Pervasive and Mobile Computing最新文献

LAAS-KM: Lightweight authentication with aggregate signature verification and key management protocol for VANETs LAAS-KM：用于VANETs的具有聚合签名验证和密钥管理协议的轻量级身份验证

IF 3.5 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2026-05-01 Epub Date: 2026-02-09 DOI: 10.1016/j.pmcj.2026.102183

A. Anshima , Jegadeesan Subramani , Arun Sekar Rajasekaran

Vehicular Ad Hoc Networks (VANETs) are a significant component of upcoming intelligent transportation systems. VANETs improve road safety by sending danger alerts to drivers; therefore, their messages must be secure and unaltered. Digital signatures are used to verify the integrity and authenticity of transmitted messages; however, existing digital signature-based schemes require a high computational time owing to the repeated use of mathematical operations. To address this issue, a novel signature aggregation and key management (LAAS-KM) scheme is proposed in this paper to reduce the computational cost without compromising security. First, the LAAS-KM allows roadside infrastructure to cluster multiple vehicle signatures into a compact signature to reduce the large computational overhead during the verification process. Moreover, LAAS-KM supports group communication with novel key management to update keys as vehicles move and network topologies change dynamically in VANETs. Moreover, the security analysis section indicates that the LAAS-KM can prevent various security attacks, including impersonation and replay attacks. Furthermore, a formal security analysis is performed using the Scyther tool to validate the critical security properties of LAAS-KM. Performance evaluations show that LAAS-KM outperforms traditional schemes in terms of communication and computation overheads. Finally, a practical simulation is performed using MATLAB, and the performance metrics are analyzed.

车辆自组织网络（vanet）是未来智能交通系统的重要组成部分。VANETs通过向驾驶员发送危险警报来改善道路安全；因此，他们的消息必须是安全且未被更改的。数字签名用于验证传输消息的完整性和真实性；然而，现有的基于数字签名的方案由于重复使用数学运算，需要大量的计算时间。为了解决这一问题，本文提出了一种新的签名聚合和密钥管理（LAAS-KM）方案，在不影响安全性的前提下降低了计算成本。首先，LAAS-KM允许路边基础设施将多个车辆签名聚类为一个紧凑的签名，以减少验证过程中的大量计算开销。此外，LAAS-KM支持群组通信，采用新颖的密钥管理，在vanet中随着车辆移动和网络拓扑动态变化而更新密钥。此外，安全分析部分指出，LAAS-KM可以防止各种安全攻击，包括模拟攻击和重放攻击。此外，使用Scyther工具执行了正式的安全性分析，以验证LAAS-KM的关键安全属性。性能评估表明，LAAS-KM在通信和计算开销方面优于传统方案。最后，利用MATLAB进行了实际仿真，并对性能指标进行了分析。

{"title":"LAAS-KM: Lightweight authentication with aggregate signature verification and key management protocol for VANETs","authors":"A. Anshima , Jegadeesan Subramani , Arun Sekar Rajasekaran","doi":"10.1016/j.pmcj.2026.102183","DOIUrl":"10.1016/j.pmcj.2026.102183","url":null,"abstract":"<div><div>Vehicular Ad Hoc Networks (VANETs) are a significant component of upcoming intelligent transportation systems. VANETs improve road safety by sending danger alerts to drivers; therefore, their messages must be secure and unaltered. Digital signatures are used to verify the integrity and authenticity of transmitted messages; however, existing digital signature-based schemes require a high computational time owing to the repeated use of mathematical operations. To address this issue, a novel signature aggregation and key management (LAAS-KM) scheme is proposed in this paper to reduce the computational cost without compromising security. First, the LAAS-KM allows roadside infrastructure to cluster multiple vehicle signatures into a compact signature to reduce the large computational overhead during the verification process. Moreover, LAAS-KM supports group communication with novel key management to update keys as vehicles move and network topologies change dynamically in VANETs. Moreover, the security analysis section indicates that the LAAS-KM can prevent various security attacks, including impersonation and replay attacks. Furthermore, a formal security analysis is performed using the Scyther tool to validate the critical security properties of LAAS-KM. Performance evaluations show that LAAS-KM outperforms traditional schemes in terms of communication and computation overheads. Finally, a practical simulation is performed using MATLAB, and the performance metrics are analyzed.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"118 ","pages":"Article 102183"},"PeriodicalIF":3.5,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146147121","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

Coordination-free decentralised federated learning in pervasive networks: Overcoming heterogeneity 普适网络中无协调的去中心化联邦学习：克服异质性

IF 3.5 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2026-05-01 Epub Date: 2026-02-06 DOI: 10.1016/j.pmcj.2026.102184

Lorenzo Valerio , Chiara Boldrini , Andrea Passarella , János Kertész , Márton Karsai , Gerardo Iñiguez

Fully decentralised federated learning enables collaborative model training among edge devices without relying on a central coordinator, thereby avoiding single points of failure and supporting spontaneous collaboration in pervasive environments. However, the absence of coordination introduces challenges that go beyond data heterogeneity alone. In realistic decentralised settings, devices often start from different model initializations, possess limited and non-IID local data, and interact over unstructured communication graphs, making naive parameter averaging ineffective and potentially destructive. In this paper, we address decentralised learning under combined data and initial model heterogeneity by proposing DecDiff+VT, a coordination-free decentralised learning algorithm specifically designed for such environments. DecDiff+VT integrates two complementary mechanisms: DecDiff, a disruption-aware aggregation strategy that updates local models towards their neighborhood average with a magnitude inversely proportional to model disagreement, and a lightweight virtual teacher (VT) mechanism based on soft-label regularization to improve local generalization in the absence of strong or centralized teacher models. Extensive experiments on image classification and activity recognition benchmarks (MNIST, Fashion-MNIST, EMNIST, CIFAR-10, and UCI-HAR) show that DecDiff+VT consistently outperforms or matches state-of-the-art decentralised baselines, achieving faster convergence, improved generalization, and greater robustness to overfitting, without incurring additional communication or memory overhead compared to standard decentralised averaging.

