Ad Hoc Networks最新文献

{"title":"SDN-Qache: A Q-Learning-based Hybrid Caching Scheme in SDN-based Mobile Named Data Networks (MNDN)","authors":"Shahid Md. Asif Iqbal ,&nbsp;Asaduzzaman ,&nbsp;Mohammad Ashfak Habib","doi":"10.1016/j.adhoc.2025.104054","DOIUrl":"10.1016/j.adhoc.2025.104054","url":null,"abstract":"<div><div>In-network caching and name-based forwarding features of Named <em>Data</em> Networks (<em>NDN</em>) enable it to counteract the unstable connectivity and resource constraints problems of Mobile Ad Hoc Networks (<em>MANET</em>). The topology-aware and hybrid <em>NDN</em> caching schemes often struggle to adapt to dynamic topology changes in <em>NDN</em>-based <em>MANET</em>. Moreover, the decentralized nature of <em>MANET</em> leads the existing schemes, especially the hybrid ones that install multiple caching schemes in a node and select the best option at any given time, to become stuck with the local best scheme. Software-defined networking (<em>SDN</em>) is an approach that decouples and centralizes the control planes of nodes from the data planes. The centralized controller is connected to each node and is aware of the underlying cache state of each node. It can be programmed to recommend a global caching strategy to the nodes. Under such <em>SDN</em>-based <em>NDN</em> circumstances, the hybrid caching schemes that utilize identical parameters, such as hop-distance, to make caching decisions or that operate the cache based on the local best solution may undermine the efficient content retrieval in <em>MANET</em>s. A new hybrid caching strategy that can combine content and node attributes to make caching decisions under changing network contexts, such as varying resource availability or traffic load, is inevitable. Such a hybrid strategy can scale well in terms of network resource usage and optimizing network performance. In this direction, we propose a reinforcement learning-based hybrid caching scheme, namely <em>SDN-Qache</em>, that equips each router with a content-attribute-based and a node-attribute-based caching schemes and uses the <em>Q</em>-learning algorithm to pick the most suitable local caching option. The nodes communicate their local optimal caching choices to the controller, which utilizes the information to compute a global optimal solution and recommend it back to the nodes. Simulation reveals that <em>SDN-Qache</em> improves the <em>PDR</em> by approximately 10%, content retrieval latency by approximately 40%, retransmission ratio by approximately 8.5%, and cache replacement rate by approximately 70% compared to the reference strategies.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"180 ","pages":"Article 104054"},"PeriodicalIF":4.8,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145322001","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}

{"title":"A multi-AUV adaptive collaborative target coverage algorithm for unknown environment","authors":"Jie Li ,&nbsp;Qing Chen","doi":"10.1016/j.adhoc.2025.104033","DOIUrl":"10.1016/j.adhoc.2025.104033","url":null,"abstract":"<div><div>With the rapid development and popularisation of autonomous underwater vehicle (AUV) technology, AUVs are increasingly being used in target coverage. Due to the limited communication range and power of AUV, collaboration among AUV swarm is particularly critical, especially in unknown environment. To solve this problem, we propose a multi-AUV adaptive cooperative target coverage algorithm for unknown environment. First, we design a greedy-based multi-AUV adaptive cooperative detection mechanism, utilising a potential field-based AUV force model to achieve efficient detection. Second, a multi-AUV adaptive connectivity mechanism based on potential field is introduced to maintain the connectivity of the AUV network. Simulation results demonstrate the validity of the proposed algorithm. Compared to other methods, our algorithm achieves target coverage under unknown and known target scenarios, ensures energy balance within the AUV network throughout the coverage process, and extends the lifetime of the network.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"180 ","pages":"Article 104033"},"PeriodicalIF":4.8,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145269959","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}

