Ad Hoc Networks最新文献_第3页

A general task offloading and resources allocation strategy for multi-RSUs with load unbalance and priority awareness 具有负载不平衡和优先级意识的多 RSU 的一般任务卸载和资源分配策略

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-10-23 DOI: 10.1016/j.adhoc.2024.103690

Dun Cao , WenQian Wang , Meihua Wu , Shuo Cai , Fayez Alqahtani , Jin Wang

Vehicular Edge Computing is a new computing paradigm that enables real-time response to vehicular applications and servers by performing data processing on edge computing devices near the vehicle. However, on the one hand, the random distribution and the mobility of vehicles may lead to load unbalance among different Roadside Units (RSUs), and some tasks may not be able to get timely response due to inadequate computing resources and communication resources in the high-load RSU areas. On the other hand, considering the different urgency of the tasks, the service quality of the system will be seriously affected if these tasks are not treated indistinguishably. To address the above challenges, this paper constructs a priority-aware task offloading and computing&communication resources allocation problem in a general scenario of unbalanced load among multi-RSUs, aiming at minimising the average delay. In the problem, considering the absence of communication resources, the relay vehicle is used to offload the subtasks of splittable tasks to the RSUs that are in the neighbouring and low-load. Moreover, to take full advantage of computing resources, the task can be reasonably split into at most four parts and processed in parallel on a relay vehicle, a current RSU, a neighbouring RSU and a local vehicle. To solve the problem, a Split-Hop Offloading and Resources Allocation Strategy (SHORAS) based on an improved particle swarm optimisation algorithm is proposed, which uses a penalty function to incline resources towards high priority tasks. Simulation results show that SHORAS improves 24% in terms of the total system delay and effectively reduces the processing delay in the high-load areas compared to other strategies, while ensuring the delay requirements of high priority tasks.

车载边缘计算是一种新的计算模式，通过在车辆附近的边缘计算设备上执行数据处理，实现对车载应用和服务器的实时响应。然而，一方面，车辆的随机分布和流动性可能导致不同路侧单元（RSU）之间的负载不平衡，在高负载的 RSU 区域，由于计算资源和通信资源不足，一些任务可能无法得到及时响应。另一方面，考虑到任务的紧迫性不同，如果不对这些任务进行区别对待，将严重影响系统的服务质量。针对上述挑战，本文构建了一个在多 RSU 负载不平衡的一般场景下的优先级感知任务卸载和计算&通信资源分配问题，旨在最小化平均延迟。在该问题中，考虑到通信资源的缺失，利用中继车将可分拆任务的子任务卸载到邻近且负载较低的 RSU 上。此外，为了充分利用计算资源，任务最多可合理地拆分为四个部分，并在中继车、当前 RSU、邻近 RSU 和本地车上并行处理。为解决这一问题，提出了一种基于改进的粒子群优化算法的分跳卸载和资源分配策略（SHORAS），该策略使用惩罚函数将资源向高优先级任务倾斜。仿真结果表明，与其他策略相比，SHORAS 在确保高优先级任务延迟要求的前提下，将系统总延迟提高了 24%，并有效减少了高负载区域的处理延迟。

{"title":"A general task offloading and resources allocation strategy for multi-RSUs with load unbalance and priority awareness","authors":"Dun Cao , WenQian Wang , Meihua Wu , Shuo Cai , Fayez Alqahtani , Jin Wang","doi":"10.1016/j.adhoc.2024.103690","DOIUrl":"10.1016/j.adhoc.2024.103690","url":null,"abstract":"<div><div>Vehicular Edge Computing is a new computing paradigm that enables real-time response to vehicular applications and servers by performing data processing on edge computing devices near the vehicle. However, on the one hand, the random distribution and the mobility of vehicles may lead to load unbalance among different Roadside Units (RSUs), and some tasks may not be able to get timely response due to inadequate computing resources and communication resources in the high-load RSU areas. On the other hand, considering the different urgency of the tasks, the service quality of the system will be seriously affected if these tasks are not treated indistinguishably. To address the above challenges, this paper constructs a priority-aware task offloading and computing&communication resources allocation problem in a general scenario of unbalanced load among multi-RSUs, aiming at minimising the average delay. In the problem, considering the absence of communication resources, the relay vehicle is used to offload the subtasks of splittable tasks to the RSUs that are in the neighbouring and low-load. Moreover, to take full advantage of computing resources, the task can be reasonably split into at most four parts and processed in parallel on a relay vehicle, a current RSU, a neighbouring RSU and a local vehicle. To solve the problem, a Split-Hop Offloading and Resources Allocation Strategy (SHORAS) based on an improved particle swarm optimisation algorithm is proposed, which uses a penalty function to incline resources towards high priority tasks. Simulation results show that SHORAS improves 24% in terms of the total system delay and effectively reduces the processing delay in the high-load areas compared to other strategies, while ensuring the delay requirements of high priority tasks.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"167 ","pages":"Article 103690"},"PeriodicalIF":4.4,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142573351","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

Enhanced reinforcement learning-based two-way transmit-receive directional antennas neighbor discovery in wireless ad hoc networks 无线 ad hoc 网络中基于强化学习的双向收发定向天线邻居发现功能

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-10-23 DOI: 10.1016/j.adhoc.2024.103689

Zongheng Wei , Huakun Wu , Zhiyong Lin , Qingji Wen , Lili Zheng , Jianfeng Wen , Hai Liu

