Ad Hoc Networks最新文献_第3页

RPL-TSCH cross-layer design for improve quality of service in LLNs of IIoT RPL-TSCH跨层设计提高工业物联网lln服务质量

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-03-31 DOI: 10.1016/j.adhoc.2025.103843

Mehdi Zirak, Yasser Sedaghat, Mohammad Hossein Yaghmaee Moghaddam

{"title":"RPL-TSCH cross-layer design for improve quality of service in LLNs of IIoT","authors":"Mehdi Zirak, Yasser Sedaghat, Mohammad Hossein Yaghmaee Moghaddam","doi":"10.1016/j.adhoc.2025.103843","DOIUrl":"10.1016/j.adhoc.2025.103843","url":null,"abstract":"<div><div>The Internet of Things (IoT) facilitates mutual interaction by establishing a connection between humans and objects. The adoption of IoT is rapidly expanding across various aspects of human life. Industrial IoT (IIoT) is the intersection point between IoT and industry, serving as a key driver of the Fourth Industrial Revolution, also referred to as Industry 4.0 (I4.0). Low-Power and Lossy Networks (LLNs), which contain many resource-constrained nodes, as the basic block in IoT and IIoT, are an essential part of this revolution. Given the resource constraint of LLNs and the mission, safety, and business criticality of IIoT, enhancing Quality of Service (QoS) has become a significant challenge. Addressing this challenge requires the optimal utilization of resources and fully coordinated decision-making across different layer protocols, which can be achieved through cross-layer design. Routing Protocol for Low-Power and Lossy Networks (RPL) and Time Slotted Channel Hopping (TSCH) are two widely used standard protocols in the IIoT protocol stack. In this paper, we investigate the fundamental factors affecting QoS within the RPL and TSCH and propose an RPL-TSCH Cross-Layer (RTCL) design for LLNs in IIoT, motivated by equations derived from queuing theory. The equations and simulation results reveal that the inconsistency between the arrival rate and service rate of the node's queue leads to increasing <em>queue overflow</em> and delay and decreasing reliability and throughput. The proposed RTCL design, structured as a six-step solution that integrates RPL and TSCH information, enhances QoS by employing two primary strategies: <em>controlling the arrival rate</em> and <em>increasing the service rate</em> of the nodes’ queues. Evaluation results from various simulation scenarios demonstrate that RTCL improves QoS parameters while also enhancing load balancing and network stability.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"174 ","pages":"Article 103843"},"PeriodicalIF":4.4,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143785931","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

KAIM: A distributed K-anonymity selection mechanism based on dual incentives KAIM：基于双重激励的分布式k -匿名选择机制

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-03-28 DOI: 10.1016/j.adhoc.2025.103839

Zhaowei Hu, Shiyun Ni, Hangyi Quan, Bocheng Ding, Peng He

{"title":"KAIM: A distributed K-anonymity selection mechanism based on dual incentives","authors":"Zhaowei Hu, Shiyun Ni, Hangyi Quan, Bocheng Ding, Peng He","doi":"10.1016/j.adhoc.2025.103839","DOIUrl":"10.1016/j.adhoc.2025.103839","url":null,"abstract":"<div><div>With the growing demand for privacy protection, the construction of anonymous zones based on distributed K-anonymity mechanisms has gained widespread attention in the field of location privacy protection. However, existing methods often overlook the limitations of reputation evaluation in identifying potential unknown malicious behaviors of collaborators when selecting assistants to build K-anonymous zones. At the same time, the issue of delayed responses from collaborators during the process of encouraging user cooperation through incentive mechanisms, which may lead to construction failures, has not been effectively addressed. To tackle these challenges, this paper proposes a dual-incentive distributed K-anonymity selection mechanism (KAIM) that combines the Hidden Markov Model (HMM). This mechanism encourages collaborators to participate in the construction of anonymous zones quickly and on time by establishing two incentive models: the requester collaboration incentive model and the collective benefit optimization incentive model. These dual incentives help form the optimal requester-collaborator participation set, enabling efficient construction of K-anonymous zones. Additionally, the KAIM mechanism uses the HMM to model the behaviors of requesters and collaborators, and its effectiveness in identifying malicious user behaviors is validated on real datasets. Experimental results show that the HMM model can identify anomalous activities that significantly differ from normal behavioral patterns with high accuracy, providing strong assurance for the construction of anonymous zones.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"175 ","pages":"Article 103839"},"PeriodicalIF":4.4,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143873395","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

