Today I am pleased to announce the release of a new public dataset called the Rainforest Automation Energy Dataset (RAE). There is an accompanying paper that describes the dataset in detail. Here is a brief summary:
Datasets are important for researchers to build models and test how well their machine learning algorithms perform. This paper presents the Rainforest Automation Energy (RAE) dataset to help smart grid researchers test their algorithms which make use of smart meter data. RAE contains 72 days of 1Hz data from a residential house’s mains and 24 sub-meters resulting in 6.2 million samples for each sub-meter. In addition to power data, environmental and sensor data from the house’s thermostat is included. Sub-meter data includes heat pump and rental suite captures which is of interest to power utilities. We also show (by example) how RAE can be used to test non-intrusive load monitoring (NILM) algorithms.
Hopefully, the non-intrusive load monitoring (NILM) research community will be pleased!
RAE can be freely downloaded from Harvard Dataverse: doi:10.7910/DVN/ZJW4LC.
Like this:
Like Loading...
Related
Published by Stephen Makonin
Dr. Stephen Makonin is an Adjunct Professor in Engineering Science and the Principal Investigator of the Computational Sustainability Lab at Simon Fraser University (SFU). He received his PhD in Computing Science at Simon Fraser University in 2014 in the area of computational sustainability. He has been a software engineer for over 24 years working for various local/international industry clients. Stephen is a registered Professional Engineering (PEng) with Engineers and Geoscientists BC and a Senior Member of the IEEE. His research interests include computational sustainability and the understanding of socioeconomic issues that pertain to technological advancement. Stephen is an expert in data engineering, software engineering, and a world-renowned researcher in non-intrusive load monitoring (NILM) and disaggregation. Stephen is currently the Vice-Chair of the IEEE Signal Processing Society Vancouver Chapter and sits on the IEEE DataPort Advisory Committee. He currently serves as the Editor in Chief of the IEEE DataPort Metadata Review Board, and as an Editorial Board Member of Nature's Scientific Data journal.
View all posts by Stephen Makonin
Non-Intrusive Load Monitoring (NILM) 