The utilization of directional antennas for neighbor discovery in wireless ad hoc networks brings notable benefits, such as extended transmission range, reduced transmission interference, and enhanced antenna gain. However, when nodes use directional antennas for neighbor discovery, the communication range is limited, resulting in a lack of knowledge of potential neighbors. Hence, it is necessary to design a special antenna direction switching strategy for neighbor discovery based on directional antennas. Traditional methods of switching antenna directions are often random or follow predefined sequences, overlooking the historical knowledge of sector exploration for antenna directions. In contrast, existing machine learning approaches aim to leverage observed historical knowledge to adjust antenna directions for faster neighbor discovery. Nonetheless, the latency of neighbor discovery is still high because the node cannot fully utilize the observed historical knowledge (i.e.., only using the knowledge observed by the node in transmission mode, ignoring the knowledge observed by the node in reception mode). Meanwhile, the corresponding reward and penalty mechanisms are still not detailed enough (i.e.., these reward and penalty mechanisms only consider the sectors of discovered and undiscovered neighboring nodes, ignoring the scenario of sectors that have been rewarded). In this paper, the neighbor discovery process is modeled as a reinforcement learning-based learning automaton. We propose an enhanced reinforcement learning-based two-way transmit-receive directional antennas neighbor discovery algorithm, called ERTTND. The algorithm consists of a two-way transmit-receive reinforcement learning mechanism (TTRL) and an enhanced reward-and-penalty mechanism (ERAP). This algorithm leverages insights from nodes in transmission and reception modes to refine their tactical decisions. Then, through an enriched reward-and-penalty framework, nodes optimize their strategies, thus expediting neighbor discovery based on directional antennas in wireless ad hoc networks. Simulation results demonstrate that compared to existing representative algorithms, the proposed ERTTND algorithm can achieve over 30% savings in terms of average discovery delay and energy consumption.

在无线 ad hoc 网络中利用定向天线进行邻居发现具有显著的优势，如扩大传输范围、减少传输干扰和增强天线增益。然而，当节点使用定向天线进行邻居发现时，通信范围会受到限制，导致对潜在邻居的了解不足。因此，有必要为基于定向天线的邻居发现设计一种特殊的天线方向切换策略。传统的天线方向切换方法通常是随机的或遵循预定义的序列，忽略了对天线方向进行扇区探索的历史知识。相比之下，现有的机器学习方法旨在利用观察到的历史知识来调整天线方向，从而更快地发现邻居。然而，由于节点无法充分利用观察到的历史知识（即只利用节点在发送模式下观察到的知识，而忽略节点在接收模式下观察到的知识），邻居发现的延迟仍然很高。同时，相应的奖惩机制还不够细致（即这些奖惩机制只考虑已发现和未发现邻居节点的扇区，忽略了已奖励扇区的情况）。本文将邻居发现过程建模为基于强化学习的学习自动机。我们提出了一种基于增强学习的双向收发定向天线邻居发现算法，称为 ERTTND。该算法由双向收发强化学习机制（TTRL）和增强奖惩机制（ERAP）组成。该算法利用节点在发送和接收模式下的洞察力来完善其战术决策。然后，通过增强型奖惩框架，节点可优化其策略，从而加快无线 ad hoc 网络中基于定向天线的邻居发现。仿真结果表明，与现有的代表性算法相比，所提出的ERTTND算法在平均发现延迟和能耗方面可节省30%以上。

{"title":"Enhanced reinforcement learning-based two-way transmit-receive directional antennas neighbor discovery in wireless ad hoc networks","authors":"Zongheng Wei , Huakun Wu , Zhiyong Lin , Qingji Wen , Lili Zheng , Jianfeng Wen , Hai Liu","doi":"10.1016/j.adhoc.2024.103689","DOIUrl":"10.1016/j.adhoc.2024.103689","url":null,"abstract":"<div><div>The utilization of directional antennas for neighbor discovery in wireless ad hoc networks brings notable benefits, such as extended transmission range, reduced transmission interference, and enhanced antenna gain. However, when nodes use directional antennas for neighbor discovery, the communication range is limited, resulting in a lack of knowledge of potential neighbors. Hence, it is necessary to design a special antenna direction switching strategy for neighbor discovery based on directional antennas. Traditional methods of switching antenna directions are often random or follow predefined sequences, overlooking the historical knowledge of sector exploration for antenna directions. In contrast, existing machine learning approaches aim to leverage observed historical knowledge to adjust antenna directions for faster neighbor discovery. Nonetheless, the latency of neighbor discovery is still high because the node cannot fully utilize the observed historical knowledge (<em>i.e.</em>., only using the knowledge observed by the node in transmission mode, ignoring the knowledge observed by the node in reception mode). Meanwhile, the corresponding reward and penalty mechanisms are still not detailed enough (<em>i.e.</em>., these reward and penalty mechanisms only consider the sectors of discovered and undiscovered neighboring nodes, ignoring the scenario of sectors that have been rewarded). In this paper, the neighbor discovery process is modeled as a reinforcement learning-based learning automaton. We propose an enhanced reinforcement learning-based two-way transmit-receive directional antennas neighbor discovery algorithm, called ERTTND. The algorithm consists of a two-way transmit-receive reinforcement learning mechanism (TTRL) and an enhanced reward-and-penalty mechanism (ERAP). This algorithm leverages insights from nodes in transmission and reception modes to refine their tactical decisions. Then, through an enriched reward-and-penalty framework, nodes optimize their strategies, thus expediting neighbor discovery based on directional antennas in wireless ad hoc networks. Simulation results demonstrate that compared to existing representative algorithms, the proposed ERTTND algorithm can achieve over 30% savings in terms of average discovery delay and energy consumption.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"167 ","pages":"Article 103689"},"PeriodicalIF":4.4,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142586555","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 weighted hybrid indoor positioning method based on path loss exponent estimation 基于路径损耗指数估计的加权混合室内定位方法

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-10-21 DOI: 10.1016/j.adhoc.2024.103684

