Building Energy Data Research Articles

From roads to roofs: How urban and rural mobility influence building energy consumption

Understanding the relationship between travel behavior and building energy use at an urban scale is crucial for developing effective energy management strategies. Mobility patterns significantly impact building occupancy, which in turn affects energy consumption. However, existing methods often focus on individual buildings, whereas geographical influences on energy usage are not adequately examined. This study addresses this gap by using transportation origin-destination (OD) data to estimate building occupancy and energy. The proposed method assigns OD trips from census block groups to the building level, incorporating building, travel survey, and census data to derive building occupancy profiles. This method was applied to urban and rural areas with 4062 buildings in 70 census block groups. We found that the OD-informed occupancy profile exhibits smoother energy consumption patterns compared with that of Department of Energy reference occupancy profiles. Our analysis reveals distinct building energy consumption patterns among groups with long and short commutes, emphasizing the effect of commute times and work schedules on residential energy usage. This framework is useful for practitioners in transportation agencies and utility companies, enabling the estimation of building energy based on mobility patterns. Overall, this study shows the potential of integrating transportation and building energy data to inform cross-sector energy management strategies.

Dyna-PINN: Physics-informed deep dyna-q reinforcement learning for intelligent control of building heating system in low-diversity training data regimes

This paper introduces Dyna-PINN, a novel physics-informed Deep Dyna-Q (DDQ) reinforcement learning (RL) approach, designed to address the data-intensive training requirements and model-agnostic nature of the conventional model-free RL methods. The DDQ approach blends model-based and model-free elements to enhance both learning and decision-making processes. By utilizing a physics-informed neural network (PINN) based model, our method enriches the learning process with physical information, enhancing the agent's planning capabilities and leading to faster learning compared to conventional model-free RL methods like Deep Q-Network (DQN) in scenarios with low-diversity training data availability. Our results demonstrate that Dyna-PINN has 50% greater sample efficiency than DQN and outperforms rule-based control in terms of thermal discomfort. Due to physics incorporation, the Dyna-PINN implements a more logical and interpretable control policy. It shows consistently good performance compared to all control variants across low-diversity data scenarios, i.e., 6 weeks of building data, and in higher-diversity data regimes, i.e., 6 months of building energy data, demonstrating the value of physics incorporation into the RL training. Additionally, we present two other DDQ-based techniques, RC-DDQ and NN-DDQ, exploring the synergy between neural networks and physical data in intelligent control designs for building energy systems. Rigorous controller testing is performed using the Building Optimization and Testing Framework (BOPTEST), a high-fidelity simulator that closely represents a real building's operation. Through comprehensive comparisons and realistic simulations, our study underscores the effectiveness of incorporating physics-informed approaches into RL-based control strategies, paving the way for more efficient and robust building energy management systems.

Personalized federated learning for buildings energy consumption forecasting

Buildings' energy consumption forecasting is critical for energy saving and building maintenance. However, most studies only focus on centralized learning of one dataset, which ignores the data privacy and data shortage issue. Meanwhile, the difference in energy data distributions from many buildings causes difficulties in training a good machine learning model. Although these two challenges of data privacy and data heterogeneity could be resolved through personalized federated learning algorithms to some degree, there is still a lack of investigation into applying these algorithms to building energy data analytics. Besides using existing personalized federated learning algorithms, we design a new deep learning model through a mixture of experts to support personalization for heterogeneous data distribution. This new design is the first trial to tackle the data heterogeneity through ensemble architecture in federated load forecasting. Extensive experiments are conducted to evaluate the effectiveness of our proposed model with different training algorithms. The results show that our proposed method outperforms other state-of-the-art models in energy forecasting accuracies by 10% to 40% across the buildings' energy data from university campuses.

Optimizing the thermal performance of phase change materials in building applications using deep reinforcement learning and Bayesian optimization

This research presents a novel methodology for Deep Reinforcement Learning (DRL) and Bayesian Optimisation of the thermal performance of PCMs in building operations. The developed models utilise a unique and large dataset comprising 1500 building thermal profiles, simulated for various climates and building setups obtained from our industry partners and as open data. PCM-based systems are deployed for thermal insulation of building envelopes to regulate indoor temperature conditions and reduce the need for heating and cooling systems, resulting in enhanced energy efficiency. Through the real-time management of the thermal efficacy of PCMs using the DRL method trained on the large dataset and fine-tuning of the underlying model parameters using Bayesian Optimisation, the optimised system achieves energy saving in heating and cooling load of up to 45 percent, along with the induced reduction in CO2 emission. At the same time, DRL contributes to decreasing the thermal fluctuation in the indoor temperature and keeps it in the narrow range of 1.2 °C in case of high thermal variability scenarios. Currently, the best performance is reported in the literature. This research exemplifies the potential of DRL and Bayesian optimisation in sustainable building. It depicts the applications of advanced intelligent computing algorithms with big building energy data as a novel, robust and superior approach for optimising real-world building energy management systems. The methodology and the improvements in energy savings in thermal and energy management of buildings highlight the novelty and potential benefit of the implemented research as a new intellectual property towards sustainable building design.

