Big Data-Based Multivariate Correlation and Regression for Energy Performance Analysis in Buildings
Keywords:
Neural Network, Energy Consumption Prediction, Big Data, Machine Learning, Regression Analysis, Multivariate Correlation, Electricity Forecasting, Data-Driven Model, Energy ManagementAbstract
Accurate prediction of electricity consumption is critical for optimizing energy usage and enabling effective energy management strategies, particularly in the context of modern smart buildings. This study proposes a predictive modeling approach based on neural networks to forecast future electricity consumption in buildings. Leveraging big data and advanced machine learning techniques, we developed a data-driven model specifically tailored to the operational environment of Turin Polytechnic University in Tashkent. The model achieved a prediction accuracy of up to 96%, demonstrating the potential of neural network-based methods for efficient energy forecasting. This research contributes to the growing field of intelligent energy systems by showcasing how multivariate correlation, regression analysis, and neural network modeling can support sustainable and efficient energy use in buildings.
References
International Energy Agency (IEA), “Energy Efficiency 2023,” [Online]. Available: https://www.iea.org/reports/energy-efficiency-2023
S. Haykin, Neural Networks and Learning Machines, 3rd ed., Pearson Education, 2009.
Y. Bengio, A. Courville, and P. Vincent, “Representation learning: A review and new perspec-tives,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 8, pp. 1798–1828, 2013.
Sh. Abdufattokhov, N. Mahamatov, K. Ibragimova, D. Gulyamova, and D. Yuldashev, “Super-visory optimal control using machine learning for building thermal comfort,” Operations Research and Decisions, vol. 26, no. 3, pp. 1–15, 2023.
Sh. Abdufattokhov, K. Ibragimova, and D. Gulyamova, “The applicability of machine learning algorithms in predictive modeling for sustainable energy management,” in Forthcoming Networks and Sustainability in the IoT Era: Second International Conference, FoNeS-IoT, vol. 1, pp.
–391, Springer International Publishing, 2022.