REACT: Reinforcement learning and multi-objective optimization for task scheduling in ultra-dense edge networks REACT：超密集边缘网络任务调度的强化学习和多目标优化

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-03-27 DOI: 10.1016/j.adhoc.2025.103834

Smithamol M.B. , Rajeswari Sridhar

{"title":"REACT: Reinforcement learning and multi-objective optimization for task scheduling in ultra-dense edge networks","authors":"Smithamol M.B. , Rajeswari Sridhar","doi":"10.1016/j.adhoc.2025.103834","DOIUrl":"10.1016/j.adhoc.2025.103834","url":null,"abstract":"<div><div>This paper addresses the challenges of task scheduling and resource allocation in ultra-dense edge cloud (UDEC) networks, which integrate micro and macro base stations with diverse user equipment in 5G environments. To optimize system performance, we propose REACT, a novel two-level scheduling framework leveraging reinforcement learning (RL) for energy-efficient task scheduling. At the upper level, RL-based adaptive optimization replaces conventional power allocation techniques, dynamically minimizing transmission energy consumption under the Non-Orthogonal Multiple Access (NOMA) protocol. At the lower level, the joint task offloading and resource allocation problem is modeled as a multi-objective optimization challenge. This is solved using a hybrid approach combining meta-heuristic algorithms and Long Short-Term Memory (LSTM) predictive models, maximizing response rates and system throughput. Sensitivity analyses explore the effects of user density, channel quality, workload, and request size on performance. Comparative evaluations against state-of-the-art methods demonstrate the proposed framework’s superior efficiency in tackling dynamic scheduling challenges, achieving energy savings and enhancing user experience.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"174 ","pages":"Article 103834"},"PeriodicalIF":4.4,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143725258","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

Zero trust-based authentication for Inter-Satellite Links in NextGen Low Earth Orbit networks 下一代低地球轨道网络中星间链路的零信任认证

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-03-26 DOI: 10.1016/j.adhoc.2025.103817

Kerry Anne Farrea , Zubair Baig , Robin Doss , Dongxi Liu

{"title":"Zero trust-based authentication for Inter-Satellite Links in NextGen Low Earth Orbit networks","authors":"Kerry Anne Farrea , Zubair Baig , Robin Doss , Dongxi Liu","doi":"10.1016/j.adhoc.2025.103817","DOIUrl":"10.1016/j.adhoc.2025.103817","url":null,"abstract":"<div><div>Next Generation (NextGen) Low Earth Orbit satellite networks are rapidly expanding to support global communication and 6G technology transition. This growth exposes networks to new security challenges due to wide coverage in hostile areas and increased access points in space and on Earth. Traditional static authentication methods prove inadequate in this dynamic environment. We address these challenges by developing a Zero Trust Authentication Protocol for Inter-Satellite Link (ISL) communication. Our protocol implements a novel verification process that leverages orbital signals to authenticate ISLs. This approach ensures secure data access and transmission exclusively among verified satellites, mitigating threats from eavesdropping, signal spoofing, impersonation, and replay attacks. To optimize security and resource efficiency, we integrate Hyperelliptic Curve Cryptography (HECC) into our protocol. We validate our approach through MATLAB and Systems Tool Kit (STK) simulations, complemented by BAN Logic and Scyther analyses. Our findings demonstrate that our protocol enhances the security framework of NextGen LEO networks without compromising their performance or operational capabilities.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"174 ","pages":"Article 103817"},"PeriodicalIF":4.4,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143734789","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