Evaluating missing data handling methods for developing building energy benchmarking models

This study explored methods for handling missing data in the development of machine learning-based energy benchmarking models, assessing their training time, performance, and variance. Unlike the common assumption of missing completely at random, this study adopted a missing at random (MAR) perspective, which is more appropriate for building data. We compared the inherent missing data handling method of extreme gradient boosting (XGBoost) with the Median, k-nearest neighbors (KNN), and classification and regression trees (CART) methods, alongside Shapley additive explanation (SHAP) method for model interpretability. The findings indicate that, despite its computational demands, the CART method most accurately mirrors the original data distribution, thereby enhancing model performance and stability. The KNN method is effective, while the XGBoost method is viable under computational time constraints. This work highlights the importance of reliable test data for performing accurate evaluations of imputation methods. These results offer guidelines for the selection of imputation methods in model development, contributing to the improved accuracy of energy benchmarking models. The MAR-based approach for missing data analysis holds promise for future research on building energy data, providing crucial insights for accurate energy benchmark model performance assessments.

Impact of data for forecasting on performance of model predictive control in buildings with smart energy storage

Data is required to develop forecasting models for use in Model Predictive Control (MPC) schemes in building energy systems. However, data is costly to both collect and exploit. Determining cost optimal data usage strategies requires understanding of the forecast accuracy and resulting MPC operational performance it enables. This study investigates the performance of both simple and state-of-the-art machine learning prediction models for MPC in multi-building energy systems using a simulated case study with historic building energy data. The impact on forecast accuracy of measures to improve model data efficiency is quantified, specifically for: reuse of prediction models, reduction of training data duration, reduction of model data features, and online model training. A simple linear multi-layer perceptron model is shown to provide equivalent forecast accuracy to state-of-the-art models, with greater data efficiency and generalisability. The use of more than 2 years of training data for load prediction models provided no significant improvement in forecast accuracy. Forecast accuracy and data efficiency were improved simultaneously by using change-point analysis to screen training data. Reused models and those trained with 3 months of data had on average 10% higher error than baseline, indicating that deploying MPC systems without prior data collection may be economic.

Method to establish time-series building energy data inventory based on frequency for energy-sharing community planning

This study aims to establish a foundation for estimating energy demand according to building types by proposing a method to establish a time-series energy data inventory solely based on energy consumption in countries where typical models or benchmarking data by building types have not been developed. First, we presented the characteristics of energy consumption patterns that can be defined from the energy consumption itself based on frequency characteristics. Then, we defined a method to normalize and classify types of daily energy consumption patterns using this method and validated it with measured data. Finally, based on the results, a generalized method for establishing building time series energy data inventory was proposed. This method has a simple procedure and its result can be interpreted intuitively. It does not require data to be converted into stationary time-series data, unlike statistical methods, and it can avoid data distortion due to building operational errors. Moreover, it is easy to find the reasons for the results because the processes are easy to understand, unlike artificial intelligence methods. This study proposes a method to establish a time-series building energy data inventory by classifying types based solely on energy consumption. Furthermore, it suggests the possibility of its application in the early stages of planning an energy-sharing community.

VOD: Vision-Based Building Energy Data Outlier Detection

Outlier detection plays a critical role in building operation optimization and data quality maintenance. However, existing methods often struggle with the complexity and variability of building energy data, leading to poorly generalized and explainable results. To address the gap, this study introduces a novel Vision-based Outlier Detection (VOD) approach, leveraging computer vision models to spot outliers in the building energy records. The models are trained to identify outliers by analyzing the load shapes in 2D time series plots derived from the energy data. The VOD approach is tested on four years of workday time-series electricity consumption data from 290 commercial buildings in the United States. Two distinct models are developed for different usage purposes, namely a classification model for broad-level outlier detection and an object detection model for the demands of precise pinpointing of outliers. The classification model is also interpreted via Grad-CAM to enhance its usage reliability. The classification model achieves an F1 score of 0.88, and the object detection model achieves an Average Precision (AP) of 0.84. VOD is a very efficient path to identifying energy consumption outliers in building operations, paving the way for the enhancement of building energy data quality, operation efficiency, and energy savings.