{"title":"An energy-aware distributed federated soft actor-critic framework for intelligent task offloading in vehicular mobile edge computing networks","authors":"Komeil Moghaddasi ,&nbsp;Raja Jurdak","doi":"10.1016/j.adhoc.2025.104043","DOIUrl":"10.1016/j.adhoc.2025.104043","url":null,"abstract":"<div><div>Today, modern intelligent transportation systems increasingly depend on Mobile Edge Computing (MEC) to process real-time data for perception and cooperative driving. However, meeting strict low-latency requirements is challenging because Electric Vehicles (EVs) have limited battery capacity, and must carefully balance the energy used for computation and communication with preserving driving range. While each operation may consume only a small amount of power, their combined effect can substantially reduce how far an EV can travel on a single charge. In this study, we introduce a distributed Federated Soft Actor–Critic (Fed-SAC) framework designed specifically for intelligent, energy-aware, low-latency task offloading in dynamic vehicular MEC networks. Our approach enables each agent to learn privacy-preserving offloading policies in situ, jointly optimizing execution location, transmit power, and offloading ratio through a multi-dimensional discrete action space, addressing both scalability and adaptability under strict latency and energy constraints. Simulations of mobility, wireless channels, and deadline-sensitive workloads show Fed-SAC reduces mean task delay by 77 %, energy use by 89 %, and combined cost by 93 % compared to state-of-the-art methods.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"180 ","pages":"Article 104043"},"PeriodicalIF":4.8,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145269961","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}

{"title":"M2PFSL: Multi-task and multi-modal IoMT healthcare system via personalized split federated learning","authors":"Bohan Hu ,&nbsp;Yuhang Li ,&nbsp;Yinghao Zhang","doi":"10.1016/j.adhoc.2025.104032","DOIUrl":"10.1016/j.adhoc.2025.104032","url":null,"abstract":"<div><div>This paper presents M<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span>PFSL, a novel Internet of Medical Things (IoMT) system that revolutionizes health monitoring through integrated multi-task multi-modal personalized processing. Unlike conventional approaches that address computational distribution, communication efficiency, and personalization as separate challenges, our unified framework leverages their synergistic relationships to achieve superior performance while dramatically reducing communication overhead. We develop a distributed processing paradigm where edge devices perform modality-level compression followed by cross-attention fusion to generate compact multi-modal features, while cloud servers execute intensive personalized multi-task analytics. Our systematic two-phase training methodology first establishes robust global models through iterative federated split learning across multiple communication rounds, then adapts these models to individual patient characteristics through GAN-based personalization in compressed feature spaces. This approach enables personalized model adaptation without compromising global knowledge or increasing communication costs, representing a fundamental advance in distributed healthcare system development. The strategic architecture achieves substantial communication overhead reduction while maintaining diagnostic quality, making continuous health monitoring feasible in bandwidth-constrained environments. Extensive experimental validation demonstrates consistent and substantial performance improvements across multiple datasets and compression ratios, with the discovered task-specific compression sensitivity hierarchy providing critical insights for adaptive IoMT system design.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"180 ","pages":"Article 104032"},"PeriodicalIF":4.8,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145269957","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}

{"title":"Connection in the air: QoE-centric multi-hop transmission in UAV-assisted emergency communication system","authors":"Weihao Sun ,&nbsp;Hai Wang ,&nbsp;Zhen Qin","doi":"10.1016/j.adhoc.2025.104051","DOIUrl":"10.1016/j.adhoc.2025.104051","url":null,"abstract":"<div><div>In this paper, we investigate the multi-hop transmission scheme for quality of experience (QoE)-centric air-ground collaborative emergency communication system (ECS). In unmanned aerial vehicle (UAV) assisted communication, existing efforts focus on the quality of service (QoS) metric, such as fairness and throughput. The optimization mechanism centered on the QoS metric ignores the matching relationship between the transmission demands and achievable end-to-end (E2E) data rate, leading to an underutilized resource utilization. Considering the heterogeneous transmission demands, we apply general utility theory to portray model-free user satisfaction. Assuming the positions of users are previously unknown and network size may dynamically change, we focus on optimizing the UAV deployment and multi-hop transmission scheme to maximize the network-wide QoE while maintaining the regional coverage rate and connectivity. However, the formulated problem is a non-convex problem with the curse of dimensionality. To address this challenge, we propose a game-based best response algorithm for UAV deployment. The game-based many-to-many matching algorithm performs the multi-hop transmission scheme. Simulation results demonstrate that the proposed QoE-centric optimization method can efficiently improve the QoE performance compared to the existing QoS-centric multi-hop transmission algorithms. The proposed QoE optimization improves resource utilization without incurring additional system costs.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"180 ","pages":"Article 104051"},"PeriodicalIF":4.8,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145364132","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}

