性，并且在缓存命中率和服务延迟方面也优于基线。

{"title":"A knowledge graph-based reinforcement learning approach for cooperative caching in MEC-enabled heterogeneous networks","authors":"Dan Wang, Yalu Bai, Bin Song","doi":"10.1016/j.dcan.2024.12.006","DOIUrl":"10.1016/j.dcan.2024.12.006","url":null,"abstract":"<div><div>Existing wireless networks are flooded with video data transmissions, and the demand for high-speed and low-latency video services continues to surge. This has brought with it challenges to networks in the form of congestion as well as the need for more resources and more dedicated caching schemes. Recently, Multi-access Edge Computing (MEC)-enabled heterogeneous networks, which leverage edge caches for proximity delivery, have emerged as a promising solution to all of these problems. Designing an effective edge caching scheme is critical to its success, however, in the face of limited resources. We propose a novel Knowledge Graph (KG)-based Dueling Deep Q-Network (KG-DDQN) for cooperative caching in MEC-enabled heterogeneous networks. The KG-DDQN scheme leverages a KG to uncover video relations, providing valuable insights into user preferences for the caching scheme. Specifically, the KG guides the selection of related videos as caching candidates (i.e., actions in the DDQN), thus providing a rich reference for implementing a personalized caching scheme while also improving the decision efficiency of the DDQN. Extensive simulation results validate the convergence effectiveness of the KG-DDQN, and it also outperforms baselines regarding cache hit rate and service delay.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"11 4","pages":"Pages 1237-1245"},"PeriodicalIF":7.5,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144926715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

FlyCache: Recommendation-driven edge caching architecture for full life cycle of video streaming FlyCache：推荐驱动的边缘缓存架构，用于视频流的全生命周期

IF 7.5 2区计算机科学 Q1 TELECOMMUNICATIONS

Digital Communications and Networks

Pub Date : 2025-08-01 DOI: 10.1016/j.dcan.2025.01.001

Shaohua Cao , Quancheng Zheng , Zijun Zhan , Yansheng Yang , Huaqi Lv , Danyang Zheng , Weishan Zhang

With the rapid development of 5G technology, the proportion of video traffic on the Internet is increasing, bringing pressure on the network infrastructure. Edge computing technology provides a feasible solution for optimizing video content distribution. However, the limited edge node cache capacity and dynamic user requests make edge caching more complex. Therefore, we propose a recommendation-driven edge Caching network architecture for the Full life cycle of video streaming (FlyCache) designed to improve users' Quality of Experience (QoE) and reduce backhaul traffic consumption. FlyCache implements intelligent caching management across three key stages: before-playback, during-playback, and after-playback. Specifically, we introduce a cache placement policy for the before-playback stage, a dynamic prefetching and cache admission policy for the during-playback stage, and a progressive cache eviction policy for the after-playback stage. To validate the effectiveness of FlyCache, we developed a user behavior-driven edge caching simulation framework incorporating recommendation mechanisms. Experiments conducted on the MovieLens and synthetic datasets demonstrate that FlyCache outperforms other caching strategies in terms of byte hit rate, backhaul traffic, and delayed startup rate.

随着5G技术的快速发展，互联网上视频流量的比例越来越大，给网络基础设施带来了压力。边缘计算技术为优化视频内容分发提供了可行的解决方案。然而，有限的边缘节点缓存容量和动态用户请求使得边缘缓存更加复杂。因此，我们提出了一种推荐驱动的边缘缓存网络架构，用于视频流的全生命周期（FlyCache），旨在提高用户的体验质量（QoE）并减少回程流量消耗。FlyCache在三个关键阶段实现智能缓存管理：播放前、播放期间和播放后。具体来说，我们为播放前阶段引入了一个缓存放置策略，为播放期间阶段引入了一个动态预取和缓存准入策略，并为播放后阶段引入了一个渐进的缓存清除策略。为了验证FlyCache的有效性，我们开发了一个包含推荐机制的用户行为驱动的边缘缓存模拟框架。在MovieLens和合成数据集上进行的实验表明，FlyCache在字节命中率、回程流量和延迟启动率方面优于其他缓存策略。

{"title":"FlyCache: Recommendation-driven edge caching architecture for full life cycle of video streaming","authors":"Shaohua Cao , Quancheng Zheng , Zijun Zhan , Yansheng Yang , Huaqi Lv , Danyang Zheng , Weishan Zhang","doi":"10.1016/j.dcan.2025.01.001","DOIUrl":"10.1016/j.dcan.2025.01.001","url":null,"abstract":"<div><div>With the rapid development of 5G technology, the proportion of video traffic on the Internet is increasing, bringing pressure on the network infrastructure. Edge computing technology provides a feasible solution for optimizing video content distribution. However, the limited edge node cache capacity and dynamic user requests make edge caching more complex. Therefore, we propose a recommendation-driven edge <strong>C</strong>aching network architecture for the <strong>F</strong>ull <strong>l</strong>ife c<strong>y</strong>cle of video streaming (FlyCache) designed to improve users' Quality of Experience (QoE) and reduce backhaul traffic consumption. FlyCache implements intelligent caching management across three key stages: before-playback, during-playback, and after-playback. Specifically, we introduce a cache placement policy for the before-playback stage, a dynamic prefetching and cache admission policy for the during-playback stage, and a progressive cache eviction policy for the after-playback stage. To validate the effectiveness of FlyCache, we developed a user behavior-driven edge caching simulation framework incorporating recommendation mechanisms. Experiments conducted on the MovieLens and synthetic datasets demonstrate that FlyCache outperforms other caching strategies in terms of byte hit rate, backhaul traffic, and delayed startup rate.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"11 4","pages":"Pages 961-974"},"PeriodicalIF":7.5,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144925845","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0