Comprehensive transferability assessment of short-term cross-building-energy prediction using deep adversarial network transfer learning

Data-driven models are widely used for building-energy predictions (BEPs). In practice, these models may fail when the available data on the target building is insufficient. Transfer learning (TL), where useful knowledge from information-rich source buildings with sufficient data is learned to enhance the prediction of information-poor buildings with data shortages, can address the problem of poor prediction performance caused by insufficient data. However, an important issue is finding suitable information-rich buildings to maximize the advantages of TL in cross- BEP. To address this issue, this study explored the selection of source buildings from three perspectives: building-energy data similarity between source and target buildings, building information characteristics, and the volume of training data. The impact of these three factors on the performance improvement of cross- BEP was assessed in a data-centric manner. Based on our previous studies, we selected a deep adversarial neural network (DANN) as the TL strategy for cross-BEP and systematically investigated the performance improvement and transferability of DANN from multiple perspectives of both post-hoc and ex-ante analysis. The Building Data Genome Project datasets were used for validation. Thirty-six buildings of six types and 180 source-target building pairs were considered. Our results demonstrated that DANN could effectively improve model performance by 40–90 % and 20%–80 % compared to non-optimized LSTM and parameter-optimized LSTM. When the same type and location source-target building pairs were only considered, the DTW index showed a relative strong negative linear correlation with the DANN prediction performance improvement, and the goodness of fitting is around 0.80. For building energy data within one year considered, DANN should be trained using no less than 6-month source domain data and no more than 4-week target domain data to improve transferability and reduce the cross-building energy prediction error.

Comparing the Performance of Dimensional Reduction and Model Prediction Performance Due to Missing Data Handling for Building Energy Data Analysis

Comparing the Performance of Dimensional Reduction and Model Prediction Performance Due to Missing Data Handling for Building Energy Data Analysis

Seasonal threshold to reduce false positives for prediction-based outlier detection in building energy data

Recent studies have shown that artificial intelligence-based model predictive control systems have the potential to optimize building operations for energy and cost. But for these systems to function as designed, they require high-quality datasets, which can be challenging when working with actual sensor data that may contain missing or outlier values. Using contaminated data in these carefully tuned machine learning algorithms can cause errors in the prediction results, leading to unexpected building operations. There is a need to clean incoming data in real-time by detecting the outliers in incoming sensor data and correcting them to an appropriate value before incorporating them into the prediction algorithm. This research proposes using a seasonal threshold for prediction-based point outlier detection methods to accurately detect the outliers while maintaining the reliability of the data by reducing false positive detections. The approach combining the global and seasonal threshold showed improvement to the detection accuracy by 83 % and reduced the falsely positives by up to 78 % for the best improvement, making the method a more trustworthy way to detect outliers in building energy data. This method can utilize an already existing model to detect outliers is a promising approach, especially for buildings that have already been implemented or are in the process of implementing an artificial intelligence-based control systems. This will allow the system to predict and control building energy without interruption and with reduced risk of unexpected operation due to corrupted data.

ENABLING INTEROPERABILITY OF URBAN BUILDING ENERGY DATA BASED ON OGC API STANDARDS AND CITYGML 3D CITY MODELS

Abstract. This paper presents an investigation into the interoperability of 3D building energy data management, delivery, processing, and visualization via web clients using Open Geospatial Consortium – Application Programming Interface (OGC API) standard-based data models and web interfaces. Specifically, the OGC API – 3D GeoVolumes enable access to 3D city model geometries and semantics on the web, the OGC API – Features support the 2D version of the same geospatial data, the OGC API – Processes are used for CityGML analytics and building energy computation with the SimStadt urban simulation software and the OGC SensorThings API is utilized to manage related spatiotemporal or time-series datasets. The efficacy of this approach has been demonstrated in the OGC Testbed 18 Innovation Program, which highlighted the capacity of OGC API web services to synchronize building energy data and computation results between client and server for the case study of Helsinki, Finland, and Montreal, Canada. The advantages of using OGC API services for 3D building energy data interoperability are discussed, and it is suggested that the use of OGC API be promoted to the general public as well as extended to other domains and on a larger scale in future research.

