Farklı İklim Koşulları Altındaki Veri Merkezlerinde Enerji Yönetimi için Hibrit IoT ve AI Tabanlı Çözüm

Abstract

Hızla artan veri işleme ve depolama talebi, veri merkezlerini dünyanın en büyük enerji tüketicilerinden biri haline getirmiştir. Bu çalışma, veri merkezlerinde enerji tüketimini optimize etmek için dizel jeneratörler, güneş panelleri ve rüzgâr türbinlerini entegre eden bir hibrit enerji yönetim modeli önermektedir. Geliştirilen sistem, değişen iklim koşullarına uyum sağlamak için Nesnelerin İnterneti (IoT) altyapısı ve Yapay Zekâ (AI) tabanlı makine öğrenimi algoritmalarını kullanmaktadır. IoT sensörlerinden toplanan gerçek zamanlı veriler (hava durumu parametreleri, pil şarj seviyeleri ve enerji üretim oranları gibi) Destek Vektör Sınıflandırıcı (SVC), Rastgele Orman (RF), AdaBoost, Lojistik Regresyon (LR) ve Naive Bayes (NB) gibi algoritmalar kullanılarak işlenir ve bu da otonom ve son derece doğru enerji kaynağı yönetimini mümkün kılar. MATLAB ve Python'da yapılan simülasyonlar, enerji tüketiminde %20'ye varan azalma, işletme maliyetlerinde %15'lik düşüş ve yenilenebilir enerji kullanımında %50,1'lik artış olduğunu göstermektedir. Önerilen sistem, çevresel sürdürülebilirliği desteklemenin yanı sıra, değişken hava koşulları altında güvenilirliği artırarak, İstanbul gibi yenilenebilir enerji potansiyeli olan bölgelerdeki veri merkezleri için akıllı ve pratik bir çözüm sunmaktadır

Keywords

• Yapay Zekâ
• Nesnelerin İnterneti
• Veri Madenciliği
• Enerji Tüketimi
• Makine Öğrenimi
• Yenilenebilir Enerji Kaynakları.

Hybrid IoT and AI-based Solution for Energy Management in Data Centres under Various Climate Conditions

Abstract

The rapidly increasing demand for data processing and storage has made data centers one of the largest global energy consumers. This study proposes a hybrid energy management model that integrates diesel generators, solar panels, and wind turbines to optimize energy consumption in data centers. The developed system utilizes the Internet of Things (IoT) infrastructure and Artificial Intelligence (AI)-based machine learning algorithms to adapt to varying climatic conditions. Real-time data collected from IoT sensors—such as weather parameters, battery charge levels, and energy production rates—are processed using algorithms including Support Vector Classifier (SVC), Random Forest (RF), AdaBoost, Logistic Regression (LR), and Naive Bayes (NB), enabling autonomous and highly accurate energy source management. Simulations conducted in MATLAB and Python show up to a 20% reduction in energy consumption, a 15% decrease in operational costs, and a 50.1% increase in renewable energy utilization. In addition to supporting environmental sustainability, the proposed system enhances reliability under variable weather conditions, offering an intelligent and practical solution for data centers located in regions with renewable energy potential, such as Istanbul.

Keywords

• Artificial Intelligence
• Internet of Things
• Data Mining
• Energy Consumption
• Machine Learning
• Renewable Energy Sources

References

1. W. He, Y. Yang, and C. Jiang, “Analysis on data center power supply system based on multiple renewable power configurations and multiobjective optimization,” Renewable Energy, vol. 222, pp. 715–732, 2023.
2. A. Roy, S. S. Das, and S. Chatterjee, “Energy-Efficient Data Centers and Smart temperature control system with IoT sensing,” in Proc. IEEE IEMCON, Vancouver, Canada, 2016, pp. 1–5.
3. Q. Zhang, Y. Liu, and Y. Zhang, “A survey on data center cooling systems,” Journal of Systems Architecture, vol. 119, p. 102253, 2021.
4. T. Deepika and P. Prakash, “Power consumption prediction in cloud data center using machine learning,” Int. J. Electr. Comput. Eng., vol. 10, no. 2, pp. 1524–1532, 2019.
5. S. H. Lee, H. G. Kim, and J. W. Lee, “Energy Consumption Prediction System Based on Deep Learning with Edge Computing,” in Proc. IEEE ICET, Chengdu, China, 2019, pp. 1–6.
6. A. Merizig and S. Merzoug, “Machine Learning Approach for Energy Consumption Prediction in Datacenters,” in Proc. ICMIT, Adrar, Algeria, 2020, pp. 1–5.
7. G. Mehta and G. Mittra, “Application of IoT to optimize Data Center operations,” in Proc. GUCON, Greater Noida, India, 2018, pp. 1–5.
8. İşler, B., Kaya, Ş. M., & Kılıç, F. R. (2025). Fog-Enabled Machine Learning Approaches for Weather Prediction in IoT Systems: A Case Study. Sensors, 25(13), 4070.

