Task‐Oriented: Dynamic Optimization Deployment Strategy of Intelligent Sensor Networks Based on Joint Probability Density
IET Wireless Sensor Systems · 2026-01 · 16 (1)
DOI: 10.1049/wss2.70044 ↗Kurz gefasst
Fachartikel in der Zeitschrift IET Wireless Sensor Systems, online erschienen am 15.11.2026. Verfasst von Hao Yuan und 4 weiteren Autor:innen. Die Arbeit nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
With the development of IoT technology, Intelligent Sensor Networks (ISNs) are widely used in fields such as environmental monitoring, intelligent transportation, and smart healthcare. In dynamic environments, stable task execution requires the node deployment of ISNs to be optimised adaptively according to the current task state. This paper proposes a dynamic deployment optimization method for ISNs based on joint probability density, in which target tracking is achieved by updating the network structure. First, an unscented Kalman filter (UKF) is used to predict the target state. A pretrained Restricted Boltzmann Machine (RBM) is then employed to perform energy‐based modelling of the joint sensing information collected by the selected mobile nodes. The KL divergence between the fused observation distributions before and after node movement, together with the movement energy cost, is used to construct the reward for Deep Deterministic Policy Gradient (DDPG), thereby guiding multiple nodes to coordinate their positions in a continuous action space. Furthermore, when the energy of a tracking node falls below a threshold, node replacement or node rescue is adaptively triggered based on whether a candidate node can directly sense the target, allowing the newly selected node to continue participating in observation‐driven deployment. Experimental results show that the proposed strategy can maintain continuous target tracking while balancing task‐observation performance against node‐movement energy consumption, providing a practical reinforcement‐learning formulation for task‐driven deployment of intelligent sensor networks.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Yuan, H., Du, R., Cui, N., Wu, J., & Wang, W. (2026). Task‐Oriented: Dynamic Optimization Deployment Strategy of Intelligent Sensor Networks Based on Joint Probability Density. IET Wireless Sensor Systems, 16(1). https://doi.org/10.1049/wss2.70044
Vancouver
Yuan H, Du R, Cui N, Wu J, Wang W. Task‐Oriented: Dynamic Optimization Deployment Strategy of Intelligent Sensor Networks Based on Joint Probability Density. IET Wireless Sensor Systems. 2026;16(1). doi:10.1049/wss2.70044
BibTeX
@article{Yuan2026,
author = {Yuan, Hao and Du, Rongfang and Cui, Naiyu and Wu, Jiaxin and Wang, Wei},
title = {Task‐Oriented: Dynamic Optimization Deployment Strategy of Intelligent Sensor Networks Based on Joint Probability Density},
journal = {IET Wireless Sensor Systems},
year = {2026},
volume = {16},
number = {1},
doi = {10.1049/wss2.70044}
}
EUVIMED