Benchmarking Energy Quantification Methods to Predict Heating Energy Performance of Residential Buildings in Germany

Abstract

To achieve ambitious climate goals, it is necessary to increase the rate of purposeful retrofit measures in the building sector. As a result, Energy Performance Certificates have been designed as important evaluation and rating criterion to increase the retrofit rate in the EU and Germany. Yet, today’s most frequently used and legally required methods to quantify building energy performance show low prediction accuracy, as recent research reveals. To enhance prediction accuracy, the research community introduced data-driven methods which obtained promising results. However, there are no insights in how far Energy Quantification Methods are particularly suited for energy performance prediction. In this research article the data-driven methods Artificial Neural Network, D-vine copula quantile regression, Extreme Gradient Boosting, Random Forest, and Support Vector Regression are compared with and validated by real-world Energy Performance Certificates of German residential buildings issued by qualified auditors using the engineering method required by law. The results, tested for robustness and systematic bias, show that all data-driven methods exceed the engineering method by almost 50% in terms of prediction accuracy. In contrast to existing literature favoring Artificial Neural Networks and Support Vector Regression, all tested methods show similar prediction accuracy with marginal advantages for Extreme Gradient Boosting and Support Vector Regression in terms of prediction accuracy. Given the higher prediction accuracy of data-driven methods, it seems appropriate to revise the current legislation prescribing engineering methods. In addition, data-driven methods could support different organizations, e.g., asset management, in decision-making in order to reduce financial risk and to cut expenses.

Impact of socio-economic factors on local energetic retrofitting needs - A data analytics approach

“…RFR is capable of handling non-linear relations and thus well suited for revealing the most important socio-economic factors (Ma and Cheng, 2016;Roth et al, 2020). Moreover, in their recent study, Wenninger and Wiethe (2021) found that among the investigated machine learning algorithms, RFR shows comparable accuracy for residential building energy performance prediction to artificial neural networks or extreme gradient boosting, thus constituting a sensible choice. Because our underlying goal is to explain and not to predict, we follow the explanatory modelling process by Shmueli and Koppius (2010).…”

Design of Ensemble Forecasting Models for Home Energy Management Systems

“…Among them, the polynomial kernel support vector regression showed the best accuracy at the level of a single building, and the Gaussian radial basis function kernel support vector regression performed the best at the stock level. Another study that compares many machine learning-based models may be found in [53], where these models were validated against energy certifications (within the German regulation) for residential buildings; this data-driven approach is more accurate by almost 50% in comparison to the first approach.…”

Structural design and construction using energy analytical modelling for sustainability: a review

“…Computer simulations, systems for building monitoring, end-use sub-metering systems, building audit information, and bills of utility are among the methods for energy quantification (EQ) [84]. These methods involve collecting data on a building's EC and using it to calculate (EP) indicators [85]. Computer simulations use software to model a building's EC based on its design, construction, and occupancy characteristics [86].…”

“…End-use submetering systems measure the EC of individual systems or equipment within a building, such as lighting or HVAC systems. This data can be used to identify areas for energy savings and track the performance of individual systems or equipment [85]. Building audit information involves conducting a detailed audit to identify areas for improvement.…”