Internet of Things最新文献_第4页

Cross-network cross-interface relaying via LoRa-ZigBee synergy: Enabling energy-efficient delay-constrained communication across low-power IoT networks 通过LoRa-ZigBee协同实现跨网络跨接口中继：在低功耗物联网网络中实现高能效延迟约束通信

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2026-01-20 DOI: 10.1016/j.iot.2026.101878

Hua Qin , Ni Li , Gelan Yang , Yang Peng

The rapid expansion of the Internet of Things (IoT) ecosystem has propelled widespread deployment of distributed low-power wireless networks, among which ZigBee stands out for diverse innovative applications. However, energy-efficient cross-network communication remains challenging, as existing solutions like multi-hop ZigBee and one-hop LoRa entail trade-offs between communication delays and deployment costs. To tackle these issues, we propose a novel cross-interface relaying paradigm that utilizes a star topology within each ZigBee network and designates a relay node with an additional LoRa interface to bridge networks via a central LoRa gateway. Compared with existing methods, this approach reduces energy consumption and costs while improving scalability. To implement this paradigm while balancing energy conservation with delay guarantees, we introduce a Cross-network Cross-interface Relaying (CCR) scheme, which jointly schedules LoRa and ZigBee transmission behaviors to minimize energy consumption under delay constraints. CCR uses a scheduling framework that breaks down end-to-end delay constraints into link-level constraints, enabling global optimization of transmission parameters and dynamic adaptation to link quality variations. The effectiveness of CCR is demonstrated through extensive field tests on a prototype implemented on Raspberry Pi 3B+. Results show that CCR reduces energy consumption by 55.4% and 39.1% compared with an advanced LoRa communication protocol and a state-of-the-art cross-interface relaying scheme, respectively, while ensuring that 98.7% of packets satisfy their delay constraints. These findings highlight the potential of CCR for efficient and reliable cross-network communication in large-scale IoT deployments.

物联网（IoT）生态系统的快速扩展推动了分布式低功耗无线网络的广泛部署，其中ZigBee在各种创新应用中脱颖而出。然而，节能的跨网络通信仍然具有挑战性，因为现有的解决方案（如多跳ZigBee和单跳LoRa）需要在通信延迟和部署成本之间进行权衡。为了解决这些问题，我们提出了一种新的跨接口中继范例，该范例在每个ZigBee网络中利用星形拓扑，并指定一个具有附加LoRa接口的中继节点，通过中央LoRa网关桥接网络。与现有方法相比，该方法降低了能耗和成本，同时提高了可扩展性。为了实现这种模式，同时平衡节能和延迟保证，我们引入了一种跨网络跨接口中继（CCR）方案，该方案联合调度LoRa和ZigBee传输行为，以最大限度地减少延迟约束下的能耗。CCR使用调度框架，将端到端延迟约束分解为链路级约束，实现传输参数的全局优化和对链路质量变化的动态适应。CCR的有效性通过在树莓派3B+上实现的原型进行了广泛的现场测试。结果表明，与先进的LoRa通信协议和最先进的跨接口中继方案相比，CCR分别降低了55.4%和39.1%的能耗，同时确保98.7%的数据包满足其延迟约束。这些发现突出了CCR在大规模物联网部署中高效可靠的跨网络通信的潜力。

{"title":"Cross-network cross-interface relaying via LoRa-ZigBee synergy: Enabling energy-efficient delay-constrained communication across low-power IoT networks","authors":"Hua Qin , Ni Li , Gelan Yang , Yang Peng","doi":"10.1016/j.iot.2026.101878","DOIUrl":"10.1016/j.iot.2026.101878","url":null,"abstract":"<div><div>The rapid expansion of the Internet of Things (IoT) ecosystem has propelled widespread deployment of distributed low-power wireless networks, among which ZigBee stands out for diverse innovative applications. However, energy-efficient cross-network communication remains challenging, as existing solutions like multi-hop ZigBee and one-hop LoRa entail trade-offs between communication delays and deployment costs. To tackle these issues, we propose a novel cross-interface relaying paradigm that utilizes a star topology within each ZigBee network and designates a relay node with an additional LoRa interface to bridge networks via a central LoRa gateway. Compared with existing methods, this approach reduces energy consumption and costs while improving scalability. To implement this paradigm while balancing energy conservation with delay guarantees, we introduce a Cross-network Cross-interface Relaying (CCR) scheme, which jointly schedules LoRa and ZigBee transmission behaviors to minimize energy consumption under delay constraints. CCR uses a scheduling framework that breaks down end-to-end delay constraints into link-level constraints, enabling global optimization of transmission parameters and dynamic adaptation to link quality variations. The effectiveness of CCR is demonstrated through extensive field tests on a prototype implemented on Raspberry Pi 3B+. Results show that CCR reduces energy consumption by 55.4% and 39.1% compared with an advanced LoRa communication protocol and a state-of-the-art cross-interface relaying scheme, respectively, while ensuring that 98.7% of packets satisfy their delay constraints. These findings highlight the potential of CCR for efficient and reliable cross-network communication in large-scale IoT deployments.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101878"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146023232","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

SCENE: Serving cluster formation in cEll-free dyNamic environments 场景：在无细胞动态环境中服务集群形成

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2026-01-24 DOI: 10.1016/j.iot.2026.101873