9. Z. Zhou, W. Zhang, and L. Shu, “AFED-EF: An Energy-Efficient VM Allocation Algorithm for IoT Applications in Cloud Data Center,” IEEE Trans. Green Commun. Netw., vol. 5, no. 2, pp. 658–669, 2021.
10. Kaya, Ş. M., İşler, B., Abu-Mahfouz, A. M., Rasheed, J., & AlShammari, A. (2023). An Intelligent Anomaly Detection Approach for Accurate and Reliable Weather Forecasting at IoT Edges: A Case Study. Sensors, 23(5), 2426.
11. Kaya, Ş.M.; Erdem, A., & Güneş, A. (2022). Anomaly Detection and Performance Analysis by Using Big Data Filtering Techniques For Healthcare on IoT Edges. Sakarya University Journal of Science, 26(1), 1-13,
12. J. Smith and A. Johnson, “Predictive Model for the Impact of Consumption on Power Demand in Data Centers,” J. Energy Res., vol. 12, no. 3, pp. 123–145, 2023.
13. Q. Liu, Z. Zheng, and T. Wang, “Green data center with IoT sensing and cloud-assisted smart temperature control system,” Computer Networks, vol. 101, pp. 104–112, 2015.
14. R. Buyya, S. N. Srirama, and K. Thulasiraman, “Energy-efficiency and sustainability in new generation cloud computing,” Software: Pract. Exper., vol. 54, pp. 24–38, 2023.
15. K. M. U. Ahmed, M. A. Khan, and A. A. Khan, “A review of data centers energy consumption and reliability modeling,” IEEE Access, vol. 9, pp. 152536–152563, 2021.
16. M. Dayarathna, Y. Wen, and R. Fan, “Data Center Energy Consumption Modeling: A Survey,” IEEE Commun. Surv. Tutor., vol. 18, no. 1, pp. 732–794, 2016.
17. E. Masanet, A. Shehabi, N. Lei, S. Smith, and J. Koomey, “Recalibrating global data center energy-use estimates,” Science, vol. 367, no. 6481, pp. 984–986, Feb. 2020.
18. M. Dayarathna, Y. Wen, and R. Fan, “Data Center Energy Consumption Modeling: A Survey,” IEEE Commun. Surv. Tutor., vol. 18, no. 1, pp. 732–794, 2016.
19. M. K. J. Ramphela, L. M. Kekwaletswe, and T. S. Letsholo, “IoT Integrated Data Center Infrastructure Monitoring System,” in Proc. icABCD, Durban, South Africa, 2020, pp. 1–6.
20. M. Babiuch, T. Brzeski, and P. Roztocki, “Using the ESP32 Microcontroller for Data Processing,” in Proc. 2019 Carpathian Control Conf., Krakow, Poland, 2019, pp. 1–4.
21. A. Medina-Santiago, M. R. Zuniga, and J. G. Morales, “Adaptive Model IoT for Monitoring in Data Centers,” IEEE Access, vol. 8, pp. 5622–5634, 2020.
22. A. Shehabi, S. Smith, D. Sartor, R. Brown, M. Herrlin, J. Koomey, E. Masanet, N. Horner, I. Azevedo, and W. Lintner, “United States Data Center Energy Usage Report,” Lawrence Berkeley National Laboratory, Berkeley, California, Tech. Rep. LBNL-1005775, 2016.
23. Ş. M. Kaya, A. Güneş and A. Erdem, "A Smart Data Pre-Processing Approach by Using ML Algorithms on IoT Edges: A Case Study," 2021 International Conference on Artificial Intelligence of Things (ICAIoT), Nicosia, Turkey, 2021, pp. 36-42.