Intrusion detection in internet of things using differential privacy: A hybrid machine learning approach 使用差分隐私的物联网入侵检测：一种混合机器学习方法

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-03-26 DOI: 10.1016/j.adhoc.2025.103818

Ankit Manderna , Upasana Dohare , Sushil Kumar , Balak Ram

{"title":"Intrusion detection in internet of things using differential privacy: A hybrid machine learning approach","authors":"Ankit Manderna , Upasana Dohare , Sushil Kumar , Balak Ram","doi":"10.1016/j.adhoc.2025.103818","DOIUrl":"10.1016/j.adhoc.2025.103818","url":null,"abstract":"<div><div>With the rising integration of the Internet of Things (IoT) into our daily lives, ensuring the security and privacy of these interconnected systems has become paramount. Traditional cybersecurity approaches often fall short in addressing the dual challenges of protecting IoT systems from intrusions while preserving user privacy, particularly given the complexity of IoT data and increased concerns about data privacy. Therefore, a Machine Learning (ML) based model is implemented in the proposed system to accurately classify intrusions, tailored for IoT security. In this context, this paper proposes a hybrid machine learning model: Average Orthogonal Probabilistic Random Forest-Extreme Gradient Boosting (AOPRF-XGBoost) to classify the presence and absence of intrusions in the datasets while considering different data privacy budgets. The AOPRF-XGBoost model makes use of a proposed enhanced version of Random Forest: Average Orthogonal Probabilistic Random Forest and Extreme Gradient Boosting models. A key aspect of this work is the incorporation of differential privacy mechanisms to safeguard sensitive data during model training. Differential Privacy Datasets are created by adding Gaussian noise to the existing datasets: AFDA-IDS and UNR-IDD for the AOPRF-XGBoost model, ensuring privacy protection. The experimental results of the AOPRF-XGBoost model show that the model’s accuracy improves by 3% and 1% in AFDA-IDS dataset and UNR-IDD dataset respectively, over state-of-the-art existing machine learning models, achieving a balance between Security and Privacy.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"174 ","pages":"Article 103818"},"PeriodicalIF":4.4,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143747262","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

Q-learning-based semi-fixed clustering routing algorithm in WSNs 基于q学习的wsn半固定聚类路由算法

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-03-26 DOI: 10.1016/j.adhoc.2025.103837

Zhang Zhaohui, Zhou Jiaqi, Li Jing

引用次数: 0

Joint aerial base station placement and user association for aerial–terrestrial networks: A whale optimization approach 联合空中基地台安置与空中-地面网路的使用者关联：鲸鱼优化方法

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-03-23 DOI: 10.1016/j.adhoc.2025.103836

Yong Hao Chin , Shengqi Jiang , Ying Loong Lee , Yee Kai Tee , Chen Chen , Muhammad Sheraz , Teong Chee Chuah , Yoong Choon Chang

{"title":"Joint aerial base station placement and user association for aerial–terrestrial networks: A whale optimization approach","authors":"Yong Hao Chin , Shengqi Jiang , Ying Loong Lee , Yee Kai Tee , Chen Chen , Muhammad Sheraz , Teong Chee Chuah , Yoong Choon Chang","doi":"10.1016/j.adhoc.2025.103836","DOIUrl":"10.1016/j.adhoc.2025.103836","url":null,"abstract":"<div><div>Aerial–terrestrial networks have been envisaged as a key feature of sixth generation (6G) communications to resolve the capacity and coverage issues of the existing terrestrial ground base stations (GBSs) via unmanned aerial vehicle-mounted base stations (ABSs). However, with the introduction of ABSs into the mobile networks, load balancing among ABSs becomes more challenging, as it additionally requires careful placement of ABSs in the three-dimensional (3D) airspace for coverage provisioning. Also, user quality of service (QoS) requirements and interference between ABSs and GBSs require meticulous management during the user association process for effective load balancing. In this paper, we propose a new joint ABS placement and user association scheme based on a whale optimization algorithm (WOA) for throughput maximization and load balancing in aerial–terrestrial networks. Firstly, a multi-objective ABS placement and user association problem is formulated for an aerial–terrestrial network to jointly maximize an <span><math><mi>α</mi></math></span>-fairness-based load balancing utility function and the network throughput. Then, we develop a WOA algorithmic framework to solve the multi-objective problem, with each whale representing a candidate ABS placement solution, whose optimality is evaluated using a fitness function designed based on network throughput maximization and physical isolation constraints. Also, a QoS-aware greedy user association algorithm that maximizes the load balancing utility function is developed to facilitate the fitness evaluation of each whale. Simulation results show that the proposed scheme outperforms several state-of-the-art schemes in terms of Jain’s fairness index, probability of blocking and total throughput.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"173 ","pages":"Article 103836"},"PeriodicalIF":4.4,"publicationDate":"2025-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143680581","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

