Comprehensive energy demand and usage data for building automation
Abstract
Buildings are essential in satisfying our daily need for comfort (privacy, protection from weather, etc.) and are responsible for almost half of the world’s total energy consumption. Research at the interface of room comfort and energy efficiency is of critical societal importance. At the same time, there is a lack of publicly available data to optimize important building functions automatically. It is only through data-driven approaches that building automation becomes financially affordable and achieves widespread adoption. In this publication, measurement data from three buildings of the NEST platform are made publicly available. The dataset includes detailed information on energy consumption (electricity, heating, cooling, domestic hot water), building operation (set points, valve openings, windows), and occupant practice (e.g., presence, operation of blinds and kitchen, showering patterns). All data have been measured over four years and with a temporal resolution of 1 minute. This combination of information allows learning the function of different building types (office and residential) and thus addresses important research gaps.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.