Cost-Effective TinyML-Ready Design and Field Deployment of a Solar-Powered Environmental Monitoring Data Collector Using LTE-M Communication
Source abstract
Abstract
Environmental monitoring is essential for smart agriculture, renewable energy assessment, and climate-aware farm management. However, deploying autonomous sensing platforms in rural environments remains challenging because of energy constraints, communication reliability, and real-time processing requirements. This paper presents a modular, solar-powered environmental monitoring platform integrating LTE-M communication and TinyML-enabled edge sensing. The proposed system adopts a dual-microcontroller architecture that combines an Arduino Nano 33 BLE for real-time sensor acquisition and edge processing with an Arduino MKR NB 1500 dedicated to low-power wide-area communication. The platform integrates temperature, humidity, atmospheric pressure, rainfall, wind, and light sensors within a scalable framework. Two monitoring stations were deployed in rural regions of Romania to evaluate communication robustness, sensing stability, and energy autonomy. Field results demonstrated reliable LTE-M connectivity (4306 received signal strength indicator [RSSI] samples; mean −75.51 dBm) and strong agreement with a regional weather station, with mean deviations of −0.71 °C (temperature), 4.98% (humidity), and a stable pressure offset of −9.58 hPa attributable to altitude differences. Despite a total system cost of €315, the platform achieved measurement performance comparable to that of professional meteorological stations while maintaining long-term solar-powered operation. The proposed architecture provides a scalable and cost-effective solution for distributed smart agriculture and environmental monitoring applications.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Smart Agriculture and AI · IoT Networks and Protocols · Air Quality Monitoring and Forecasting
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Communications Department, Polytechnic University of Timișoara, 300006 Timișoara, Romania
Orange Romania S.A., 010665 Bucharest, Romania
References (23)
Show source-provided references
1. Big Data in Smart Farming—A review10.1016/j.agsy.2017.01.023 ↗
2. Deep learning in agriculture: A survey10.1016/j.compag.2018.02.016 ↗
3. Liakos, K.G., Busato, P., Moshou, D., Pearson, S., and Bochtis, D. (2018). Machine Learning in Agriculture: A Review. Sensors, 18.10.3390/s18082674 ↗
4. The Internet of Things: A survey10.1016/j.comnet.2010.05.010 ↗
5. Internet of Things (IoT): A vision, architectural elements, and future directions10.1016/j.future.2013.01.010 ↗
6. Ratasuk, R., Mangalvedhe, N., Zhang, Y., Robert, M., and Koskinen, J.P. (2016). Overview of narrowband IoT in LTE Rel-13. Proceedings of the 2016 IEEE Conference on Standards for Communications and Networking (CSCN), IEEE.10.1109/CSCN.2016.7785170 ↗
7. A comparative study of LPWAN technologies for large-scale IoT deployment10.1016/j.icte.2017.12.005 ↗
8. Banbury, C.R., Reddi, V.J., Lam, M., Fu, W., Fazel, A., Holleman, J., Huang, X., Hurtado, R., Kanter, D., and Lokhmotov, A. (2021). Benchmarking TinyML Systems: Challenges and Direction. arXiv.
9. Warden, P., and Situnayake, D. (2019). TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers, O’Reilly Media.
10. Solar Powered Wireless Sensor Networks for Environmental Monitoring10.3923/itj.2011.1.10 ↗
11. Helmy, H.A., El-Rifaie, A.M., Youssef, A.A.F., Haggag, A., Hamad, H., and Eltokhy, M. (2025). Improving Solar Energy-Harvesting Wireless Sensor Network (SEH-WSN) with Hybrid Li-Fi/Wi-Fi, Integrating Markov Model, Sleep Scheduling, and Smart Switching Algorithms. Technologies, 13.10.3390/technologies13100437 ↗
12. Machine learning methods for solar radiation forecasting: A review10.1016/j.renene.2016.12.095 ↗
13. Kalaany, C.M.A., Kimaita, H.N., Abdelmoneim, A.A., Khadra, R., Derardja, B., and Dragonetti, G. (2025). The Potential of Low-Cost IoT-Enabled Agrometeorological Stations: A Systematic Review. Sensors, 25.10.3390/s25196020 ↗
14. IoT-enabled Smart Weather Stations: Innovations, Challenges, and Future Directions10.56532/mjsat.v4i2.293 ↗
15. Khan, S., Mahi, M., and Rasheduzzaman, M. (2024). Design and Implementation of a Low-Cost Weather Monitoring System using ESP-NOW. 2024 13th International Conference on Electrical and Computer Engineering (ICECE), IEEE.10.1109/ICECE64886.2024.11024940 ↗
16. Jasso-Reyes, D.A., Cabrera-Perdomo, C.I., and Reyes-Villagrana, R.A. (2025). On the Architecture of a Low-Cost Meteorological Station Based on the Internet of Things (IoT): Preliminary Results. Environ. Earth Sci. Proc., 34.10.3390/eesp2025034014 ↗
17. CropSynergy: Harnessing IoT solutions for smart and efficient crop management
18. Zhurakovskyi, B., Pliushch, O., Saiko, V., and Shutenko, V. (2025, January 28). Machine Learning-based Environmental Monitoring and Analysis System. Proceedings of the Cybersecurity Providing in Information and Telecommunication Systems, Kyiv, Ukraine.
19. Zhao, B., Zheng, D., Yang, C., Wang, S., Mansurova, M., Jomartova, S., Kunicina, N., Zabasta, A., Beliaev, V., and Caiko, J. (2025). Design and Optimization of an Internet of Things-Based Cloud Platform for Autonomous Agricultural Machinery Using Narrowband Internet of Things and 5G Dual-Channel Communication. Electronics, 14.10.3390/electronics14081672 ↗
20. Lukic, M., Sobot, S., Mezei, I., Vukobratovic, D., and Danilovic, D. (2020). In-depth Real-World Evaluation of NB-IoT Module Energy Consumption. Proceedings of the 2020 IEEE International Conference on Smart Internet of Things (SmartIoT), IEEE.10.1109/SmartIoT49966.2020.00046 ↗
21. Michelinakis, F., Al-selwi, A.S., Capuzzo, M., Zanella, A., Mahmood, K., and Elmokashfi, A. (2020). Dissecting Energy Consumption of NB-IoT Devices Empirically. arXiv.10.1109/JIOT.2020.3013949 ↗
22. Advancing NB-IoT communication: Performance analysis and novel gap-aware hybrid scheduling for delay-sensitive traffic10.1007/s11276-025-04052-9 ↗
23. Masoum, A., Meratnia, N., and Havinga, P.J. (2013). An energy-efficient adaptive sampling scheme for wireless sensor networks. Proceedings of the 2013 IEEE Eighth International Conference on Intelligent Sensors, Sensor Networks and Information Processing, IEEE.10.1109/ISSNIP.2013.6529794 ↗