Ad Hoc Networks最新文献_第2页

Performance of MPTCP over emulated LEO satellite networks with ECMP routing 基于ECMP路由的模拟LEO卫星网络MPTCP性能研究

IF 4.8 3区计算机科学

Ad Hoc Networks Pub Date : 2026-04-01 Epub Date: 2026-01-30 DOI: 10.1016/j.adhoc.2026.104161

Juan Pedro Muñoz-Gea, Josemaria Malgosa-Sanahuja, Pilar Manzanares-Lopez

{"title":"Performance of MPTCP over emulated LEO satellite networks with ECMP routing","authors":"Juan Pedro Muñoz-Gea, Josemaria Malgosa-Sanahuja, Pilar Manzanares-Lopez","doi":"10.1016/j.adhoc.2026.104161","DOIUrl":"10.1016/j.adhoc.2026.104161","url":null,"abstract":"<div><div>Low Earth Orbit (LEO) satellite networks are gaining prominence in 6G and large-scale IoT infrastructures, where traffic patterns range from low-rate telemetry to bandwidth-intensive applications such as high-resolution sensing, edge-assisted computation, and real-time vehicular services. Next-generation LEO constellations are designed to support high-capacity connectivity and heterogeneous IoT/6G services, some of which demand sustained high throughput and strict reliability guarantees. Multipath TCP (MPTCP) offers a transport-layer solution by enabling simultaneous use of multiple paths through concurrent subflows. This paper evaluates MPTCP version 1 in a LEO environment using <em>bLEO</em>, a new emulation tool for LEO networks specifically developed by the authors for this work. <em>bLEO</em> is an eBPF-based emulator capable of handling heavily loaded, large-scale constellations while providing efficient real-time control of link delay and state dynamics. We demonstrate MPTCP integration in Linux, including default scheduler behavior and subflow configuration. Additionally, we leverage Equal-Cost Multi-Path (ECMP) routing via OSPF using FRRouting to distribute MPTCP subflows across multiple network paths. The experimental results reveal a fundamental trade-off between robustness and scalability in the Linux MPTCP scheduler: although it maintains session continuity under handovers and failures, it underutilizes available paths unless load conditions force progressive subflow activation, reflecting a conservative design that prioritizes reordering avoidance and performance stability over full multipath utilization. The proposed platform serves as a flexible foundation for evaluating transport-layer protocols in dynamic satellite scenarios.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"184 ","pages":"Article 104161"},"PeriodicalIF":4.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146079059","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

DRUID: Coordinating drone movements for compromised node identification 德鲁伊：协调无人机移动以识别受损节点

IF 4.8 3区计算机科学

Ad Hoc Networks Pub Date : 2026-04-01 Epub Date: 2026-01-05 DOI: 10.1016/j.adhoc.2026.104135

Mauro Farina, Erica Salvato, Martino Trevisan, Alberto Bartoli

{"title":"DRUID: Coordinating drone movements for compromised node identification","authors":"Mauro Farina, Erica Salvato, Martino Trevisan, Alberto Bartoli","doi":"10.1016/j.adhoc.2026.104135","DOIUrl":"10.1016/j.adhoc.2026.104135","url":null,"abstract":"<div><div>In recent years, Unmanned Aerial Vehicles (UAVs) (also called drones) networks have become increasingly popular in scenarios where rapid deployment, flexible mobility, and real-time data acquisition are crucial, such as disaster relief, environmental monitoring, military operations, and smart city infrastructure. However, due to their dynamic nature and dependence on wireless communication, they are intrinsically vulnerable to a variety of cyberattacks. In this work, we present <span>DRUID</span>, a decentralized scheme for silently identifying a compromised drone that selectively alters the messages it forwards. The scheme uses a combination of secret sharing and multipath routing to allow a pair of communicating drones, namely <span><math><mi>A</mi></math></span> and <span><math><mi>B</mi></math></span>, to detect the presence of a compromised drone along any route between them, thereby categorizing each route as either safe or compromised. The scheme operates iteratively and consists of three key modules: (i) an Information Retrieval Procedure that allows <span><math><mi>A</mi></math></span> to learn more about the topology, (ii) a binary search-like Identification Procedure, and (iii) if the previous module fails to identify the compromised drone, a Node Repositioning Procedure that relocates nodes closer to the compromised path. We validate <span>DRUID</span> on a large and diverse set of 178731 graphs representing realistic UAV networks with different communication ranges. Comparing our scheme to previous work, experiments show that <span>DRUID</span> achieves a 97% identification rate—up from the 54% of the most recent alternative approach. We analyze the cost associated with the node repositioning procedure in terms of computation time and drone movement, and show that it generally takes a few seconds.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"184 ","pages":"Article 104135"},"PeriodicalIF":4.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145908940","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