Marco Silva , José Santos , Marília Curado , Chan-Tong Lam , Benjamin K. Ng

This paper introduces SCENE (Serving Cluster formation in cEll-free dyNamic Environments), a novel optimization model for serving cluster formation in Cell-Free massive Multiple-Input Multiple-Output networks. SCENE addresses the challenge of supporting heterogeneous service requirements - including critical Internet of Things (IoT) and latency-sensitive services as well as regular broadband applications - under dynamic network conditions. Unlike traditional approaches that rely on iterative refinement algorithms, SCENE performs one-shot serving cluster formation, eliminating the overhead of successive optimization loops. This innovation leads to significantly lower computational complexity and faster execution times while preserving service quality. Simulation results show that SCENE achieves superior performance in both average and 90%-likely spectral efficiency compared to state-of-the-art baselines, while demonstrating strong robustness under varying traffic profiles and pilot scarcity. SCENE enables efficient, scalable, and service-aware cluster formation, making it a promising candidate for dynamic and heterogeneous 6G and IoT environments

本文介绍了一种新的无cell的大规模多输入多输出网络服务集群形成优化模型SCENE （service Cluster formation in cEll-free dyNamic Environments）。SCENE解决了在动态网络条件下支持异构服务需求的挑战，包括关键的物联网（IoT）和延迟敏感服务以及常规宽带应用。与依赖迭代优化算法的传统方法不同，SCENE执行一次性服务集群形成，消除了连续优化循环的开销。这一创新显著降低了计算复杂度，加快了执行时间，同时保持了服务质量。仿真结果表明，与最先进的基线相比，SCENE在平均和90%可能的频谱效率方面都取得了卓越的性能，同时在不同的流量概况和飞行员稀缺情况下表现出强大的鲁棒性。SCENE支持高效、可扩展和服务感知的集群形成，使其成为动态和异构6G和物联网环境的有希望的候选者

{"title":"SCENE: Serving cluster formation in cEll-free dyNamic environments","authors":"Marco Silva , José Santos , Marília Curado , Chan-Tong Lam , Benjamin K. Ng","doi":"10.1016/j.iot.2026.101873","DOIUrl":"10.1016/j.iot.2026.101873","url":null,"abstract":"<div><div>This paper introduces SCENE (Serving Cluster formation in cEll-free dyNamic Environments), a novel optimization model for serving cluster formation in Cell-Free massive Multiple-Input Multiple-Output networks. SCENE addresses the challenge of supporting heterogeneous service requirements - including critical Internet of Things (IoT) and latency-sensitive services as well as regular broadband applications - under dynamic network conditions. Unlike traditional approaches that rely on iterative refinement algorithms, SCENE performs one-shot serving cluster formation, eliminating the overhead of successive optimization loops. This innovation leads to significantly lower computational complexity and faster execution times while preserving service quality. Simulation results show that SCENE achieves superior performance in both average and 90%-likely spectral efficiency compared to state-of-the-art baselines, while demonstrating strong robustness under varying traffic profiles and pilot scarcity. SCENE enables efficient, scalable, and service-aware cluster formation, making it a promising candidate for dynamic and heterogeneous 6G and IoT environments</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101873"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077988","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

Adaptive artificial noise beamforming for securing grant-free massive machine-type communication 自适应人工噪声波束形成，确保大规模机器型通信免授权

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2025-12-21 DOI: 10.1016/j.iot.2025.101859

Uchenna P. Enwereonye, Ahmad Salehi Shahraki, Hooman Alavizadeh, A S M Kayes

Massive machine-type communication (mMTC) growth beyond 5G (B5G)/6G networks presents significant security challenges, particularly in grant-free scenarios where traditional cryptographic methods are insufficient. The lack of defined access control and the complexities of key management expose these systems to vulnerabilities such as pilot contamination and jamming. Existing physical layer security (PLS) techniques, including adaptive beamforming and artificial noise generation, are limited by their static nature and reliance on perfect channel state information (CSI), making them less effective in the dynamic and densely populated environments characteristic of mMTC. This paper introduces Adaptive Artificial Noise Beamforming (AANB), an enhanced PLS approach designed to optimise the trade-off between security and system performance for grant-free mMTC in B5G/6G, by dynamically adjusting beamforming vectors and artificial noise based on real-time CSI and spatial correlation, while ensuring minimal impact on legitimate users and maximising interference against eavesdroppers. The proposed AANB’s secrecy outage probability (SOP) for grant-free mMTC is analytically derived, and the impact of AANB is demonstrated through simulations, which shows that AANB significantly lowers SOP when benchmarked against Semi-grant-free (SGF) and traditional beamforming with artificial noise (BF+AN) techniques in grant-free mMTC environment. The results indicate that AANB consistently outperforms SGF and BF+AN, achieving lower SOP values across various signal-to-noise ratio (SNR) levels and spatial correlation scenarios, offering robust security in grant-free mMTC scenarios. Additionally, bit error rate (BER) analysis demonstrates that AANB consistently outperforms benchmark schemes across all SNR levels, due to its adaptive noise-to-signal ratio optimisation, thereby enhancing resistance against eavesdropping in grant-free mMTC.