Yiting Wang, Jingqi Fu, Yifan Cao

With the rapid development of the Internet of Things (IoT), location-based services (LBS) have gained significant attention due to their widespread applications in daily life. This paper addresses the indoor target positioning problem in wireless sensor networks (WSNs). A weighted constrained linear least squares algorithm based on path loss exponent estimation (PLE-WCLLS) with received signal strength (RSS) and angle of arrival (AoA) hybrid measurements is proposed. To address the challenges of unknown transmission power and path loss exponent (PLE), the proposed method employs a linear least squares (LLS) estimation approach based on the ranging maximum likelihood (ML) estimation model to estimate both parameters. Subsequently, a confidence weight adjustment strategy is designed to reduce positioning errors. To handle the highly non-convex and nonlinear nature of the RSS/AoA hybrid optimization model, a linearization method based on Taylor series expansion is presented. Accurate target position estimation is achieved by solving a constrained quadratic programming problem. The effectiveness of the proposed algorithm is validated through numerical simulations and experimental evaluation in a real indoor environment. Compared to traditional positioning methods, the PLE-WCLLS algorithm improves positioning accuracy by 13.2%, and it performs exceptionally well even in scenarios with fewer sensor nodes. This gives it broad application prospects in areas such as IoT device management, personnel tracking in smart buildings, and asset localization in industrial automation.

随着物联网（IoT）的快速发展，基于位置的服务（LBS）因其在日常生活中的广泛应用而备受关注。本文探讨了无线传感器网络（WSN）中的室内目标定位问题。本文提出了一种基于接收信号强度（RSS）和到达角（AoA）混合测量的路径损耗指数估计（PLE-WCLLS）的加权约束线性最小二乘法算法。为了应对未知传输功率和路径损耗指数（PLE）的挑战，所提出的方法采用了基于测距最大似然（ML）估计模型的线性最小二乘（LLS）估计方法来估计这两个参数。随后，设计了一种置信度权重调整策略，以减少定位误差。为了处理 RSS/AoA 混合优化模型的高度非凸和非线性性质，提出了一种基于泰勒级数展开的线性化方法。通过求解约束二次编程问题，实现了精确的目标位置估计。通过数值模拟和真实室内环境的实验评估，验证了所提算法的有效性。与传统的定位方法相比，PLE-WCLLS 算法的定位精度提高了 13.2%，即使在传感器节点较少的情况下也表现出色。这为它在物联网设备管理、智能建筑中的人员跟踪和工业自动化中的资产定位等领域带来了广阔的应用前景。

{"title":"A weighted hybrid indoor positioning method based on path loss exponent estimation","authors":"Yiting Wang, Jingqi Fu, Yifan Cao","doi":"10.1016/j.adhoc.2024.103684","DOIUrl":"10.1016/j.adhoc.2024.103684","url":null,"abstract":"<div><div>With the rapid development of the Internet of Things (IoT), location-based services (LBS) have gained significant attention due to their widespread applications in daily life. This paper addresses the indoor target positioning problem in wireless sensor networks (WSNs). A weighted constrained linear least squares algorithm based on path loss exponent estimation (PLE-WCLLS) with received signal strength (RSS) and angle of arrival (AoA) hybrid measurements is proposed. To address the challenges of unknown transmission power and path loss exponent (PLE), the proposed method employs a linear least squares (LLS) estimation approach based on the ranging maximum likelihood (ML) estimation model to estimate both parameters. Subsequently, a confidence weight adjustment strategy is designed to reduce positioning errors. To handle the highly non-convex and nonlinear nature of the RSS/AoA hybrid optimization model, a linearization method based on Taylor series expansion is presented. Accurate target position estimation is achieved by solving a constrained quadratic programming problem. The effectiveness of the proposed algorithm is validated through numerical simulations and experimental evaluation in a real indoor environment. Compared to traditional positioning methods, the PLE-WCLLS algorithm improves positioning accuracy by 13.2%, and it performs exceptionally well even in scenarios with fewer sensor nodes. This gives it broad application prospects in areas such as IoT device management, personnel tracking in smart buildings, and asset localization in industrial automation.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"166 ","pages":"Article 103684"},"PeriodicalIF":4.4,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533788","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 energy efficient prediction based protocol for target tracking in wireless sensor networks 基于能效预测的无线传感器网络目标跟踪协议

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-10-20 DOI: 10.1016/j.adhoc.2024.103688

Nadia Khiadani , Faramarz Hendessi

Target tracking is one of the most attractive applications of wireless sensor networks, used for estimating the moving target's position accurately. A primary challenge in this domain is achieving precise target path estimation while conserving energy resources. This paper introduces an energy-efficient target tracking protocol in wireless sensor networks, considering both accuracy and reduced energy consumption. The protocol uses the Kalman filter to estimate the target's position and predict the subsequent step of its path. In each step of target tracking, a selected sensor, named the ‘leader’ performs computations for position estimation and path prediction, while two other sensors, known as ‘assistants’ help the leader in the tracking process. Leader selection within the protocol is performed in two phases: an initial phase occurring upon the target's entry to the network and a subsequent phase named the forced handoff phase. The forced handoff phase performs the selection of a new leader when either the target exits the sensing range of the current leader or the leader's energy decreases significantly. Although the proposed protocol is a new work, it can be considered as an improvement of the PPCP protocol by adding several changes and also replacing the binary variational filter with the Kalman filter. The efficiency of the proposed protocol is evaluated through simulations in Matlab. Results demonstrate the protocol's ability to achieve high-precision target tracking while maintaining low energy consumption. Comparative analysis shows its energy efficiency, which significantly increases the network lifetime.