完全分散的联邦学习可以在边缘设备之间进行协作模型训练，而无需依赖中央协调器，从而避免单点故障，并支持无处不在的环境中的自发协作。然而，缺乏协调带来的挑战不仅仅是数据异构。在现实的分散设置中，设备通常从不同的模型初始化开始，拥有有限的非iid本地数据，并在非结构化通信图上进行交互，使得朴素的参数平均无效且具有潜在的破坏性。在本文中，我们通过提出DecDiff+VT来解决组合数据和初始模型异质性下的分散学习问题，DecDiff+VT是一种专门为这种环境设计的无协调分散学习算法。DecDiff+VT集成了两种互补机制：DecDiff是一种干扰感知聚合策略，它将局部模型更新为其邻域平均值，其大小与模型分歧成反比；DecDiff是一种基于软标签正则化的轻量级虚拟教师（VT）机制，用于在缺乏强或集中的教师模型的情况下提高局部泛化。在图像分类和活动识别基准（MNIST、Fashion-MNIST、EMNIST、CIFAR-10和UCI-HAR）上进行的大量实验表明，DecDiff+VT始终优于或匹配最先进的分散基线，实现了更快的收敛、改进的泛化和更强的过拟合鲁棒性，与标准分散平均相比，不会产生额外的通信或内存开销。

{"title":"Coordination-free decentralised federated learning in pervasive networks: Overcoming heterogeneity","authors":"Lorenzo Valerio , Chiara Boldrini , Andrea Passarella , János Kertész , Márton Karsai , Gerardo Iñiguez","doi":"10.1016/j.pmcj.2026.102184","DOIUrl":"10.1016/j.pmcj.2026.102184","url":null,"abstract":"<div><div>Fully decentralised federated learning enables collaborative model training among edge devices without relying on a central coordinator, thereby avoiding single points of failure and supporting spontaneous collaboration in pervasive environments. However, the absence of coordination introduces challenges that go beyond data heterogeneity alone. In realistic decentralised settings, devices often start from different model initializations, possess limited and non-IID local data, and interact over unstructured communication graphs, making naive parameter averaging ineffective and potentially destructive. In this paper, we address decentralised learning under <em>combined data and initial model heterogeneity</em> by proposing DecDiff+VT, a coordination-free decentralised learning algorithm specifically designed for such environments. DecDiff+VT integrates two complementary mechanisms: DecDiff, a disruption-aware aggregation strategy that updates local models towards their neighborhood average with a magnitude inversely proportional to model disagreement, and a lightweight <em>virtual teacher</em> (VT) mechanism based on soft-label regularization to improve local generalization in the absence of strong or centralized teacher models. Extensive experiments on image classification and activity recognition benchmarks (MNIST, Fashion-MNIST, EMNIST, CIFAR-10, and UCI-HAR) show that DecDiff+VT consistently outperforms or matches state-of-the-art decentralised baselines, achieving faster convergence, improved generalization, and greater robustness to overfitting, without incurring additional communication or memory overhead compared to standard decentralised averaging.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"118 ","pages":"Article 102184"},"PeriodicalIF":3.5,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192891","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

FreTransLS: Frequency Transformer based large-scale group activity recognition model for sensor data FreTransLS：基于变频器的传感器数据大规模群体活动识别模型

IF 3.5 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2026-04-01 Epub Date: 2026-01-28 DOI: 10.1016/j.pmcj.2026.102179

Ruohong Huan, Meijiao Cao, Yantong Zhou, Ji Zhang, Peng Chen, Guodao Sun, Ronghua Liang

In large-scale group activities, participants engage in a wider variety of actions, and the interactions among them become significantly more complex. This gives rise to challenges including synchronization and coordination analysis in group activity recognition. As a result, existing methods designed for recognizing small-scale group activities using sensor data often lead to inaccurate identification of dynamic patterns in large-scale settings. To address this issue, this paper proposes FreTransLS—a frequency Transformer-based model for large-scale group activity recognition using sensor data. FreTransLS introduces a novel approach for extracting time–frequency features in large-scale group activities. The approach integrates a spatio-temporal graph convolutional network (ST-GCN) module to capture spatio-temporal features within the group, along with a group location feature extraction (GLFE) module to acquire group location features. These two feature streams are fused to derive comprehensive time-domain representations of group activities. Furthermore, FreTransLS incorporates a frequency Transformer encoder built around a frequency attention mechanism. This encoder performs global analysis in the frequency domain to better model synchronization and coordination patterns in group activities. To enhance the generalization capability of the model, FreTransLS adopts a joint optimization strategy through complementary classification and reconstruction modules, which jointly refine the extracted time–frequency features. Experiments on two public datasets demonstrate that the proposed method effectively captures discriminative features from sensor data in large-scale group scenarios, leading to improved accuracy and robustness in group activity recognition.

在大规模的群体活动中，参与者参与的行动种类越来越多，他们之间的互动也变得更加复杂。这给群体活动识别中的同步性和协调性分析带来了挑战。因此，现有的利用传感器数据识别小规模群体活动的方法往往无法准确识别大规模环境下的动态模式。为了解决这个问题，本文提出了fretransls -一种基于频率转换器的模型，用于使用传感器数据进行大规模群体活动识别。FreTransLS提出了一种新的大规模群体活动时频特征提取方法。该方法集成了一个时空图卷积网络（ST-GCN）模块来捕获群体内的时空特征，以及一个群体位置特征提取（GLFE）模块来获取群体位置特征。这两种特征流融合在一起，得到了群体活动的综合时域表示。此外，FreTransLS集成了一个围绕频率注意机制构建的频率转换器编码器。该编码器在频域执行全局分析，以更好地模拟群体活动中的同步和协调模式。为了增强模型的泛化能力，FreTransLS采用互补分类和重构模块的联合优化策略，共同细化提取的时频特征。在两个公共数据集上的实验表明，该方法能有效地捕获大规模群体场景下传感器数据的判别特征，提高了群体活动识别的准确性和鲁棒性。