超过5G (B5G)/6G网络的大规模机器类型通信（mMTC）增长带来了重大的安全挑战，特别是在传统加密方法不足的无授权场景中。缺乏定义的访问控制和密钥管理的复杂性使这些系统暴露于诸如先导污染和干扰之类的漏洞。现有的物理层安全（PLS）技术，包括自适应波束形成和人工噪声产生，由于其静态特性和对完美信道状态信息（CSI）的依赖，使得它们在mMTC的动态和密集环境中效果不佳。本文介绍了自适应人工噪声波束形成（AANB），这是一种增强型PLS方法，旨在通过动态调整波束形成矢量和基于实时CSI和空间相关性的人工噪声来优化B5G/6G中免费mMTC的安全性和系统性能之间的权衡，同时确保对合法用户的影响最小，并最大限度地干扰窃听者。分析了该方法对无授权mMTC保密中断概率（SOP）的影响，并通过仿真验证了该方法的影响，结果表明，在无授权mMTC环境下，与半无授权（SGF）和传统的人工噪声波束形成（BF+AN）技术进行基准测试时，AANB显著降低了SOP。结果表明，AANB始终优于SGF和BF+AN，在各种信噪比（SNR）水平和空间相关场景下实现更低的SOP值，在无授权的mMTC场景中提供强大的安全性。此外，误码率（BER）分析表明，由于其自适应噪声与信号比优化，AANB在所有信噪比水平上始终优于基准方案，从而增强了对无授权mMTC窃听的抵抗力。

{"title":"Adaptive artificial noise beamforming for securing grant-free massive machine-type communication","authors":"Uchenna P. Enwereonye, Ahmad Salehi Shahraki, Hooman Alavizadeh, A S M Kayes","doi":"10.1016/j.iot.2025.101859","DOIUrl":"10.1016/j.iot.2025.101859","url":null,"abstract":"<div><div>Massive machine-type communication (mMTC) growth beyond 5G (B5G)/6G networks presents significant security challenges, particularly in grant-free scenarios where traditional cryptographic methods are insufficient. The lack of defined access control and the complexities of key management expose these systems to vulnerabilities such as pilot contamination and jamming. Existing physical layer security (PLS) techniques, including adaptive beamforming and artificial noise generation, are limited by their static nature and reliance on perfect channel state information (CSI), making them less effective in the dynamic and densely populated environments characteristic of mMTC. This paper introduces Adaptive Artificial Noise Beamforming (AANB), an enhanced PLS approach designed to optimise the trade-off between security and system performance for grant-free mMTC in B5G/6G, by dynamically adjusting beamforming vectors and artificial noise based on real-time CSI and spatial correlation, while ensuring minimal impact on legitimate users and maximising interference against eavesdroppers. The proposed AANB’s secrecy outage probability (SOP) for grant-free mMTC is analytically derived, and the impact of AANB is demonstrated through simulations, which shows that AANB significantly lowers SOP when benchmarked against Semi-grant-free (SGF) and traditional beamforming with artificial noise (BF+AN) techniques in grant-free mMTC environment. The results indicate that AANB consistently outperforms SGF and BF+AN, achieving lower SOP values across various signal-to-noise ratio (SNR) levels and spatial correlation scenarios, offering robust security in grant-free mMTC scenarios. Additionally, bit error rate (BER) analysis demonstrates that AANB consistently outperforms benchmark schemes across all SNR levels, due to its adaptive noise-to-signal ratio optimisation, thereby enhancing resistance against eavesdropping in grant-free mMTC.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101859"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841106","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

Scalable and low-power edge architecture with Wi-Fi HaLow and on-device spectrograms generation for flexible urban bioacoustics monitoring 可扩展和低功耗边缘架构，具有Wi-Fi HaLow和设备上的频谱生成，用于灵活的城市生物声学监测

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2025-12-23 DOI: 10.1016/j.iot.2025.101864

Francisco A. Delgado-Rajó , Carlos M. Travieso-González , Ruyman Hernández-López

Urban biodiversity monitoring in smart cities requires scalable and efficient computing architectures capable of handling real-time, distributed sensing tasks. This paper proposes a low-power edge computing and Internet of Things (IoT) framework that enables on-device acoustic detection and classification of bird species, serving as bioindicators of ecosystem health. The architecture leverages lightweight convolutional neural networks (CNNs) deployed on energy-efficient sensor nodes, significantly reducing communication overhead by transmitting only detection events and compact spectrogram data. A key contribution is the automatic generation of Mel-spectrograms at the edge, which supports the continuous creation of training datasets and iterative neural network refinement without manual preprocessing. The proposed system incorporates dual Wi-Fi and Wi-Fi HaLow connectivity, providing adaptable long-range, low-power communication for heterogeneous urban environments. Field experiments validate the framework’s scalability and effectiveness, demonstrating robust detection of both native and invasive species. By combining distributed intelligence, resource-aware computation, and flexible networking, the system offers a practical edge–IoT solution for large-scale, real-time environmental monitoring in smart city contexts.

智慧城市的城市生物多样性监测需要可扩展和高效的计算架构，能够处理实时、分布式的传感任务。本文提出了一种低功耗边缘计算和物联网（IoT）框架，可以实现设备上的鸟类声学检测和分类，作为生态系统健康的生物指标。该架构利用部署在节能传感器节点上的轻量级卷积神经网络（cnn），通过仅传输检测事件和紧凑的频谱图数据，显著降低了通信开销。一个关键的贡献是在边缘自动生成mel谱图，它支持连续创建训练数据集和迭代神经网络细化，而无需手动预处理。该系统采用双Wi-Fi和Wi-Fi HaLow连接，为异构城市环境提供适应性强的远程低功耗通信。现场实验验证了该框架的可扩展性和有效性，展示了对本地和入侵物种的鲁棒检测。通过结合分布式智能、资源感知计算和灵活的网络，该系统为智慧城市背景下的大规模、实时环境监测提供了实用的边缘物联网解决方案。

