AMPds: A Public Dataset for Load Disaggregation and Eco-Feedback Research
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 know what appliances (or loads) are being used in the home and when they are being used in order to provide intelligent feedback or to make intelligent decisions. This analysis task is known as load disaggregation or non-intrusive load monitoring (NILM). The datasets used for NILM research generally contain real power readings, with the data often being too coarse for more sophisticated analysis algorithms, and often covering too short a time period. We present the Almanac of Minutely Power dataset (AMPds) for load disaggregation research; it contains one year of data that includes 11 measurements at one minute intervals for 21 sub-meters. AMPds also includes natural gas and water consumption data. Finally, we use AMPds to present findings from our own load disaggregation algorithm to show that current, rather than real power, is a more effective measure for NILM.
Keywords: Power Meter, Current, Dataset, Load Disaggregation, Eco-Feedback, Single-Measurement, Maximum a Posteriori (MAP), Energy Conservation
The dataset (and paper) can be found at
http://ampds.org
.
New Consumption Report
So I have finally had a chance to update the My Smart Home: Consumption Report to reflect readings from the new DENT PowerScout 18 meters and a new database design. Checkout:
http://makonin.com/report_consumption.html
.
Related articles
- Branch Circuit Power Metering (eco-sustain.org)
Home Occupancy Agent: Occupancy and Sleep Detection
Earlier this month I learnt that I (and co-author Fred Popowich) will have my first journal paper published in the GSTF Journal on Computing in the April/2012 edition (vol 2, no 1). Here is the paper abstract:
Smart homes of the future will have a number of different types of sensors. What types of sensors and how they will be used depends on the behaviour needed from the smart home. Using the sensors to automatically determine if a home is occupied can lead to a wide range of benefits. For example, it could trigger a change in the thermostat setting to save money, or even a change in security monitoring systems. Our prototype Home Occupancy Agent (HOA), which we present in this paper, uses a rule based system that monitors power consumption from meters and ambient light sensor readings in order to determine occupancy. The agent is also able to determine when the occupants are asleep, and thus provide the potential for further energy saving opportunities.
Keywords: Smart Home, Intelligent Agent, Occupancy Detection, Power Consumption, Ambient Light Sensors, Sleep Detection, Energy Conservation, Sustainability.
Keep your eyes peeled as there are a number of other submissions that I am either waiting on review or in the midst of writing. Write on…
Related articles
- The Affect of Lifestyle Factors on Eco-Visualization Design (eco-sustain.org)
Security system working with mControl via NPort
So yesterday and today I spent time installing the NPort 5250A Serial to IP Server and hooking it up to my DSC security system. After the hardware was setup, I enabled the “DSC PS” driver in mControl Service Manager and configured it with the right IP address and port. Then I added a new device in mControl Editor. Once done, I was able to arm/disarm the security system without issue. What I like about mControl is that once the hard work of installing the hardware is done, there is no struggle on the automation software side; only add or change some settings/configurations and it just works! Next task is to get the NPort to talk RS485 to my ION6200 power meters and write the corresponding mControl driver.
In the next couple of weeks I will be posting more information on:
- how to create a meter enclosure for your smart/revenue meter;
- how to start writing mControl drivers;
- a project page on how to create you own Arduino power meter reader (the APMR project), that uses a real-time clock (RTC) and RS485/MODBUS.
One thing to note is that I am trying to get the “DSC PS” driver in mControl modified. My security system has 4 partitions and the driver, in its current form, only support 2.
Related articles
- Installing mControl v3 (eco-sustain.org)
- mControl Device Drivers (eco-sustain.org)
Insteon phase coupler installed
So I installed the SignaLinc hardwired phase coupler and the 10A FilterLinc today and it looks like all the communication issues I was having are gone. I am still getting hop counts of 3 on some devices, but I think that may go away once I install more Insteon hardware.
Related articles
- Insteon communication issues (eco-sustain.org)
mControl Device Drivers
I just finished having a meeting with Ted and Roger from Embedded Automation on how to write device drivers for mControl. It was great that they took some time out of their busy day to meet with me at the SFU Surrey Campus. Now that I have a handle on this I am looking to create a number of drivers that can:
- talk to RS485/Modbus devices, in this case my power meters;
- receive consumption data from the AcquiLite about water and natural gas usage;
- update my ambient display, Elements of Consumption.
These devices that I will be adding to mControl will allow me to start monitoring my energy consumption more closely. I will using a new service in mControl v3 to capture and store data in a database. That data will be analyzed by machine learning algorithms to find patterns of usage and to identify what appliances were used. If you are interested in learning more about this project feel free to contact me. Soon I will announce a way for anyone that uses mControl v3 to participate…

