Presentation videos from NILM 2018 in Austin now available

I only recently noticed that videos from NILM 2018 in Austin are now available as a YouTube playlist. Here's a full list of the videos:

• An Experimental Comparison of Performance Metrics for Event Detection Algorithms in NILM
• Real-Time Itemized Electricity Consumption Intelligence for Military Bases
• Scalable Energy Breakdown Across Regions
• Pecan Street's Dataport
• Making Sense of UK smart meter data
• Poster Lightning Talks
• A Practical Discussion of Lessons Learned Deploying Disaggregation at Broad Scale
• An Emulator for NILM and Smart Home Research
• Panel Discussion on NILM Outlook & Next-Generation Applications
• On the Feasibility of Generic Deep Disaggregation for Single-Load Extraction
• FactorNet for Energy Disaggregation
• Post-processing for Event-based Non-intrusive Load Monitoring
• Power Signature Obfuscation using Flexible Building Loads

Credit to Stephen Makonin for cutting up the videos and uploading them!

BLOND office environment data set released

Thomas Kriechbaumer & Hans-Arno Jacobsen of The Technical University of Munich (TUM) recently released BLOND - a building-level office environment dataset of typical electrical appliances. The data set contains voltage and current readings for aggregated circuits and matching fully-labeled ground truth data (individual appliance measurements). The study covers 53 appliances (16 classes) in a 3-phase power grid in Germany. The authors have released two versions of the data set:

1. BLOND-50 contains 213 days of measurements sampled at 50 kHz (aggregate) and 6.4 kHz (individual appliances).
2. BLOND-250 consists of the same setup: 50 days, 250 kHz (aggregate), 50 kHz (individual appliances).

The data set is also described in more detail in the following publications:

• Kriechbaumer, T., & Jacobsen, H. A. (2018). BLOND, a building-level office environment dataset of typical electrical appliances. Scientific data, 5, 180048.