Project

DataFEE - Data mining, machine learning, feedback, and feedforward - energy efficiency through user-centric building systems

Goal: Numerous studies on building energy performance show the significant influence of the occupants on energy use. Simultaneously, there is a large discrepancy between predicted energy use in the design phase and observed energy use during operation due to insufficient knowledge of occupant behaviour. The objective of this joint project is the reduction of this performance gap by means of systematical exploitation and optimization of the processes of data usage. Such reduction will allow reliable predictions for the operation of buildings, while guaranteeing a high level of energy efficiency. This sub-project focusses on the feedforward user-information system and its effect on comfort and energy use.

Updates
0 new
0
Recommendations
0 new
0
Followers
0 new
28
Reads
2 new
190

Project log

Romana Markovic
added 3 research items
As the number of installed meters in buildings increases, there is a growing number of data time-series that could be used to develop data-driven models to support and optimize building operation. However, building data sets are often characterized by errors and missing values, which are considered, by the recent research, among the main limiting factors on the performance of the proposed models. Motivated by the need to address the problem of missing data in building operation, this work presents a data-driven approach to fill these gaps. In this study, three different autoencoder neural networks are trained to reconstruct missing short-term indoor environment data time-series in a data set collected in an office building in Aachen, Germany. This consisted of a four year-long monitoring campaign in and between the years 2014 and 2017, of 84 different rooms. The models are applicable for different time-series obtained from room automation, such as indoor air temperature, relative humidity and CO2 data streams. The results prove that the proposed methods outperform classic numerical approaches and they result in reconstructing the corresponding variables with average RMSEs of 0.42 °C, 1.30% and 78.41 ppm, respectively.
This paper explores the applicability of deep learning-driven models for the prediction of energy consumption in generic commercial buildings. The modeling approach relies on recurrent neural networks (RNNs), while the input consists of physical data streams such as indoor air temperature in different thermal zones and data obtained from the central heating ventilation and air conditioning (HVAC) system. The research steps include the implementation of an existing RNN-based model for energy consumption and further model optimization using training and validation sets. The final model was evaluated using the data from two datasets. Additionally, the evaluation performance was tested in case of the varied spatial and system granularities. The results showed that the optimal model architecture was dataset-agnostic. The results showed that predicting the HVAC energy consumption is more challenging at the higher spatial granularity, when compared to building wise or multi-zone wise modeling. Key innovations Exploring the impact of the spatial granularity on the predictive performance of data-driven HVAC energy consumption models in commercial buildings. Practical implications The practical implications of this work can be summarized as follows: • Applicability of the model to different energy consumption data sets with no tuning and calibration costs. • Adaptation of the model to the day-ahead estimation of energy consumption data for a better load scheduling and an increased use of renewable energy sources.
This study explores the applicability of a deep learning-based approach for reconstructing missing room temperature data from different domains where relatively few training samples are available. For that purpose, the existing convolutional, long short-term memory (LSTM) and feed-forward autoencoders were combined with a suitable domain adaptation procedure. Eventually, the developed models were evaluated on data collected in four buildings with significant differences in thermal mass, design and location. The findings pointed out that the domain adaptation can be conducted efficiently by using a small data sample from the target domain. Additionally, the results showed that the proposed model can reconstruct up to 80 % of the missing daily room temperature inputs with RMSE accuracy of 0.6°C.
Romana Markovic
added a research item
As the number of installed meters in buildings increases, there is a growing number of data time-series that could be used to develop data-driven models to support and optimize building operation. However, building data sets are often characterized by errors and missing values, which are considered, by the recent research, among the main limiting factors on the performance of the proposed models. Motivated by the need to address the problem of missing data in building operation, this work presents a data-driven approach to fill these gaps. In this study, three different autoencoder neural networks are trained to reconstruct missing indoor environment data time-series in a data set collected in an office building in Aachen, Germany. The models are applicable for different time-series obtained from room automation, such as indoor air temperature, relative humidity and CO2 data streams. The results prove that the proposed methods outperform classic numerical approaches and they result in reconstructing the corresponding variables with average RMSEs of 0.42 °C, 1.30 % and 78.41 ppm, respectively.
