A Model for Artificial Intelligence Supported Energy Management in Smart Campuses

Öz

Rising energy consumption and inefficiencies in large-scale facilities, such as university campuses, present critical financial and environmental challenges. Traditional energy management systems rely on static strategies, failing to adapt to real-time variations in demand, which leads to unnecessary energy waste and increased operational costs. This study introduces an AI-driven integrated energy management framework that utilizes real-time data from IoT sensors to optimize energy consumption across key campus systems, such as lighting, ventilation, heating, air conditioning, renewable energy sources, information and communication technology infrastructure, and building energy management systems. By leveraging machine learning techniques such as Artificial Neural Networks, Convolutional Neural Networks, and Reinforcement Learning, the system has potential to adjust energy-intensive operations, achieving a 59.125% reduction in total energy consumption. This translates into substantial financial savings of ₺7,390,625 annually for a mid-sized campus and a significantly lower carbon footprint, with heating cooling and lighting optimizations delivering the most significant impact. A cloud-edge computing architecture is integrated to enable real-time decision-making, ensuring efficient energy distribution without compromising user comfort or operational efficiency. However, the system's effectiveness depends on high-quality sensor data, adaptive AI algorithms, and robust cybersecurity measures to protect the IoT-based infrastructure. The results highlight the transformative potential of Artificial Intelligence in sustainable energy management, demonstrating that smart campus implementations can significantly reduce costs, enhance efficiency, and set a benchmark for autonomous AI-driven energy optimization in facilities.

Anahtar Kelimeler

• Artificial intelligence
• Deep learning
• Energy management
• HVAC
• Smart campus.

Akıllı Kampüslerde Yapay Zeka Destekli Enerji Yönetimi için Bir Model

Öz

Üniversite kampüsleri gibi büyük ölçekli tesislerde artan enerji tüketimi ve verimsizlikler, ciddi finansal ve çevresel sorunlar doğurmaktadır. Geleneksel enerji yönetim sistemleri, talepteki anlık değişimlere uyum sağlayamayan statik stratejilere dayanmakta olup, bu durum gereksiz enerji israfına ve artan işletme maliyetlerine yol açmaktadır. Bu çalışma, kampüs genelinde aydınlatma, havalandırma, ısıtma, iklimlendirme, yenilenebilir enerji kaynakları, bilgi ve iletişim teknolojileri altyapısı ile bina enerji yönetim sistemleri gibi temel sistemlerde enerji tüketimini optimize etmek amacıyla IoT sensörlerinden alınan gerçek zamanlı verileri kullanan, yapay zeka destekli entegre bir enerji yönetim çerçevesi sunmaktadır. Yapay Sinir Ağları, Evrişimli Sinir Ağları ve Pekiştirmeli Öğrenme gibi makine öğrenmesi tekniklerinden yararlanan sistem, enerji yoğun işlemleri optimize ederek toplam enerji tüketiminde %59,125 oranında azalma sağlama potansiyeline sahiptir. Bu da orta ölçekli bir kampüs için yıllık ₺7.390.625 tutarında önemli bir finansal tasarrufa ve daha düşük bir karbon ayak izine karşılık gelmektedir; özellikle ısıtma, soğutma ve aydınlatma optimizasyonları en büyük etkiyi yaratmaktadır. Gerçek zamanlı karar alma süreçlerini mümkün kılmak için bulut-kenar (cloud-edge) bilişim mimarisi entegre edilmiştir; bu sayede kullanıcı konforu veya operasyonel verimlilikten ödün vermeksizin etkin enerji dağıtımı sağlanmaktadır. Ancak sistemin etkinliği, yüksek kaliteli sensör verilerine, uyum sağlayabilen yapay zeka algoritmalarına ve IoT tabanlı altyapıyı koruyacak sağlam siber güvenlik önlemlerine bağlıdır. Elde edilen sonuçlar, yapay zekanın sürdürülebilir enerji yönetimindeki dönüştürücü potansiyelini ortaya koymakta; akıllı kampüs uygulamalarının maliyetleri önemli ölçüde azaltabileceğini, verimliliği artırabileceğini ve tesislerde otonom yapay zeka destekli enerji optimizasyonu için bir referans oluşturabileceğini göstermektedir.