{"title":"Scalable and low-power edge architecture with Wi-Fi HaLow and on-device spectrograms generation for flexible urban bioacoustics monitoring","authors":"Francisco A. Delgado-Rajó , Carlos M. Travieso-González , Ruyman Hernández-López","doi":"10.1016/j.iot.2025.101864","DOIUrl":"10.1016/j.iot.2025.101864","url":null,"abstract":"<div><div>Urban biodiversity monitoring in smart cities requires scalable and efficient computing architectures capable of handling real-time, distributed sensing tasks. This paper proposes a low-power edge computing and Internet of Things (IoT) framework that enables on-device acoustic detection and classification of bird species, serving as bioindicators of ecosystem health. The architecture leverages lightweight convolutional neural networks (CNNs) deployed on energy-efficient sensor nodes, significantly reducing communication overhead by transmitting only detection events and compact spectrogram data. A key contribution is the automatic generation of Mel-spectrograms at the edge, which supports the continuous creation of training datasets and iterative neural network refinement without manual preprocessing. The proposed system incorporates dual Wi-Fi and Wi-Fi HaLow connectivity, providing adaptable long-range, low-power communication for heterogeneous urban environments. Field experiments validate the framework’s scalability and effectiveness, demonstrating robust detection of both native and invasive species. By combining distributed intelligence, resource-aware computation, and flexible networking, the system offers a practical edge–IoT solution for large-scale, real-time environmental monitoring in smart city contexts.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101864"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145885165","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

Smart parking with pixel-wise ROI selection for vehicle detection using YOLOv8, YOLOv9, YOLOv10, and YOLOv11 使用YOLOv8， YOLOv9， YOLOv10和YOLOv11进行车辆检测，具有逐像素ROI选择的智能停车

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2025-12-19 DOI: 10.1016/j.iot.2025.101858

Gustavo P C P da Luz, Gabriel Massuyoshi Sato, Luis Fernando Gomez Gonzalez, Juliana Freitag Borin

The increasing urbanization and the growing number of vehicles in cities have underscored the need for efficient parking management systems. Traditional smart parking solutions often rely on sensors or cameras for occupancy detection, each with its limitations. Recent advancements in deep learning have introduced new YOLO models (YOLOv8, YOLOv9, YOLOv10, and YOLOv11), but these models have not been extensively evaluated in the context of smart parking systems, particularly when combined with Region of Interest (ROI) selection for object detection. Existing methods still rely on fixed polygonal ROI selections or simple pixel-based modifications, which limit flexibility and precision. This work introduces a novel approach that integrates Internet of Things, Edge Computing, and Deep Learning concepts, by using the latest YOLO models for vehicle detection. By exploring both edge and cloud computing, it was found that inference times on edge devices ranged from 1 to 92 seconds, depending on the hardware and model version. Additionally, a highly flexible pixel-wise post-processing ROI selection method is proposed for accurately identifying regions of interest to count vehicles in parking lot images, overcoming the limitations of conventional polygon-based approaches. The proposed system achieved 99.68 % balanced accuracy on a custom dataset of 3484 images, providing a cost-effective smart parking solution that ensures precise vehicle detection while preserving data privacy, improving upon the previously used method by over 20 percentage points while maintaining the inference at the edge.

随着城市化进程的加快和城市车辆数量的增加，对高效停车管理系统的需求日益突出。传统的智能停车解决方案通常依赖于传感器或摄像头进行占用检测，每种解决方案都有其局限性。深度学习的最新进展引入了新的YOLO模型（YOLOv8, YOLOv9， YOLOv10和YOLOv11），但这些模型尚未在智能停车系统的背景下进行广泛评估，特别是在与感兴趣区域（ROI）选择相结合进行目标检测时。现有的方法仍然依赖于固定的多边形ROI选择或简单的基于像素的修改，这限制了灵活性和精度。这项工作通过使用最新的YOLO模型进行车辆检测，引入了一种集成了物联网、边缘计算和深度学习概念的新方法。通过探索边缘和云计算，发现边缘设备上的推理时间从1秒到92秒不等，具体取决于硬件和模型版本。此外，提出了一种高度灵活的逐像素后处理ROI选择方法，用于准确识别停车场图像中感兴趣的区域以对车辆进行计数，克服了传统基于多边形的方法的局限性。该系统在3484张图像的自定义数据集上实现了99.68%的平衡精度，提供了一种具有成本效益的智能停车解决方案，确保了精确的车辆检测，同时保持了数据隐私，在之前使用的方法的基础上提高了20个百分点以上，同时保持了边缘推理。

{"title":"Smart parking with pixel-wise ROI selection for vehicle detection using YOLOv8, YOLOv9, YOLOv10, and YOLOv11","authors":"Gustavo P C P da Luz, Gabriel Massuyoshi Sato, Luis Fernando Gomez Gonzalez, Juliana Freitag Borin","doi":"10.1016/j.iot.2025.101858","DOIUrl":"10.1016/j.iot.2025.101858","url":null,"abstract":"<div><div>The increasing urbanization and the growing number of vehicles in cities have underscored the need for efficient parking management systems. Traditional smart parking solutions often rely on sensors or cameras for occupancy detection, each with its limitations. Recent advancements in deep learning have introduced new YOLO models (YOLOv8, YOLOv9, YOLOv10, and YOLOv11), but these models have not been extensively evaluated in the context of smart parking systems, particularly when combined with Region of Interest (ROI) selection for object detection. Existing methods still rely on fixed polygonal ROI selections or simple pixel-based modifications, which limit flexibility and precision. This work introduces a novel approach that integrates Internet of Things, Edge Computing, and Deep Learning concepts, by using the latest YOLO models for vehicle detection. By exploring both edge and cloud computing, it was found that inference times on edge devices ranged from 1 to 92 seconds, depending on the hardware and model version. Additionally, a highly flexible pixel-wise post-processing ROI selection method is proposed for accurately identifying regions of interest to count vehicles in parking lot images, overcoming the limitations of conventional polygon-based approaches. The proposed system achieved 99.68 % balanced accuracy on a custom dataset of 3484 images, providing a cost-effective smart parking solution that ensures precise vehicle detection while preserving data privacy, improving upon the previously used method by over 20 percentage points while maintaining the inference at the edge.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101858"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841198","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

