HVAC Sistemlerinde Gradyan Arttırma Regresyonu ile Anomali Tespiti

Year 2024, Volume: 27 Issue: 6, 2117 - 2125

Muhammed Fatih Adak , Refik Kibar , Kevser Ovaz

https://doi.org/10.2339/politeknik.1379049

Abstract

HVAC sistemleri, önemli enerji tüketimleri, iç mekan hava kalitesi üzerindeki etkileri ve bina sakinlerinin konforundaki rolleri nedeniyle binalarda büyük önem taşımaktadır. Bu sistemlerin çalışmasını ve kontrolünü optimize etmek, enerji verimliliğini artırmak ve maliyetleri düşürmek için çok önemlidir. HVAC sistemlerinde anomali tespiti, enerji tüketimini optimize etmeyi, termal konforu ve iç mekan hava kalitesini iyileştirmeyi ve sensör hatalarını tespit edip izole etmeyi, ancak daha da önemlisi siber saldırıları tespit etmeyi amaçlamaktadır. Anomali tespiti, olağandışı modeller veya yetkisiz erişim girişimleri için sistem verilerini analiz ederek, HVAC sistemlerinin siber tehditlere karşı korunmasında hayati bir rol oynayabilir. Potansiyel siber saldırıların tespit edilmesi ve izole edilmesi, bina operasyonlarındaki kesintileri önleyebilir, hassas verileri koruyabilir ve HVAC sistemlerinin güvenilir bir şekilde işlevselliğini sürdürmesini sağlayabilir. Bu çalışmada, HVAC sistemlerinin anomali tespit yeteneklerini geliştirmek için Gradyan Arttırma Regresyonu kullanılmıştır. Geleneksel anomali tespit yöntemleri genellikle HVAC sistemlerinin dinamik yapısına uyum sağlamakta zorlanır ve yanlış alarmlar üretebilir veya kritik sorunları gözden kaçırabilir. Bu zorlukların üstesinden gelmek için, anomali tespit doğruluğunu ve güvenilirliğini artırmak üzere güçlü bir makine öğrenimi tekniği olan Gradyan Arttırma Regresyonu bu çalışmada kullanılmıştır. Modelin performansını ölçmek adına gerçek HVAC verileri kullanılarak anomali tespit yöntemleriyle karşılaştırılmıştır. Sonuçlar, yanlış alarmları en aza indirirken sistemin anormallikleri doğru bir şekilde tanımlama becerisinde önemli gelişmeler olduğunu göstermektedir. Genel olarak, bu araştırma daha sağlam ve uyarlanabilir bir anomali tespit çözümü sağlayarak HVAC sistem güvenliğinin ilerlemesine katkıda bulunmaktadır. Bu çalışma, Gradyan Arttırma Regresyonu'nun HVAC sistemlerinin siber güvenlik çerçevesine entegrasyonu ile siber tehditlere karşı gelişmiş koruma sağlayacağı ve böylece kritik altyapıların esnekliğini ve güvenilirliğini arttıracağını göstermiştir.

Keywords

HVAC, Gradyan Arttırma Regresyonu, siber saldırı, anomali tespiti, zaman serisi

Supporting Institution

Sakarya University Scientific Research Projects Commission (BAPK)

Project Number

2023-19-43-16

Anomaly Detection with Gradient Boosting Regressor on HVAC Systems

Abstract

HVAC systems are important in buildings due to their significant energy consumption, impact on indoor air quality, and role in occupant comfort. Optimizing the operation and control of these systems is crucial for improving energy efficiency and reducing costs. Anomaly detection in HVAC systems aims to optimize energy consumption, improve thermal comfort and indoor air quality, detect and isolate sensor faults, and, more importantly, detect cyber-attacks. By analyzing system data for unusual patterns or unauthorized access attempts, anomaly detection can play a vital role in safeguarding HVAC systems against cyber threats. Detecting and isolating potential cyber-attacks can prevent disruptions in building operations, protect sensitive data, and ensure the continued functionality of HVAC systems securely and reliably. In this study, Gradient Boosting Regressor is used to improve the anomaly detection capabilities of HVAC systems. Traditional anomaly detection methods often struggle to adapt to the dynamic nature of HVAC systems and may generate false alarms or miss critical issues. To address these challenges, we propose the application of Gradient Boosting Regressor, a powerful machine learning technique, to enhance anomaly detection accuracy and reliability. We evaluate the model's performance using real-world HVAC data, comparing it with existing anomaly detection methods. The results demonstrate significant improvements in the system's ability to identify anomalies accurately while minimizing false alarms. This research advances HVAC system security by providing a more robust and adaptive anomaly detection solution. Integrating Gradient Boosting Regressor into the cybersecurity framework of HVAC systems offers improved protection against cyber threats, thereby enhancing the resilience and reliability of critical infrastructures.