目标跟踪是无线传感器网络最具吸引力的应用之一，用于准确估计移动目标的位置。这一领域的主要挑战是在节约能源资源的同时实现精确的目标路径估计。本文介绍了无线传感器网络中的一种节能目标跟踪协议，同时考虑了精确度和降低能耗。该协议使用卡尔曼滤波器来估计目标位置，并预测其路径的后续步骤。在目标跟踪的每一步中，一个被称为 "领导者 "的选定传感器执行位置估计和路径预测计算，而另外两个被称为 "助手 "的传感器则在跟踪过程中帮助领导者。协议中的 "领导者 "选择分两个阶段进行：初始阶段发生在目标进入网络时，随后的阶段称为 "强制交接 "阶段。当目标退出当前领导者的感应范围或领导者的能量显著下降时，强制切换阶段就会选择新的领导者。虽然所提出的协议是一项新的工作，但它可以被视为 PPCP 协议的改进版，增加了一些变化，还用卡尔曼滤波器取代了二元变分滤波器。通过在 Matlab 中进行仿真，对所提协议的效率进行了评估。结果表明，该协议既能实现高精度目标跟踪，又能保持低能耗。对比分析表明，该协议的能效显著提高了网络寿命。

{"title":"An energy efficient prediction based protocol for target tracking in wireless sensor networks","authors":"Nadia Khiadani , Faramarz Hendessi","doi":"10.1016/j.adhoc.2024.103688","DOIUrl":"10.1016/j.adhoc.2024.103688","url":null,"abstract":"<div><div>Target tracking is one of the most attractive applications of wireless sensor networks, used for estimating the moving target's position accurately. A primary challenge in this domain is achieving precise target path estimation while conserving energy resources. This paper introduces an energy-efficient target tracking protocol in wireless sensor networks, considering both accuracy and reduced energy consumption. The protocol uses the Kalman filter to estimate the target's position and predict the subsequent step of its path. In each step of target tracking, a selected sensor, named the ‘leader’ performs computations for position estimation and path prediction, while two other sensors, known as ‘assistants’ help the leader in the tracking process. Leader selection within the protocol is performed in two phases: an initial phase occurring upon the target's entry to the network and a subsequent phase named the forced handoff phase. The forced handoff phase performs the selection of a new leader when either the target exits the sensing range of the current leader or the leader's energy decreases significantly. Although the proposed protocol is a new work, it can be considered as an improvement of the PPCP protocol by adding several changes and also replacing the binary variational filter with the Kalman filter. The efficiency of the proposed protocol is evaluated through simulations in Matlab. Results demonstrate the protocol's ability to achieve high-precision target tracking while maintaining low energy consumption. Comparative analysis shows its energy efficiency, which significantly increases the network lifetime.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"167 ","pages":"Article 103688"},"PeriodicalIF":4.4,"publicationDate":"2024-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142656958","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

EDRP-GTDQN: An adaptive routing protocol for energy and delay optimization in wireless sensor networks using game theory and deep reinforcement learning EDRP-GTDQN：利用博弈论和深度强化学习优化无线传感器网络能量和延迟的自适应路由协议

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-10-19 DOI: 10.1016/j.adhoc.2024.103687

Ning Liu, Jun Wang, Fazhan Tao, Zhumu Fu, Bo Liu

Routing protocols, as a crucial component of the internet of things (IoT), play a significant role in data collection and environmental monitoring tasks. However, existing clustering routing protocols suffer from issues such as uneven network energy consumption, high communication delays, and inadequate adaptation to topology changes. To address these issues, this study proposes an adaptive routing algorithm to balance energy consumption and delay using game theory and deep Q-network (DQN) algorithms (EDRP-GTDQN). Specifically, EDRP-GTDQN evaluates the importance of node positions using node centrality and integrates a game-theoretic-based approach to select optimal cluster heads in terms of node centrality and residual energy. Moreover, graph convolutional networks (GCN) and DQN are incorporated to construct transmission paths for cluster heads, adapt to network topology changes, and balance energy consumption and performance. Furthermore, a cluster rotation mechanism is employed to optimize overall network energy consumption and prevent the formation of hotspots. Experimental results demonstrate that EDRP-GTDQN achieves average performance improvements of 19.76%, 30.04%, 44.2%, and 61.42% in average energy consumption, network lifetime, and average end-to-end delay compared to conventional routing protocols such as EECRAIFA, MRP-GTCO, DEEC, and MH-LEACH. Therefore, EDRP-GTDQN is undoubtedly an effective solution to reduce energy consumption and enhance service quality in wireless sensor networks.

路由协议作为物联网（IoT）的重要组成部分，在数据收集和环境监测任务中发挥着重要作用。然而，现有的聚类路由协议存在网络能耗不均衡、通信延迟高、对拓扑变化适应性不足等问题。为解决这些问题，本研究提出了一种自适应路由算法，利用博弈论和深度 Q 网络（DQN）算法（EDRP-GTDQN）来平衡能耗和延迟。具体来说，EDRP-GTDQN 利用节点中心度评估节点位置的重要性，并整合基于博弈论的方法，从节点中心度和剩余能量的角度选择最佳簇头。此外，还采用图卷积网络（GCN）和 DQN 为簇头构建传输路径，适应网络拓扑变化，平衡能耗和性能。此外，还采用了簇轮换机制，以优化整体网络能耗，防止形成热点。实验结果表明，与 EECRAIFA、MRP-GTCO、DEEC 和 MH-LEACH 等传统路由协议相比，EDRP-GTDQN 在平均能耗、网络寿命和平均端到端延迟方面的平均性能分别提高了 19.76%、30.04%、44.2% 和 61.42%。因此，EDRP-GTDQN 无疑是无线传感器网络中降低能耗、提高服务质量的有效解决方案。