Fault detection of industrial air separation stations based on metaheuristic optimization and bidirectional long short-term memory technique 基于元启发式优化和双向长短期记忆技术的工业空分站故障检测

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2025-12-09 DOI: 10.1016/j.iot.2025.101850

Thanh-Phuong Nguyen , Chung-Chieh Lin , Ming-Yuan Cho

Industrial air separation stations play a critical role in numerous sectors, necessitating robust fault detection frameworks to ensure reliability and operational safety. This study presents a novel approach combining Bidirectional Long Short-Term Memory (BLSTM) networks with Enhanced Particle Swarm Optimization (EPSO) for fault detection in industrial air separation stations. The BLSTM model, renowned for its ability to capture temporal dependencies in sequential data, is optimized using EPSO to fine-tune its hyperparameters, enhancing its fault detection performance. The proposed EPSO-BLSTM framework is rigorously evaluated against conventional techniques, including Recurrent Neural Networks (RNN), Bidirectional RNN, Gated Recurrent Units (GRU), LSTM, Convolutional Neural Networks (CNN), and standard BLSTM model with the most notable improvements of error-based 58.32 % Loss, 63.37 % Val Loss, 1.24 % CP, 0.6 % Val CP, 60.11 % MAE, 63.37 % Val MAE, 63.46 % MSE, and 81.75 % Val MSE, and with accurate-based 4.68 % Pre, 5.55 % Val Pre, 5.72 % Rec, and 4.39 % Val Rec. Comparative analysis highlights the superior fault classification accuracy and generalization capability of the EPSO-BLSTM model under diverse operational scenarios. This research underscores the potential of integrating metaheuristic optimization with advanced deep learning architectures to address complex fault detection challenges, offering a scalable and efficient solution for industrial air separation stations.

工业空分站在许多领域发挥着关键作用，需要强大的故障检测框架来确保可靠性和运行安全性。提出了一种将双向长短期记忆（BLSTM）网络与增强粒子群优化（EPSO）相结合的工业空分站故障检测新方法。BLSTM模型以其捕获时序数据中的时间依赖性的能力而闻名，该模型使用EPSO对其超参数进行了优化，从而提高了其故障检测性能。提出的EPSO-BLSTM框架与常规技术（包括循环神经网络（RNN）、双向RNN、门控循环单元（GRU）、LSTM、卷积神经网络（CNN）和标准BLSTM模型）进行了严格的评估，其中最显著的改进是基于误差的58.32% Loss、63.37% Val Loss、1.24% CP、0.6% Val CP、60.11% MAE、63.37% Val MAE、63.46% MSE和81.75% Val MSE，以及基于精度的4.68% Pre、5.55% Val Pre、5.72% Rec，对比分析表明，EPSO-BLSTM模型在不同运行场景下具有较好的故障分类精度和泛化能力。这项研究强调了将元启发式优化与先进的深度学习架构相结合的潜力，以解决复杂的故障检测挑战，为工业空分站提供可扩展和高效的解决方案。

{"title":"Fault detection of industrial air separation stations based on metaheuristic optimization and bidirectional long short-term memory technique","authors":"Thanh-Phuong Nguyen , Chung-Chieh Lin , Ming-Yuan Cho","doi":"10.1016/j.iot.2025.101850","DOIUrl":"10.1016/j.iot.2025.101850","url":null,"abstract":"<div><div>Industrial air separation stations play a critical role in numerous sectors, necessitating robust fault detection frameworks to ensure reliability and operational safety. This study presents a novel approach combining Bidirectional Long Short-Term Memory (BLSTM) networks with Enhanced Particle Swarm Optimization (EPSO) for fault detection in industrial air separation stations. The BLSTM model, renowned for its ability to capture temporal dependencies in sequential data, is optimized using EPSO to fine-tune its hyperparameters, enhancing its fault detection performance. The proposed EPSO-BLSTM framework is rigorously evaluated against conventional techniques, including Recurrent Neural Networks (RNN), Bidirectional RNN, Gated Recurrent Units (GRU), LSTM, Convolutional Neural Networks (CNN), and standard BLSTM model with the most notable improvements of error-based 58.32 % Loss, 63.37 % Val Loss, 1.24 % CP, 0.6 % Val CP, 60.11 % MAE, 63.37 % Val MAE, 63.46 % MSE, and 81.75 % Val MSE, and with accurate-based 4.68 % Pre, 5.55 % Val Pre, 5.72 % Rec, and 4.39 % Val Rec. Comparative analysis highlights the superior fault classification accuracy and generalization capability of the EPSO-BLSTM model under diverse operational scenarios. This research underscores the potential of integrating metaheuristic optimization with advanced deep learning architectures to address complex fault detection challenges, offering a scalable and efficient solution for industrial air separation stations.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101850"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738841","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

Group-based link modeling for wireless digital twins: Towards accurate network performance prediction 基于分组的无线数字孪生链路建模：迈向准确的网络性能预测

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2026-01-24 DOI: 10.1016/j.iot.2026.101875

Samir Si-Mohammed , Fabrice Théoleyre

Wireless networks are increasingly deployed in diverse domains, from best-effort object tracking to real-time control in smart factories. Yet, their performance strongly depends on configuration choices, especially at the MAC level. Thus, a single homogeneous configuration is often suboptimal due to the heterogeneous nature of individual links. We argue that Digital Twins (DTs) are a promising enabler for autonomous networks, capable of adapting configurations dynamically to prevailing conditions. However, global modeling approaches in DTs make it difficult to capture link-level variability and to accurately model the impact of configuration changes on performance. In this work, we propose a link-oriented prediction model designed to serve as a cornerstone for future wireless Digital Twins. Our model estimates the Packet Reception Rate (Packet Reception Rate (PRR)) under different MAC configurations, capturing the unique characteristics of each communication link. To improve scalability in large deployments, we explore a clustering-based approach, where predictive models are trained per group of similar links rather than per individual link. Our experimental evaluation shows that these data-driven methods effectively capture link heterogeneity while offering robust prediction accuracy and enhanced generalization capabilities.

