İlhan UMUT, Dinçer AKAL

Yapay zeka tarafından kontrol edilen yeni bir termoelektrik CPU soğutma sistemi

Merkezi İşlem Birimi'ndeki (CPU) aşırı sıcaklık artışı nedeniyle, bilgisayarlar zamanla kapanma ve sistem hasarları meydana gelmektedir. Bu çalışmada, CPU'daki sıcaklığı azaltmak amacıyla yeni bir termoelektrik soğutma sistemi tasarlanmıştır. Ayrıca sistemin dinamik kontrolü için 3 farklı yapay zeka modeli oluşturulup başarıları karşılaştırılmıştır. Yeni soğutma sistemi, termoelektrik modül kullanılarak tasarlanmıştır. Sisteme eklediğimiz termoelektrik soğutucu ile CPU arasındaki sıcaklık farkından faydalanarak fazla ısıyı iletim ve konveksiyon yoluyla uzaklaştırmaktır. Termoelektrik soğutucunun sıcaklığı her zaman CPU sıcaklığından düşük olacağından dolayı etkin soğutma sağlanmış olacaktır. Soğutma ünitesinin kontrolü için özel bir elektronik devre ve yazılım geliştirilmiştir. Ek soğutma sistemini dinamik olarak kontrol etmek için üç farklı yapay zeka modeli (yapay sinir ağı, rastgele orman ve k-en yakın komşu) oluşturulup başarıları karşılaştırılmıştır. Yapay zeka, termoelektrik soğutma sisteminin gücünü ve fan hızını belirler. Bu kontrolü belirli bir CPU yükü veya belirli bir sıcaklık değeri yerine tüm parametreleri (CPU frekansı, voltajı, işlem sayısı gibi farklı değerler) değerlendirerek gerçekleştirir. Maksimum yükte CPU sıcaklığı 41⁰C iken, tasarlanan termoelektrik soğutma sistemi sayesinde bu sıcaklık 31⁰C'ye düşürülmüştür. Tüm yöntemler eğitimde yüksek bir sınıflandırma başarısı sağlamıştır. Ancak yapay sinir ağı yönteminin sınıflandırma başarısı (%97,973) rastgele ormana (%97,297) ve k-en yakın komşuya (%96,306) göre daha yüksektir.

Anahtar Kelimeler:

CPU, sıcaklık, termoelektrik soğutma, enerji, yapay zeka

A novel thermoelectric CPU cooling system controlled by artificial intelligence

Due to the 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. 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. While the CPU temperature was 41⁰C at maximum load, this temperature was reduced to 31⁰C thanks to the designed thermoelectric cooling system. All methods provided a high classification success in education. 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%).

Keywords:

CPU, Temperature, Thermoelectric cooling, Energy, Artificial Intelligence,

PDF

___

Wiriyasart, S., Hommalee, C., Naphon, P., Thermal cooling enhancement of dual processors computer with thermoelectric air cooler modüle, Case Studies in Thermal Engineering, 14, 100445, 2019.
Septiadi ,W.N., Ula, W.A.W., Wulandari, I.G.A.A.D.,Tnunay ,I.A.,Murti, M.R., Thermal resistance analysis of central processing unit cooling system based on cascade straight heat pipe, International Conference on Design, Energy, Materials and Manufacture, Materials Science and Engineering, 539, 012036, 2019.
Dogan, A., Ozbalci, O., Experimental Investigation of the Effect of Metal Foam Material on CPU Cooling, Journal of Engineering Technology and Applied Sciences, 2, 3, 113-120, 2017.
Al-Rashed, M.H., Dzido , G., Korpyś , M., Smołka , J ., Wójcik , J. , Investigation on the CPU nanofluid cooling,Microelectronics Reliability, 63,159–165, 2016.
Siricharoenpanich , A ., Wiriyasart , S ., Srichat , A ., Naphon, P ., Thermal management system of CPU cooling with a novel short heat pipe cooling system, Case Studies in Thermal Engineering, 15, 100545, 2019.
Zhang, Y., Long, E., Zhang, M., Experimental study on heat sink with porous copper as conductive material for CPU cooling, Materials Today, Proceedings, 5 , 15004- 15009, 2018.
Anandakrishnan , M., Balaji , C ., Cfd Simulations of Thermal And Flow Fields Inside A Desktop Personal Computer Cabin With Multi-Core Processors, Engineering Applications of Computational Fluid Mechanics, 3, 2, 277–288, 2019.
Rashidi , M.A., Paknezhad , M., Yousefi, T., Experimental and artificial neural network investigation on the effect of inclination angle on the interface temperature of CPU/metal foam heat sink, International Journal of Numerical Methods for Heat & Fluid Flow, 28, 12, 2758-2768, 2018.
Zhu, Y ., Newbrook ,W .D., Dai , P., Groot , K.H.C., Huang , R ., Artificial neural network enabled accurate geometrical design and optimisation of thermoelectric generator, Applied Energy, 305, 117800, 2022.
Tan, O.S., Demirel, H., Performance and cooling efficiency of thermoelectric modules on server central processing unit and Northbridge, Computers and Electrical Engineering, 46, 46-55, 2015.
Liu, D., Zhao, F., Yang, H., Tang, G., Thermoelectric mini cooler coupled with micro thermosiphon for CPU cooling system, Energy, 83, 29-36, 2015.
Harun, A.M., Che Sidik , A.N. , A Review on Development of Liquid Cooling System for Central Processing Unit (CPU) Journal of Advanced Research in Fluid Mechanics and Thermal Sciences, 78, 2, 98-113, 2021.
Cai , Y .,Liu, D., Yang, J., Wang, Y.,Zhao, F. ,Optimization of thermoelectric cooling system for application in CPU cooler, Energy Procedia, 105, 1644 – 1650, 2017.
Chen, W., Shi, X., Zou, J., Chen, Z., Thermoelectric Coolers: Progress, Challenges, and Opportunities, Small Methods, 6, 2101235, 2022.
Belarbi , A.A., Beriache , M., Che Sidik ,A.N., Mamat, R., Experimental investigation on controlled cooling by coupling of thermoelectric and an air impinging jet for CPU, Heat Transfer, 50, 2242–2258, 2020.
Rizkin, A,B ., Popovich, K., Hartman, L.R., Artificial Neural Network control of thermoelectrically-cooled microfluidics using computer vision based on IR thermography, Computers and Chemical Engineering, 121, 584-593, 2019.
Lerat, J., Mahmoudi, A.S., Mahmoudi, S., Single node deep learning frameworks, Comparative study and CPU/GPU performance analysis, Concurrency Computat Pract Exper, 6730, 2021.
Neyestani, M.,Nazari , M., Shahmardan,M.M., Sharifpur, M., Ashouri , M., Meyer,P.J., Thermal characteristics of CPU cooling by using a novel porous heat sink and nanofluids, Journal of Thermal Analysis and Calorimetry, 138, 805–817, 2019.
Manikandan, S., Selvam, C., Praful,S.P.P., Lamba, R., Kaushik,C.S., Zhao, D.,Yang, R., A novel technique to enhance thermal performance of a thermoelectric cooler using phase-change materials. Journal of Thermal Analysis and Calorimetry 140, 1003–1014, 2020.
Soltangheis, S., Siavashi, M., Izadi, A.A., Xiong, Q,, Semi-analytical study of impingement cooling of metal foam heat sinks of CPUs with air and hydrogen jets under LTNE condition, Journal of Thermal Analysis and Calorimetry, 145, 1801-1816, 2021.
Kotsur , M., Optimal Control of Distributed Parameter Systems with Application to Transient Thermoelectric Cooling, Advances in Electrical and Computer Engineering, 15, 2, 2015.
Milicevic ,M., Baranavic , M.,Zubrinic , K.,Application of Machine Learning Algorithms for the Query Performance Prediction, Advances in Electrical and Computer Engineering, 15, 3, 2015.
Das ,A., Pradhan , N.S., Design Time Temperature Reduction in Mixed Polarity Dual Reed-Muller Network: a NSGA-II Based Approach, Advances in Electrical and Computer Engineering, 20, 1, 2020.
Timcenko , V., Gajin , S., Machine Learning Enhanced Entropy-Based Network Anomaly Detection. Advances in Electrical and Computer Engineering, 21, 4, 2021.
https://html.alldatasheet.com/html- pdf/227422/ETC2/TEC1-12706/99/1/TEC1- 12706.html.
Mao, J., Chen, G., Ren, Z.,Thermoelectric cooling materials, Nature Materials, 20, 454–461, 2021.
Asharf, J., Moustafa, N., Khurshid, H., Debie, E.,Haider, W., Wahab, A., Review of Intrusion Detection Systems Using Machine and Deep Learning in Internet of Things: Challenges, Solutions and Future Directions, Electronics 9, 1177, 2020.
Verikas, A., Gelzinis, A., Bacauskiene, M., Mining data with random forests: A survey and results of new tests, Pattern Recognition, 44, 2, 2011.