{"title":"EDRP-GTDQN: An adaptive routing protocol for energy and delay optimization in wireless sensor networks using game theory and deep reinforcement learning","authors":"Ning Liu, Jun Wang, Fazhan Tao, Zhumu Fu, Bo Liu","doi":"10.1016/j.adhoc.2024.103687","DOIUrl":"10.1016/j.adhoc.2024.103687","url":null,"abstract":"<div><div>Routing protocols, as a crucial component of the internet of things (IoT), play a significant role in data collection and environmental monitoring tasks. However, existing clustering routing protocols suffer from issues such as uneven network energy consumption, high communication delays, and inadequate adaptation to topology changes. To address these issues, this study proposes an adaptive routing algorithm to balance energy consumption and delay using game theory and deep Q-network (DQN) algorithms (EDRP-GTDQN). Specifically, EDRP-GTDQN evaluates the importance of node positions using node centrality and integrates a game-theoretic-based approach to select optimal cluster heads in terms of node centrality and residual energy. Moreover, graph convolutional networks (GCN) and DQN are incorporated to construct transmission paths for cluster heads, adapt to network topology changes, and balance energy consumption and performance. Furthermore, a cluster rotation mechanism is employed to optimize overall network energy consumption and prevent the formation of hotspots. Experimental results demonstrate that EDRP-GTDQN achieves average performance improvements of 19.76%, 30.04%, 44.2%, and 61.42% in average energy consumption, network lifetime, and average end-to-end delay compared to conventional routing protocols such as EECRAIFA, MRP-GTCO, DEEC, and MH-LEACH. Therefore, EDRP-GTDQN is undoubtedly an effective solution to reduce energy consumption and enhance service quality in wireless sensor networks.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"166 ","pages":"Article 103687"},"PeriodicalIF":4.4,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533786","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

Growth-adaptive distillation compressed fusion model for network traffic identification based on IoT cloud–edge collaboration 基于物联网云边协作的网络流量识别的增长自适应蒸馏压缩融合模型

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-10-18 DOI: 10.1016/j.adhoc.2024.103676

Yang Yang, Chengwen Fan, Shaoyin Chen, Zhipeng Gao, Lanlan Rui

The development of the Internet of Things (IoT) has led to the rapid growth of the types and number of connected devices and has generated large amounts of complex and diverse traffic data. Traffic identification on edge servers solves the real-time and privacy requirements of IoT management and has attracted much attention, but still faces several problems: (1) traditional machine learning (ML) models rely on artificially constructed features, and the existing deep learning (DL) traffic identification models have reached their performance limit; and (2) insufficient computing resources of edge servers limit the possible improvement in the performance of deep learning models by increasing the number of parameters and structural complexity. To address these issues, we propose a lightweight fusion model. First, the Network-in-Network (NiN) model and Random Forest (RF) model are used on the cloud server to construct a traffic identification fusion model. The excellent representation extraction capability of the NiN compensates for the RF’s dependence on manual feature extraction, and its modular structure is suitable for the subsequent model compression operations. Then, the NiN was distilled. We propose Growth-Adaptive Distillation to lightweight the NiN model, which can reduce the operation of manually adjusting the structure of the student model and ensure the efficiency and low power consumption of the fusion model deployment. In addition, both the RF in the cloud and the distilled NiN are deployed on the edge server. Comparisons with multiple algorithms on two network traffic datasets show that the proposed model achieves state-of-the-art performance while ensuring the use of minimal computational resources.

物联网（IoT）的发展带动了联网设备种类和数量的快速增长，并产生了大量复杂多样的流量数据。边缘服务器上的流量识别解决了物联网管理对实时性和隐私性的要求，受到了广泛关注，但仍面临几个问题：（1）传统的机器学习（ML）模型依赖于人工构建的特征，现有的深度学习（DL）流量识别模型已经达到了性能极限；（2）边缘服务器计算资源不足，增加了参数数量和结构复杂度，限制了深度学习模型性能的可能提升。针对这些问题，我们提出了一种轻量级融合模型。首先，在云服务器上使用网络中网络（NiN）模型和随机森林（RF）模型构建流量识别融合模型。NiN 卓越的表征提取能力弥补了 RF 对人工特征提取的依赖，其模块化结构也适合后续的模型压缩操作。然后，对 NiN 进行蒸馏。我们提出了生长自适应蒸馏法来实现 NiN 模型的轻量化，这样可以减少人工调整学生模型结构的操作，保证融合模型部署的高效率和低功耗。此外，云中的 RF 和蒸馏后的 NiN 都部署在边缘服务器上。在两个网络流量数据集上与多种算法的比较表明，所提出的模型达到了最先进的性能，同时确保使用最少的计算资源。

{"title":"Growth-adaptive distillation compressed fusion model for network traffic identification based on IoT cloud–edge collaboration","authors":"Yang Yang, Chengwen Fan, Shaoyin Chen, Zhipeng Gao, Lanlan Rui","doi":"10.1016/j.adhoc.2024.103676","DOIUrl":"10.1016/j.adhoc.2024.103676","url":null,"abstract":"<div><div>The development of the Internet of Things (IoT) has led to the rapid growth of the types and number of connected devices and has generated large amounts of complex and diverse traffic data. Traffic identification on edge servers solves the real-time and privacy requirements of IoT management and has attracted much attention, but still faces several problems: (1) traditional machine learning (ML) models rely on artificially constructed features, and the existing deep learning (DL) traffic identification models have reached their performance limit; and (2) insufficient computing resources of edge servers limit the possible improvement in the performance of deep learning models by increasing the number of parameters and structural complexity. To address these issues, we propose a lightweight fusion model. First, the Network-in-Network (NiN) model and Random Forest (RF) model are used on the cloud server to construct a traffic identification fusion model. The excellent representation extraction capability of the NiN compensates for the RF’s dependence on manual feature extraction, and its modular structure is suitable for the subsequent model compression operations. Then, the NiN was distilled. We propose Growth-Adaptive Distillation to lightweight the NiN model, which can reduce the operation of manually adjusting the structure of the student model and ensure the efficiency and low power consumption of the fusion model deployment. In addition, both the RF in the cloud and the distilled NiN are deployed on the edge server. Comparisons with multiple algorithms on two network traffic datasets show that the proposed model achieves state-of-the-art performance while ensuring the use of minimal computational resources.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"167 ","pages":"Article 103676"},"PeriodicalIF":4.4,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142573350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Approximation schemes for age of information minimization in UAV grid patrols 无人机网格巡逻中信息年龄最小化的近似方案