{"title":"FreTransLS: Frequency Transformer based large-scale group activity recognition model for sensor data","authors":"Ruohong Huan, Meijiao Cao, Yantong Zhou, Ji Zhang, Peng Chen, Guodao Sun, Ronghua Liang","doi":"10.1016/j.pmcj.2026.102179","DOIUrl":"10.1016/j.pmcj.2026.102179","url":null,"abstract":"<div><div>In large-scale group activities, participants engage in a wider variety of actions, and the interactions among them become significantly more complex. This gives rise to challenges including synchronization and coordination analysis in group activity recognition. As a result, existing methods designed for recognizing small-scale group activities using sensor data often lead to inaccurate identification of dynamic patterns in large-scale settings. To address this issue, this paper proposes FreTransLS—a frequency Transformer-based model for large-scale group activity recognition using sensor data. FreTransLS introduces a novel approach for extracting time–frequency features in large-scale group activities. The approach integrates a spatio-temporal graph convolutional network (ST-GCN) module to capture spatio-temporal features within the group, along with a group location feature extraction (GLFE) module to acquire group location features. These two feature streams are fused to derive comprehensive time-domain representations of group activities. Furthermore, FreTransLS incorporates a frequency Transformer encoder built around a frequency attention mechanism. This encoder performs global analysis in the frequency domain to better model synchronization and coordination patterns in group activities. To enhance the generalization capability of the model, FreTransLS adopts a joint optimization strategy through complementary classification and reconstruction modules, which jointly refine the extracted time–frequency features. Experiments on two public datasets demonstrate that the proposed method effectively captures discriminative features from sensor data in large-scale group scenarios, leading to improved accuracy and robustness in group activity recognition.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"117 ","pages":"Article 102179"},"PeriodicalIF":3.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146079111","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

FedEMMD: Entropy and MMD-based data and aggregation selection for non-iid and long-tailed data in federated learning FedEMMD：联邦学习中基于熵和mmd的数据和非id和长尾数据的聚合选择

IF 3.5 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2026-04-01 Epub Date: 2025-12-30 DOI: 10.1016/j.pmcj.2025.102159

Nafas Gul Saadat, Santhosh Kumar G.

The increasing need for privacy-preserving machine learning has rendered centralized data collection progressively unfeasible. To solve this, Federated Learning (FL) has emerged as a distributed learning paradigm in which multiple clients collectively train a shared global model while keeping all data locally, ensuring that no private data is sent over the network. However, FL is often hindered by statistical heterogeneity, where clients’ data are non-independent and identically distributed (non-iid), resulting in biased local updates and reduced global model performance. To overcome these key challenges, this study proposes FedEMMD, a novel method to enhance model performance under heterogeneous data. First, entropy-based data selection is used to identify and select high-quality data with a lower degree of non-iidness. Second, Maximum Mean Discrepancy (MMD) is used to calculate the divergence between local updates and the global model, guaranteeing that only stable and consistent updates are aggregated on the global model. Experiments have been conducted in two heterogeneous settings (non-iid and long-tailed distribution), using CIFAR-10 and CIFAR-10-LT. Additionally, we conduct experiments with centralized Machine Learning (ML) under the same settings to establish a baseline to evaluate the effect of data heterogeneity on centralized ML. The experimental results demonstrate that FedEMMD outperforms state-of-the-art algorithms such as FedAvg, FedProx, Scaffold, and FedOpt in terms of accuracy and convergence speed in both non-iid and long-tailed scenarios, thereby improving robustness and performance under heterogeneous settings.

对保护隐私的机器学习的需求日益增长，使得集中收集数据变得越来越不可行。为了解决这个问题，联邦学习（FL）作为一种分布式学习范例出现了，在这种范例中，多个客户端共同训练一个共享的全局模型，同时将所有数据保存在本地，确保没有私有数据通过网络发送。然而，FL经常受到统计异质性的阻碍，其中客户端的数据是非独立和同分布的（non-iid），导致局部更新有偏差，降低了全局模型的性能。为了克服这些关键挑战，本研究提出了一种新的方法FedEMMD来提高异构数据下的模型性能。首先，使用基于熵的数据选择来识别和选择非完整性程度较低的高质量数据。其次，利用最大平均差异（Maximum Mean difference， MMD）计算局部更新与全局模型之间的差异，保证在全局模型上只聚合稳定一致的更新。使用CIFAR-10和CIFAR-10- lt在两种异质环境下（非id分布和长尾分布）进行了实验。此外，我们在相同设置下对集中式机器学习（ML）进行了实验，以建立基线来评估数据异质性对集中式机器学习的影响。实验结果表明，FedEMMD在非id和长尾场景下的准确性和收敛速度都优于FedAvg、FedProx、Scaffold和FedOpt等最先进的算法，从而提高了异构设置下的鲁棒性和性能。