Anahtar Kelimeler

• Yapay zeka
• Derin öğrenme
• Enerji yönetimi
• Akıllı kampüs
• HVAC

Kaynakça

1. Abbas, S. R., & Arif, M. (2006, December). Electric load forecasting using support vector machines optimized by genetic algorithm. In 2006 IEEE International Multitopic Conference (pp. 395-399). IEEE.
2. Adewoyin, M. A., Adediwin, O., & Audu, A. J. (2025). Artificial intelligence and sustainable energy development: A review of applications, challenges, and future directions. International Journal of Multidisciplinary Research and Growth Evaluation, 6(2), 196-203.
3. Advanced Energy Management Company. (2024). Commercial building energy consumption breakdown: Full analysis. Retrieved from: https://aemaco.com/2024/12/08/commercial-building-energy-consumption-breakdown/
4. Almasri, R. A., Abu-Hamdeh, N. H., & Al-Tamimi, N. (2024). A state-of-the-art review of energy-efficient and renewable energy systems in higher education facilities. Frontiers in Energy Research, 11, 1344216. Analytics Vidhya. (2022, March 14). A brief overview of recurrent neural networks (RNN). Retrieved from: https://www.analyticsvidhya.com/blog/2022/03/a-brief-overview-of-recurrent-neural-networks-rnn/.
5. Australian Government Department of the Environment and Energy (2024). Factsheet HVAC energy breakdown. Retrieved from: https://www.energy.gov.au/sites/default/files/hvac-factsheet-energy-breakdown.pdf Baduge, S. K., Thilakarathna, S., Perera, J. S., Arashpour, M., Sharafi, P., Teodosio, B., ... & Mendis, P. (2022). Artificial intelligence and smart vision for building and construction 4.0: Machine and deep learning methods and applications. Automation in Construction, 141, 104440.
6. Bayramov, S., Prokazov, I., Kondrashev, S., & Kowalik, J. (2021). Household electricity generation as a way of energy independence of states—Social context of energy management. Energies, 14(12), 3407. Byun, J., Hong, I., Lee, B., & Park, S. (2013). Intelligent household LED lighting system considering energy efficiency and user satisfaction. IEEE Transactions on Consumer Electronics, 59(1), 70-76.
7. Bajwa, A., Jahan, F., & Ahmed, I. (2024). A Systematic Literature Review On AI-Enabled Smart Building Management Systems for Energy Efficiency and Sustainability. Noor alam and Ahmed, Ishtiaque, A Systematic Literature Review on Ai-Enabled Smart Building Management Systems for Energy Efficiency And Sustainability (December 15, 2024). Energy Exchange Istanbul (EXIST) (2025). Transparency platform. Retrieved from: https://seffaflik.epias.com.tr/
8. Farzaneh, H., Malehmirchegini, L., Bejan, A., Afolabi, T., Mulumba, A., & Daka, P. P. (2021). Artificial intelligence evolution in smart buildings for energy efficiency. Applied Sciences, 11(2), 763.

