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