A predictive actuator for IoT-based air conditioner unit

  • Henrique Tome Damasio UNIOESTE
  • Marcio Oyamada UNIOESTE


The energy consumption used in cooling systems is increasing year by year. In data centers, such consumption can represent more than 50% of the total energy consumption. This work aims to develop an actuator to reduce the energy consumption of air conditioner (AC) systems in a small server room. This work uses machine learning techniques to create an accurate model that predicts the short-term AC energy consumption in the next 30 minutes window based on the inside and outside temperature. Three different actuators were evaluated in this work, the first using the AC unit at 22ºC in automatic mode, the second one using fixed rules based on the time and day of the week, and a third using a predictionbased rule system. The case study using rules-based actuators resulted in energy savings compared to the AC automatic mode. In the comparison of the three actuators, the prediction-based actuator model presented the best results, obtaining a reduction of approximately 37.84% in energy consumption compared to the automatic mode.

Palavras-chave: Energy consumption, data center, predictive system


C. Delmastro Cooling tracking clean energy progress 2007.

P. Singh L. Klein D. Agonafer J. M. Shah and K. D. Pujara "Effect of Relative Humidity Temperature and Gaseous and Particulate Contaminations on Information Technology Equipment Reliability" International Electronic Packaging Technical Conference and Exhibition vol. 1 07 2015.

Thermal Guidelines for Data Processing Environments Atlanta GA USA:ASHRAE 2008.

M. Dayarathna Y. Wen and R. Fan "Data center energy consumption modeling: A survey" IEEE COMMUNICATIONS SURVEYS TUTO-RIALS vol. 18 no. 1 pp. 732-794 FIRST QUARTER 2016.

I. Cheung S. Greenberg R. Mahdavi R. Brown and W. Tschudi "Energy efficiency in small server rooms: Field surveys and findings" 2014 ACEEE Summer Study on Energy Efficiency in Buildings no. 12 2014.

M. Kowsigan K. Induja S. Kalicharan and P. Karthik "An enhaced automatic cooling system in cloud data center using IoT" 2017 International Conference on Intelligent Computing and Control (I2C2) no. 5 2017.

L. Xuemei D. Lixing S. Ming X. Gang and L. Jibin "A novel air-conditioning load prediction based on ARIMA and BPNN model" 2009 Asia-Pacific Conference on Information Processing vol. 1 pp. 51-54 2009.

F. H. Purwanto E. Utami and E. Pramono "Design of server room temperature and humidity control system using fuzzy logic based on micro controller" 2018 International Conference on Information and Communications Technology (ICOIACT) pp. 390-395 2018.

F. H. Purwanto E. Utami and E. Pramono "Implementation and optimization of server room temperature and humidity control system using fuzzy logic based on microcontroller" Journal of Physics: Conference Series vol. 1140 no. 012050 2018.

Y. Tarutani K. Hashimoto G. Hasegawa Y. Nakamura T. Tamura K. Matsuda et al. "Temperature distribution prediction in data centers for decreasing power consumption by machine learning" 2015 IEEE 7th International Conference on Cloud Computing Technology and Science pp. 635-642 2015.

Y. Tarutani K. Hashimoto G. Hasegawa Y. Nakamura T. Tamura K. Matsuda et al. "Reducing power consumption in data center by predicting temperature distribution and air conditioner efficiency with machine learning" 2016 IEEE International Conference on Cloud Engineering pp. 226-227 2016.

Y. Chen G. Fu and X. Liu "Air-conditioning load forecasting for prosumer based on meta ensemble learning" IEEE Access vol. 8 pp. 123673-123682 2020.

F. Pedregosa G. Varoquaux A. Gramfort V. Michel B. Thirion O. Grisel et al. "Scikit-learn: Machine learning in Python" Journal of Machine Learning Research vol. 12 pp. 2825-2830 2011.

Cloud automl Google 2019.
Como Citar

Selecione um Formato
DAMASIO, Henrique Tome; OYAMADA, Marcio. A predictive actuator for IoT-based air conditioner unit. In: SIMPÓSIO BRASILEIRO DE ENGENHARIA DE SISTEMAS COMPUTACIONAIS (SBESC), 10. , 2020, Evento Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2020 . p. 87-94. ISSN 2237-5430.