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-10-18 DOI: 10.1016/j.adhoc.2024.103686

Weiqi Wang , Jin Xu

Motivated by the critical need for unmanned aerial vehicles (UAVs) to patrol grid systems in hazardous and dynamically changing environments, this study addresses a routing problem aimed at minimizing the time-average Age of Information (AoI) for edges in general graphs. We establish a lower bound for all feasible patrol policies and demonstrate that this bound is tight when the graph contains an Eulerian cycle. For graphs without Eulerian cycles, it becomes challenging to identify the optimal patrol strategy due to the extensive range of feasible options. Our analysis shows that restricting the strategy to periodic sequences still results in an exponentially large number of possible strategies. To address this complexity, we introduce two polynomial-time approximation schemes, each involving a two-step process: constructing multigraphs first and then embedding Eulerian cycles within these multigraphs. We prove that both schemes achieve an approximation ratio of 2. Further, both analytical and numerical results suggest that evenly and sparsely distributing edge visits within a periodic route significantly reduces the average AoI compared to strategies that merely minimize the route travel distance. Building on this insight, we propose a heuristic method that not only maintains the approximation ratio of 2 but also ensures robust performance across varying random graphs.

无人驾驶飞行器（UAV）亟需在危险和动态变化的环境中巡逻网格系统，受此激励，本研究探讨了一个路由问题，旨在最大限度地降低一般图中边的平均时间信息年龄（AoI）。我们为所有可行的巡逻策略建立了一个下限，并证明当图中包含欧拉循环时，这个下限是紧密的。对于没有欧拉循环的图，由于可行方案的范围很广，确定最佳巡逻策略变得很有挑战性。我们的分析表明，将策略限制在周期序列上仍会导致可能的策略数量呈指数级增长。为了解决这种复杂性，我们引入了两种多项式时间近似方案，每种方案都涉及两个步骤：首先构建多图，然后在这些多图中嵌入欧拉循环。此外，分析和数值结果表明，与仅最小化路径旅行距离的策略相比，在周期性路径中均匀、稀疏地分布边缘访问可显著降低平均 AoI。在此基础上，我们提出了一种启发式方法，它不仅能保持 2 的近似率，还能确保在不同随机图中的稳健性能。

{"title":"Approximation schemes for age of information minimization in UAV grid patrols","authors":"Weiqi Wang , Jin Xu","doi":"10.1016/j.adhoc.2024.103686","DOIUrl":"10.1016/j.adhoc.2024.103686","url":null,"abstract":"<div><div>Motivated by the critical need for unmanned aerial vehicles (UAVs) to patrol grid systems in hazardous and dynamically changing environments, this study addresses a routing problem aimed at minimizing the time-average Age of Information (AoI) for edges in general graphs. We establish a lower bound for all feasible patrol policies and demonstrate that this bound is tight when the graph contains an Eulerian cycle. For graphs without Eulerian cycles, it becomes challenging to identify the optimal patrol strategy due to the extensive range of feasible options. Our analysis shows that restricting the strategy to periodic sequences still results in an exponentially large number of possible strategies. To address this complexity, we introduce two polynomial-time approximation schemes, each involving a two-step process: constructing multigraphs first and then embedding Eulerian cycles within these multigraphs. We prove that both schemes achieve an approximation ratio of 2. Further, both analytical and numerical results suggest that evenly and sparsely distributing edge visits within a periodic route significantly reduces the average AoI compared to strategies that merely minimize the route travel distance. Building on this insight, we propose a heuristic method that not only maintains the approximation ratio of 2 but also ensures robust performance across varying random graphs.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"166 ","pages":"Article 103686"},"PeriodicalIF":4.4,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533785","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

Requester mobility for mobile crowdsensing system: A dynamic alliance-based incentive mechanism 移动人群感应系统的请求者流动性：基于联盟的动态激励机制

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-10-16 DOI: 10.1016/j.adhoc.2024.103680

Zhilin Xu , Hao Sun , Panfei Sun , Qianqian Kong

In the Mobile Crowdsensing (MCS) system, due to the heterogeneity of requesters, they are in mobile which means requesters will join or leave the MCS system at different times and their data demands are time-varying. The uncertainty of requesters caused by requester mobility will generate the instability of the match between requesters and participants which means the established matching algorithm cannot be completed due to the dissatisfaction of requesters and participants caused by the changes in the intensity of competition. For requester mobility, we design a dynamic alliance-based incentive mechanism where requesters can leave, join the MCS system separately, and change their data needs. To the instability, we divide the dynamic mechanism into different stages and will update the matching rules in each stage. A unique algorithm based on the dynamic Stackelberg game and the corresponding updated algorithm is proposed to analyze the matching strategies of requesters and participants to make an optimal match. By proving the stability of the updated rules, we guarantee the stability of the match with requester mobility. Through numerical analysis, alliance formation can significantly reduce weak requesters’ costs by at most 90%. Besides, in our mechanism any requester participates in the game at most twice, the chosen rate can be up to 100%.

