Ad Hoc Networks最新文献_第5页

AoI-Guaranteed UAV Crowdsensing: A UGV-assisted deep reinforcement learning approach aoi保证无人机群体感知：一种ugv辅助的深度强化学习方法

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-03-06 DOI: 10.1016/j.adhoc.2025.103805

Shoulan Chen, Kaimin Wei, Tingrui Pei, Saiqin Long

{"title":"AoI-Guaranteed UAV Crowdsensing: A UGV-assisted deep reinforcement learning approach","authors":"Shoulan Chen, Kaimin Wei, Tingrui Pei, Saiqin Long","doi":"10.1016/j.adhoc.2025.103805","DOIUrl":"10.1016/j.adhoc.2025.103805","url":null,"abstract":"<div><div>Unmanned Aerial Vehicles (UAVs), with their excellent environmental adaptability and flexible maneuverability, are increasingly being deployed in smart city applications for data collection. The Age of Information (AoI) is essential in these applications. Prior research on AoI has predominantly focused on static task scenarios, often overlooking the dynamics of task arrivals. For this reason, we propose an unmanned ground vehicle (UGV)-assisted deep reinforcement learning approach (U-DRL), which employs key factors affecting AoI to mitigate the AoI of data in dynamic task scenarios. We use EfficientNet, a state-of-the-art neural network architecture, to effectively extract features from dynamic task arrival scenarios. Based on these features, we utilize an intrinsic reward module (IRM) to swiftly process the input encapsulating global information, optimizing flight paths and enabling the exploration of expanded areas by UAVs. In addition, we leverage the active mobility of UGVs to recharge UAVs timely, thereby maximizing the flight time of UAVs. Through an extensive series of experiments, we validate the effectiveness of U-DRL. The experimental results demonstrate that U-DRL outperforms comparative algorithms in key performance metrics, significantly reducing the AoI of data, with breakthroughs of 54.14% and 67.90% in two real-world maps.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"173 ","pages":"Article 103805"},"PeriodicalIF":4.4,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Energy-efficient Nonuniform Cluster-based Routing Protocol with Q-Learning for UASNs 基于q -学习的高效非均匀集群路由协议

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-03-05 DOI: 10.1016/j.adhoc.2025.103797

Zhigang Jin, Ying Wang, Jiawei Liang, Haoyong Li, Yishan Su

{"title":"Energy-efficient Nonuniform Cluster-based Routing Protocol with Q-Learning for UASNs","authors":"Zhigang Jin, Ying Wang, Jiawei Liang, Haoyong Li, Yishan Su","doi":"10.1016/j.adhoc.2025.103797","DOIUrl":"10.1016/j.adhoc.2025.103797","url":null,"abstract":"<div><div>Underwater Acoustic Sensor Networks (UASNs) are widely used in various fields. The limited energy of underwater nodes and the difficulty of replenishment constrain the lifetime of UASNs. Thus, it is important to effectively balance energy consumption and design a routing protocol that ensures efficient data transmission and extends network lifetime. Cluster routing protocol is widely recognized as an energy efficient strategy for UASNs. However, it faces challenges including “hotspot” issues caused by nodes frequently acting as cluster heads (CHs) and forwarding packets, as well as energy inefficiency resulting from packet conflicts and redundant transmissions. Therefore, we propose an Energy-efficient Nonuniform Cluster-based Routing Protocol with Q-Learning (ENCRQ) to balance energy consumption and improve packet forwarding efficiency. In the CH election phase, a “CH competitiveness” function is created based on node weighted density and residual energy. Nodes outside the sink neighborhood adaptively compete for CHs based on this function, aiming to achieve an uneven distribution of CHs and balance energy consumption. Meanwhile, nodes within the sink neighborhood remain sleeping to further reduce energy consumption. In the inter-cluster routing phase, the forwarding area is hierarchically divided based on node depth and distance to the sink node. The optimal forwarding area is adaptively adjusted to form the next-hop candidate set. On this basis, holding time is designed for candidate nodes based on Q-Learning technique to prioritize forwarding, minimizing packet conflicts and redundant transmissions, thereby enhancing network transmission efficiency. Simulation results show that compared with LEACH, QELAR and QHUC, ENCRQ has significant improvement in terms of network lifetime, energy balance and energy efficiency.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"173 ","pages":"Article 103797"},"PeriodicalIF":4.4,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143577564","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

