EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Reinforcement Learning-Based Intelligent Water Level Control: From Simulation to Embedded Implementation

Kevin Cusihuallpa-Huamanttupa iD, Erwin J Sacoto-Cabrera iD, Roger Jesus Coaquira-Castillo iD, L Walter Utrilla Mego iD, Julio Cesar Herrera-Levano iD, Yesenia Concha-Ramos iD, Edison Moreno-Cardenas iD

Sensors · 31.12.2025 · 26 (1) · 245

DOI: 10.3390/s26010245 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 31.12.2025. Verfasst von Kevin Cusihuallpa-Huamanttupa und 6 weiteren Autor:innen. Beteiligte Einrichtung: TESLA Laboratory, Universidad Nacional de San Antonio Abad del Cusco (UNSAAC), Cusco 08003, Peru. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National University of Saint Anthony the Abbot in Cuzco, Politecnica Salesiana University, Universidad Nacional San Antonio Abad del Cusco.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This article presents the design, simulation, and real-time implementation of an intelligent water level control system using Deep Reinforcement Learning (DRL) with the Deep Deterministic Policy Gradient (DDPG) algorithm. The control policy was initially trained in a MATLAB-based simulation environment, where actor–critic neural networks were trained and optimized to ensure accurate and robust performance under dynamic and nonlinear conditions. The trained policy was subsequently deployed on a low-cost embedded platform (Arduino Uno), demonstrating its feasibility for real-time embedded applications. Experimental results confirm the controller’s ability to adapt to external disturbances. Quantitatively, the proposed controller achieved a steady-state error of less than 0.05 cm and an overshoot of 16% in the physical implementation, outperforming conventional proportional–integral–derivative (PID) control by 22% in tracking accuracy. The combination of the DDPG algorithm and low-cost hardware implementation demonstrates the feasibility of real-time deep learning-based control for intelligent water management. Furthermore, the proposed architecture is directly applicable to low-cost Internet of Things (IoT)-based water management systems, enabling autonomous and adaptive control in real-world hydraulic infrastructures. This proposal demonstrates its potential for smart agriculture, distributed sensor networks, and scalable and resource-efficient water systems. Finally, the main novelty of this work is the deployment of a DRL-based controller on a resource-constrained microcontroller, validated under real-world perturbations and sensor noise.

Schlagwörter

Stichwörter der Autor:innen

Arduino UnoDDPG algorithmdeep reinforcement learningneural networksreal-time systemswater level control

Autor:innen und Institutionen

  • TESLA Laboratory, Universidad Nacional de San Antonio Abad del Cusco (UNSAAC), Cusco 08003, Peru.
  • Professional Academic School of Systems and Computer Engineering, Universidad Continental, Cusco 08000, Peru.
  • GIHP4C, Universidad Politécnica Salesiana, Cuenca 010102, Ecuador.
  • LIECAR Laboratory, Universidad Nacional de San Antonio Abad del Cusco (UNSAAC), Cusco 08003, Peru.

ORCID-Profile: Kevin Cusihuallpa-Huamanttupa, Erwin J Sacoto-Cabrera, Roger Jesus Coaquira-Castillo, L Walter Utrilla Mego, Julio Cesar Herrera-Levano, Yesenia Concha-Ramos, Edison Moreno-Cardenas

Förderung

  • National University of Saint Anthony the Abbot in Cuzco
  • Politecnica Salesiana University
  • Universidad Nacional San Antonio Abad del Cusco
  • projects of the Professional School of Electronic Engineering
  • Universidad Politécnica Salesiana
  • Fog Computing Simulation project

Zitieren

APA

Cusihuallpa-Huamanttupa, K., Sacoto-Cabrera, E. J., Coaquira-Castillo, R. J., Utrilla Mego, L. W., Herrera-Levano, J. C., Concha-Ramos, Y., & Moreno-Cardenas, E. (2025). Deep Reinforcement Learning-Based Intelligent Water Level Control: From Simulation to Embedded Implementation. Sensors, 26(1), 245. https://doi.org/10.3390/s26010245

Vancouver

Cusihuallpa-Huamanttupa K, Sacoto-Cabrera EJ, Coaquira-Castillo RJ, Utrilla Mego LW, Herrera-Levano JC, Concha-Ramos Y, et al. Deep Reinforcement Learning-Based Intelligent Water Level Control: From Simulation to Embedded Implementation. Sensors. 2025;26(1):245. doi:10.3390/s26010245

BibTeX
@article{CusihuallpaHuamanttupa2025,
  author = {Cusihuallpa-Huamanttupa, Kevin and Sacoto-Cabrera, Erwin J and Coaquira-Castillo, Roger Jesus and Utrilla Mego, L Walter and Herrera-Levano, Julio Cesar and Concha-Ramos, Yesenia and Moreno-Cardenas, Edison},
  title = {Deep Reinforcement Learning-Based Intelligent Water Level Control: From Simulation to Embedded Implementation},
  journal = {Sensors},
  year = {2025},
  volume = {26},
  number = {1},
  pages = {245},
  doi = {10.3390/s26010245}
}
Kostenlos starten →