Avaliação de Desempenho e Consumo Energético de TinyML em Dispositivos de Borda para Previsão de Precipitação
Resumo
No ecossistema da Internet das Coisas (IoT), dispositivos de borda operam com recursos computacionais e energéticos limitados, exigindo modelos de aprendizado de máquina eficientes. Neste trabalho, é desenvolvido um sistema de predição de chuva baseado em modelos Tiny Machine Learning (TinyML) executados em um dispositivo de borda com recursos limitados. São implementados modelos Convolutional Neural Network (CNN) e Multilayer Perceptron (MLP) no Arduino Nano 33 BLE Sense. A partir desse sistema, avalia-se a eficiência energética durante a inferência e o impacto de técnicas de otimização de modelos, incluindo poda, quantização e knowledge distillation. Os resultados permitem comparar consumo energético e desempenho, contribuindo para a escolha de soluções mais eficientes para aplicações IoT baseadas em TinyML.Referências
Abadade, Y., Temouden, A., Bamoumen, H., Benamar, N., Chtouki, Y., and Hafid, A. S. (2023). A comprehensive survey on tinyml. IEEE access, 11:96892–96922.
Bhushan, C. M., Koppuravuri, P., Prasanthi, N., Gazi, F., Hussain, M. M., Abdussami, M., Devi, A. A., and Faizi, J. (2025). Deploying tinyml for energy-efficient object detection and communication in low-power edge ai systems. Scientific Reports.
Bourechak, A., Zedadra, O., Kouahla, M. N., Guerrieri, A., Seridi, H., and Fortino, G. (2023). At the confluence of artificial intelligence and edge computing in iot-based applications: A review and new perspectives. Sensors, 23(3):1639.
Breder, G. B., Vasconcelos, G., and Ferro, M. (2025). Beyond accuracy: A comparative study of machine learning models for extreme weather forecasting in rio de janeiro with a green ai perspective. In Encontro Nacional de Inteligência Artificial e Computacional (ENIAC), pages 1996–2007. SBC.
Choudhary, A. (2024). Internet of things: a comprehensive overview, architectures, applications, simulation tools, challenges and future directions. Discover Internet of Things, 4(1):31.
de Albuquerque, A. S. and de Araujo, D. R. (2025). Short-term rainfall forecasting aided by iot and deep learning. In 2025 IEEE Latin Conference on IoT (LCIoT), pages 107–110. IEEE.
Kallimani, R., Pai, K., Raghuwanshi, P., Iyer, S., and López, O. L. (2024). Tinyml: Tools, applications, challenges, and future research directions. Multimedia Tools and Applications, 83(10):29015–29045.
Kumar, R., Goel, R., Sidana, N., Sharma, A. P., ghai, S., Singh, T., singh, R., Priyadarshi, N., Twala, B., and Ahmad, V. (2024). Enhancing climate forecasting with ai: Current state and future prospect. F1000Research, 13:1094.
Liyew, C. M. and Melese, H. A. (2021). Machine learning techniques to predict daily rainfall amount. Journal of Big Data, 8(1):153.
Mnif, M., Sahnoun, S., Saad, Y. B., Fakhfakh, A., and Kanoun, O. (2024). Combinative model compression approach for enhancing 1d cnn efficiency for eit-based hand gesture recognition on iot edge devices. Internet of things, 28:101403.
Rahman, H. U., Ritu, A. T., Rasha, H. J., and Anower, M. S. (2024). Comparative analysis of microcontrollers in wearable devices for real-time arrhythmia classification: an embedded machine learning approach. In 2024 6th International Conference on Electrical Engineering and Information & Communication Technology (ICEEICT), pages 1327–1331. IEEE.
Scheifer, E. L., de Queiroz Pereira, G., Guimarães, A. A., Souza, L. F., and Lorenzetto, J. A. S. (2025). Uso de dados climáticos e machine learning na previsão de chuvas para gestão sustentável do ecoturismo em francisco beltrão (pr). Revista Brasileira de Ecoturismo (RBEcotur), 18(5):706–717.
Sham, F. A. F., El-Shafie, A., Jaafar, W. Z. W., Sherif, M., Ahmed, A. N., et al. (2025). Advances in ai-based rainfall forecasting: A comprehensive review of past, present, and future directions with intelligent data fusion and climate change models. Results in Engineering, 27:105774.
Tao, Y., Hioka, Y., and Lu, Y. (2022). Experimental energy consumption analysis of neural network model compression methods on microcontrollers with applications in bird call classification. In 2022 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE), pages 1–8. IEEE.
