Robust High-Precision Time Synchronization for Distributed Sensor Systems in Challenging Environments

Збережено в:
Бібліографічні деталі
Опубліковано в::Remote Sensing vol. 17, no. 22 (2025), p. 3715-3744
Автор: Wang, Zhouji
Інші автори: Lyu Daqian, Zhou, Peiyuan, Ge Yulong, Hu, Yao, Zhu Rangang, Wang, Wei, Yang Xiaoniu
Опубліковано:
MDPI AG
Предмети:
Онлайн доступ:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Теги: Додати тег
Немає тегів, Будьте першим, хто поставить тег для цього запису!

MARC

LEADER 00000nab a2200000uu 4500
001 3275550258
003 UK-CbPIL
022 |a 2072-4292 
024 7 |a 10.3390/rs17223715  |2 doi 
035 |a 3275550258 
045 2 |b d20250101  |b d20251231 
084 |a 231556  |2 nlm 
100 1 |a Wang, Zhouji  |u College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China; zhoujiwang@mail.ustc.edu.cn (Z.W.); 
245 1 |a Robust High-Precision Time Synchronization for Distributed Sensor Systems in Challenging Environments 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a <sec sec-type="highlights"> What are the main findings? <list list-type="bullet"> <list-item> </list-item>A novel DSTS architecture was proposed, integrating Bayesian filtering with DDPG reinforcement learning to solve synchronization in Challenging environments. <list-item> The DSTS architecture achieved a final frequency synchronization precision of <inline-formula>4×10−10</inline-formula> and a phase precision of <inline-formula>5×10−10</inline-formula> s. </list-item> What are the implications of the main findings? <list list-type="bullet"> <list-item> </list-item>The fusion of ToF and CIR data via Bayesian filtering provides an effective method to address non-linear communication errors and propagation path state uncertainty. <list-item> The use of a DDPG agent as an “attention-like” mechanism is a viable strategy for managing network heterogeneity. </list-item> Timing and time synchronization are critical capabilities of Global Navigation Satellite Systems (GNSSs), but their performance deteriorates significantly in challenging environments like urban canyons and tunnels. To address this issue, this paper proposes the Distributed Sensor Time Synchronization architecture (DSTS), a novel architecture integrating Bayesian filtering with deep reinforcement learning. DSTS utilizes Bayesian filtering to fuse Time-of-Flight (ToF) measurements with Channel Impulse Response features for real-time compensation of non-linear errors and accurate path state prediction. Concurrently, the Deep Deterministic Policy Gradient (DDPG) algorithm trains each node into an intelligent agent that dynamically learns optimal synchronization weights based on local information like neighbor clock stability and link quality. This allows the architecture to adaptively amplify reliable nodes while mitigating the negative effects of unstable peers and adverse channels, ensuring high accuracy and availability. Simulation experiments based on a real-world UWB dataset demonstrate the architecture’s exceptional performance. The Bayesian filtering module effectively mitigates non-linear errors, reducing the standard deviation of ToF measurements in NLOS scenarios by up to 51.6% (over 41.2% consistently) while achieving high path state prediction accuracy (>85% static, >95% simulated dynamic). In simulated dynamic and heterogeneous networks, the DDPG algorithm achieves a synchronization accuracy better than traditional average-consensus algorithms, ultimately reaching a frequency and phase precision of <inline-formula>4×10−10</inline-formula> and <inline-formula>5×10−10</inline-formula> s, respectively. 
653 |a Wireless communications 
653 |a Accuracy 
653 |a Intelligent agents 
653 |a Protocol 
653 |a Algorithms 
653 |a Clocks & watches 
653 |a Synchronization 
653 |a Distributed sensor systems 
653 |a Time synchronization 
653 |a Machine learning 
653 |a Localization 
653 |a Reinforcement 
653 |a Heterogeneity 
653 |a Frequency synchronization 
653 |a Propagation 
653 |a Remote sensing 
653 |a Bayesian analysis 
653 |a Canyons 
653 |a Sensors 
653 |a Design 
653 |a Crystal oscillators 
653 |a Error reduction 
653 |a Impulse response 
653 |a Deep learning 
653 |a Real time 
653 |a Street canyons 
653 |a Filtration 
653 |a Global navigation satellite system 
700 1 |a Lyu Daqian  |u College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China; zhoujiwang@mail.ustc.edu.cn (Z.W.); 
700 1 |a Zhou, Peiyuan  |u Institute of Geospatial Information, Information Engineering University, Zhengzhou 450001, China 
700 1 |a Ge Yulong  |u College of Marine Science and Engineering, Nanjing Normal University, Nanjing 210023, Chinayaohu@nnu.edu.cn (Y.H.) 
700 1 |a Hu, Yao  |u College of Marine Science and Engineering, Nanjing Normal University, Nanjing 210023, Chinayaohu@nnu.edu.cn (Y.H.) 
700 1 |a Zhu Rangang  |u College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China; zhoujiwang@mail.ustc.edu.cn (Z.W.); 
700 1 |a Wang, Wei  |u National Key Laboratory of Electromagentic Space Security, Jiaxing 314033, China 
700 1 |a Yang Xiaoniu  |u National Key Laboratory of Electromagentic Space Security, Jiaxing 314033, China 
773 0 |t Remote Sensing  |g vol. 17, no. 22 (2025), p. 3715-3744 
786 0 |d ProQuest  |t Advanced Technologies & Aerospace Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3275550258/abstract/embedded/H09TXR3UUZB2ISDL?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3275550258/fulltextwithgraphics/embedded/H09TXR3UUZB2ISDL?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3275550258/fulltextPDF/embedded/H09TXR3UUZB2ISDL?source=fedsrch