An Assessment of Long-Term Climate Change on Building Energy in Indonesia

This paper reports on modelling outcomes for improvements to building energy performance in Indonesia. Long-term climate effects due to building energy demand and carbon emissions are also considered. The global change assessment model (GCAM) was used to generate the related end-user building energy data, including socioeconomics, for urban areas of Indonesia. As a comprehensive study, the total life cycle of carbon in the building sector and the concept of zero-carbon buildings, including energy efficiency, zero-emissions electricity and fuel-switching options, were considered. Building shell conductance (U-value) of the building envelope, floor area ratio (FAR), air conditioner (AC) efficiency, electrical appliance (APL) efficiency, rooftop photovoltaic (PV) performance and ground source heat pump (GSHP) systems were considered as parameters to mitigate carbon emissions under the operational energy category in the GCAM. Carbon mitigation associated with the cement production process was considered in the raw material category. Urban population and labour productivity in Indonesia were used as base inputs with projected growth rates to 2050 determined from the available literature. Low growth rate ‘LowRate’ and high growth rate ‘HighRate’ were considered as variable inputs for U-value, FAR, AC efficiency, APLs efficiency and PV capacity factor to model emissions mitigation. The energy consumption of the GSHP was compared to the conventional reverse cycle ACs to identify the potential of the GSHP as a fuel-switching option. In the GCAM, the benchmark (base case scenario) data set was generated based on input parameters (urban population and labour productivity rate) only for the residential building sector in Indonesia. Total potential carbon emissions mitigation was found to be 432 Mt CO2-e for the residential building sector in Indonesia over 2020–2050. It was found that an average of 24% carbon emissions mitigation could be achieved by 2020–2030 and 76% by 2031–2050.

Enhancing Building Energy Management: Adaptive Edge Computing for Optimized Efficiency and Inhabitant Comfort

Nowadays, in contemporary building and energy management systems (BEMSs), the predominant approach involves rule-based methodologies, typically employing supervised or unsupervised learning, to deliver energy-saving recommendations to building occupants. However, these BEMSs often suffer from a critical limitation—they are primarily trained on building energy data alone, disregarding crucial elements such as occupant comfort and preferences. This inherent lack of adaptability to occupants significantly hampers the effectiveness of energy-saving solutions. Moreover, the prevalent cloud-based nature of these systems introduces elevated cybersecurity risks and substantial data transmission overheads. In response to these challenges, this article introduces a cutting-edge edge computing architecture grounded in virtual organizations, federated learning, and deep reinforcement learning algorithms, tailored to optimize energy consumption within buildings/homes and facilitate demand response. By integrating energy efficiency measures within virtual organizations, which dynamically learn from real-time inhabitant data while prioritizing comfort, our approach effectively optimizes inhabitant consumption patterns, ushering in a new era of energy efficiency in the built environment.

An adaptive federated learning system for community building energy load forecasting and anomaly prediction

Energy load forecasting is critical for sustainable building development and management. Although the energy data could be collected through Internet of Things (IoT) systems, it is a big challenge to train a large-scale machine learning model due to data isolation. Since the building energy data could reveal confidential information such as user behaviors and building operations, the privacy regulations would not allow central service to collect distributed data from data owners directly. This paper designs a secure federated data analytics system for forecasting community buildings' energy data load. A novel adaptive weight federated learning algorithm is proposed to handle the system faults frequently happening during networking operations. Moreover, a new deep learning model is re-invented to improve energy load forecasting performance. The experiments of the system are performed on an actual university campus dataset, and the results show the new federated algorithm improves the load forecasting accuracy and achieves the best load forecasting result. The new deep learning model improves the forecasting accuracy by almost 10% on error reduction under the same federated learning settings. To evaluate the load forecasting model's practical usefulness, an anomaly prediction pipeline is designed through the combination of gaussian mixture model and load forecasting model, which reveals the system's effectiveness at building energy management that 92% F1 score with 97% accuracy is achieved by the best model.

Importance of HVAC System Selection in Reducing the Energy Consumption of Building Retrofits–Case Study: Office Building in London

The analysis of the holistic life cycle and energy has become more important due to the escalating energy demands in existing office stock. HVAC system retrofits to save energy are an outstanding way when compared to envelope improvements. The study proposes a parametric workflow to analyze and reduce energy, carbon and cost in HVAC retrofits. Based on the workflow, the energy demands of an existing office building were gathered using energy modelling software. The results then were calibrated with the building's energy data. Using the equation-based modelling workflow, HVAC plant side systems were simulated parametrically to calculate energy, carbon and cost. In total, 5184 iterations of 10 interventions were tested. It was found that heating plant type and heat recovery were the prominent savings inputs in the case study. The study presented a comprehensive approach to the HVAC system retrofit of existing buildings, which uses real energy data calibration, verifiable, and parametric methods.

