EUVIMEDEUVIMED entdecken
Crossref

Hybrid Deep Reinforcement Learning and Particle Swarm Optimization for Energy-Efficient Nano-Enabled Smart Agriculture

Farooq Syed, Rahman Khan

Journal of Quantum Nano- Green Environmental Systems · 2026

DOI: 10.70023/21606 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Quantum Nano- Green Environmental Systems, 2026. Verfasst von Farooq Syed und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The increasing deployment of nano-enabled sensing technologies in smart agriculture has transformed crop monitoring, environmental sensing, and precision farming by enabling real-time data acquisition at unprecedented scales. However, the limited energy capacity of nanosensors and the dynamic nature of agricultural environments pose significant challenges to maintaining reliable, sustainable network operations. To address these issues, this study proposes AgriNano-RLPSO (Agricultural Nano-Network Deep Reinforcement Learning and Particle Swarm Optimization Framework), a hybrid intelligent optimization approach designed to enhance energy efficiency and communication performance in nanoenabled smart agricultural networks. The proposed framework integrates Deep Reinforcement Learning to enable adaptive decision-making and intelligent resource allocation, while Particle Swarm Optimization is employed to identify optimal routing paths and transmission parameters that minimize energy expenditure. Comprehensive experiments were conducted across diverse agricultural monitoring scenarios, including soil moisture sensing, crop health assessment, and environmental data collection. The results demonstrate that AgriNano-RLPSO reduces overall energy consumption by 34.7%, extends network lifetime by 29.3%, improves packet delivery ratio by 25.8%, and decreases communication delay by 19.6% compared with existing state-of-the-art methods. Additionally, the framework improves resource utilization efficiency by 31.4%, ensuring stable, reliable network performance. These findings confirm that the synergistic integration of Deep Reinforcement Learning and Particle Swarm Optimization provides an effective solution for energy-aware nano-network management. Consequently, AgriNano-RLPSO offers a scalable and sustainable framework for next-generation smart agriculture systems, supporting improved productivity, resource conservation, and long-term agricultural sustainability.

Zitieren

APA

Syed, F., & Khan, R. (2026). Hybrid Deep Reinforcement Learning and Particle Swarm Optimization for Energy-Efficient Nano-Enabled Smart Agriculture. Journal of Quantum Nano- Green Environmental Systems. https://doi.org/10.70023/21606

Vancouver

Syed F, Khan R. Hybrid Deep Reinforcement Learning and Particle Swarm Optimization for Energy-Efficient Nano-Enabled Smart Agriculture. Journal of Quantum Nano- Green Environmental Systems. 2026. doi:10.70023/21606

BibTeX
@article{Syed2026,
  author = {Syed, Farooq and Khan, Rahman},
  title = {Hybrid Deep Reinforcement Learning and Particle Swarm Optimization for Energy-Efficient Nano-Enabled Smart Agriculture},
  journal = {Journal of Quantum Nano- Green Environmental Systems},
  year = {2026},
  doi = {10.70023/21606}
}
Kostenlos starten →