Joint optimization of resource allocation and position deployment in UAV swarm emergency communication networks under interference 干扰下无人机群应急通信网络资源配置与位置部署联合优化

IF 4.8 3区计算机科学

Ad Hoc Networks Pub Date : 2026-04-01 Epub Date: 2026-01-21 DOI: 10.1016/j.adhoc.2026.104152

Fulai Liu , Yajie Gao , Ruiyan Du

{"title":"Joint optimization of resource allocation and position deployment in UAV swarm emergency communication networks under interference","authors":"Fulai Liu , Yajie Gao , Ruiyan Du","doi":"10.1016/j.adhoc.2026.104152","DOIUrl":"10.1016/j.adhoc.2026.104152","url":null,"abstract":"<div><div>Unmanned aerial vehicle (UAV) swarms serve as airborne mobile base stations in post-disaster emergency communications but are highly susceptible to both internal interference and external malicious attacks. In addition, the increasing number of UAVs leads to high-dimensional inputs, thereby slowing the convergence of anti-interference algorithms. To address these challenges, this paper proposes an attention-enhanced multi-agent proximal policy optimization (AEMAPPO) framework that jointly optimizes resource allocation and position deployment. A constructed RNN–Bahdanau module is integrated into MAPPO to replace traditional linear feature extraction with attention-based interference feature learning. This enables the decoder to focus on the most relevant components within the high-dimensional interference sequence, alleviating the dimensionality-explosion problem and improving convergence speed. Simulation results demonstrate that, compared with benchmark methods, AEMAPPO significantly enhances training efficiency, accelerates policy convergence, and achieves superior anti-interference performance.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"184 ","pages":"Article 104152"},"PeriodicalIF":4.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146079056","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 trajectory planning for UAV-assisted communication recovery using multi-agent graph reinforcement learning 基于多智能体图强化学习的无人机辅助通信恢复节能轨迹规划

IF 4.8 3区计算机科学

Ad Hoc Networks Pub Date : 2026-04-01 Epub Date: 2026-01-09 DOI: 10.1016/j.adhoc.2026.104145

Cong Wang , Menglong Dong , Ying Yuan , Guorui Li

{"title":"Energy-efficient trajectory planning for UAV-assisted communication recovery using multi-agent graph reinforcement learning","authors":"Cong Wang , Menglong Dong , Ying Yuan , Guorui Li","doi":"10.1016/j.adhoc.2026.104145","DOIUrl":"10.1016/j.adhoc.2026.104145","url":null,"abstract":"<div><div>Unmanned aerial vehicle base stations (UAV-BSs) are effective and rapid to provide recovery of emergency communication after disasters due to their maneuverability. However, the throughput of mobile terminals (MTs) is prone to be limited by the trajectory and energy constraints of UAV-BSs. To improve throughput for MTs while guaranteeing energy efficiency of UAV-BSs, we propose an energy-efficient trajectory planning framework based on multi-agent heterogeneous graph reinforcement learning. We formulate the joint optimization problem as a partially observable Markov decision process. Then, we propose a heterogeneous graph-based method to represent relationships between UAV-BSs and network entities. Subsequently, we design a multi-agent graph attention recurrent actor-critic framework (MA-GAR) to efficiently learn over the heterogeneous graphs. Finally, we introduce a digital twin empowered centralized training and decentralized execution mechanism in MA-GAR to reduce energy consumption of UAV-BSs. Experimental results show that the proposed MA-GAR outperforms the benchmark algorithms in convergence speed, system throughput, energy consumption, and service fairness.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"184 ","pages":"Article 104145"},"PeriodicalIF":4.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928710","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