Lyapunov optimization-based power control policy for time-critical applications in a hybrid cognitive radio IoT network 基于Lyapunov优化的功率控制策略，用于混合认知无线电物联网网络中的时间关键应用

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-03-22 DOI: 10.1016/j.adhoc.2025.103833

Mohamed F. El-Sherif , Sherif I. Rabia , Ahmed H. Abd El-Malek , W.K. Zahra

{"title":"Lyapunov optimization-based power control policy for time-critical applications in a hybrid cognitive radio IoT network","authors":"Mohamed F. El-Sherif , Sherif I. Rabia , Ahmed H. Abd El-Malek , W.K. Zahra","doi":"10.1016/j.adhoc.2025.103833","DOIUrl":"10.1016/j.adhoc.2025.103833","url":null,"abstract":"<div><div>Ensuring timely quality of service for critical data in internet of things (IoT) networks is vital, demanding adequate spectrum and energy resources. However, these networks face challenges such as spectrum leakage and the limited power capacity of IoT devices. Merging cognitive radio (CR) technology in these networks is a potential solution to mitigate the challenge of the insufficient frequency spectrum. In this paper, we consider a scenario of two secondary users (SUs) accessing a CR network with a single primary user (PU) within the interweave/underlay access scheme. The SUs have two heterogeneous traffic: status update packets and deadline-constrained packets, which are measured using the age of information (AoI) and the timely throughout metrics, respectively. To address the energy limitation issue, an adaptive power allocation strategy for the SUs’ transmissions is initially developed. Subsequently, we investigate the trade-off between power consumption for the secondary system and specific demands of each traffic type independently. A stochastic optimization problem is then constructed to minimize the weighted sum average power consumption of the secondary system while ensuring a maximum average AoI threshold and an average minimum timely throughput per frame requirement for the corresponding SUs. The Lyapunov optimization theory is employed to convert the formulated problem into an unconstrained Markov decision process (MDP) per frame. Moreover, we derive a formula for the outage probability of SUs’ transmissions, considering the presence of multiple primary receivers. Simulation results demonstrate how the total consumed power is affected by the variations in the key system parameters, such as the activity and transmission power of the PU. Furthermore, experimental simulations show that the proposed policy achieves significant enhancement over two baseline policies.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"174 ","pages":"Article 103833"},"PeriodicalIF":4.4,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143715417","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

Open source user mobility and activity datasets: Taxonomy and applications 开源用户移动性和活动数据集：分类法和应用程序

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-03-21 DOI: 10.1016/j.adhoc.2025.103835