WSN-based wildlife localization framework in dense forests through optimization techniques 基于wsn的密林野生动物定位框架优化技术

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-03-05 DOI: 10.1016/j.adhoc.2025.103815

Mauricio González-Palacio , Liliana González-Palacio , José Aguilar , Long Bao Le

{"title":"WSN-based wildlife localization framework in dense forests through optimization techniques","authors":"Mauricio González-Palacio , Liliana González-Palacio , José Aguilar , Long Bao Le","doi":"10.1016/j.adhoc.2025.103815","DOIUrl":"10.1016/j.adhoc.2025.103815","url":null,"abstract":"<div><div>Wildlife in forests is threatened by land use changes, requiring tracking to characterize movement patterns and propose preservation policies. The positioning uses GPS-based collars (End Nodes (ENs)), which are energy-consuming and require a line of sight with the satellites, a condition rarely fulfilled in forests. It motivates using Wireless Sensor Networks, which rely on the Received Signal Strength Indicator (RSSI) and Time of Flight (ToF) to determine the distance between the EN and Anchor Nodes (ANs) with known positions and, subsequently, apply trilateration. However, existing approaches may have significant errors due to multipath and shadow fading caused by dense canopies. Thus, this paper proposes a three-step framework to address these limitations. First, it optimizes the ANs positions, increasing the redundancy of trilateration and coverage, enhancing the likelihood of accurate localization, and ensuring sufficient data to mitigate adverse channel effects. Second, it presents an optimization problem that minimizes the variance of distance estimation since the associated errors can increase exponentially. Finally, it scores the ANs with the most reliable position estimations to mitigate the effects of outliers. Numerical studies show that our optimized AN placement improves coverage by 25% compared to random or equispaced strategies. The distance estimator achieves a Mean Average Percentage Error (MAPE) below 7%, outperforming the Wiener-based estimator at 20%. Finally, our scoring method reduced MAPE to 5.53% with a standard deviation of 7.15% compared with the median strategy that achieved 9.66% and a standard deviation of 15.87% when ten ANs are placed in a region of 100 km<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span>.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"173 ","pages":"Article 103815"},"PeriodicalIF":4.4,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143577685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Attention model-driven MADDPG algorithm for delay and cost-aware placement of service function chains in 5G 关注模型驱动的madpg算法用于5G业务功能链的延迟和成本感知布局

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-03-04 DOI: 10.1016/j.adhoc.2025.103806

Joy Munshi , Sumaya Sultana , Md. Jahid Hassan , Palash Roy , Md. Abdur Razzaque , Abdulhameed Alelaiwi , Md. Zia Uddin , Mohammad Mehedi Hassan

{"title":"Attention model-driven MADDPG algorithm for delay and cost-aware placement of service function chains in 5G","authors":"Joy Munshi , Sumaya Sultana , Md. Jahid Hassan , Palash Roy , Md. Abdur Razzaque , Abdulhameed Alelaiwi , Md. Zia Uddin , Mohammad Mehedi Hassan","doi":"10.1016/j.adhoc.2025.103806","DOIUrl":"10.1016/j.adhoc.2025.103806","url":null,"abstract":"<div><div>The rapidly expanding applications of 5G networks necessitate strategic placement of Virtual Network Functions (VNFs) within Service Function Chains (SFCs) to minimize placement costs while delivering real-time services to users. The dual objectives of this efficient placement strategy are to simultaneously reduce resource usage costs and application service delays in the 5G network. Previous studies have limitations, typically constrained by fixed resource costs or by adopting a greedy approach for resource selection from nearby nodes. In this paper, we introduce a multi-objective linear programming (MOLP) based optimization framework designed for the placement of VNFs in SFC requests, considering a real-time pricing scheme of the resources and the demands of user applications. This framework allows for the analysis of the boundary performances regarding cost and delay, facilitating a balanced trade-off between the two. Given that this problem is proven to be NP-hard in large networks, we have also developed a Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm, which leverages an attention model-based approach for the placement of SFC VNFs. This method focuses on neighboring nodes to help agents reduce the complexity of the solution and effectively capture the dynamic nature of the network environment. Simulation experiments demonstrate that our proposed system model surpasses existing state-of-the-art approaches in terms of resource placement cost and service latency.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"173 ","pages":"Article 103806"},"PeriodicalIF":4.4,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143562351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Sum rate maximization for RSMA aided small cells edge users using meta-learning variational quantum algorithm 基于元学习变分量子算法的RSMA辅助小蜂窝边缘用户和速率最大化