System energy efficiency maximization-oriented clustering protocol design for active IRS-aided EH-CRSNs 面向系统能效最大化的主动irs辅助EH-CRSNs聚类协议设计

IF 4.8 3区计算机科学

Ad Hoc Networks Pub Date : 2026-04-01 Epub Date: 2026-01-15 DOI: 10.1016/j.adhoc.2026.104148

Jihong Wang, Yongxin Fan, Yanan Zhu, Miao Yu, Yang Li

{"title":"System energy efficiency maximization-oriented clustering protocol design for active IRS-aided EH-CRSNs","authors":"Jihong Wang, Yongxin Fan, Yanan Zhu, Miao Yu, Yang Li","doi":"10.1016/j.adhoc.2026.104148","DOIUrl":"10.1016/j.adhoc.2026.104148","url":null,"abstract":"<div><div>In clustered energy harvesting-cognitive radio sensor networks (EH-CRSNs), reliance on direct links for both EH and data transmission causes distant nodes to deplete energy faster, thereby shortening network lifetime. To address the above issues, this paper integrates an active intelligent reflecting surface (IRS) into EH-CRSNs and proposes a system energy efficiency (EE) maximization-oriented clustering protocol (EEMCP) to achieve a trade-off between network lifetime and monitoring capability. Specifically, by optimizing the reflection coefficient matrix of the active IRS during uplink transmission, the transmission range of cluster heads (CHs) is extended, enabling direct communication with the sink and mitigating data delivery failures caused by the absence of suitable relay nodes in conventional clustered EH-CRSNs. Furthermore, the optimal cluster radius is theoretically derived with the objective of maximizing system EE, thereby constraining local control signaling and intra-cluster communication ranges to reduce energy consumption. High-quality CHs are then selected to form clusters through joint evaluation of node-level communication capacity and channel quality to enhance data transmission performance. Simulations indicate that the EEMCP protocol enables superior system EE, exceeding the peak EE of existing clustering protocols by at least 1.98 times.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"184 ","pages":"Article 104148"},"PeriodicalIF":4.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146023873","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 integrated tracking technique for underwater navigation using acoustic and IMU measurements 利用声学和IMU测量的水下导航综合跟踪技术

IF 4.8 3区计算机科学

Ad Hoc Networks Pub Date : 2026-04-01 Epub Date: 2026-01-21 DOI: 10.1016/j.adhoc.2026.104151

Mainul Islam Chowdhury, Quoc Viet Phung, Iftekhar Ahmed, Daryoush Habibi

{"title":"An integrated tracking technique for underwater navigation using acoustic and IMU measurements","authors":"Mainul Islam Chowdhury, Quoc Viet Phung, Iftekhar Ahmed, Daryoush Habibi","doi":"10.1016/j.adhoc.2026.104151","DOIUrl":"10.1016/j.adhoc.2026.104151","url":null,"abstract":"<div><div>Accurate navigation is essential for underwater vehicles like AUVs, which often operate in deep or remote areas. However, complex ocean dynamics, cumulative inertial-measurement unit (IMU) drift, and diverse noise sources often result in erratic and unreliable position estimates. To overcome these challenges, we proposed a method that combines underwater acoustic signals with onboard motion sensor data to improve the underwater position tracking system. The proposed system uses a long baseline (LBL) acoustic array of surface buoys to capture the Time-difference-of-Arrival (TDoA) of a multi-pulse beacon. We extract arrival times using a superimposed-envelope-spectrum (SES) detector, which exploits the beacon’s periodic structure to stay reliable even in heavy noise. These acoustic measurements are fused with six-degree-of-freedom IMU data using a particle filter (PF). The filter suppresses IMU drift and reveals how long dead-reckoning remains reliable before an acoustic update becomes essential. Simulation results demonstrated that our PF-TDoA fusion method achieved up to 40% reduction in mean localization error compared to traditional fusion filters and optimization method. In the experiment, we compared the simulated IMU prediction with real-world acoustic measurements, and the resulting fused position estimated remained within <span><math><mrow><mn>3</mn><mi>m</mi></mrow></math></span> of Global Positioning System (GPS)-reported trajectory, demonstrating robust performance under operational conditions.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"184 ","pages":"Article 104151"},"PeriodicalIF":4.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146023876","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

