BTS: Building Timeseries Dataset: Empowering Large-Scale Building Analytics

TL;DR

This paper tackles the lack of public, real-world, multi-building building analytics data by introducing the Building TimeSeries (BTS) dataset. BTS includes data from three buildings over three years, with more than $10,000$ timeseries and 240 ontologies, with metadata standardized by the Brick schema to enable interoperability. The authors benchmark two interoperability tasks—timeseries ontology multi-label classification and zero-shot forecasting—highlighting domain shift and long-tail distributions and demonstrating BTS's utility for cross-building generalization. By releasing BTS and benchmarking code, they aim to accelerate research in scalable, privacy-preserving building analytics to improve energy efficiency and occupant well-being.

Abstract

Buildings play a crucial role in human well-being, influencing occupant comfort, health, and safety. Additionally, they contribute significantly to global energy consumption, accounting for one-third of total energy usage, and carbon emissions. Optimizing building performance presents a vital opportunity to combat climate change and promote human flourishing. However, research in building analytics has been hampered by the lack of accessible, available, and comprehensive real-world datasets on multiple building operations. In this paper, we introduce the Building TimeSeries (BTS) dataset. Our dataset covers three buildings over a three-year period, comprising more than ten thousand timeseries data points with hundreds of unique ontologies. Moreover, the metadata is standardized using the Brick schema. To demonstrate the utility of this dataset, we performed benchmarks on two tasks: timeseries ontology classification and zero-shot forecasting. These tasks represent an essential initial step in addressing challenges related to interoperability in building analytics. Access to the dataset and the code used for benchmarking are available here: https://github.com/cruiseresearchgroup/DIEF_BTS .

Figures (6)

• Figure 1: Visualisation of six timeseries with varying ontology. The data is from the snippet of our BTS dataset available at https://github.com/cruiseresearchgroup/DIEF_BTS
• Figure 2: Brick Schema Illustration and Visualization, depicting machine-readable metadata for buildings as a knowledge graph. It reveals the logical and spatial links between distinct entities within a building, including the associated timeseries.
• Figure 3: Histogram of class of timeseries by buildings.
• Figure 4: Histogram of class of timeseries by buildings, continued.
• Figure 5: Histogram of class of timeseries by buildings, continued.