A semantic ontology for representing and quantifying energy flexibility of buildings

• EFOnt, a semantic ontology for building energy flexibility applications, is introduced. • EFOnt is designed to work with other building energy data tools as part of an ecosystem • EFOnt standardizes energy flexibility definition, characterization, and quantification. • One measurement-based and one simulation-based use case of EFOnt are given. • The future development and potential use cases of EFOnt are discussed. Energy flexibility of buildings can be an essential resource for a sustainable and reliable power grid with the growing variable renewable energy shares and the trend to electrify and decarbonize buildings. Traditional demand-side management technologies, advanced building controls, and emerging distributed energy resources (including electric vehicle, energy storage, and on-site power generation) enable the transition of the building stock to grid-interactive efficient buildings (GEBs) that operate efficiently to meet service needs and are responsive to grid pricing or carbon signals to achieve energy and carbon neutrality. Although energy flexibility has received growing attention from industry and the research community, there remains a lack of common ground for energy flexibility terminologies, characterization, and quantification methods. This paper presents a semantic ontology—EFOnt (Energy Flexibility Ontology)—that extends existing terminologies, ontologies, and schemas for building energy flexibility applications. EFOnt aims to serve as a standardized tool for knowledge co-development and streamlining energy flexibility related applications. We demonstrate potential use cases of EFOnt via two examples: ( 1 ) energy flexibility analytics with measured data from a residential smart thermostat dataset and a commercial building, and ( 2 ) modeling and simulation to evaluate energy flexibility of buildings. The compatibility of EFOnt with existing ontologies and the outlook of EFOnt's role in the building energy data tool ecosystem are discussed.

Semantic-Similarity-Based Schema Matching for Management of Building Energy Data

The increase in heterogeneous data in the building energy domain creates a difficult challenge for data integration. Schema matching, which maps the raw data from the building energy domain to a generic data model, is the necessary step in data integration and provides a unique representation. Only a small amount of labeled data for schema matching exists and it is time-consuming and labor-intensive to manually label data. This paper applies semantic-similarity methods to the automatic schema-mapping process by combining knowledge from natural language processing, which reduces the manual effort in heterogeneous data integration. The active-learning method is applied to solve the lack-of-labeled-data problem in schema matching. The results of the schema matching with building-energy-domain data show the pre-trained language model provides a massive improvement in the accuracy of schema matching and the active-learning method greatly reduces the amount of labeled data required.

Analyzing the Multiscale Impacts of Implementing Energy-Efficient HVAC Improvements Through Energy Audits and Economic Input–Output Analysis

Abstract Heating, ventilation, and air-conditioning (HVAC) systems are usually an industry’s highest consumer of energy, most of which goes toward space cooling in buildings. Industrial energy-efficiency audits not only benefit manufacturers but also generate significant economic and environmental benefits to localities, states, and the nation. This article analyzes the micro- and macro scale impacts of implementing energy-efficient HVAC systems by integrating the industrial building energy data with the macroeconomic regional economic flow model. Micro-scale data include 10 years of historical energy, cost, and carbon dioxide savings achieved from energy-efficient HVAC implementation offered to manufacturers through industrial energy audits. The data were integrated into the macroeconomic modeling framework to illuminate the cascading regional economic impacts of implementing energy-efficient HVAC recommendations in manufacturing facilities. Results show that if recommendations had been implemented throughout all manufacturers in the region, $656 M energy costs would have been directly saved, 7.8 million metric tons of carbon dioxide emissions would have been avoided, and 4387 jobs could have been created, resulting in a total annual economic impact of $899 M stemming from direct, indirect, and induced impacts. The results offer insight into how industrial energy systems can be designed and provide models for how communities can accomplish a net-zero society.

A Systematic Literature Review of Physics-Based Urban Building Energy Modeling (UBEM) Tools, Data Sources, and Challenges for Energy Conservation

Urban building energy modeling (UBEM) is a practical approach in large-scale building energy modeling for stakeholders in the energy industry to predict energy use in the building sector under different design and retrofit scenarios. UBEM is a relatively new large-scale building energy modeling (BEM) approach which raises different challenges and requires more in-depth study to facilitate its application. This paper performs a systematic literature review on physics-based modeling techniques, focusing on assessing energy conservation measures. Different UBEM case studies are examined based on the number and type of buildings, building systems, occupancy schedule modeling, archetype development, weather data type, and model calibration methods. Outcomes show that the existing tools and techniques can successfully simulate and assess different energy conservation measures for a large number of buildings. It is also concluded that standard UBEM data acquisition and model development, high-resolution energy use data for calibration, and open-access data, especially in heating and cooling systems and occupancy schedules, are among the biggest challenges in UBEM adoption. UBEM research studies focused on developing auto-calibration routines, adding feedback loops for real-time updates, future climate data, and sensitivity analysis on the most impactful modeling inputs should be prioritized for future research.