{"title":"FedEMMD: Entropy and MMD-based data and aggregation selection for non-iid and long-tailed data in federated learning","authors":"Nafas Gul Saadat, Santhosh Kumar G.","doi":"10.1016/j.pmcj.2025.102159","DOIUrl":"10.1016/j.pmcj.2025.102159","url":null,"abstract":"<div><div>The increasing need for privacy-preserving machine learning has rendered centralized data collection progressively unfeasible. To solve this, Federated Learning (FL) has emerged as a distributed learning paradigm in which multiple clients collectively train a shared global model while keeping all data locally, ensuring that no private data is sent over the network. However, FL is often hindered by statistical heterogeneity, where clients’ data are non-independent and identically distributed (non-iid), resulting in biased local updates and reduced global model performance. To overcome these key challenges, this study proposes FedEMMD, a novel method to enhance model performance under heterogeneous data. First, entropy-based data selection is used to identify and select high-quality data with a lower degree of non-iidness. Second, Maximum Mean Discrepancy (MMD) is used to calculate the divergence between local updates and the global model, guaranteeing that only stable and consistent updates are aggregated on the global model. Experiments have been conducted in two heterogeneous settings (non-iid and long-tailed distribution), using CIFAR-10 and CIFAR-10-LT. Additionally, we conduct experiments with centralized Machine Learning (ML) under the same settings to establish a baseline to evaluate the effect of data heterogeneity on centralized ML. The experimental results demonstrate that FedEMMD outperforms state-of-the-art algorithms such as FedAvg, FedProx, Scaffold, and FedOpt in terms of accuracy and convergence speed in both non-iid and long-tailed scenarios, thereby improving robustness and performance under heterogeneous settings.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"117 ","pages":"Article 102159"},"PeriodicalIF":3.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145915146","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

Mobility-aware Q-learning for workload offloading in vehicular edge–cloud environment 基于移动感知q学习的车辆边缘云环境下的工作负载卸载

IF 3.5 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2026-04-01 Epub Date: 2026-01-13 DOI: 10.1016/j.pmcj.2026.102172

Afzal Badshah , Abdulrahman Ahmed Gharawi , Mona Eisa , Nada Alzaben , Saud Yonbawi , Ali Daud

The Intelligent Transportation System (ITS) continuously generates data that needs to be processed under strict latency and connectivity constraints across a heterogeneous computing architecture (e.g., Vehicular Edge Computing (VEC), Mobile Edge Computing (MEC), and Cloud Computing (CC)). In this context, efficient task offloading requires mobility and server-aware intelligence to optimize communication delay, cost, and resource utilization. In this paper, we propose a mobility-aware Q-learning offloading scheduler that learns optimal tier selection on real-time metrics (e.g., resource availability, signal strength, and Base Station (BS) handover dynamics). Unlike the previous investigation, this approach explicitly incorporates vehicle mobility patterns to the offloading decision using Q-learning. The scheduler favors VEC when underutilized, transitions to MEC when the VEC is overutilized, and falls back to the cloud only when VEC and MEC are infeasible. A structured reward model reinforces decisions that improve resource efficiency and penalizes excessive switching or skipping underutilized resources. The proposed framework is evaluated using DriveNetSim, a custom-developed vehicular simulator that models realistic mobility, signal degradation, and BS switching. Simulation results show a strong preference for VEC, with shifts to MEC only under VEC over-utilization and minimal reliance on the cloud. As a result, the system achieves up to 43% reduction in transmission delay and 38% reduction in processing cost, validating its effectiveness in dynamic vehicular environments.

智能交通系统（ITS）不断生成数据，这些数据需要在严格的延迟和连接约束下跨异构计算架构（例如，车辆边缘计算（VEC），移动边缘计算（MEC）和云计算（CC））进行处理。在这种情况下，高效的任务卸载需要机动性和服务器感知智能来优化通信延迟、成本和资源利用率。在本文中，我们提出了一个移动性感知的q -学习卸载调度程序，该调度程序根据实时指标（例如，资源可用性，信号强度和基站（BS）切换动态）学习最佳层选择。与之前的研究不同，该方法明确地将车辆移动模式结合到使用q学习的卸载决策中。调度程序在未充分利用时倾向于VEC，在VEC被过度利用时过渡到MEC，只有在VEC和MEC不可行的情况下才会回到云。结构化的奖励模式强化了提高资源效率的决策，并惩罚过度转换或跳过未充分利用的资源。所提出的框架使用DriveNetSim进行评估，DriveNetSim是一种定制开发的车辆模拟器，可以模拟现实的移动性、信号退化和BS切换。模拟结果显示，人们对VEC有强烈的偏好，只有在VEC过度利用和对云的依赖最小的情况下，才会转向MEC。结果表明，该系统的传输延迟降低了43%，处理成本降低了38%，验证了其在动态车辆环境中的有效性。

{"title":"Mobility-aware Q-learning for workload offloading in vehicular edge–cloud environment","authors":"Afzal Badshah , Abdulrahman Ahmed Gharawi , Mona Eisa , Nada Alzaben , Saud Yonbawi , Ali Daud","doi":"10.1016/j.pmcj.2026.102172","DOIUrl":"10.1016/j.pmcj.2026.102172","url":null,"abstract":"<div><div>The Intelligent Transportation System (ITS) continuously generates data that needs to be processed under strict latency and connectivity constraints across a heterogeneous computing architecture (e.g., Vehicular Edge Computing (VEC), Mobile Edge Computing (MEC), and Cloud Computing (CC)). In this context, efficient task offloading requires mobility and server-aware intelligence to optimize communication delay, cost, and resource utilization. In this paper, we propose a mobility-aware Q-learning offloading scheduler that learns optimal tier selection on real-time metrics (e.g., resource availability, signal strength, and Base Station (BS) handover dynamics). Unlike the previous investigation, this approach explicitly incorporates vehicle mobility patterns to the offloading decision using Q-learning. The scheduler favors VEC when underutilized, transitions to MEC when the VEC is overutilized, and falls back to the cloud only when VEC and MEC are infeasible. A structured reward model reinforces decisions that improve resource efficiency and penalizes excessive switching or skipping underutilized resources. The proposed framework is evaluated using <em>DriveNetSim</em>, a custom-developed vehicular simulator that models realistic mobility, signal degradation, and BS switching. Simulation results show a strong preference for VEC, with shifts to MEC only under VEC over-utilization and minimal reliance on the cloud. As a result, the system achieves up to 43% reduction in transmission delay and 38% reduction in processing cost, validating its effectiveness in dynamic vehicular environments.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"117 ","pages":"Article 102172"},"PeriodicalIF":3.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145980648","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

