Optimizing Air Quality Data Delivery  With Q-Learning for Power Savings in IoT

Muhammad Zulfarhan; Imran Lubis

doi:10.59934/jaiea.v5i1.1740

Authors

Muhammad Zulfarhan Universitas Harapan Medan
Imran Lubis Universitas Harapan Medan

DOI:

https://doi.org/10.59934/jaiea.v5i1.1740

Keywords:

Adaptive data transmission, Air quality, Energy efficiency, IoT, Q-Learning

Abstract

The Internet of Things (IoT) plays a crucial role in real-time air quality monitoring, yet battery-powered devices face energy constraints that make conventional periodic transmission inefficient. This study proposes the use of the Q-Learning algorithm to optimize adaptive air quality data delivery. A prototype system was built using an ESP32 with MQ-2, MQ-135, DHT22, and INA219 sensors connected to a web-based server. Experimental results showed a decision distribution of 55.6% transmit and 44.4% delay, with the average reward for delay actions (87.44) higher than for transmit actions (54.83). Compared to the periodic method, Q-Learning reduced transmission frequency by 40–50%, lowered energy consumption, and maintained data accuracy. These findings confirm that Q-Learning is effective in designing an energy-efficient, adaptive, and reliable IoT transmission mechanism for air quality monitoring.

Downloads

Download data is not yet available.

References

A. Choudhary, “Internet of Things: a comprehensive overview, architectures, applications, simulation tools, challenges and future directions,” Discover Internet of Things, vol. 4, no. 1, p. 31, Dec. 2024, doi: 10.1007/s43926-024-00084-3.

R. Amalianti, A. Jabbar Lubis, and I. Lubis, “Rancang Bangun Miniatur Stasiun Cuaca Untuk Monitoring Hujan, Suhu dan Kelembaban Udara Area Lokal Menggunakan Berbasis IoT,” in Seminar Nasional Teknologi Informasi & Komunikasi, Medan: Universitas Harapan Medan, 2021, pp. 241–247.

S. Shahid, D. J. Brown, P. Wright, A. M. Khasawneh, B. Taylor, and O. Kaiwartya, “Innovations in Air Quality Monitoring: Sensors, IoT and Future Research,” Sensors, vol. 25, no. 7, p. 2070, Mar. 2025, doi: 10.3390/s25072070.

T. Seesaard, K. Kamjornkittikoon, and C. Wongchoosuk, “A comprehensive review on advancements in sensors for air pollution applications,” Science of The Total Environment, vol. 951, p. 175696, Nov. 2024, doi: 10.1016/j.scitotenv.2024.175696.

E. Collado et al., “Open-source Internet of Things (IoT)-based air pollution monitoring system with protective case for tropical environments,” HardwareX, vol. 19, p. e00560, Sep. 2024, doi: 10.1016/j.ohx.2024.e00560.

A. Z. da Costa, J. P. S. Aniceto, and M. Lopes, “Low-Cost Sensor Network for Air Quality Assessment in Cabo Verde Islands,” Sensors, vol. 24, no. 23, p. 7656, Nov. 2024, doi: 10.3390/s24237656.

F. O. Adunola, V. N. Omeke, A. A. Ahmad, A. R. Bunu, A. J. Nkohon, and E. Obiajulu, “Energy-efficient wireless sensor network for real-time environmental monitoring: Simulink-based design,” Discover Electronics, vol. 2, no. 1, p. 63, Jul. 2025, doi: 10.1007/s44291-025-00104-8.

N. Yu et al., “Data-driven control, optimization, and decision-making in active power distribution networks,” Appl Energy, vol. 397, p. 126253, Nov. 2025, doi: 10.1016/j.apenergy.2025.126253.

S.-Y. Kim and H. Ko, “Energy-Efficient Cooperative Transmission in Ultra-Dense Millimeter-Wave Network: Multi-Agent Q-Learning Approach,” Sensors, vol. 24, no. 23, p. 7750, Dec. 2024, doi: 10.3390/s24237750.

J. Lansky et al., “A Q-learning-based routing scheme for smart air quality monitoring system using flying ad hoc networks,” Sci Rep, vol. 12, no. 1, p. 20184, Nov. 2022, doi: 10.1038/s41598-022-20353-x.

T. T. Nguyen, T. Thao Nguyen, T. A. Nguyen Dinh, T.-H. Nguyen, and P. Le Nguyen, “Q-learning-based Opportunistic Communication for Real-time Mobile Air Quality Monitoring Systems,” in 2021 IEEE International Performance, Computing, and Communications Conference (IPCCC), IEEE, Oct. 2021, pp. 1–7. doi: 10.1109/IPCCC51483.2021.9679398.