Kalman filter scheduling for 6TiSCH network with traffic adaptation optimized for bursty traffic 基于突发通信量的6TiSCH网络自适应卡尔曼滤波调度

IF 4.8 3区计算机科学

Ad Hoc Networks Pub Date : 2026-04-01 Epub Date: 2026-01-05 DOI: 10.1016/j.adhoc.2025.104130

Yan Zhang, Shijie Xu, Qingqing Huang, Yan Han

{"title":"Kalman filter scheduling for 6TiSCH network with traffic adaptation optimized for bursty traffic","authors":"Yan Zhang, Shijie Xu, Qingqing Huang, Yan Han","doi":"10.1016/j.adhoc.2025.104130","DOIUrl":"10.1016/j.adhoc.2025.104130","url":null,"abstract":"<div><div>The sensor nodes equipped with IEEE 802.15.4e (6TiSCH) wireless protocol stack and IPv6 time slot channel hopping mode have deterministic network characteristics after networking, providing low-latency and highly reliable communication for industrial scenarios with growing demand for low-power sensor networks. However, existing scheduling algorithms perform poorly under the bursty traffic commonly found in industrial environments. Due to the limitations of their design principles, they are unable to respond quickly to changes in traffic or differentiate between bursty traffic patterns to accurately sense traffic conditions, resulting in high latency, low reliability and additional power consumption. Therefore, we propose a scheduling method called the Kalman Filter Traffic Sensing Prediction Scheduling Function (KSF). KSF utilizes the filtered processing of node Cell usage and per-slot frame queue increment as the primary basis for scheduling decisions, coupled with adaptive filtering parameters, to achieve the ability to ignore transient fluctuation noise and respond quickly after the occurrence of bursts. In addition, we utilize filtering to predict the ratio of the number of received data packets to the number of sent data packets in the next slot frame to distinguish burst patterns and dynamically change KSF’s scheduling strategy. Experiments demonstrate that KSF exhibits more optimal scheduling performance under bursty traffic conditions, reducing latency by 14.82% compared to the well-known OTF while maintaining the lowest power consumption across all traffic rates.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"184 ","pages":"Article 104130"},"PeriodicalIF":4.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928709","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

A reinforcement learning–based active interception algorithm for wireless networks topology identification 一种基于强化学习的无线网络拓扑识别主动拦截算法

IF 4.8 3区计算机科学

Ad Hoc Networks Pub Date : 2026-04-01 Epub Date: 2025-12-30 DOI: 10.1016/j.adhoc.2025.104134

Liping Luo , Zhou Peng , Han Xu , Renhai Feng

{"title":"A reinforcement learning–based active interception algorithm for wireless networks topology identification","authors":"Liping Luo , Zhou Peng , Han Xu , Renhai Feng","doi":"10.1016/j.adhoc.2025.104134","DOIUrl":"10.1016/j.adhoc.2025.104134","url":null,"abstract":"<div><div>Accurate Topology Identification (TI) in non-cooperative networks is critical, particularly during various communication engagements that demand low computational overhead. Active interception has proven effective in such scenarios. Specifically, active interception is performed on full-duplex eavesdroppers which cause frequency hopping, thereby obtaining corresponding received signal strength as indicator. However, its interference power adjustment requires numerous iterations and causes overwhelming frequency hopping. This paper proposes a novel Reinforcement Learning-based Active Interception and Node Localization (RLAI-NL) method. RLAI-NL aims to accurately identify network topology. Four different frequency hopping patterns are designed to evaluate the performance of RLAI-NL. Using Reinforcement Learning (RL), an intelligent agent is trained to dynamically adjust its interference power. Through dynamic learning and policy optimization, the agent avoids unnecessary power consumption associated with specially designed search strategies, while adapting effectively to both small- and large-scale networks as well as various communication modes. Simulation results demonstrate that RLAI significantly outperforms traditional active interception methods, achieving 99% accuracy with fewer frequency hops and iterations, thereby reducing computational complexity and power consumption.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"184 ","pages":"Article 104134"},"PeriodicalIF":4.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146023874","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

Offloading and computational resources allocation of tasks with dependency in MEC environment based on deep reinforcement learning 基于深度强化学习的MEC环境中具有依赖关系的任务卸载与计算资源分配