ZEL+: Wearable net-zero-energy lifelogging using heterogeneous energy harvesters for sustainable context sensing ZEL+：可穿戴的零能耗生活记录，利用异构能量采集器实现可持续环境感知

IF 3.5 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2026-04-01 Epub Date: 2026-01-29 DOI: 10.1016/j.pmcj.2026.102180

Mitsuru Arita , Yugo Nakamura , Shigemi Ishida , Yutaka Arakawa

This paper presents ZEL+, a wearable lifelogging system designed to operate with net-zero energy consumption by leveraging multiple energy harvesting technologies for continuous context sensing. Self-powered wearable devices often encounter difficulties in environments with inconsistent or low-intensity ambient energy, particularly in indoor settings. To address this challenge, ZEL+ incorporates three key design features. First, it employs a power-switching mechanism based on dual comparators and a capacitor to manage surplus energy and support operation under varying lighting conditions. Second, the system integrates heterogeneous energy harvesters not only as power sources but also as sensing elements. Specifically, a dye-sensitized solar cell provides stable responses under low-light indoor environments, while an amorphous solar cell exhibits sensitivity to changes in ambient illumination; together with a piezoelectric element capturing motion-induced signals, these components contribute complementary cues for location and activity recognition. Third, a Spatial Consistency-Based Correction (SCC) algorithm is applied as a post-processing step to mitigate transient recognition errors and improve the coherence of inferred lifelogs. The system is implemented as a 192 g nametag-shaped wearable device and evaluated in a real-world office environment with 11 participants. Under a person-dependent setting, ZEL+ achieved an accuracy of 96.62% for 8-location place recognition and 97.09% for static/dynamic activity recognition, while maintaining robust performance on more fine-grained tasks. In terms of energy sustainability, the device sustained autonomous operation using harvested energy alone for approximately 93.97% of a standard 8-hour office workday. These results indicate that ZEL+ provides a practical and energy-sustainable solution for continuous lifelogging in indoor mobile computing environments.

本文介绍了ZEL+，这是一种可穿戴的生活记录系统，旨在通过利用多种能量收集技术进行连续环境感知，以零能耗运行。自供电的可穿戴设备在环境能量不一致或低强度的环境中经常遇到困难，特别是在室内环境中。为了应对这一挑战，ZEL+结合了三个关键的设计特性。首先，它采用基于双比较器和电容器的功率开关机制来管理剩余能量并支持在不同照明条件下的运行。其次，该系统集成了异构能量采集器，不仅作为电源，而且作为传感元件。具体来说，染料敏化太阳能电池在低光室内环境下提供稳定的响应，而非晶太阳能电池对环境光照的变化表现出敏感性；这些元件与捕捉运动诱导信号的压电元件一起，为位置和活动识别提供了互补的线索。第三，采用基于空间一致性的校正（SCC）算法作为后处理步骤，以减轻瞬态识别误差，提高推断生命日志的一致性。该系统是一个192克的胸牌形状的可穿戴设备，并在真实的办公环境中与11名参与者进行了评估。在依赖人的环境下，ZEL+在8个位置的位置识别上的准确率为96.62%，在静态/动态活动识别上的准确率为97.09%，同时在更细粒度的任务上保持了稳健的性能。在能源可持续性方面，在标准的8小时工作日中，该设备仅使用收集的能源就能维持大约93.97%的自主运行。这些结果表明，ZEL+为室内移动计算环境下的连续生命记录提供了一种实用且能源可持续的解决方案。

{"title":"ZEL+: Wearable net-zero-energy lifelogging using heterogeneous energy harvesters for sustainable context sensing","authors":"Mitsuru Arita , Yugo Nakamura , Shigemi Ishida , Yutaka Arakawa","doi":"10.1016/j.pmcj.2026.102180","DOIUrl":"10.1016/j.pmcj.2026.102180","url":null,"abstract":"<div><div>This paper presents ZEL+, a wearable lifelogging system designed to operate with net-zero energy consumption by leveraging multiple energy harvesting technologies for continuous context sensing. Self-powered wearable devices often encounter difficulties in environments with inconsistent or low-intensity ambient energy, particularly in indoor settings. To address this challenge, ZEL+ incorporates three key design features. First, it employs a power-switching mechanism based on dual comparators and a capacitor to manage surplus energy and support operation under varying lighting conditions. Second, the system integrates heterogeneous energy harvesters not only as power sources but also as sensing elements. Specifically, a dye-sensitized solar cell provides stable responses under low-light indoor environments, while an amorphous solar cell exhibits sensitivity to changes in ambient illumination; together with a piezoelectric element capturing motion-induced signals, these components contribute complementary cues for location and activity recognition. Third, a Spatial Consistency-Based Correction (SCC) algorithm is applied as a post-processing step to mitigate transient recognition errors and improve the coherence of inferred lifelogs. The system is implemented as a 192g nametag-shaped wearable device and evaluated in a real-world office environment with 11 participants. Under a person-dependent setting, ZEL+ achieved an accuracy of 96.62% for 8-location place recognition and 97.09% for static/dynamic activity recognition, while maintaining robust performance on more fine-grained tasks. In terms of energy sustainability, the device sustained autonomous operation using harvested energy alone for approximately 93.97% of a standard 8-hour office workday. These results indicate that ZEL+ provides a practical and energy-sustainable solution for continuous lifelogging in indoor mobile computing environments.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"117 ","pages":"Article 102180"},"PeriodicalIF":3.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173757","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

Delay optimized task offloading and performance evaluation in Fog-Enabled IoT networks 基于雾的物联网网络延迟优化任务卸载和性能评估

IF 3.5 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2026-04-01 Epub Date: 2026-01-23 DOI: 10.1016/j.pmcj.2026.102177