无线网络越来越多地部署在不同的领域，从最努力的目标跟踪到智能工厂的实时控制。然而，它们的性能很大程度上取决于配置选择，尤其是在MAC级别。因此，由于单个链接的异构性，单个同构配置通常不是最优的。我们认为数字孪生（dt）是自主网络的一个有前途的推动者，能够动态地调整配置以适应当前条件。然而，DTs中的全局建模方法很难捕获链接级别的可变性，也很难准确地为配置更改对性能的影响建模。在这项工作中，我们提出了一个面向链路的预测模型，旨在作为未来无线数字孪生的基石。我们的模型估计了不同MAC配置下的数据包接收率（Packet Reception Rate (PRR)），捕获了每个通信链路的独特特征。为了提高大型部署中的可伸缩性，我们探索了一种基于集群的方法，在这种方法中，预测模型是按一组相似链接而不是按单个链接进行训练的。我们的实验评估表明，这些数据驱动的方法有效地捕获了链路异质性，同时提供了稳健的预测精度和增强的泛化能力。

{"title":"Group-based link modeling for wireless digital twins: Towards accurate network performance prediction","authors":"Samir Si-Mohammed , Fabrice Théoleyre","doi":"10.1016/j.iot.2026.101875","DOIUrl":"10.1016/j.iot.2026.101875","url":null,"abstract":"<div><div>Wireless networks are increasingly deployed in diverse domains, from best-effort object tracking to real-time control in smart factories. Yet, their performance strongly depends on configuration choices, especially at the MAC level. Thus, a single homogeneous configuration is often suboptimal due to the heterogeneous nature of individual links. We argue that Digital Twins (DTs) are a promising enabler for autonomous networks, capable of adapting configurations dynamically to prevailing conditions. However, global modeling approaches in DTs make it difficult to capture link-level variability and to accurately model the impact of configuration changes on performance. In this work, we propose a link-oriented prediction model designed to serve as a cornerstone for future wireless Digital Twins. Our model estimates the Packet Reception Rate (Packet Reception Rate (PRR)) under different MAC configurations, capturing the unique characteristics of each communication link. To improve scalability in large deployments, we explore a clustering-based approach, where predictive models are trained per group of similar links rather than per individual link. Our experimental evaluation shows that these data-driven methods effectively capture link heterogeneity while offering robust prediction accuracy and enhanced generalization capabilities.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101875"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077992","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

Analysis of microservices-based IoT systems: deployment challenges, industry practices, and performance insights 基于微服务的物联网系统分析：部署挑战、行业实践和性能洞察

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2026-01-07 DOI: 10.1016/j.iot.2025.101867

Yahia El Fellah , Jean Baptiste Minani , Naouel Moha , Julien Gascon-Samson , Yann-Gaël Guéhéneuc

As the adoption of microservices in Internet of Things (IoT) systems grows, deploying them on the Edge remains a significant challenge for practitioners. While Edge Computing offers improved latency and resource efficiency by processing data near the source, it also introduces complexity in managing microservices. Despite increasing academic interest, few comprehensive studies have investigated the specific challenges and effective software engineering (SE) practices for deploying microservices-based IoT systems on the Edge. Therefore, we conducted a multi-method study to bridge this gap. We used three methods: (1) a systematic literature review (SLR) to identify known challenges and approaches, (2) a gray literature review (GLR) to extract SE practices used in the field, and (3) an empirical evaluation using two versions of a case study, one with and one without selected SE practices. The findings show that (1) the most reported challenges relate to resource utilization and performance optimization, (2) containerized microservices, API gateways, and database-per-service are among the most commonly recommended practices, and (3) implementing these practices led to a 132% throughput improvement, 49% reduction in latency, and memory savings of up to 13% in Edge-based IoT systems. However, increased architectural complexity also led to higher CPU usage. This study offers a catalog of best practices and empirical evidence to support IoT developers aiming to optimize microservices-based deployments on the Edge, particularly in resource-constrained environments.

随着微服务在物联网（IoT）系统中的应用越来越多，在边缘部署它们仍然是从业者面临的一个重大挑战。虽然边缘计算通过在源附近处理数据提供了改进的延迟和资源效率，但它也引入了管理微服务的复杂性。尽管学术界越来越感兴趣，但很少有全面的研究调查了在边缘部署基于微服务的物联网系统的具体挑战和有效的软件工程（SE）实践。因此，我们进行了一项多方法研究来弥补这一差距。我们使用了三种方法：(1)系统文献综述（SLR）来确定已知的挑战和方法，(2)灰色文献综述（GLR）来提取该领域使用的SE实践，以及(3)使用两个版本的案例研究进行实证评估，一个有一个没有选定的SE实践。研究结果表明：(1)报告的最大挑战与资源利用和性能优化有关；(2)容器化微服务、API网关和每服务数据库是最常用的推荐实践；(3)在基于边缘的物联网系统中，实施这些实践可以提高132%的吞吐量，减少49%的延迟，节省高达13%的内存。然而，增加的体系结构复杂性也导致了更高的CPU使用率。本研究提供了一系列最佳实践和经验证据，以支持物联网开发人员优化基于微服务的边缘部署，特别是在资源受限的环境中。

