EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

IGWO-AS: An enhanced grey wolf optimizer for relay-node deployment in LoRa-based smart greenhouse systems

Yibo Shang, Hongling Li

Smart Agricultural Technology · 2026-12 · 15 · 102538

DOI: 10.1016/j.atech.2026.102538 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Smart Agricultural Technology, 2026-12. Verfasst von Yibo Shang und 1 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Innovation Fund, Gansu Agricultural University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Greenhouse Internet of Things (IoT) systems often suffer from uneven sensing coverage and unstable long-range communication links in obstacle-constrained environments, which limits the stability of environmental monitoring and control. To address these issues, this study proposes an integrated algorithm–system framework for relay-node deployment in LoRa-based smart greenhouse systems. An improved Grey Wolf Optimizer, termed IGWO-AS, is developed by incorporating an adaptive phase adjustment mechanism (APAM), a stochastic disturbance-based diversity enhancement mechanism (SDDE), and a communication-aware simulated annealing acceptance criterion (SAIAC). These mechanisms are designed to regulate the exploration–exploitation transition, maintain population diversity, and improve local-optimum escape while considering communication feasibility. In addition, a LoRa-based three-layer greenhouse architecture is constructed, consisting of the perception layer, network layer, and application layer, to support environmental sensing, data transmission, cloud-side management, and closed-loop regulation. Field experiments conducted in a 5 0 m × 5 0 m obstacle-constrained greenhouse show that IGWO-AS achieved a measured effective coverage rate of 93.5% and the lowest average packet-loss rate of 0.2% at 100 m among the tested deployment schemes. After mapping the fine-grid simulation output to the 2 m × 2 m field-scale grid, the deviation between mapped simulation coverage and measured field coverage was 3.5 percentage points. Parameter sensitivity analysis, ablation experiments, multi-scenario comparative simulations, and statistical stability analysis further demonstrated that IGWO-AS achieved faster convergence, higher final coverage, and more stable optimization results than the selected benchmark algorithms, especially in larger and obstacle-constrained greenhouse scenarios. The results indicate that the proposed IGWO-AS-based deployment method and LoRa system architecture provide a practical basis for reliable greenhouse monitoring and future integration with advanced closed-loop control strategies.

Förderung

  • Innovation Fund
  • Gansu Agricultural University

Zitieren

APA

Shang, Y., & Li, H. (2026). IGWO-AS: An enhanced grey wolf optimizer for relay-node deployment in LoRa-based smart greenhouse systems. Smart Agricultural Technology, 15, 102538. https://doi.org/10.1016/j.atech.2026.102538

Vancouver

Shang Y, Li H. IGWO-AS: An enhanced grey wolf optimizer for relay-node deployment in LoRa-based smart greenhouse systems. Smart Agricultural Technology. 2026;15:102538. doi:10.1016/j.atech.2026.102538

BibTeX
@article{Shang2026,
  author = {Shang, Yibo and Li, Hongling},
  title = {IGWO-AS: An enhanced grey wolf optimizer for relay-node deployment in LoRa-based smart greenhouse systems},
  journal = {Smart Agricultural Technology},
  year = {2026},
  volume = {15},
  pages = {102538},
  doi = {10.1016/j.atech.2026.102538}
}
Kostenlos starten →