Megha Sharma , Abhinav Tomar , Abhishek Hazra

The rapid growth and proliferation of Internet of Things (IoT) applications have intensified the demand for low-latency, energy-efficient task processing at the network edge. Fog computing has emerged as a key enabler to address these challenges by offloading computational workloads from resource-constrained sensor nodes to nearby fog nodes. In this context, we propose TSTO, a Thompson Sampling-based task offloading framework tailored for dynamic and non-stationary fog-enabled IoT environments. The scheme employs a two-tier mechanism: a greedy utility-based fog node selection followed by probabilistic decision-making using Thompson Sampling, ensuring balanced exploration and exploitation in volatile network states. To accelerate learning, a precomputation module estimates early rewards for tasks with optimistic deadlines. We provide a comprehensive delay-aware mathematical formulation, analyze the time complexity of the algorithm, and validate its scalability. Simulation results demonstrate that TSTO outperforms baseline methods such as D2CIT and BLOT, achieving up to 6% lower latency and 5% improved energy efficiency. Additionally, prototype-level validation using Raspberry Pi devices highlights the real-world applicability of the proposed model. These results confirm TSTO’s suitability for adaptive and intelligent task offloading in next-generation fog-assisted IoT systems.

物联网（IoT）应用的快速增长和扩散加剧了对网络边缘低延迟、节能任务处理的需求。通过将计算工作负载从资源受限的传感器节点卸载到附近的雾节点，雾计算已经成为解决这些挑战的关键推动者。在这种情况下，我们提出了TSTO，这是一种基于汤普森采样的任务卸载框架，专为动态和非静态雾支持物联网环境量身定制。该方案采用两层机制：基于贪婪效用的雾节点选择，然后使用汤普森采样进行概率决策，确保在不稳定的网络状态下平衡探索和利用。为了加速学习，预计算模块估计了具有乐观截止日期的任务的早期奖励。我们提供了一个全面的延迟感知数学公式，分析了算法的时间复杂度，并验证了其可扩展性。仿真结果表明，TSTO优于D2CIT和BLOT等基准方法，延迟降低6%，能效提高5%。此外，使用树莓派设备的原型级验证突出了所提出模型的实际适用性。这些结果证实了TSTO在下一代雾辅助物联网系统中的适应性和智能任务卸载的适用性。

{"title":"Delay optimized task offloading and performance evaluation in Fog-Enabled IoT networks","authors":"Megha Sharma , Abhinav Tomar , Abhishek Hazra","doi":"10.1016/j.pmcj.2026.102177","DOIUrl":"10.1016/j.pmcj.2026.102177","url":null,"abstract":"<div><div>The rapid growth and proliferation of Internet of Things (IoT) applications have intensified the demand for low-latency, energy-efficient task processing at the network edge. Fog computing has emerged as a key enabler to address these challenges by offloading computational workloads from resource-constrained sensor nodes to nearby fog nodes. In this context, we propose TSTO, a Thompson Sampling-based task offloading framework tailored for dynamic and non-stationary fog-enabled IoT environments. The scheme employs a two-tier mechanism: a greedy utility-based fog node selection followed by probabilistic decision-making using Thompson Sampling, ensuring balanced exploration and exploitation in volatile network states. To accelerate learning, a precomputation module estimates early rewards for tasks with optimistic deadlines. We provide a comprehensive delay-aware mathematical formulation, analyze the time complexity of the algorithm, and validate its scalability. Simulation results demonstrate that TSTO outperforms baseline methods such as D2CIT and BLOT, achieving up to 6% lower latency and 5% improved energy efficiency. Additionally, prototype-level validation using Raspberry Pi devices highlights the real-world applicability of the proposed model. These results confirm TSTO’s suitability for adaptive and intelligent task offloading in next-generation fog-assisted IoT systems.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"117 ","pages":"Article 102177"},"PeriodicalIF":3.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146024310","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

Interpretable healthcare localization with Explainable Artificial Intelligence 可解释的医疗本地化与可解释的人工智能

IF 3.5 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2026-04-01 Epub Date: 2026-01-08 DOI: 10.1016/j.pmcj.2026.102162

Mina Mohammadi , Mohammad Mehdi Sepehri , Vahideh Moghtadaiee , Motahareh Dehghan

Real-time location solutions, such as the Global Positioning System (GPS), encounter significant limitations in indoor environments. To overcome these challenges, indoor positioning systems (IPS) offer a viable alternative. IPS have emerged as critical tools for healthcare environments, where precise localization of patients and medical equipment can directly impact safety and clinical outcomes. To address the limitations of existing IPS solutions, this study introduces an interpretable framework that leverages Wi-Fi access points (APs) and Received Signal Strength Indicator (RSSI) data. The framework employs a dual-phase approach: the initial phase involves spatial fingerprinting to map indoor locations, where each position is labeled, and the task is addressed as a classification problem. In the second phase, we reframe the task as a regression problem to predict fine-grained coordinates. Extreme Gradient Boosting (XGBoost) achieves the highest performance across both classification and regression tasks. To enhance transparency, Explainable Artificial Intelligence (XAI) techniques, including SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME), are applied to identify key signal contributors and interpret model behavior. Results show that XGBoost achieves 99.07% accuracy for location classification and

R^{2} = 0.9997

for coordinate regression on a real dataset, while SHAP and LIME provide consistent global and local explanations of the APs contributions. These results indicate that the combination of XGBoost and XAI yields both high accuracy and interpretability in controlled indoor conditions, supporting practical deployment and motivating future validation under dynamic hospital environments.