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-02-25 DOI: 10.1016/j.adhoc.2025.103802

Deepak Gupta, Ishan Budhiraja, Bireshwar Dass Mazumdar

{"title":"Sum rate maximization for RSMA aided small cells edge users using meta-learning variational quantum algorithm","authors":"Deepak Gupta, Ishan Budhiraja, Bireshwar Dass Mazumdar","doi":"10.1016/j.adhoc.2025.103802","DOIUrl":"10.1016/j.adhoc.2025.103802","url":null,"abstract":"<div><div>This study aims to enhance wireless communication efficiency by maximizing the sum rate through optimized rate allocation and power control for edge users in small cell networks. Small cells improve coverage and bandwidth in congested networks but face challenges such as interference and limited resources, particularly for users at the cell edge. This article introduces a Meta-LVQA technique to boost system throughput by optimizing rate allocation and power control, ensuring equitable resource distribution among users, and managing in-cell interference using Rate Splitting Multiple Access (RSMA). The problem is initially framed using classical methods. However, this manuscript employs the Meta-Learning Variational Quantum Algorithm (Meta-LVQA) to optimize the sum rate. Therefore, it is necessary to transform the classical equation into an equivalent quantum equation using a quantum circuit. Numerical results demonstrate that RSMA with Meta-LVQA consistently outperforms all other methods. Specifically, RSMA with Meta-LVQA surpasses RSMA with Variational Quantum Algorithm (VQA), NOMA with Meta-LVQA, and NOMA with VQA by <span><math><mrow><mn>3</mn><mo>.</mo><mn>91</mn><mtext>%</mtext><mo>,</mo><mn>10</mn><mo>.</mo><mn>11</mn><mtext>%</mtext><mo>,</mo></mrow></math></span> and <span><math><mrow><mn>31</mn><mo>.</mo><mn>99</mn><mtext>%</mtext><mo>,</mo></mrow></math></span> respectively, when the sum rate is measured against a minimum rate requirement of 1.15 Mbps at SCEU1. When computing the sum rate using four SCEUs, RSMA with Meta-LVQA outperforms RSMA with VQA, NOMA with Meta-LVQA, and NOMA with VQA by <span><math><mrow><mn>13</mn><mo>.</mo><mn>91</mn><mtext>%</mtext><mo>,</mo><mn>18</mn><mo>.</mo><mn>63</mn><mtext>%</mtext><mo>,</mo></mrow></math></span> and <span><math><mrow><mn>43</mn><mo>.</mo><mn>06</mn><mtext>%</mtext><mo>,</mo></mrow></math></span> respectively.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"172 ","pages":"Article 103802"},"PeriodicalIF":4.4,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Reliability and bandwidth aware routing in SDN-based fog computing for IoT applications 物联网应用中基于sdn的雾计算的可靠性和带宽感知路由

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-02-25 DOI: 10.1016/j.adhoc.2025.103803