Felix Nienaber
added a research item
In diesem Paper wird die Anwendung eines CO2-basierten Algorithmus zur Anwesenheitsbestimmung in der Regel-strategie von Fassadenlüftungsgeräten (FLG) vorgestellt. Insgesamt werden fünf neue Regelstrategien mit der be-reits auf den Geräten vorhandenen Regelstrategie vergli-chen. Die Auswertung geschieht hinsichtlich der Häufig-keiten der, von der Regelstrategie ausgeführten, Schaltak-tionen und der Dauer von, für den Büronutzer unangeneh-men, Raumklimabedingungen. Diese Untersuchungen zei-gen, dass bei geringer relativen Interaktionshäufigkeit drei der neuen Regelstrategien bessere Bedingungen für den Nutzer erzeugt haben, als die zuvor implementierte Regel-strategie.
Marc Syndicus
added a research item
Nach Angaben der Internationalen Energieagentur sind Gebäude für über 40% der weltweiten CO2 Emissionen verantwortlich [1] und so stellt vor dem Hintergrund des globalen Klimawandels, die effiziente Planung, Ausführung und Bewirtschaftung von Gebäuden eine signifikante Herausforderung dar. In diesem Zusammenhang kann die Digitalisierung aller Prozessschritte einen sinnvollen Beitrag zur Steigerung der Kosten- und Energieeffizienz leisten.
Marcel Schweiker
added a research item
Data was collected in the field, from an office building located in Frankfurt, Germany, over the period of 4 years. The building was designed as a low-energy building and featured natural ventilation for individual control of air quality as well as buoyancy-driven night ventilation in combination with a central atrium as a passive cooling strategy. The monitored data include in total 116 data points related to outdoor and indoor environmental data, energy related data, and data related to occupancy and occupant behaviour. Data points representing a state were logged with the real timestamp of the event taking place, all other data points were recorded in 10 minute intervals. Data were collected in 17 cell offices with a size of ~20 m², facing either east or west). Each office has one fixed and two operable windows, internal top light windows between office and corridor (to allow for night ventilation into the atrium) and sun protection elements (operated both manually and automatically). Each office is occupied by one or two persons.
Marcel Schweiker
added 6 research items
The objectives of this study are to analyze interactions between thermal and visual influences on comfort and behaviors and to present a clustering method based on the results of mixed-effect regression analyses for simulation and control purposes. Results show a) interactions between thermal and visual influences on comfort and behavior, b) the advantage of this method in creating independent and distinct patterns related to thermal comfort, visual comfort, and occupant behavior, and c) that the relationship between clusters e.g. between clusters of thermal and visual comfort or between thermal comfort and heating behavior is not significant.
Occupant behavior (OB) and in particular window openings need to be considered in building performance simulation (BPS), in order to realistically model the indoor climate and energy consumption for heating ventilation and air conditioning (HVAC). However, the proposed OB window opening models are often biased towards the over-represented class where windows remained closed. In addition, they require tuning for each occupant which can not be efficiently scaled to the increased number of occupants. This paper presents a window opening model for commercial buildings using deep learning methods. The model is trained using data from occupants from an office building in Germany. In total, the model is evaluated using almost 20 mio. data points from 3 independent buildings, located in Aachen, Frankfurt and Philadelphia. Eventually, the results of 3100 core hours of model development are summarized, which makes this study the largest of its kind in window states modeling. Additionally, the practical potential of the proposed model was tested by incorporating it in the Modelica-based thermal building simulation. The resulting evaluation accuracy and F1 scores on the office buildings ranged between 86 and 89% and 0.53–0.65 respectively. The performance dropped around 15% points in case of sparse input data, while the F1 score remained high.
Marcel Schweiker
added a project goal
Numerous studies on building energy performance show the significant influence of the occupants on energy use. Simultaneously, there is a large discrepancy between predicted energy use in the design phase and observed energy use during operation due to insufficient knowledge of occupant behaviour. The objective of this joint project is the reduction of this performance gap by means of systematical exploitation and optimization of the processes of data usage. Such reduction will allow reliable predictions for the operation of buildings, while guaranteeing a high level of energy efficiency. This sub-project focusses on the feedforward user-information system and its effect on comfort and energy use.