An Adaptive Deep Reinforcement Learning Routing Decision Algorithm-Based on ResNet-BiLSTM-ProbSparseAttention and Imitation Learning
IEEE Sensors Journal · 2026-04 · 26 (8) · 12777-12793
DOI: 10.1109/jsen.2026.3673702 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Sensors Journal, 2026-04. Verfasst von Wen Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Gansu Provincial Department of Education: School Teacher Innovation Fund Project.
Abstract (Originalsprache)
Wireless sensor networks (WSNs) have become an indispensable part of the Internet of Things (IoT). How to balance energy consumption and data transmission to further extend the overall lifetime of WSNs remains a key issue for IoT applications deployed on WSN infrastructure. Different from traditional clustering routing algorithms, this article proposes an adaptive intelligent routing decision algorithm based on deep reinforcement learning (DRL). The proposed model leverages a residual network (ResNet) to extract local spatial features from the WSN topology diagram, while BiLSTM captures bidirectional sequence dependencies. These two models are used to address the problems of frequent WSN topology changes and large state spaces. In addition, the ProbSparseAttention mechanism is adopted to prune large-scale action spaces and make routing decisions. To accelerate the convergence speed of reinforcement learning (RL), the deep Q-network (DQN) algorithm incorporates imitation learning (IL) from existing clustering algorithms to balance exploration and exploitation. Experimental evaluations demonstrate the superior performance of the proposed algorithm on network lifespan and energy efficiency. Furthermore, ablation experiments highlight the importance of each model and strategy component.
Förderung
- National Natural Science Foundation of China
- Gansu Provincial Department of Education: School Teacher Innovation Fund Project
Zitieren
APA
Li, W., Yang, J., Lian, J., & Wang, F. (2026). An Adaptive Deep Reinforcement Learning Routing Decision Algorithm-Based on ResNet-BiLSTM-ProbSparseAttention and Imitation Learning. IEEE Sensors Journal, 26(8), 12777-12793. https://doi.org/10.1109/jsen.2026.3673702
Vancouver
Li W, Yang J, Lian J, Wang F. An Adaptive Deep Reinforcement Learning Routing Decision Algorithm-Based on ResNet-BiLSTM-ProbSparseAttention and Imitation Learning. IEEE Sensors Journal. 2026;26(8):12777-12793. doi:10.1109/jsen.2026.3673702
BibTeX
@article{Li2026,
author = {Li, Wen and Yang, Jun and Lian, Jing and Wang, Fan},
title = {An Adaptive Deep Reinforcement Learning Routing Decision Algorithm-Based on ResNet-BiLSTM-ProbSparseAttention and Imitation Learning},
journal = {IEEE Sensors Journal},
year = {2026},
volume = {26},
number = {8},
pages = {12777--12793},
doi = {10.1109/jsen.2026.3673702}
}
EUVIMED