IF 4.8 3区计算机科学

Ad Hoc Networks Pub Date : 2026-04-01 Epub Date: 2026-01-27 DOI: 10.1016/j.adhoc.2026.104136

Yifan Liu , Erdong Xue , Wenlei Chai , Yi Liu , Fan Feng

{"title":"Offloading and computational resources allocation of tasks with dependency in MEC environment based on deep reinforcement learning","authors":"Yifan Liu , Erdong Xue , Wenlei Chai , Yi Liu , Fan Feng","doi":"10.1016/j.adhoc.2026.104136","DOIUrl":"10.1016/j.adhoc.2026.104136","url":null,"abstract":"<div><div>Mobile edge computing (MEC) has emerged as a key technology for handling computation-intensive tasks generated by multiple terminal devices. However, due to task dependencies within applications, offloading decisions must consider not only the current task but also the remaining tasks, significantly increasing the complexity of task management. To address this challenge, we propose a priority-sensitive type (PST) scheme for joint tasks offloading and computational resources allocation, with the aim of minimizing the overall execution urgency of applications. A mixed integer optimization model is formulated, where task dependencies are represented by a directed acyclic graph (DAG), and a novel definition of task execution urgency is introduced. To solve the tasks offloading and access point (AP) selection problem, we adopt a multi-agent deep reinforcement learning (MADRL) framework, leveraging the proximal policy optimization (PPO) algorithm based on the actor-critic architecture. In addition, a greedy-based algorithm is designed to allocate computational resources of edge servers by considering task dependencies and refining offloading decisions when necessary. The simulation results demonstrate that the proposed PPO-PST approach significantly outperforms existing methods in terms of long-term execution efficiency and resource utilization across various application scenarios, highlighting its practicality and effectiveness.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"184 ","pages":"Article 104136"},"PeriodicalIF":4.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146079058","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

Explainable energy-efficient UAV-assisted cluster-based data collection in WSNs 可解释的节能无人机辅助的基于簇的无线传感器网络数据收集

IF 4.8 3区计算机科学

Ad Hoc Networks Pub Date : 2026-04-01 Epub Date: 2026-01-06 DOI: 10.1016/j.adhoc.2026.104137

Nadine Abbas

{"title":"Explainable energy-efficient UAV-assisted cluster-based data collection in WSNs","authors":"Nadine Abbas","doi":"10.1016/j.adhoc.2026.104137","DOIUrl":"10.1016/j.adhoc.2026.104137","url":null,"abstract":"<div><div>The use of unmanned aerial vehicles (UAVs) is becoming an integral element in modern wireless sensor networks (WSNs), due to their flexibility and cost-effectiveness, especially for data collection in challenging hard-to-reach environments. Cluster-based solutions further enhance data collection efficiency by allowing sensor nodes (SNs) to act as cluster heads (CHs) aggregating and relaying data to UAVs. Traditional approaches often rely on static clustering and lack transparency in decision-making regarding CH selection and UAV deployment. This work proposes an explainable energy-efficient UAV-assisted cluster-based data collection framework that integrates optimal and sub-optimal solutions as well as adopts machine learning-based CH prediction augmented with explainable AI techniques. First, we formulate a joint multi-objective optimization problem to minimize UAV usage, ensure energy-efficient CH selection, and guarantee data collection within deadline constraints. Second, we propose a sequential solving approach and then a scalable iterative cluster-based approach to provide real-time solutions for large-scale networks. Moreover, we develop machine learning (ML) models to predict CH selection using a customized dataset generated from extensive simulations of our proposed approach, capturing features like location, neighborhood density, data size, and deadlines. Furthermore, we use Explainable AI (XAI) techniques, particularly SHAP, to interpret the CH prediction model, providing insights into feature importance and decision rationale. This transparency enables network operators to validate CH assignments and strategically plan UAV deployment. Overall, the proposed framework achieves near-optimal trade-offs between UAV deployment, energy consumption, and execution time, leveraging flexible communication, emphasizing spatial and connectivity features and enhancing model interpretability for real-world applications.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"184 ","pages":"Article 104137"},"PeriodicalIF":4.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145908941","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