The aim of this thesis is to add to the as of yet mostly missing literature on how a D-vine copula based quantile regression model can be used to predicte the accurate level of energy consumption.
Energetic retrofitting of residential buildings is poised to play an important role in the achievement of ambitious global climate targets. A prerequisite for purposeful policy-making and private investments is the accurate prediction of energy consumption. Building energy models are mostly based on engineering methods quantifying theoretical energy consumption. However, a performance gap between predicted and actual consumption has been identified in literature. Data- driven methods using historical data can potentially overcome this issue. The D-vine copula-based quantile regression model used in this study achieved very good fitting results based on a representative data set comprising 25,000 German households. The findings suggest that quantile regression increases transparency by analyzing the entire distribution of heating energy consumption for individual building characteristics. More specifically, the analyses reveal the following exemplary insights. First, for different levels of energy efficiency, the rebound effect exhibits cyclical behavior and significantly varies across quantiles. Second, very energy-conscious and energy-wasteful households are prone to more extreme rebound effects. Third, with regards to the performance gap, heating energy demand of inefficient buildings is systematically underestimated, while it is overestimated for efficient buildings.
Therefore, The remainder of this thesis is organized as follows. Section 2 presents a concise categorization of building energy models. Section 3 presents existing data-driven methods used for the pre-diction of heating energy consumption in the residential sector. Next, Section 4 elaborates on vine copula-based quantile regression. This is followed by a description of the data employed in Section 5. Section 6 presents the empirical results and Section 7 provides the practical im-plications and contribution of the quantile regression approach introduced. Finally, the conclu-sions and limitations of this thesis are discussed in Section 8.
Table of Contents
1 Introduction
2 Categorizing Energy Models
2.1 Building Type
2.2 Energy Type
2.3 Occupant Behavior
2.4 Prediction Model Type for Energy Consumption
3 Data-Driven Methods for the Prediction of Heating Energy Consumption
3.1 Common Characteristics of Data-Driven Methods
3.2 Data-Driven Methods in Academic Literature
3.2.1 Least Squares Regression
3.2.2 Artificial Neural Network
3.2.3 Genetic Algorithm
3.2.4 Support Vector Machines
3.2.5 Quantile Regression
3.3 Summary of Data-Driven Methods for Prediction of Heating Energy Consumption
4 An Introduction to Copula-Based Quantile Regression
4.1 Pair-Copula Construction
4.2 Bivariate Copula Families and Parameter Estimation
4.3 D-Vine Copula-Based Quantile Regression
4.4 Model Evaluation
5 Description of the Underlying Data Set
5.1 Pre-Processing of the Data
5.2 Data Understanding
6 Empirical Results
6.1 Performance of Point Estimation Methods
6.2 D-Vine Copula Fitting Results
7 Practical Implications of the Introduced Quantile Regression
7.1 Prediction of Quantiles for Post-Retrofit Energy Consumption
7.2 Quantile-Based Analysis of the Rebound Effect and Performance Gap
7.3 Rebound Effect Similarity Analysis
8 Conclusion
Objectives and Topics
The primary objective of this thesis is to address the limitations of existing building energy prediction models by applying a novel D-vine copula-based quantile regression approach to predict heating energy consumption. The study aims to overcome the performance gap associated with engineering-based methods and the inaccuracies of point estimation models when dealing with the high variance found in real-world historical data from German households.
- Analysis of the performance gap between predicted and actual energy consumption.
- Evaluation of data-driven modeling techniques, specifically machine learning and regression models.
- Application of D-vine copula-based quantile regression to capture complex dependence structures.
- Investigation of the rebound effect and its variation across different quantiles of energy consumption.
- Assessment of the efficacy of various energetic retrofit measures using a representative real-world data set.
Auszug aus dem Buch
1 Introduction
The residential building sector is one of the biggest energy consumers worldwide (IEA, 2017). Therein, one- and two-family houses are of particular interest, as they account for 60% of the total heating related CO2 emissions of the residential building sector in the European Union (Petersdorff et al., 2006). However, while research and policy-makers have focused on the energy efficiency potential of residential buildings, the resulting investment volume in retrofit measures is rather disappointing. The lack of energy efficiency gains can be attributed to the so-called performance gap, a state in which the realized energy savings negatively deviate from the predicted energy savings (Ahn et al., 2017; Calì et al., 2016). It is not to be confused with the energy efficiency gap, which refers to a slower than optimal diffusion of seemingly cost-effective energy efficiency technology (Jaffe and Stavins, 1994). In academic literature, the existence of the energy efficiency gap is mostly explained by diverse market barriers and the concepts of behavioral economics (Brown, 2001; Weber, 1997). The performance gap on the other hand is unrelated to the decision making of economic agents. It stems in large part from the fact that deficient prediction methods are applied and the used data is often inappropriate (de Wilde, 2014).