9. Hou, Y., & Wang, Q. (2023). Big data and artificial intelligence application in energy field: a bibliometric analysis. Environmental Science and Pollution Research, 30(6), 13960-13973.
10. Hu, Q., Chi, M., & Liu, Z. W. (2023). A pricing game strategy with virtual prosumer guidance in community grid. IET Renewable Power Generation, 17(11), 2701-2710.
11. Hu, W., Zhang, Y., & Li, L. (2019). Study of the application of deep convolutional neural networks (CNNs) in processing sensor data and biomedical images. Sensors, 19(16), 3584.
12. Islam, S. N. (2024). A review of peer-to-peer energy trading markets: Enabling models and technologies. Energies, 17(7), 1702.
13. Jayakody, D. (2022, December 18). Deep Q-Networks (DQN) - A quick introduction (with code). Retrieved from: https://dilithjay.com/blog/dqn.
14. Jiang, K., Han, Q., Bai, Y., & Du, X. (2020). Data-driven ultimate conditions prediction and stress-strain model for FRP-confined concrete. Composite Structures, 242, 112094.
15. Kılıç, D. K., Nielsen, P., & Thibbotuwawa, A. (2024). Intraday Electricity Price Forecasting via LSTM and Trading Strategy for the Power Market: A Case Study of the West Denmark DK1 Grid Region. Energies, 17(12), 2909.
16. Kim, S., & Lim, H. (2018). Reinforcement learning based energy management algorithm for smart energy buildings. Energies, 11(8), 2010.
17. Klaučo, M., Drgoňa, J., Kvasnica, M., & Di Cairano, S. (2014). Building temperature control by simple mpc-like feedback laws learned from closed-loop data. IFAC Proceedings Volumes, 47(3), 581-586.
18. Kolokotsa, D. (2003). Comparison of the performance of fuzzy controllers for the management of the indoor environment. Building and Environment, 38(12), 1439-1450.
19. Lee, D. S., Chen, Y. T., & Chao, S. L. (2022). Universal workflow of artificial intelligence for energy saving. Energy Reports, 8, 1602-1633.
20. Lee, D., & Tsai, F. P. (2020). Air conditioning energy saving from cloud-based artificial intelligence: Case study of a split-type air conditioner. Energies, 13(8), 2001.
21. L’Heureux, A., Grolinger, K., & Capretz, M. A. (2022). Transformer-based model for electrical load forecasting. Energies, 15(14), 4993.
22. Li, N., Palaoag, T. D., Du, H., & Guo, T. (2023). Design and optimization of smart campus framework based on artificial intelligence. J Inf Syst Eng Manag, 8(3), 23086.
23. Li, X., Han, Z., Zhao, T., Zhang, J., & Xue, D. (2021). Modeling for indoor temperature prediction based on time-delay and Elman neural network in air conditioning system. Journal of Building Engineering, 33, 101854.
24. Ma, G. (2023). Intelligent Campus Informatization Management Model Based on BD and AI. The Frontiers of Society, Science and Technology, 5(13).
25. Mayer, B., Killian, M., & Kozek, M. (2016). A branch and bound approach for building cooling supply control with hybrid model predictive control. Energy and Buildings, 128, 553-566.
26. Purdon, S., Kusy, B., Jurdak, R., & Challen, G. (2013, October). Model-free HVAC control using occupant feedback. In 38th Annual IEEE Conference on Local Computer Networks-Workshops (pp. 84-92). IEEE.
27. Ruliyanta, R., Kusumoputro, R. S., Nugroho, R., & Nugroho, E. R. (2022, July). A novel green building energy consumption intensity: Study in inalum green building. In 2022 IEEE Region 10 Symposium (TENSYMP) (pp. 1-6). IEEE.
28. Salakij, S., Yu, N., Paolucci, S., & Antsaklis, P. (2016). Model-Based Predictive Control for building energy management. I: Energy modeling and optimal control. Energy and Buildings, 133, 345-358.
29. Silva-da-Nóbrega, P. I., Chim-Miki, A. F., & Castillo-Palacio, M. (2022). A smart campus framework: Challenges and opportunities for education based on the sustainable development goals. Sustainability, 14(15), 9640.
30. Sinclair, N., Harle, D., Glover, I. A., Irvine, J., & Atkinson, R. C. (2013). An advanced SOM algorithm applied to handover management within LTE. IEEE Transactions on vehicular technology, 62(5), 1883-1894.
31. Sreekumar, G., Martin, J. P., Raghavan, S., Joseph, C. T., & Raja, S. P. (2024). Transformer-based forecasting for sustainable energy consumption toward improving socioeconomic living: AI-enabled energy consumption forecasting. IEEE Systems, Man, and Cybernetics Magazine, 10(2), 52-60.
32. Szczepaniuk, H., & Szczepaniuk, E. K. (2022). Applications of artificial intelligence algorithms in the energy sector. Energies, 16(1), 347.
33. Trinh, H. D., Bui, N., Widmer, J., Giupponi, L., & Dini, P. (2017, October). Analysis and modeling of mobile traffic using real traces. In 2017 IEEE 28th annual international symposium on personal, indoor, and mobile radio communications (PIMRC) (pp. 1-6). IEEE.
34. Valks, B., Arkesteijn, M., Koutamanis, A., & Den Heijer, A. (2021). Towards smart campus management: Defining information requirements for decision making through dashboard design. Buildings, 11(5), 201.
35. Wang, H., & Zhang, B. (2018, August). Energy storage arbitrage in real-time markets via reinforcement learning. In 2018 IEEE Power & Energy Society General Meeting (PESGM) (pp. 1-5). IEEE.
36. Yao, R., & Steemers, K. (2005). A method of formulating energy load profile for domestic buildings in the UK. Energy and buildings, 37(6), 663-671.
37. Yuce, B., & Rezgui, Y. (2015). An ANN-GA semantic rule-based system to reduce the gap between predicted and actual energy consumption in buildings. IEEE Transactions on Automation Science and Engineering, 14(3), 1351-1363.