Keywords

HVAC, Gradient Boosting Regressor, cyber-attack, anomaly detection, time series

Project Number

2023-19-43-16

References

• [1] Asim, N., Badiei, M., Mohammad, M., Razali, H., Rajabi, A., Chin Haw, L., & Jameelah Ghazali, M. “Sustainability of heating, ventilation and air-conditioning (HVAC) systems in buildings—An overview”. International journal of environmental research and public health, 19(2): (2022).
• [2] Pérez-Lombard, L., Ortiz, J., & Pout, C. “A review on buildings energy consumption information.” Energy and buildings, 40(3): 394-398, (2008).
• [3] Xiao, F., & Wang, S. “Progress and methodologies of lifecycle commissioning of HVAC systems to enhance building sustainability.” Renewable and sustainable energy reviews, 13(5): 1144-1149, (2009).
• [4] Ahmad, M. W., Mourshed, M., Yuce, B., & Rezgui, Y. “Computational intelligence techniques for HVAC systems: A review In Building Simulation” 9: 359-398. Tsinghua University Press, (2016).
• [5] Reppa, V., Papadopoulos, P., Polycarpou, M. M., & Panayiotou, C. G. “A distributed architecture for HVAC sensor fault detection and isolation.” IEEE Transactions on Control Systems Technology, 23(4): 1323-1337, (2014).
• [6] Wang, Z., Parkinson, T., Li, P., Lin, B., & Hong, T. “The Squeaky wheel: Machine learning for anomaly detection in subjective thermal comfort votes.” Building and Environment, 151: 219-22, (2019).
• [7] Novikova, E., Belimova, P., Dzhumagulova, A., Bestuzhev, M., Bezbakh, Y., Volosiuk, A.& Lavrov, A. Usability assessment of the visualization-driven approaches to the HVAC data exploration. In Proceedings of the 30th International Conference on Computer Graphics and Machine Vision 1-12, (2020).
• [8] Tasfi, N. L., Higashino, W. A., Grolinger, K., & Capretz, M. A. “Deep neural networks with confidence sampling for electrical anomaly detection.” In 2017 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) 1038-1045, (2017).
• [9] Hindy, H., Brosset, D., Bayne, E., Seeam, A., & Bellekens, X. “Improving SIEM for critical SCADA water infrastructures using machine learning.” In International Workshop on Security and Privacy Requirements Engineering, 3-19. Cham: Springer International Publishing, (2018).
• [10] Nixon, C., Sedky, M., & Hassan, M. “Practical application of machine learning based online intrusion detection to internet of things networks.” In 2019 IEEE Global Conference on Internet of Things (GCIoT) 1-5, (2019).
• [11] Krishnamurthy, S., Sarkar, S., & Tewari, A. Scalable anomaly detection and isolation in cyber-physical systems using bayesian networks. In Dynamic Systems and Control Conference 46193, V002T26A006. American Society of Mechanical Engineers, (2014).
• [12] Bazlur Rashid, A. N. M., Ahmed, M., & Pathan, A. S. K. “Infrequent pattern detection for reliable network traffic analysis using robust evolutionary computation”, Sensors, 21(9), (2021).
• [13] Jadidi, Z., Pal, S., Hussain, M., & Nguyen Thanh, K. “Correlation-Based Anomaly Detection in Industrial Control Systems”. Sensors, 23(3): 1561, (2023).
• [14] Wang, Z., Parkinson, T., Li, P., Lin, B., & Hong, T. “The Squeaky wheel: Machine learning for anomaly detection in subjective thermal comfort votes.” Building and Environment, 151: 219-227, (2019).
• [15] J. Vijayan, "With the Internet of Things, smart buildings pose big risk," Computer World, (2014).
• [16] Khan, I. U., Aslam, N., AlShedayed, R., AlFrayan, D., AlEssa, R., AlShuail, N. A., & Al Safwan, A. “A proactive attack detection for heating, ventilation, and air conditioning (HVAC) system using explainable extreme gradient boosting model (XGBoost)”. Sensors, 22(23): 9235, (2022).