实时定位解决方案，如全球定位系统（GPS），在室内环境中会遇到很大的限制。为了克服这些挑战，室内定位系统（IPS）提供了一个可行的替代方案。IPS已成为医疗保健环境的关键工具，在医疗保健环境中，患者和医疗设备的精确定位可以直接影响安全性和临床结果。为了解决现有IPS解决方案的局限性，本研究引入了一个利用Wi-Fi接入点（ap）和接收信号强度指示器（RSSI）数据的可解释框架。该框架采用了两阶段的方法：初始阶段涉及空间指纹来绘制室内位置，其中每个位置都被标记，并且任务被解决为分类问题。在第二阶段，我们将任务重新定义为一个回归问题，以预测细粒度坐标。极端梯度提升（XGBoost）在分类和回归任务中都实现了最高的性能。为了提高透明度，可解释人工智能（XAI）技术，包括SHapley加性解释（SHAP）和局部可解释模型不可知论解释（LIME），被应用于识别关键信号贡献者和解释模型行为。结果表明，XGBoost在真实数据集上的位置分类准确率达到99.07%，坐标回归的R2=0.9997，而SHAP和LIME对ap贡献的全局和局部解释一致。这些结果表明，XGBoost和XAI的组合在受控室内条件下具有较高的准确性和可解释性，支持实际部署，并激励未来在动态医院环境下进行验证。

{"title":"Interpretable healthcare localization with Explainable Artificial Intelligence","authors":"Mina Mohammadi , Mohammad Mehdi Sepehri , Vahideh Moghtadaiee , Motahareh Dehghan","doi":"10.1016/j.pmcj.2026.102162","DOIUrl":"10.1016/j.pmcj.2026.102162","url":null,"abstract":"<div><div>Real-time location solutions, such as the Global Positioning System (GPS), encounter significant limitations in indoor environments. To overcome these challenges, indoor positioning systems (IPS) offer a viable alternative. IPS have emerged as critical tools for healthcare environments, where precise localization of patients and medical equipment can directly impact safety and clinical outcomes. To address the limitations of existing IPS solutions, this study introduces an interpretable framework that leverages Wi-Fi access points (APs) and Received Signal Strength Indicator (RSSI) data. The framework employs a dual-phase approach: the initial phase involves spatial fingerprinting to map indoor locations, where each position is labeled, and the task is addressed as a classification problem. In the second phase, we reframe the task as a regression problem to predict fine-grained coordinates. Extreme Gradient Boosting (XGBoost) achieves the highest performance across both classification and regression tasks. To enhance transparency, Explainable Artificial Intelligence (XAI) techniques, including SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME), are applied to identify key signal contributors and interpret model behavior. Results show that XGBoost achieves 99.07% accuracy for location classification and <span><math><mrow><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup><mo>=</mo><mn>0</mn><mo>.</mo><mn>9997</mn></mrow></math></span> for coordinate regression on a real dataset, while SHAP and LIME provide consistent global and local explanations of the APs contributions. These results indicate that the combination of XGBoost and XAI yields both high accuracy and interpretability in controlled indoor conditions, supporting practical deployment and motivating future validation under dynamic hospital environments.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"117 ","pages":"Article 102162"},"PeriodicalIF":3.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173758","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

Gradient-driven exploration and pattern matching experience replay for efficient UAV path planning: Flying over or around? 高效无人机路径规划的梯度驱动探索和模式匹配经验回放：飞越还是绕飞？

IF 3.5 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2026-04-01 Epub Date: 2025-12-14 DOI: 10.1016/j.pmcj.2025.102156

Zhengmiao Jin , Renxiang Chen , Ke Wu , Dong Liang , Li Yan

The flexibility of unmanned aerial vehicle (UAV) provides a promising solution for large-scale urban services. However, their limited energy remains one of the primary constraints affecting task efficiency. Trajectory optimization is required for energy management, as incorrect path decisions can result in lower task performance and potentially cause damage to the UAV or the urban environment. This paper investigates the path decision-making problem of UAV in dense, high-rise urban environments, characterized by optimal decisions for flying over or around obstacles to minimize energy consumption. Firstly, this study establishes a UAV energy consumption model based on the differences in energy usage across various flight states, and frames the UAV trajectory optimization problem as a Markov Decision Process (MDP), solved using the Deep Deterministic Policy Gradient (DDPG) framework. Secondly, within the Deep Reinforcement Learning (DRL) environment, when the UAV faces a choice between flying over or around obstacles, the exploration-exploitation dilemma arises due to the target-proximity-based dense reward function setup. This research proposes a three-stage learning framework, with a notable feature in the second stage, where exploration is driven by the gradient features of obstacle height to counteract excessive exploitation induced by the reward function. Finally, to address the issue of the algorithm’s experience sampling strategy neglecting the mismatch between the current state and past experiences, which arises due to the progression of the training process, this paper proposes a two-stage experience replay strategy. One notable feature of this strategy is the pattern-matching filtering method in the second stage, which selects experiences that closely match the current state for sampling, thereby accelerating the training process. Extensive simulation experiments demonstrate the necessity and effectiveness of the proposed exploration strategy and experience replay strategy.

无人机（UAV）的灵活性为大规模城市服务提供了一个很有前景的解决方案。然而，他们有限的精力仍然是影响任务效率的主要制约因素之一。轨迹优化是能源管理所必需的，因为不正确的路径决策可能导致较低的任务性能，并可能对无人机或城市环境造成损害。本文研究了密集高层城市环境中无人机的路径决策问题，该问题的特征是飞越或绕过障碍物以最小化能量消耗的最优决策。首先，基于不同飞行状态下的能量消耗差异，建立了无人机的能量消耗模型，并将无人机的轨迹优化问题框架为马尔可夫决策过程（MDP），利用深度确定性策略梯度（DDPG）框架进行求解。其次，在深度强化学习（DRL）环境中，当无人机面临飞越或绕过障碍物的选择时，由于基于目标接近度的密集奖励函数设置，导致了探索-利用困境。本研究提出了一个三阶段的学习框架，其中第二阶段的一个显著特征是，探索是由障碍物高度的梯度特征驱动的，以抵消奖励函数引起的过度开发。最后，为了解决算法的经验采样策略忽略当前状态和过去经验之间不匹配的问题，本文提出了一种两阶段的经验重播策略。该策略的一个显著特点是第二阶段的模式匹配滤波方法，该方法选择与当前状态密切匹配的经验进行采样，从而加快了训练过程。大量的仿真实验证明了所提出的勘探策略和经验回放策略的必要性和有效性。