{"title":"Enhanced hybrid PSO-FA: Joint optimization of resource allocation for VFC in 6G networks","authors":"Fuqi Zhang ,&nbsp;Huilin Jiang ,&nbsp;Fu Liu ,&nbsp;Kevin I-Kai Wang ,&nbsp;Tao Hou ,&nbsp;Yujia Liu ,&nbsp;Xingtong Mu","doi":"10.1016/j.adhoc.2025.104048","DOIUrl":"10.1016/j.adhoc.2025.104048","url":null,"abstract":"<div><div>Mobile vehicular ad hoc networks with fog computing in 6 G present a novel distributed architecture to enhance network computing capabilities in dynamic environments. However, these self-organizing networks face significant quality-of-service challenges including large average latency, high total energy consumption, and poor load balancing among fog nodes during multi-task offloading in mobile scenarios. This paper proposes a cross-layer resource and information management approach based on enhanced hybrid particle swarm optimization and firefly algorithm (EH-PSO-FA) for joint optimization. A fitness function incorporating load balancing and local computation penalties is designed to address mobility-aware resource allocation. To enhance global search capability and robustness in dynamic ad hoc environments, both PSO and FA algorithms are enhanced with adaptive mechanisms to avoid premature convergence and local optima. Extensive performance analysis and simulation demonstrate that EH-PSO-FA significantly outperforms baseline protocols, achieving up to 26.18% reduction in average latency and 57.74% improvement in energy-efficient design. The scalable solution effectively supports power-aware computing in mobile wireless ad hoc networks for urban vehicular scenarios.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"180 ","pages":"Article 104048"},"PeriodicalIF":4.8,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145321997","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}

{"title":"Secret-key generation from wireless channels using variational autoencoders and domain adversarial neural networks","authors":"Syed Shafaq Ali Shah,&nbsp;Chunyi Chen,&nbsp;Ruiyue Liang","doi":"10.1016/j.adhoc.2025.104042","DOIUrl":"10.1016/j.adhoc.2025.104042","url":null,"abstract":"<div><div>Physical layer key distribution is an emerging technology in which legitimate communicating parties can extract secret keys with low computational cost and high security by using inherent randomness in the wireless channel. Due to a large number of wireless communication devices, the wireless channel has become weakly correlated with substantial noise, making the channel imperfect, leading to unreliable extraction of secret keys and increased key disagreement rates. However, existing knowledge is working for specific environments where the training and testing conditions are the same, but in the real world the environment is frequently changing, which existing knowledge did not take into account. To address these problems, we present a novel physical layer key distribution scheme based on variational autoencoders and domain adversarial neural network (VAEDANN) that ensure secret key extraction between legitimate devices from weakly correlated wireless channels. The variational autoencoder extracts the latent feature and eliminates the noise in the data, domain adversarial learning makes the model domain invariant. We used a quantization method called channel quantization alternating to address high key disagreement rates. To control information leakage and correct the discrepancy, we used cascade protocol and the toeplitz algorithm. After extensive simulation experiments, the VAEDANN-based method demonstrates a lower MSE compared to other methods across environments, highlighting its superior capability in learning channel reciprocity. Additionally, it achieves a lower bit disagreement rate and key error rate, exhibits high randomness in the key, and maintains a low computational cost. These features make the VAEDANN method highly reliable for resource constrained devices.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"180 ","pages":"Article 104042"},"PeriodicalIF":4.8,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145321998","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}