• [17] Elnour, M., Meskin, N., Khan, K., & Jain, R. “HVAC system attack detection dataset.” Data in Brief, 37: 107166, (2021).
• [18] Elnour, M., Meskin, N., Khan, K., & Jain, R. “Application of data-driven attack detection framework for secure operation in smart buildings”. Sustainable Cities and Society, 69: 102816, (2021).
• [19] A. Blázquez-García, A. Conde, U. Mori, and J. A. Lozano, “A review on outlier/anomaly detection in time series data”, ACM Computing Surveys, 54(3): 1-33, (2020).
• [20] Akpinar, M., Adak, M. F., & Guvenc, G. “SVM-based anomaly detection in remote working: Intelligent software SmartRadar.” Applied Soft Computing, 109: 107457, (2021).
• [21] Neter, J., Wasserman, W., & Kutner, M. H. “Applied linear regression models.” Richard D. Irwin (1983).
• [22] Komarasamy G and Ravishankar T.N., "The Application of Decision Tree Method for Data Mining" Technoarete Transactions on Intelligent Data Mining and Knowledge Discovery, 2(3), (2022).
• [23] Sapri, F. E., Nordin, N. S., Hasan, S. M., Yaacob, W. F. W., & Nasir, S. A. M. “Decision tree model for non-fatal road accident injury.” International Journal on Advanced Science, Engineering and Information Technology, 7(1): 63-70, (2017).
• [24] Zhang, M., Rong, J., Liu, S., Zhang, B., Zhao, Y., Wang, H., & Ding, H. “Factors related to self-rated health of older adults in rural China: A study based on decision tree and logistic regression model.” Frontiers in Public Health, 10: 952714, (2022).
• [25] Chen, D., Hu, F., Nian, G., & Yang, T. Deep residual learning for nonlinear regression. Entropy, 22(2): 193, (2020).
• [26] Cover, T. “Estimation by the nearest neighbor rule.” IEEE Transactions on Information Theory, 14(1), 50-55 (1968).
• [27] Han, J., Pei, J., & Tong, H. “Data mining: concepts and techniques. Morgan kaufmann”, MK Press, (2022).
• [28] Fazakas-Anca, I. S., Modrea, A., & Vlase, S. “Determination of Reactivity Ratios from Binary Copolymerization Using the k-Nearest Neighbor Non-Parametric Regression.” Polymers, 13(21): 3811, (2021).
• [29] Breiman L., "Random Forests," Mach Learn, 45(1), 5–32, (2001).
• [30] Xing, F., Luo, R., Liu, M., Zhou, Z., Xiang, Z., & Duan, X. “A new random forest algorithm-based prediction model of post-operative mortality in geriatric patients with hip fractures.” Frontiers in Medicine, 9: 829977, (2022).
• [31] Freund Y. and Schapire R. E., "A Short Introduction to Boosting," Journal of Japanese Society for Artificial Intelligence, 14(5): 771–780, (1999).
• [32] Schapire R. E., "The boosting approach to machine learning: An overview", Nonlinear estimation and classification, 149–171, (2003).
• [33] Chandola, V., Banerjee, A., & Kumar, V. “Anomaly detection: A survey.” ACM computing surveys (CSUR), 41(3): 1-58, (2009).
• [34] Canizo, M., Triguero, I., Conde, A., & Onieva, E. “Multi-head CNN–RNN for multi-time series anomaly detection: An industrial case study”, Neurocomputing, 363: 246-260, (2019).
• [35] Ahmed, M., & Pathan, A. S. K. “Deep learning for collective anomaly detection”, International Journal of Computational Science and Engineering, 21(1): 137-145, (2020).
• [36] Ahmed, M., & Mahmood, A. N. “Network traffic pattern analysis using improved information theoretic co-clustering based collective anomaly detection”, In International Conference on Security and Privacy in Communication Networks: 10th International ICST Conference, SecureComm Beijing, China, Revised Selected Papers, Part II 10 204-219. Springer International Publishing, (2015).