{"title":"Analysis of microservices-based IoT systems: deployment challenges, industry practices, and performance insights","authors":"Yahia El Fellah , Jean Baptiste Minani , Naouel Moha , Julien Gascon-Samson , Yann-Gaël Guéhéneuc","doi":"10.1016/j.iot.2025.101867","DOIUrl":"10.1016/j.iot.2025.101867","url":null,"abstract":"<div><div>As the adoption of microservices in Internet of Things (IoT) systems grows, deploying them on the Edge remains a significant challenge for practitioners. While Edge Computing offers improved latency and resource efficiency by processing data near the source, it also introduces complexity in managing microservices. Despite increasing academic interest, few comprehensive studies have investigated the specific challenges and effective software engineering (SE) practices for deploying microservices-based IoT systems on the Edge. Therefore, we conducted a multi-method study to bridge this gap. We used three methods: (1) a systematic literature review (SLR) to identify known challenges and approaches, (2) a gray literature review (GLR) to extract SE practices used in the field, and (3) an empirical evaluation using two versions of a case study, one with and one without selected SE practices. The findings show that (1) the most reported challenges relate to resource utilization and performance optimization, (2) containerized microservices, API gateways, and database-per-service are among the most commonly recommended practices, and (3) implementing these practices led to a 132% throughput improvement, 49% reduction in latency, and memory savings of up to 13% in Edge-based IoT systems. However, increased architectural complexity also led to higher CPU usage. This study offers a catalog of best practices and empirical evidence to support IoT developers aiming to optimize microservices-based deployments on the Edge, particularly in resource-constrained environments.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101867"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978121","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

Sustainable, QoS, and cost-aware placement of microservices on the continuum: a use case on the Internet of Medical Things 连续体上微服务的可持续、QoS和成本意识：医疗物联网的一个用例

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2026-02-11 DOI: 10.1016/j.iot.2026.101894

Alejandro Moya , Juan Luis Herrera , Juan López-Rodenas , Javier Berrocal , Juan Manuel Murillo , Elena Navarro

Domains such as healthcare, which are intensive in contrast to user-grade domains, are increasingly interested to develop Internet of Things (IoT) applications to automate their critical processes, leading to the Internet of Medical Things (IoMT). IoMT applications leverage the Computing Continuum infrastructure. However, for intensive IoT and IoMT applications to be feasible, their strict Quality of Service (QoS) requirements must be met, and the economic cost of their deployment must be low to ensure their business viability. Furthermore, sustainability and the reduction of the carbon footprint are currently a priority due to industrial and governmental initiatives and requirements, such as Green IoT or the Sustainable Development Goals. The efforts in sustainability are aimed not only at achieving energy-efficient applications, but carbon-aware ones, aligning carbon footprint reduction with high QoS and low economic cost. While all three objectives can be achieved by strategically placing the microservices of these IoT applications, navigating the trade-offs across the three is a complex issue, calling for automated solutions that provide IoT application developers with a manageable number of Pareto-optimal microservice placements. This work presents the Many-Objective Genetic Algorithm for Microservice Placement (MOGAMP), which leverages evolutionary computing to assist IoT application developers in navigating the QoS, cost, and sustainability trade-off in microservice placement. In an evaluation with an IoMT use case, MOGAMP is shown to be scalable, up to 459.82 times faster and with a memory footprint of up to 0.37% compared to alternatives, enabling IoT application developers to explore wide, yet manageable, Pareto fronts.

与用户级领域相比，医疗保健等领域是密集的，因此越来越有兴趣开发物联网（IoT）应用程序来自动化其关键流程，从而导致医疗物联网（IoMT）。IoMT应用程序利用计算连续体基础设施。然而，为了使密集的IoT和IoMT应用可行，必须满足其严格的服务质量（QoS）要求，并且部署的经济成本必须较低，以确保其业务可行性。此外，由于工业和政府的倡议和要求，例如绿色物联网或可持续发展目标，可持续性和减少碳足迹目前是一个优先事项。可持续发展的目标不仅是实现节能应用，而且是碳意识应用，将碳足迹减少与高质量和低经济成本相结合。虽然这三个目标都可以通过战略性地放置这些物联网应用程序的微服务来实现，但在三者之间进行权衡是一个复杂的问题，需要为物联网应用程序开发人员提供可管理数量的帕累托最优微服务放置的自动化解决方案。这项工作提出了微服务放置的多目标遗传算法（MOGAMP），它利用进化计算来帮助物联网应用程序开发人员在微服务放置中导航QoS、成本和可持续性权衡。在对IoMT用例的评估中，MOGAMP显示出可扩展性，与替代方案相比，速度高达459.82倍，内存占用高达0.37%，使物联网应用程序开发人员能够探索更广泛，更易于管理的帕雷托前沿。

