Today I am pleased to announce that two more houses have been added to the Hourly Usage of Energy Dataset for Buildings in British Columbia (HUE). Read the paper in Elsevier's Data in Brief journal: doi.org/10.1016/j.dib.2019.103744 HUE can be freely downloaded from Harvard Dataverse: doi:10.7910/DVN/N3HGRN. Are you a BCHydro customer? Donate your hourly data for research.
Today I am pleased to announce the release of a new public dataset called the Hourly Usage of Energy Dataset for Buildings in British Columbia (HUE). There is an accompanying paper published in Elsevier's Data in Brief journal that describes the dataset in detail. Here is a brief summary: Having access to long-term consumption data from multiple houses help … Continue reading HUE Dataset Released!
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 … Continue reading RAE Dataset Released!
A message from my good friend and colleague Jack Kelly: Source: A competition for energy disaggregation algorithms | Jack Kelly Now that I've (finally!) submitted my PhD thesis, I can focus on designing and implementing a competition for energy disaggregation algorithms. EDF Energy have kindly given me post-doc funding from now until the end of … Continue reading A competition for energy disaggregation algorithms | Jack Kelly
Today my latest journal paper was published in Nature's Scientific Data. Titled Electricity, water, and natural gas consumption of a residential house in Canada from 2012 to 2014 it discusses the release of AMPds v2. Thanks to my co-authors Bradley Ellert, Ivan V. Bajic, and Fred Popowich for all their contributions and feedback. Here is the paper … Continue reading Electricity, water, and natural gas consumption of a residential house in Canada from 2012 to 2014
Last night I stumbled upon Harvard Dataverse. I decided to sign up and upload one of my early datasets. This dataset 2010 ZigBee Sensor Data Collected From a House (in Vancouver, Canada) Dataset contains power meter, ambient light, and ambient temperature sensors readings; including weather and daylight data. Sensor readings are at 15 minute intervals for about 8 … Continue reading Earlier 2010 House Dataset on Harvard Dataverse
I have just added a new archive that contains the weather data for AMPds. Go to AMPds.org to download the file. You can use the same password for the dataset. Cheers!
Today I am releasing AMPds 2 (The Almanac of Minutely Power Dataset - 2 Years) a new version of my internationally recognized and very popular dataset. AMPds is a dataset consisting of electricity, water, and natural gas consumption. This dataset is ideal for testing load disaggregation/NILM and eco-feedback algorithms and prototypes. A total of 1,051,200 readings for 2 years of … Continue reading AMPds 2 Released! (2 years of data and other fixes)
I decided to update my NILM research website today. I added my NILM publications. Hopefully in the next month I can add some algorithm accuracy results to the website, too. One other thing to note is that come April 1 (2014) I will be making available a second year's worth of data for AMPds. I … Continue reading Research Website Update and AMPds Year 2
Last week I learnt that that my full co-authored (with co-author Fred Popowich, Lyn Bartram, Bob Gill, and Ivan Bajic) paper "AMPds: A Public Dataset for Load Disaggregation and Eco-Feedback Research" was accepted at IEEE's Annual Electrical Power and Energy Conference (EPEC 2013). So I will be travelling to Halifax, Nova Scotia in the Canada. Here is the paper abstract: A home-based intelligent energy conservation system needs to … Continue reading AMPds: A Public Dataset for Load Disaggregation and Eco-Feedback Research