Parisa Valizadeh, Mohammad Hossein Yaghmaee, Yasser Sedaghat

{"title":"Reliability and bandwidth aware routing in SDN-based fog computing for IoT applications","authors":"Parisa Valizadeh, Mohammad Hossein Yaghmaee, Yasser Sedaghat","doi":"10.1016/j.adhoc.2025.103803","DOIUrl":"10.1016/j.adhoc.2025.103803","url":null,"abstract":"<div><div>Software-Defined Networking (SDN) and fog computing are pivotal in supporting computationally intensive tasks within Internet of Things (IoT) applications, enhancing efficiency and reliability. However, many IoT applications are constrained by communication paths prone to link failures, necessitating robust fault tolerance techniques to ensure reliable traffic flow. In particular, real-time IoT applications demand stringent reliability and bandwidth requirements (constraints), which are challenging to meet simultaneously. Although previous research has investigated SDN-based routing to improve reliability, developing a routing algorithm that satisfies both reliability and bandwidth constraints remains an NP-hard problem. In this paper, we propose two novel routing algorithms: Reliability Aware Bandwidth constrained Routing (RABR) and Reliability and Bandwidth Constrained Routing (RBCR), specifically designed for SDN-enabled environments. Our approach prioritizes service reliability while meeting strict reliability and bandwidth criteria. The proposed solution integrates several phases, including reliability aware and bandwidth constrained path routing and flow duplication through parallel/hybrid and sequential routing methods. Furthermore, we introduce a greedy heuristic algorithm, implemented by the SDN controller with an efficient time complexity. Simulation results demonstrate that our algorithm surpasses state-of-the-art approaches in critical metrics such as reliability, reliability-bandwidth success rate, and Runtime. As such, our solution emerges as a robust choice for SDN-enabled IoT environments.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"172 ","pages":"Article 103803"},"PeriodicalIF":4.4,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511460","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Collaborative multi-target-tracking via graph-based deep reinforcement learning in UAV swarm networks 基于图的无人机群网络深度强化学习协同多目标跟踪

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-02-23 DOI: 10.1016/j.adhoc.2025.103801

Qianchen Ren , Yuanyu Wang, Han Liu, Yu Dai, Wenhui Ye, Yuliang Tang

{"title":"Collaborative multi-target-tracking via graph-based deep reinforcement learning in UAV swarm networks","authors":"Qianchen Ren , Yuanyu Wang, Han Liu, Yu Dai, Wenhui Ye, Yuliang Tang","doi":"10.1016/j.adhoc.2025.103801","DOIUrl":"10.1016/j.adhoc.2025.103801","url":null,"abstract":"<div><div>Due to unmanned aerial vehicles (UAVs) flexibility and affordability, the UAVs swarm network (USNET) is widely used for various complex, challenging tasks such as tracking, surveillance, and monitoring, and the key to accomplishing these tasks lies in the capabilities of the UAVs to collaborate. However, due to the high complexity of real-time information sharing and task cooperation among numerous UAVs in the USNET, it poses significant challenges for multi-target tracking in complex scenarios. In this paper, we study the collaborative multi-target-tracking (CMTT) problem based on the USNET and aim to improve task collaboration capabilities within the USNET. We first design a heuristic target assignment algorithm to simplify the CMTT problem into the optimal topology control problem of the USNET, and then propose an integrated sensing and communication multi-agent reinforcement learning for the USNET topology control algorithm (ISAC-TC) to maximize the collaborative tracking performance of UAVs within the USNET. Specifically, in heterogeneous observation graph representation, the ISAC-TC first utilizes a graph neural network to solve the time-varying dimensions of the agent observation space. Then, an encoder–decoder-based information sharing module is used to achieve efficient communication between agents in the CMTT tasks. Simulation results show that the proposed scheme achieves a higher tracking success rate and tracking fairness than other baselines.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"172 ","pages":"Article 103801"},"PeriodicalIF":4.4,"publicationDate":"2025-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143510402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An optimizing geo-distributed edge layering with double deep Q-networks for predictive mobility-aware offloading in mobile edge computing 一种基于双深度q网络的优化地理分布边缘分层，用于移动边缘计算中预测移动感知卸载

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-02-21 DOI: 10.1016/j.adhoc.2025.103804

Amir Masoud Rahmani , Amir Haider , Saqib Ali , Shakiba Rajabi , Farhad Soleimanian Gharehchopogh , Parisa Khoshvaght , Mehdi Hosseinzadeh