{"title":"A blockchain-enhanced trust-driven batch authentication scheme for secure VANETs","authors":"Longxia Liao ,&nbsp;Junhui Zhao ,&nbsp;Qingmiao Zhang ,&nbsp;He Fang","doi":"10.1016/j.adhoc.2025.104045","DOIUrl":"10.1016/j.adhoc.2025.104045","url":null,"abstract":"<div><div>Ensuring secure and efficient message authentication in vehicular ad hoc networks (VANETs) is a significant challenge, particularly in the face of insider threats and high mobility. This paper proposes a trust-driven batch authentication scheme, dynamically optimized through real-time trust updates. We introduce a lightweight certificateless elliptic curve cryptography (CL-ECC) protocol for efficient batch verification, combined with a blockchain-based dynamic trust evaluation model that incorporates a Gompertz-based trust update function and an enhanced proof-of-work (PoW) algorithm for decentralized trust management. To ensure tamper-resilience and decentralization, Practical Byzantine Fault Tolerance (PBFT) consensus is employed. Security analysis demonstrates that the proposed scheme effectively defends against forgery, message tampering, replay attacks, and internal threats such as on-off and collusion attacks. Experimental results show that our scheme reduces computational overhead by 7.9-56.9% and improves average message utilization by 114.2-198.3% compared to conventional schemes under various scenarios. These results demonstrate that the proposed scheme is secure, efficient, and well-suited for highly mobile and trust-sensitive VANET environments.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"180 ","pages":"Article 104045"},"PeriodicalIF":4.8,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145322000","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}

{"title":"Generative AI-based intrusion detection systems for intra-vehicle networks","authors":"Guettouche Asaouer,&nbsp;Djallel Eddine Boubiche","doi":"10.1016/j.adhoc.2025.104031","DOIUrl":"10.1016/j.adhoc.2025.104031","url":null,"abstract":"<div><div>With the rise of connected and autonomous vehicles, securing Intra-Vehicle Networks against cyber threats has become a critical challenge. The Controller Area Network bus, a widely used communication protocol in modern vehicles, remains highly vulnerable to sophisticated intrusion attacks. Traditional Machine Learning and Deep Learning based Intrusion Detection Systems have demonstrated limitations in adaptability, real-time performance, and handling zero-day attacks. This survey explores the emerging role of Generative Artificial Intelligence in enhancing IVN security. It examines key GenAI—assessing their potential to address the shortcomings of conventional IDS techniques. A comprehensive review of recent literature is conducted, analyzing the effectiveness of generative approaches in intrusion detection compared to deterministic methods. Key aspects such as detection time, adaptability to unknown threats, and real-time processing constraints are evaluated. Additionally, this paper identifies existing research gaps, emphasizing the need for standardized datasets, federated learning strategies, and improved deployment techniques to ensure the practical viability of GenAI-based IDS in real-world vehicular environments. The insights presented aim to guide future research toward more robust and adaptive security solutions for IVNs.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"180 ","pages":"Article 104031"},"PeriodicalIF":4.8,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145160001","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}

{"title":"CLEHTO — A multi-layered algorithm for secure, adaptive data transmission in IoT-enhanced healthcare networks","authors":"Sofiane Hamrioui ,&nbsp;Angela Voinea Ciocan ,&nbsp;Camil Adam Mohamed Hamrioui ,&nbsp;Pascal Lorenz","doi":"10.1016/j.adhoc.2025.104056","DOIUrl":"10.1016/j.adhoc.2025.104056","url":null,"abstract":"<div><div>The rapid growth of IoT in healthcare demands reliable, secure, and energy-efficient communication solutions. We propose <strong>CLEHTO</strong>, a novel cross-layer optimization framework that dynamically adapts to network conditions by integrating real-time energy monitoring, joint mobility–security assessment, and adaptive congestion control. Unlike conventional approaches, CLEHTO introduces a unified reliability scoring system that simultaneously evaluates physical channel quality, link reliability, node mobility, and transport-layer congestion. Experimental results demonstrate CLEHTO’s exceptional performance: a 92.8% Packet Delivery Ratio under 20% link failure while maintaining 4.5 Mbps throughput, a 98.6% authentication success rate using SSL/TLS (outperforming IPSec’s 98.3%), and optimal energy consumption of 0.55 mAh for battery-powered devices. CLEHTO maintains 105 ms latency (vs. IPSec’s 95 ms) for secure medical data flows, showing significant improvements over single-layer approaches. These results establish CLEHTO as a robust and efficient solution for IoT-based healthcare systems.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"180 ","pages":"Article 104056"},"PeriodicalIF":4.8,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145364133","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}