The use of statistical and machine learning tools to accurately quantify the energy performance of residential buildings

Abstract

Prediction of building energy consumption is key to achieving energy efficiency and sustainability. Nowadays, the analysis or prediction of building energy consumption using building energy simulation tools facilitates the design and operation of energy-efficient buildings. The collection and generation of building data are essential components of machine learning models; however, there is still a lack of such data covering certain weather conditions. Such as those related to arid climate areas. This paper fills this identified gap with the creation of a new dataset for energy consumption of 3,840 records of typical residential buildings of the Saudi Arabia region of Qassim, and investigates the impact of residential buildings’ eight input variables (Building Size, Floor Height, Glazing Area, Wall Area, window to wall ratio (WWR), Win Glazing U-value, Roof U-value, and External Wall U-value) on the heating load (HL) and cooling load (CL) output variables. A number of classical and non-parametric statistical tools are used to uncover the most strongly associated input variables with each one of the output variables. Then, the machine learning Multiple linear regression (MLR) and Multilayer perceptron (MLP) methods are used to estimate HL and CL, and their results compared using the Mean Absolute Error (MAE), the Root Mean Square Error (RMSE), and coefficient of determination (R2) performance measures. The use of the IES simulation software on the new dataset concludes that MLP accurately estimates both HL and CL with low MAE, RMSE, and R2, which evidences the feasibility and accuracy of applying machine learning methods to estimate building energy consumption.

Indoor Air Quality and Ventilation Energy in University Classrooms: Simplified Model to Predict Trade-Offs and Synergies

“…The literature review served to contextualize our simulation model when considering the interconnection of parameters that influence healthy air quality and the efficiency of ventilation strategies in university classrooms. The literature provided vital information on the importance of selecting environmental parameters [2,13,17,18,24,55], building and HVAC variables [18], IAQ, ventilation and filtration-related parameters [56][57][58], weather data [27,35,59], and occupant behavior [60][61][62], amongst other considerations to build an accurate model. In addition, we learned why specific types of simulation software programs are used and the complexity involved in balancing trade-offs between all the variables mentioned above [2,13,17,18,26,27,30,35,53,55,63].…”

“…The algorithm effectively improved indoor air quality and energy consumption in energy-efficient buildings. Similarly, using advanced methods of investigation, Ibrahim et al studied the feasibility and accuracy of using machine learning methods to estimate building energy consumption [27]. Their study demonstrated the potential of machine learning in accurately predicting heating and cooling loads for residential buildings.…”

TSxtend: A Tool for Batch Analysis of Temporal Sensor Data

“…This has been used in several papers in the field of energy efficiency, but there is little work. Therefore, it is interesting to continue working with this type of network and to have our architecture ready to continue studying the behaviour of this algorithm in different problems [72][73][74].…”

Harnessing the Power of Artificial Intelligence to Forecast Startup Success: An Empirical Evaluation of the SECURE AI Model

“…The chosen regression-based model, aimed at predicting a continuous set of values, leveraged the Root Mean Squared Error (RMSE) as an optimization metric. RMSE, a popular performance measure, quantifies the discrepancy between predicted and actual values, capturing the model's overall prediction error (Ibrahim et al, 2022). (Kaliappan et al, 2021).…”