A novel thermoelectric CPU cooling system controlled by artificial intelligence
Küçük Resim Yok
Tarih
2023
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Gazi Universitesi
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
(Figure Presented). shows the components of the additional TEC unit designed in addition to the CPU cooling fan. In order to realize the heat transfer by conduction between the TEC unit and the CPU, the aluminum plate (TEC Module Interface Connection), seen in (Figure A), is designed. On the plate used in this TEC unit, there are thermoelectric module (TEC-12706), heatsink and fan. Since the temperature of the thermoelectric cooler will always be lower than the CPU temperature, effective cooling will be ensured. Purpose: Temperature rise in computers is an undesirable situation that occurs depending on the processor load. Due to excessive temperature rise in the Central Processing Unit (CPU), computers shut down and system damage occurs over time. In this study, a new thermoelectric cooling system is designed to reduce the temperature in the CPU. In addition, 3 different artificial intelligence models were created for the dynamic control of the system and their successes were compared. Theory and Methods: The new cooling system is designed using a thermoelectric module. It is to remove the excess heat by conduction and convection by taking advantage of the temperature difference between the thermoelectric cooler and the CPU we add to the system. Since the temperature of the thermoelectric cooler will always be lower than the CPU temperature, effective cooling will be provided. A special electronic circuit and software have been developed for the control of the cooling unit. Three different artificial intelligence models (artificial neural network, random forest, and k-nearest neighbor) were created to dynamically control the additional cooling system and their successes were compared. Artificial intelligence determines the power and fan speed of the thermoelectric cooling system. It performs this control by evaluating all parameters (different values such as CPU frequency, voltage, number of processes) instead of a specific CPU load or a specific temperature value. Results: While the CPU temperature was 41? at maximum load, this temperature was reduced to 310C thanks to the designed thermoelectric cooling system. All methods provided a high classification success in training. However, the classification success of the artificial neural network method (97.973%) is higher than the random forest (97.297%) and the k-nearest neighbor (96.306%). Conclusion: In the standard CPU fan, the CPU temperature at maximum load was 41 °C and the maximum energy consumed by the fan for cooling was 8 Watts. Thanks to the developed thermoelectric cooler system, the CPU temperature was reduced to 31? and the energy difference for this process was maximum 12 Watts, at maximum load. © 2023 Gazi Universitesi Muhendislik-Mimarlik. All rights reserved.
Açıklama
Anahtar Kelimeler
Artificial intelligence, Central processing unit, Cooling, Energy, Thermoelectricity
Kaynak
Journal of the Faculty of Engineering and Architecture of Gazi University
WoS Q Değeri
Scopus Q Değeri
Q2
Cilt
39
Sayı
1