{"title":"An optimizing geo-distributed edge layering with double deep Q-networks for predictive mobility-aware offloading in mobile edge computing","authors":"Amir Masoud Rahmani , Amir Haider , Saqib Ali , Shakiba Rajabi , Farhad Soleimanian Gharehchopogh , Parisa Khoshvaght , Mehdi Hosseinzadeh","doi":"10.1016/j.adhoc.2025.103804","DOIUrl":"10.1016/j.adhoc.2025.103804","url":null,"abstract":"<div><div>In Mobile Edge Computing (MEC), the exponential growth of connected devices and user mobility presents significant challenges in optimizing task offloading, reducing latency, and energy usage. Predictive and adaptive task offloading mechanisms are essential as devices become more mobile and generate demanding tasks. Current methods, such as local computing and random scheduling, struggle to efficiently manage resources and maintain Quality of Service (QoS) in dynamic environments. This paper proposes an optimized Geographic Distributed Edge Layering (GDEL) architecture integrated with Double Deep Q-Networks (DDQN) to enable predictive, mobility-aware offloading. Our model leverages reinforcement learning through a Markov Decision Process (MDP) framework to dynamically allocate resources across distributed edge nodes, making optimal decisions on whether to offload or process tasks locally based on real-time conditions. Simulations show that our model outperforms other methods in key performance metrics, reducing task completion time by up to 48 %, lowering offloading decision latency by 49.3 %, and decreasing energy consumption by 26.5 % compared to traditional models.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"172 ","pages":"Article 103804"},"PeriodicalIF":4.4,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143480670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Coexistence of NR-U operators in multichannel scenarios: Fair cooperation or endless struggle for channel resources 多渠道场景下NR-U运营商的共存：公平合作还是渠道资源的无休止争夺

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-02-20 DOI: 10.1016/j.adhoc.2025.103798

Vyacheslav Loginov, Aleksandr Troegubov, Andrey Lyakhov, Evgeny Khorov

引用次数: 0

QRAVDR: A deep Q-learning-based RSU-Assisted Video Data Routing algorithm for VANETs 基于深度q学习的rsu辅助vanet视频数据路由算法

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-02-19 DOI: 10.1016/j.adhoc.2025.103790

Huahong Ma, Shuangjin Li, Honghai Wu, Ling Xing, Xiaohui Zhang

{"title":"QRAVDR: A deep Q-learning-based RSU-Assisted Video Data Routing algorithm for VANETs","authors":"Huahong Ma, Shuangjin Li, Honghai Wu, Ling Xing, Xiaohui Zhang","doi":"10.1016/j.adhoc.2025.103790","DOIUrl":"10.1016/j.adhoc.2025.103790","url":null,"abstract":"<div><div>With the rapid development of Internet of Vehicles (IoV) and the increasing demand for video services, video data routing in Vehicular Ad-hoc Networks (VANETs) has become a popular research topic. Challenges such as real-time transmission demands, instability of wireless channels, and high network topology dynamics significantly affect video transmission quality. Although some related studies have used multipath transmission and priority scheduling to improve performance, they usually require accurate models or use a static approach to make decisions, which lack the learning mechanism and the ability to adapt to the dynamic network, resulting in poor video reconstruction quality. To address the above problems, A Deep Q-Learning (DQL)-based RoadSide Unit (RSU)-Assisted Video Data Routing algorithm, named QRAVDR, is proposed for urban VANET environments. The algorithm coordinates the forwarding road segments of different layers of Scalable Video Coding (SVC) video data at the RSUs through DQL, maximizing the video quality at the receiver while minimizing the transmission delay. The Neutrosophic Set Analytic Hierarchy Process method is applied to select the best relay vehicle within the road segments, which guarantees the transmission of keyframes and improves the decoding possibility. Extensive simulation experiments on QRAVDR and other existing algorithms have been conducted using NS-2 employing simulated datasets. The results show that QRAVDR achieves a better overall performance in improving the average frame delivery ratio by about 8.02%, reducing the average end-to-end delay by approximately 9.61%, and improving the average peak signal-to-noise ratio by roughly 7.97%.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"171 ","pages":"Article 103790"},"PeriodicalIF":4.4,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143453558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0