Sinjoni Mukhopadhyay King , Faisal Nawab , Katia Obraczka

{"title":"Open source user mobility and activity datasets: Taxonomy and applications","authors":"Sinjoni Mukhopadhyay King , Faisal Nawab , Katia Obraczka","doi":"10.1016/j.adhoc.2025.103835","DOIUrl":"10.1016/j.adhoc.2025.103835","url":null,"abstract":"<div><div>The study of user mobility and activity (uMA) has numerous applications, including network resource planning, connected healthcare, localization, social media, and e-commerce. Current research in uMA heavily relies on open-source traces captured from pedestrian, vehicular, and application-based activities. These traces are rich in features and diverse, not only in the information they provide but also in their potential applications. However, this diversity presents two main challenges for researchers and practitioners who aim to utilize uMA datasets, classify existing datasets, or create new ones. Firstly, there is no readily available comprehensive classification of existing open-source uMA traces, making it typically labor-intensive and time-consuming to determine whether the identified datasets are suitable. Secondly, it is challenging to identify the key features and their specific use cases without conducting a detailed analysis of the traces.</div><div>This manuscript aims to address these challenges in three ways. First, we propose a taxonomy for classifying open-source mobility traces based on mobility mode, data source, collection technology, and application type. This taxonomy can be used to create tags for both existing and new datasets, making it easier to find problem-specific datasets compared to current search methods. Second, we demonstrate how existing datasets can be classified according to this taxonomy, providing examples of popular open-source uMA traces, along with information about their publishing source, licensing, and anonymization strategy. We also discuss how this taxonomy can guide the collection of new uMA datasets. Finally, we present three case studies using popular publicly available uMA datasets to illustrate how our taxonomy can be used to identify feature sets in the traces, helping to determine their applicability to specific use cases in networking, health, lifestyle, and location-based services.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"173 ","pages":"Article 103835"},"PeriodicalIF":4.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143680580","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

Integrated network-computing resource allocation and optimized scheduling for cyber physical production system 网络物理生产系统的综合网络计算资源分配与优化调度

IF 4.4 3区计算机科学

Ad Hoc Networks Pub Date : 2025-03-20 DOI: 10.1016/j.adhoc.2025.103831

Xiaoqian Yu , Changqing Xia , Xi Jin , Chi Xu , Dong Li , Peng Zeng

{"title":"Integrated network-computing resource allocation and optimized scheduling for cyber physical production system","authors":"Xiaoqian Yu , Changqing Xia , Xi Jin , Chi Xu , Dong Li , Peng Zeng","doi":"10.1016/j.adhoc.2025.103831","DOIUrl":"10.1016/j.adhoc.2025.103831","url":null,"abstract":"<div><div>Edge computing plays a crucial role in cyber physical production system (CPPS) by connecting the cloud, thereby enhancing system flexibility, intelligence, and agility. However, current scholarly work predominantly focuses on the tight binding of tasks and platforms to meet the real-time and deterministic requirements of CPPS, but does not fully utilize the flexibility and customization characteristics of CPPS. Therefore, there is an urgent need for intelligent and flexible task platform decoupling in the future to meet various quality of service (QoS) requirements such as flexibility, energy consumption and real-time performance, which also brings the challenge of meeting CPPS requirements. To address this issue, this work studies the decoupled flexible manufacturing dynamical scheduling problem with the aim of jointly optimizing real-time performance and energy consumption. Firstly, a multi-priority feedback queue is designed, which can dynamic adjust priority to ensure real-time performance of tasks. Subsequently, multi-objective optimization models are used to allocate network and computing resources for tasks, taking system latency and energy consumption into account as costs. To narrow the solution space and improve solving speed, a locally optimal resource allocation method is derived. Furthermore, scheduling algorithms for the end-side and edge-side are designed separately. On one hand, considering the energy sensitivity of edge devices, a lightweight scheduling algorithm called terminal double deep Q network (T-DDQN) has been proposed to quickly determine the optimal task execution location. On the other hand, a task offloading strategy named game theory edge device-level task offloading (GTETO) has been introduced to address the load imbalance issues at the edge caused by T-DDQN. Compared to existing algorithms, it can reduce system cost by up to 25.26%, and improve resource utilization of edge devices by 8.34–27.77%.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"173 ","pages":"Article 103831"},"PeriodicalIF":4.4,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143680579","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