One reason for the discrepancy between realized and predicted energy savings is that data-driven building energy models are mostly fitted on synthetic data generated by engineering simulation software. Thereby, over- and under-estimation of synthetic energy consumption occurs frequently as the simulation software neglects the variance in actual energy consumption (Ahmad and Culp, 2006). This means that the input data itself is biased, which is then used for the training of data-driven prediction models. Consequently, even the most accurate prediction could not reflect actual energy consumption. A potential remedy to overcome this bias, is the strict usage of historical data, which inherently contains variance in energy consumption such as this caused by occupant behavior.
Summary of Chapters
1 Introduction: Discusses the global importance of energy efficiency in residential buildings and introduces the performance gap as a critical issue that hinders investment and accurate prediction.
2 Categorizing Energy Models: Outlines the diversity and objectives of building energy models, categorizing them by building type, energy type, occupant behavior, and prediction model type.
3 Data-Driven Methods for the Prediction of Heating Energy Consumption: Reviews existing data-driven approaches in academic literature, including least squares regression, artificial neural networks, genetic algorithms, support vector machines, and quantile regression.
4 An Introduction to Copula-Based Quantile Regression: Provides the theoretical foundation for vine copula-based quantile regression, explaining pair-copula construction and how to model complex dependence structures.
5 Description of the Underlying Data Set: Introduces the novel real-world data set of 25,000 German households and describes the pre-processing steps and the definition of typical energetic retrofit levels.
6 Empirical Results: Compares the performance of point estimation methods versus the D-vine copula approach, demonstrating the superiority of the latter in handling real-world data variance.
7 Practical Implications of the Introduced Quantile Regression: Analyzes the practical benefits of the introduced method, focusing on the rebound effect, performance gap, and similarity analysis of retrofit measures.
8 Conclusion: Summarizes the findings of the thesis, acknowledges limitations, and provides recommendations for future research in data-driven energy modeling.
Key Keywords
Data-Driven Heating Energy Analysis, Energetic Retrofitting, Quantile Regression, D-Vine Copula, Rebound Effect, Performance Gap, Building Energy Models, Occupant Behavior, Historical Data, Statistical Modeling, Energy Efficiency, Residential Buildings, Machine Learning, Copula-Based Modeling, Uncertainty Estimation
Frequently Asked Questions
What is the fundamental focus of this research?
This thesis focuses on the accurate prediction of heating energy consumption in residential buildings using data-driven methods, specifically addressing the "performance gap" between predicted and actual energy usage.
What are the primary themes covered in this work?
The work covers building energy modeling, the application of quantile regression, the analysis of the rebound effect, the evaluation of energetic retrofit measures, and the utilization of real-world historical data.
What is the main objective or research question?
The main objective is to demonstrate that D-vine copula-based quantile regression provides a superior and more flexible method for predicting heating energy consumption compared to traditional point estimation methods, which often fail to capture real-world variance.
Which scientific methodology is applied?
The study employs a D-vine copula-based quantile regression approach, supported by non-parametric kernel density estimation, to analyze complex dependencies between building characteristics and energy consumption.
What is addressed in the main part of the thesis?
The main part covers the categorization of existing energy models, a review of data-driven methods, theoretical background on copulas, description of the representative German data set, empirical implementation, and a detailed analysis of practical implications regarding retrofitting.
Which keywords best characterize this work?
Key terms include Data-Driven Heating Energy Analysis, D-Vine Copula, Quantile Regression, Rebound Effect, Performance Gap, and Energetic Retrofitting.
How does this study specifically improve upon standard regression models?
Unlike standard regression models that estimate a conditional mean, the D-vine copula approach describes the entire conditional distribution, allowing for the analysis of specific quantiles and the robust handling of non-linear dependencies and heteroscedasticity.
How is the "rebound effect" analyzed in this thesis?
The rebound effect is analyzed by evaluating the difference in specific heat load before and after specific energetic retrofit measures across the entire distribution of households, using a one-step rebound effect definition derived from specific heat load ratios.
- Arbeit zitieren
- B.Sc. Rochus Niemierko (Autor:in), 2018, A D-Vine Copula-Based Quantile Regression Approach for the Prediction of Heating Energy Consumption. Using Historical Data for German Households, München, GRIN Verlag, https://www.grin.com/document/498767
