التفاصيل البيبلوغرافية
| العنوان: |
Temperature forecast algorithm for smart thermostat based on artificial neural network. |
| المؤلفون: |
Muhutdinov, R. M., Korolev, S. I., Goman, V., Sidorov, O. Yu. |
| المصدر: |
AIP Conference Proceedings; 2022, Vol. 2456 Issue 1, p1-7, 7p |
| مصطلحات موضوعية: |
ARTIFICIAL neural networks, THERMOSTAT, SMART power grids, THERMAL properties, TEMPERATURE, FORECASTING, RECURRENT neural networks |
| مستخلص: |
In this article, the solution to the problem of the internal temperature forecast in rooms has been considered. The ability to forecast temperature in rooms is one of the key features of smart thermostats. On such an occasion, the user is not required to enter multiple values characterizing the thermal properties of rooms or buildings. In this work, an approach to forecasting the problem was examined based on an artificial neural network (ANN). For the training purposes, we assume such initial data as the values of the internal and external temperatures, the temperature of the heating medium and the state of the heating or cooling devices. Two ANN architectures were examined: a multilayer perceptron and a long short-term memory. A comparison of three options applicable in the software of a smart thermostat was carried out. To solve the temperature forecast problem in the rooms, among the considered neural networks, the best result was shown by the recurrent neural network with a long short-term memory. According to the results of the research, the forecast accuracy came to 89% in comparison with the experimental data, while the varieties of ANNs of the multilayer perceptron type demonstrated the accuracy of 50% and 65%, accordingly. [ABSTRACT FROM AUTHOR] |
|
Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| قاعدة البيانات: |
Complementary Index |
Find this article in full text from Scitation.