在移动众测（MCS）系统中，由于请求者的异质性，他们处于移动状态，这意味着请求者会在不同时间加入或离开移动众测系统，他们的数据需求也是时变的。请求者的流动性导致的请求者的不确定性会造成请求者和参与者之间匹配的不稳定性，即由于竞争激烈程度的变化导致请求者和参与者的不满，既定的匹配算法无法完成。针对请求者的流动性，我们设计了一种基于联盟的动态激励机制，请求者可以分别离开、加入 MCS 系统，并改变自己的数据需求。针对不稳定性，我们将动态机制分为不同阶段，并在每个阶段更新匹配规则。我们提出了一种基于动态斯塔克尔伯格博弈的独特算法和相应的更新算法，以分析请求者和参与者的匹配策略，从而实现最优匹配。通过证明更新规则的稳定性，我们保证了请求者流动时匹配的稳定性。通过数值分析，联盟的形成可以大大降低弱请求者的成本，最多可降低 90%。此外，在我们的机制中，任何请求者最多参与两次博弈，选择率可达 100%。

{"title":"Requester mobility for mobile crowdsensing system: A dynamic alliance-based incentive mechanism","authors":"Zhilin Xu , Hao Sun , Panfei Sun , Qianqian Kong","doi":"10.1016/j.adhoc.2024.103680","DOIUrl":"10.1016/j.adhoc.2024.103680","url":null,"abstract":"<div><div>In the Mobile Crowdsensing (MCS) system, due to the heterogeneity of requesters, they are in mobile which means requesters will join or leave the MCS system at different times and their data demands are time-varying. The uncertainty of requesters caused by requester mobility will generate the instability of the match between requesters and participants which means the established matching algorithm cannot be completed due to the dissatisfaction of requesters and participants caused by the changes in the intensity of competition. For requester mobility, we design a dynamic alliance-based incentive mechanism where requesters can leave, join the MCS system separately, and change their data needs. To the instability, we divide the dynamic mechanism into different stages and will update the matching rules in each stage. A unique algorithm based on the dynamic Stackelberg game and the corresponding updated algorithm is proposed to analyze the matching strategies of requesters and participants to make an optimal match. By proving the stability of the updated rules, we guarantee the stability of the match with requester mobility. Through numerical analysis, alliance formation can significantly reduce weak requesters’ costs by at most 90%. Besides, in our mechanism any requester participates in the game at most twice, the chosen rate can be up to 100%.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"166 ","pages":"Article 103680"},"PeriodicalIF":4.4,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533787","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

FLAV: Federated Learning for Autonomous Vehicle privacy protection FLAV：为保护自主车辆隐私而进行的联合学习

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-10-16 DOI: 10.1016/j.adhoc.2024.103685

Yingchun Cui , Jinghua Zhu , Jinbao Li

Autonomous Vehicle Systems are committed to safer, more efficient and more convenient transportation on the roads of the future. However, concerns about vehicle data privacy and security remain significant. Federated Learning, as a decentralized machine learning approach, allows multiple devices or data sources to collaboratively train models without sharing raw data, providing essential privacy protection. In this paper, we propose a privacy-preserving framework for autonomous vehicles, named FLAV. First, we use a multi-chain parallel aggregation strategy to transmit model parameters and design a model parameter filtering mechanism, which reduces communication overhead by filtering out the local model parameters of certain vehicles, thereby alleviating bandwidth pressure. Second, we introduce a dynamic adjustment mechanism that automatically adjusts regularization strength by comparing each vehicle’s local parameters with the cumulative parameters of preceding vehicles in the chain. This mechanism balances local training with global consistency, ensuring the model’s adaptability to local data while improving coordination between vehicles in the chain. Experimental results demonstrate that our proposed method reduces communication costs while improving model accuracy and privacy protection level, effectively ensuring the security of autonomous driving data.

自动驾驶汽车系统致力于在未来的道路上提供更安全、更高效、更便捷的交通。然而，对车辆数据隐私和安全的担忧依然存在。联合学习作为一种分散的机器学习方法，允许多个设备或数据源在不共享原始数据的情况下协作训练模型，从而提供必要的隐私保护。在本文中，我们为自动驾驶汽车提出了一个隐私保护框架，命名为 FLAV。首先，我们采用多链并行聚合策略来传输模型参数，并设计了模型参数过滤机制，通过过滤掉某些车辆的本地模型参数来减少通信开销，从而减轻带宽压力。其次，我们引入了一种动态调整机制，通过比较每辆车的本地参数和链中前一辆车的累积参数，自动调整正则化强度。这种机制兼顾了局部训练和全局一致性，确保了模型对局部数据的适应性，同时改善了链中车辆之间的协调性。实验结果表明，我们提出的方法降低了通信成本，同时提高了模型的准确性和隐私保护水平，有效确保了自动驾驶数据的安全性。

