CU-BEMS, smart building electricity consumption and indoor environmental sensor datasets

Pipattanasomporn, Manisa; Chitalia, Gopal; Songsiri, Jitkomut; Aswakul, Chaodit; Pora, Wanchalerm; Suwankawin, Surapong; Audomvongseree, Kulyos; Hoonchareon, Naebboon

doi:10.1038/s41597-020-00582-3

Cited by 53 publications

(26 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, this dataset was considered and used in various literary works. The Tracebase dataset was used in the extensive study of different non-intrusive load monitoring (NILM) power consumption datasets described in [ 35 , 36 , 37 ]. The present and the future directions for energy management techniques using NILM datasets are discussed in [ 38 ].…”

Section: Description Of Datasetmentioning

confidence: 99%

Machine Learning-Based Ensemble Classifiers for Anomaly Handling in Smart Home Energy Consumption Data

Prakash

Kumar

Moganti

et al. 2022

Sensors

View full text Add to dashboard Cite

Addressing data anomalies (e.g., garbage data, outliers, redundant data, and missing data) plays a vital role in performing accurate analytics (billing, forecasting, load profiling, etc.) on smart homes’ energy consumption data. From the literature, it has been identified that the data imputation with machine learning (ML)-based single-classifier approaches are used to address data quality issues. However, these approaches are not effective to address the hidden issues of smart home energy consumption data due to the presence of a variety of anomalies. Hence, this paper proposes ML-based ensemble classifiers using random forest (RF), support vector machine (SVM), decision tree (DT), naive Bayes, K-nearest neighbor, and neural networks to handle all the possible anomalies in smart home energy consumption data. The proposed approach initially identifies all anomalies and removes them, and then imputes this removed/missing information. The entire implementation consists of four parts. Part 1 presents anomaly detection and removal, part 2 presents data imputation, part 3 presents single-classifier approaches, and part 4 presents ensemble classifiers approaches. To assess the classifiers’ performance, various metrics, namely, accuracy, precision, recall/sensitivity, specificity, and F1 score are computed. From these metrics, it is identified that the ensemble classifier “RF+SVM+DT” has shown superior performance over the conventional single classifiers as well the other ensemble classifiers for anomaly handling.

show abstract

Section: Description Of Datasetmentioning

confidence: 99%

Machine Learning-Based Ensemble Classifiers for Anomaly Handling in Smart Home Energy Consumption Data

Prakash

Kumar

Moganti

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Furthermore, while a number of datasets contain sub-metered energy demand for heating, cooling and ventilation in buildings, they seldom contain any information on indoor environment quality indicators such as temperature, humidity, air quality etc. An exception to this is the CU-BEMS dataset [46], which contains electricity demand data in a seven-story 11,700-m2 office building located in Bangkok, Thailand. The data provides measurements Finally, in many cases, energy demand for larger aggregations, such as districts or states are openly available as time series which may be useful to understand the local context for LEC developers.…”

Section: Miscellaneous Demand Datasetsmentioning

confidence: 99%

Towards data-driven energy communities: A review of open-source datasets, models and tools

Kazmi

Munné‐Collado

Mehmood

et al. 2021

Renewable and Sustainable Energy Reviews

View full text Add to dashboard Cite

Energy communities will play a central role in the sustainable energy transition by helping inform and engage end users to become more responsible consumers of energy. However, the true potential of energy communities can only be unlocked at scale. This scalability requires data-driven solutions that model not just the behaviour of building occupants but also of energy flexible resources in buildings, distributed generation and grid conditions in general. This understanding can then be utilized to improve the design and operation of energy communities in a variety of real-world settings. However, in practice, collecting and analysing the data necessary to realize these objectives forms a large part of such projects, and is often seen as a prohibitive stumbling block. Furthermore, without a proper understanding of the local context, these projects are often at risk of failure due to misplaced expectations. However, this process can be considerably accelerated by utilizing open source datasets and models from related projects, which have been carried out in the past. Likewise, a number of open source, general-purpose tools exist that can help practitioners design and operate LECs in a near-optimal manner. These resources are important because they not only help ground expectations, they also provide LECs and other relevant stakeholders, including utilities and distribution system operators, with much-needed visibility on future energy and cash flows. This review provides a detailed overview of these open-source datasets, models and tools, and the many ways they can be utilized in optimally designing and operating real-world energy communities. It also highlights some of the most important limitations in currently available open source resources, and points to future research directions. Highlights:1. The importance of open-source datasets and tools for local energy communities 2. Common use cases for open-source datasets, models and tools for energy communities 3. A thorough review of electricity demand and meteorological datasets and models 4. Most important shortcomings with currently available datasets, models and tools

show abstract

“…However, it doesn’t provide more granular information about the system and thermal zones. CU-BEMS provides system-level sub-metering of electricity consumptions, and zone-level indoor environmental measurements 14 . But it doesn’t contain system-level operation data and data only spans for over a year.…”

Section: Background and Summarymentioning

confidence: 99%

A synthetic building operation dataset

Wang

Hong

2021

Sci Data

View full text Add to dashboard Cite

This paper presents a synthetic building operation dataset which includes HVAC, lighting, miscellaneous electric loads (MELs) system operating conditions, occupant counts, environmental parameters, end-use and whole-building energy consumptions at 10-minute intervals. The data is created with 1395 annual simulations using the U.S. DOE detailed medium-sized reference office building, and 30 years’ historical weather data in three typical climates including Miami, San Francisco, and Chicago. Three energy efficiency levels of the building and systems are considered. Assumptions regarding occupant movements, occupants’ diverse temperature preferences, lighting, and MELs are adopted to reflect realistic building operations. A semantic building metadata schema - BRICK, is used to store the building metadata. The dataset is saved in a 1.2 TB of compressed HDF5 file. This dataset can be used in various applications, including building energy and load shape benchmarking, energy model calibration, evaluation of occupant and weather variability and their influences on building performance, algorithm development and testing for thermal and energy load prediction, model predictive control, policy development for reinforcement learning based building controls.

show abstract

CU-BEMS, smart building electricity consumption and indoor environmental sensor datasets

Cited by 53 publications

References 17 publications

Machine Learning-Based Ensemble Classifiers for Anomaly Handling in Smart Home Energy Consumption Data

Machine Learning-Based Ensemble Classifiers for Anomaly Handling in Smart Home Energy Consumption Data

Towards data-driven energy communities: A review of open-source datasets, models and tools

A synthetic building operation dataset

Contact Info

Product

Resources

About