{"title":"Sustainable, QoS, and cost-aware placement of microservices on the continuum: a use case on the Internet of Medical Things","authors":"Alejandro Moya , Juan Luis Herrera , Juan López-Rodenas , Javier Berrocal , Juan Manuel Murillo , Elena Navarro","doi":"10.1016/j.iot.2026.101894","DOIUrl":"10.1016/j.iot.2026.101894","url":null,"abstract":"<div><div>Domains such as healthcare, which are intensive in contrast to user-grade domains, are increasingly interested to develop Internet of Things (IoT) applications to automate their critical processes, leading to the Internet of Medical Things (IoMT). IoMT applications leverage the Computing Continuum infrastructure. However, for intensive IoT and IoMT applications to be feasible, their strict Quality of Service (QoS) requirements must be met, and the economic cost of their deployment must be low to ensure their business viability. Furthermore, sustainability and the reduction of the carbon footprint are currently a priority due to industrial and governmental initiatives and requirements, such as Green IoT or the Sustainable Development Goals. The efforts in sustainability are aimed not only at achieving energy-efficient applications, but carbon-aware ones, aligning carbon footprint reduction with high QoS and low economic cost. While all three objectives can be achieved by strategically placing the microservices of these IoT applications, navigating the trade-offs across the three is a complex issue, calling for automated solutions that provide IoT application developers with a manageable number of Pareto-optimal microservice placements. This work presents the Many-Objective Genetic Algorithm for Microservice Placement (MOGAMP), which leverages evolutionary computing to assist IoT application developers in navigating the QoS, cost, and sustainability trade-off in microservice placement. In an evaluation with an IoMT use case, MOGAMP is shown to be scalable, up to 459.82 times faster and with a memory footprint of up to 0.37% compared to alternatives, enabling IoT application developers to explore wide, yet manageable, Pareto fronts.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101894"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173164","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

Intelligent drone pickup scheduling via deep reinforcement learning in low altitude economy networks 基于深度强化学习的低空经济网络无人机智能取货调度

IF 7.6 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Internet of Things

Pub Date : 2026-03-01 Epub Date: 2026-02-03 DOI: 10.1016/j.iot.2026.101882

K M Rumman, Dimitrios Kaltsogiannis, Eirini Eleni Tsiropoulou

The advent of Low Altitude Economy (LAE) has attracted the interest of the research community to analyze the autonomous drone operations, as they become the enablers for on-demand services. In this paper, we introduce an intelligent drone pickup scheduling framework to support LAE networks based on a Deep Reinforcement Learning (DRL) approach that exploits the Maskable Proximal Policy Optimization (M-PPO). A detailed aerodynamic energy model is introduced to capture the nonlinear power requirements related to the takeoff and landing phases under varying payload masses. An aging-aware mechanism is proposed to deal with the service fairness and responsiveness by prioritizing the parcels based on their waiting time, and ultimately mitigating their backlog within the service field. A feasibility masking technique is designed to support the M-PPO framework in order to guarantee the operational constraints related to the drone’s payload capacity and its battery limitations, thus, ultimately preventing infeasible routing decisions during the policy training. A multi-objective reward function is formulated accounting for the drone’s energy efficiency optimization, backlog reduction, and service urgency and allowing the drone to adaptively balance the trade-offs among these factors. Detailed results demonstrate the superiority of the M-PPO framework in terms of its adaptability, fairness, and energy efficiency compared to traditional heuristics and non-adaptive learning mechanisms.

低空经济（LAE）的出现引起了研究界对分析自主无人机操作的兴趣，因为它们成为按需服务的推动者。在本文中，我们引入了一个智能无人机取货调度框架，以支持基于深度强化学习（DRL）方法的LAE网络，该方法利用了可屏蔽的近端策略优化（M-PPO）。引入了一个详细的气动能量模型，以捕捉不同载荷质量下与起飞和着陆阶段有关的非线性功率需求。提出了一种老化感知机制，通过基于等待时间对包裹进行优先级排序来处理服务公平性和响应性，最终缓解服务领域内的积压。可行性掩蔽技术旨在支持M-PPO框架，以保证与无人机有效载荷能力和电池限制相关的操作约束，从而最终防止在策略训练期间不可行的路由决策。制定了一个多目标奖励函数，考虑无人机的能源效率优化、积压减少和服务紧迫性，并允许无人机自适应地平衡这些因素之间的权衡。详细的研究结果表明，与传统的启发式和非自适应学习机制相比，M-PPO框架在适应性、公平性和能效方面具有优势。

{"title":"Intelligent drone pickup scheduling via deep reinforcement learning in low altitude economy networks","authors":"K M Rumman, Dimitrios Kaltsogiannis, Eirini Eleni Tsiropoulou","doi":"10.1016/j.iot.2026.101882","DOIUrl":"10.1016/j.iot.2026.101882","url":null,"abstract":"<div><div>The advent of Low Altitude Economy (LAE) has attracted the interest of the research community to analyze the autonomous drone operations, as they become the enablers for on-demand services. In this paper, we introduce an intelligent drone pickup scheduling framework to support LAE networks based on a Deep Reinforcement Learning (DRL) approach that exploits the Maskable Proximal Policy Optimization (M-PPO). A detailed aerodynamic energy model is introduced to capture the nonlinear power requirements related to the takeoff and landing phases under varying payload masses. An aging-aware mechanism is proposed to deal with the service fairness and responsiveness by prioritizing the parcels based on their waiting time, and ultimately mitigating their backlog within the service field. A feasibility masking technique is designed to support the M-PPO framework in order to guarantee the operational constraints related to the drone’s payload capacity and its battery limitations, thus, ultimately preventing infeasible routing decisions during the policy training. A multi-objective reward function is formulated accounting for the drone’s energy efficiency optimization, backlog reduction, and service urgency and allowing the drone to adaptively balance the trade-offs among these factors. Detailed results demonstrate the superiority of the M-PPO framework in terms of its adaptability, fairness, and energy efficiency compared to traditional heuristics and non-adaptive learning mechanisms.</div></div>","PeriodicalId":29968,"journal":{"name":"Internet of Things","volume":"36 ","pages":"Article 101882"},"PeriodicalIF":7.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173270","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