Development of Intelligent Climatic System for a Smart Home
DOI:
https://doi.org/10.22213/2410-9304-2022-3-76-87Keywords:
climatic system, Internet of things, control, artificial intelligence, neural networks, machine learningAbstract
The article is devoted to the solution of optimization and automation problem of temperature selection for accommodation taking into account other possible parameters. Climatic system should select comfortable temperature for a user by analyzing user’s interaction with climatic system equipment; maintain comfortable temperature in the accommodation; inform the user about abnormal situations like equipment failure and possible fire. It is difficult for a human being to determine the exact temperature value in the accommodation, and, consequently, it is difficult to define the temperature value comfortable for him/her, the present climatic system is to optimize and automize temperature selection for an accommodation. Any climatic equipment suits for system operation (a heater, air conditioner and a desktop computer) to install the developed application for system control and a microcontroller connected to the computer. Three temperature sensors and climatic equipment should be connected via switching systems to the microcontroller. To reach the objective, it is required to perform the following tasks: to collect data for prediction, develop a neural network for comfort climate prediction in the accommodation, develop an application to control the system and information about the current temperature, develop a warning system in case of abnormal situations. The present topic of the diploma project was chosen to study the processes of home automation and operation of neural networks. The work resulted in operable climatic system using a microcontroller Arduino. The principal criteria of this work are providing energy efficiency, scalability and simplicity of use. The proposed climatic system is to provide the user with opportunity to select any equipment for his system without bothering about system adjustment as it is equipped intelligent module able to select comfortable climate due to switching equipment on and off.References
The Internet of Things: The Future of Consumer adoption. (2014). https://www.accenture.com/t20150624T211456__w__/us-en/_acnmedia/Accenture/Conversion-Assets/DotCom/Documents/Global/PDF/Technology_9/Accenture-Internet-Things.pdf.
Alaa M., Zaidan A., Zaidan B., Talal M. and Kiah M. (2017). A review of smart home applications based on Internet of Things. Journal of Network and Computer Applications, vol. 97, p.p.48-65.
Spacecontrol. URL: https://spacecontrol.ru/o-kompanii (дата обращения: 12.04.2021).
Умный обогреватель Smart 1S. URL: https://xiaomi-smarthome.ru/umnyj-obogrevatel-smartmi-1s (дата обращения: 12.04.2021).
Умный кондиционер Xiaomi Mijia Fresh Air Conditioner Pro. URL: https://rozetked.me/news/16697-xiaomi-mijia-fresh-air-conditioner-umnyy-kondicioner-s-pritochnoy-ventidyaciey (дата обращения: 12.04.2021).
Zhongwang L., Bin D. (2021). A networked smart home system based on recurrent neural networks and reinforcement learning. Systems Science and Control Engineering, vol 9(1), p.p. 775-783.
Wilson H. (2018). Artificial intelligence. Grey House Publishing. ISBN 978-1-68217-867-6.
Arduino Uno R3, Программируемый контроллер на базе ATmega328. URL: https://www.chipdip.ru/product/arduino-uno-r3.
Manohar, S. (2017). Mastering Machine Learning with Python in Six Steps. Apress.
Программирование Arduino. URL: https://arduinomaster.ru/program.
Блум Д. Изучаем Arduino: инструменты и методы технического волшебства / пер. с англ. СПб. : БХВ-Петербург, 2015.
Rezaul, B., Rafiul, H. (2006). Artificial Neural Networks in Smart Homes. Designing Smart Homes, pp. 146-164.
Teich, T., Roessler, F., Kretz, D., Franke, S. (2014). Design of a Prototype Neural Network for Smart Homes and Energy Efficiency, Procedia Engineering, vol. 69, p.p. 603-608.
Монк С. Программируем Arduino. Профессиональная работа со скетчами. СПб. : Питер, 2017.
Nicholas L. (2021). Anomaly Detection in Process Control Data with Machine Learning. URL: https://towardsdatascience.com/anomaly-detection-inprocess-control-data-with-machine-learning-35056a867f5b (дата обращения: 01.03.2021).
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Д М Нечеухина, Мхд Айман Аль Аккад
This work is licensed under a Creative Commons Attribution 4.0 International License.