{"title":"FLAV: Federated Learning for Autonomous Vehicle privacy protection","authors":"Yingchun Cui , Jinghua Zhu , Jinbao Li","doi":"10.1016/j.adhoc.2024.103685","DOIUrl":"10.1016/j.adhoc.2024.103685","url":null,"abstract":"<div><div>Autonomous Vehicle Systems are committed to safer, more efficient and more convenient transportation on the roads of the future. However, concerns about vehicle data privacy and security remain significant. Federated Learning, as a decentralized machine learning approach, allows multiple devices or data sources to collaboratively train models without sharing raw data, providing essential privacy protection. In this paper, we propose a privacy-preserving framework for autonomous vehicles, named FLAV. First, we use a multi-chain parallel aggregation strategy to transmit model parameters and design a model parameter filtering mechanism, which reduces communication overhead by filtering out the local model parameters of certain vehicles, thereby alleviating bandwidth pressure. Second, we introduce a dynamic adjustment mechanism that automatically adjusts regularization strength by comparing each vehicle’s local parameters with the cumulative parameters of preceding vehicles in the chain. This mechanism balances local training with global consistency, ensuring the model’s adaptability to local data while improving coordination between vehicles in the chain. Experimental results demonstrate that our proposed method reduces communication costs while improving model accuracy and privacy protection level, effectively ensuring the security of autonomous driving data.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"166 ","pages":"Article 103685"},"PeriodicalIF":4.4,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533687","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 distributed intrusion detection framework for vehicular Ad Hoc networks via federated learning and Blockchain 通过联合学习和区块链实现车载 Ad Hoc 网络的分布式入侵检测框架

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2024-10-15 DOI: 10.1016/j.adhoc.2024.103677

Fedwa Mansouri , Mounira Tarhouni , Bechir Alaya , Salah Zidi

The emergence of connected vehicles via Vehicular Ad Hoc Networks (VANETs) has revolutionized transportation but has also brought forth challenges in security and privacy due to their open architecture. Early detection of intrusions within VANETs is paramount for ensuring safe communication. This research presents an intelligent distributed approach that leverages federated learning (FL) and blockchain for intrusion detection in VANETs. Through FL, various neural network models were implemented to distribute model training among vehicles, thus preserving privacy. Quantitative evaluation metrics demonstrate the effectiveness of the proposed framework. For example, compared to a traditionally trained Stochastic Gradient Descent (SGD) model, the Federated Trained Model achieved higher precision across various attack types, ranging from 68 % to 94 %, and consistently outperformed in terms of recall, with rates ranging from 57 % to 88 %. These results highlight FL's superiority in detecting intrusions, evidenced by gains in accuracy, recall, and precision. Integration of FL with blockchain further strengthened security and privacy protection, ensuring data integrity during collaborative FL training across decentralized nodes. This novel framework addresses VANET vulnerabilities by facilitating privacy-preserving, collaborative anomaly monitoring in a trustworthy manner. Evaluations validate the performance advantages of FL for intrusion identification, supporting wider adoption of vehicular technologies. The study underscores the potential of combining FL and blockchain to enable robust, cooperative abnormality recognition crucial for maintaining reliability, safety, and trust in VANET operations.

通过车载 Ad Hoc 网络（VANET）连接车辆的出现给交通带来了革命性的变化，但由于其开放式架构，也给安全和隐私带来了挑战。要确保通信安全，就必须及早发现 VANET 中的入侵行为。本研究提出了一种利用联合学习（FL）和区块链进行 VANET 入侵检测的智能分布式方法。通过联合学习，各种神经网络模型得以在车辆之间分布式训练，从而保护了隐私。定量评估指标证明了拟议框架的有效性。例如，与传统训练的随机梯度下降（SGD）模型相比，联合训练模型在各种攻击类型中都实现了更高的精确度，从 68% 到 94%，在召回率方面也始终保持领先，从 57% 到 88%。这些结果凸显了 FL 在检测入侵方面的优势，准确率、召回率和精确率的提高就是证明。FL 与区块链的集成进一步加强了安全性和隐私保护，确保了分散节点之间协作式 FL 培训期间的数据完整性。这种新型框架以可信的方式促进了保护隐私的协作式异常监测，从而解决了 VANET 的漏洞问题。评估验证了 FL 在入侵识别方面的性能优势，支持更广泛地采用车载技术。这项研究强调了将 FL 与区块链相结合的潜力，以实现稳健、合作的异常识别，这对维护 VANET 运行的可靠性、安全性和信任度至关重要。

{"title":"A distributed intrusion detection framework for vehicular Ad Hoc networks via federated learning and Blockchain","authors":"Fedwa Mansouri , Mounira Tarhouni , Bechir Alaya , Salah Zidi","doi":"10.1016/j.adhoc.2024.103677","DOIUrl":"10.1016/j.adhoc.2024.103677","url":null,"abstract":"<div><div>The emergence of connected vehicles via Vehicular Ad Hoc Networks (VANETs) has revolutionized transportation but has also brought forth challenges in security and privacy due to their open architecture. Early detection of intrusions within VANETs is paramount for ensuring safe communication. This research presents an intelligent distributed approach that leverages federated learning (FL) and blockchain for intrusion detection in VANETs. Through FL, various neural network models were implemented to distribute model training among vehicles, thus preserving privacy. Quantitative evaluation metrics demonstrate the effectiveness of the proposed framework. For example, compared to a traditionally trained Stochastic Gradient Descent (SGD) model, the Federated Trained Model achieved higher precision across various attack types, ranging from 68 % to 94 %, and consistently outperformed in terms of recall, with rates ranging from 57 % to 88 %. These results highlight FL's superiority in detecting intrusions, evidenced by gains in accuracy, recall, and precision. Integration of FL with blockchain further strengthened security and privacy protection, ensuring data integrity during collaborative FL training across decentralized nodes. This novel framework addresses VANET vulnerabilities by facilitating privacy-preserving, collaborative anomaly monitoring in a trustworthy manner. Evaluations validate the performance advantages of FL for intrusion identification, supporting wider adoption of vehicular technologies. The study underscores the potential of combining FL and blockchain to enable robust, cooperative abnormality recognition crucial for maintaining reliability, safety, and trust in VANET operations<strong>.</strong></div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"167 ","pages":"Article 103677"},"PeriodicalIF":4.4,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142656954","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