{"title":"Gradient-driven exploration and pattern matching experience replay for efficient UAV path planning: Flying over or around?","authors":"Zhengmiao Jin , Renxiang Chen , Ke Wu , Dong Liang , Li Yan","doi":"10.1016/j.pmcj.2025.102156","DOIUrl":"10.1016/j.pmcj.2025.102156","url":null,"abstract":"<div><div>The flexibility of unmanned aerial vehicle (UAV) provides a promising solution for large-scale urban services. However, their limited energy remains one of the primary constraints affecting task efficiency. Trajectory optimization is required for energy management, as incorrect path decisions can result in lower task performance and potentially cause damage to the UAV or the urban environment. This paper investigates the path decision-making problem of UAV in dense, high-rise urban environments, characterized by optimal decisions for flying over or around obstacles to minimize energy consumption. Firstly, this study establishes a UAV energy consumption model based on the differences in energy usage across various flight states, and frames the UAV trajectory optimization problem as a Markov Decision Process (MDP), solved using the Deep Deterministic Policy Gradient (DDPG) framework. Secondly, within the Deep Reinforcement Learning (DRL) environment, when the UAV faces a choice between flying over or around obstacles, the exploration-exploitation dilemma arises due to the target-proximity-based dense reward function setup. This research proposes a three-stage learning framework, with a notable feature in the second stage, where exploration is driven by the gradient features of obstacle height to counteract excessive exploitation induced by the reward function. Finally, to address the issue of the algorithm’s experience sampling strategy neglecting the mismatch between the current state and past experiences, which arises due to the progression of the training process, this paper proposes a two-stage experience replay strategy. One notable feature of this strategy is the pattern-matching filtering method in the second stage, which selects experiences that closely match the current state for sampling, thereby accelerating the training process. Extensive simulation experiments demonstrate the necessity and effectiveness of the proposed exploration strategy and experience replay strategy.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"117 ","pages":"Article 102156"},"PeriodicalIF":3.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145980647","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

Centralized sequential federated learning: single-server simulation for cross-region load forecasting 集中式顺序联邦学习：跨区域负载预测的单服务器模拟

IF 3.5 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Pervasive and Mobile Computing

Pub Date : 2026-04-01 Epub Date: 2026-01-23 DOI: 10.1016/j.pmcj.2026.102176

Cong Zhou , Ming Li , Longfa Yuan , Nanwei Ding , Ruijun Tie , Zheng Zeng , Zhen Li

To address data distribution heterogeneity (non-IID) and training-efficiency challenges in cross-regional electric load forecasting, this paper proposes a Centralized Sequential Federated Learning (CSFL) framework. In a single-server, centrally stored setting, CSFL emulates multi-regional “clients” via logical partitions, employs sequential local training with central aggregation, and incorporates a dynamic learning-rate decay coupled with round resets to promote progressive integration of cross-regional features. Combined with a feature-engineering pipeline based on Ward’s minimum-variance clustering and Pearson correlation analysis, CSFL substantially improves cross-regional forecasting performance. Experiments show that, compared with directly applying a single local model across regions, CSFL reduces the average forecasting error by 22.3%, and its gains are statistically significant according to five independent runs with a paired t-test (

p = 0.032

). The method achieves efficient cross-regional knowledge fusion in a single-server environment, offering a high-performing and easily deployable solution for power grid dispatch centers.

为了解决跨区域电力负荷预测中的数据分布异质性和训练效率问题，本文提出了一种集中式顺序联邦学习（CSFL）框架。在单服务器、集中存储设置中，CSFL通过逻辑分区模拟多区域的“客户端”，采用具有中央聚合的顺序局部训练，并结合动态学习率衰减与轮重置相结合，以促进跨区域特征的逐步集成。结合基于Ward最小方差聚类和Pearson相关分析的特征工程管道，CSFL大大提高了跨区域预测性能。实验表明，与直接跨区域应用单一局部模型相比，CSFL平均预测误差降低了22.3%，经5次独立运行的配对t检验，其收益具有统计学意义（p=0.032）。该方法在单服务器环境下实现了高效的跨区域知识融合，为电网调度中心提供了一种高性能、易部署的解决方案。

{"title":"Centralized sequential federated learning: single-server simulation for cross-region load forecasting","authors":"Cong Zhou , Ming Li , Longfa Yuan , Nanwei Ding , Ruijun Tie , Zheng Zeng , Zhen Li","doi":"10.1016/j.pmcj.2026.102176","DOIUrl":"10.1016/j.pmcj.2026.102176","url":null,"abstract":"<div><div>To address data distribution heterogeneity (non-IID) and training-efficiency challenges in cross-regional electric load forecasting, this paper proposes a Centralized Sequential Federated Learning (CSFL) framework. In a single-server, centrally stored setting, CSFL emulates multi-regional “clients” via logical partitions, employs sequential local training with central aggregation, and incorporates a dynamic learning-rate decay coupled with round resets to promote progressive integration of cross-regional features. Combined with a feature-engineering pipeline based on Ward’s minimum-variance clustering and Pearson correlation analysis, CSFL substantially improves cross-regional forecasting performance. Experiments show that, compared with directly applying a single local model across regions, CSFL reduces the average forecasting error by 22.3%, and its gains are statistically significant according to five independent runs with a paired <em>t</em>-test (<span><math><mrow><mi>p</mi><mo>=</mo><mn>0.032</mn></mrow></math></span>). The method achieves efficient cross-regional knowledge fusion in a single-server environment, offering a high-performing and easily deployable solution for power grid dispatch centers.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"117 ","pages":"Article 102176"},"PeriodicalIF":3.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146079114","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