Vieira, J. A., Campos, S. R., and de Sousa, G. V. M. (2025). Previsão climática no nordeste de goias: Aplicações de big data e machine learning. Iesgo Science, 1(1).
Bhushan, C. M., Koppuravuri, P., Prasanthi, N., Gazi, F., Hussain, M. M., Abdussami, M., Devi, A. A., and Faizi, J. (2025). Deploying tinyml for energy-efficient object detection and communication in low-power edge ai systems. Scientific Reports.
Bourechak, A., Zedadra, O., Kouahla, M. N., Guerrieri, A., Seridi, H., and Fortino, G. (2023). At the confluence of artificial intelligence and edge computing in iot-based applications: A review and new perspectives. Sensors, 23(3):1639.
Breder, G. B., Vasconcelos, G., and Ferro, M. (2025). Beyond accuracy: A comparative study of machine learning models for extreme weather forecasting in rio de janeiro with a green ai perspective. In Encontro Nacional de Inteligência Artificial e Computacional (ENIAC), pages 1996–2007. SBC.
Choudhary, A. (2024). Internet of things: a comprehensive overview, architectures, applications, simulation tools, challenges and future directions. Discover Internet of Things, 4(1):31.
de Albuquerque, A. S. and de Araujo, D. R. (2025). Short-term rainfall forecasting aided by iot and deep learning. In 2025 IEEE Latin Conference on IoT (LCIoT), pages 107–110. IEEE.
Kallimani, R., Pai, K., Raghuwanshi, P., Iyer, S., and López, O. L. (2024). Tinyml: Tools, applications, challenges, and future research directions. Multimedia Tools and Applications, 83(10):29015–29045.
Kumar, R., Goel, R., Sidana, N., Sharma, A. P., ghai, S., Singh, T., singh, R., Priyadarshi, N., Twala, B., and Ahmad, V. (2024). Enhancing climate forecasting with ai: Current state and future prospect. F1000Research, 13:1094.
Liyew, C. M. and Melese, H. A. (2021). Machine learning techniques to predict daily rainfall amount. Journal of Big Data, 8(1):153.
Mnif, M., Sahnoun, S., Saad, Y. B., Fakhfakh, A., and Kanoun, O. (2024). Combinative model compression approach for enhancing 1d cnn efficiency for eit-based hand gesture recognition on iot edge devices. Internet of things, 28:101403.
Rahman, H. U., Ritu, A. T., Rasha, H. J., and Anower, M. S. (2024). Comparative analysis of microcontrollers in wearable devices for real-time arrhythmia classification: an embedded machine learning approach. In 2024 6th International Conference on Electrical Engineering and Information & Communication Technology (ICEEICT), pages 1327–1331. IEEE.
Scheifer, E. L., de Queiroz Pereira, G., Guimarães, A. A., Souza, L. F., and Lorenzetto, J. A. S. (2025). Uso de dados climáticos e machine learning na previsão de chuvas para gestão sustentável do ecoturismo em francisco beltrão (pr). Revista Brasileira de Ecoturismo (RBEcotur), 18(5):706–717.
Sham, F. A. F., El-Shafie, A., Jaafar, W. Z. W., Sherif, M., Ahmed, A. N., et al. (2025). Advances in ai-based rainfall forecasting: A comprehensive review of past, present, and future directions with intelligent data fusion and climate change models. Results in Engineering, 27:105774.
Tao, Y., Hioka, Y., and Lu, Y. (2022). Experimental energy consumption analysis of neural network model compression methods on microcontrollers with applications in bird call classification. In 2022 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE), pages 1–8. IEEE.
Vieira, J. A., Campos, S. R., and de Sousa, G. V. M. (2025). Previsão climática no nordeste de goias: Aplicações de big data e machine learning. Iesgo Science, 1(1).
Publicado
19/07/2026
Como Citar
ALMEIDA, Clariele; MOURA, Rafael José; ARAÚJO, Danilo; ANDRADE, Ermeson.
Avaliação de Desempenho e Consumo Energético de TinyML em Dispositivos de Borda para Previsão de Precipitação. In: WORKSHOP EM DESEMPENHO DE SISTEMAS COMPUTACIONAIS E DE COMUNICAÇÃO (WPERFORMANCE), 25. , 2026, Gramado/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 105-116.
ISSN 2595-6167.
DOI: https://doi.org/10.5753/wperformance.2026.22165.
