I Like It! to Idea Seenergy - The Electric Meter to Appliances Itemizer
Voting Disabled

19 votes



This idea is active.
Apps for Energy II »

Seenergy - The Electric Meter to Appliances Itemizer

Team members:

Sri Kanajan

Christopher Cornwell

Julia Orwell

Matheus D. Spinelli

The goal is to automatically itemize the energy consumption down to the specific appliances and then provide specific, actionable recommendations to the consumers.

This application takes in the Green Button data that has your specific electric meter readings pattern over time and figures out automatically what each major appliance in your house consumes. The application does this by correlating specific energy signatures of specific appliances to the electric meter reading pattern over time. This technique is a new theory concept called disagreggation where an aggregate reading is decomposed to its sources through predictive machine learning algorithms. The library of appliance consumption signatures can be developed statically over time as a library. The error in the predictive algorithm can be improved by introducing more data such as outside temperature at that time or the specific time of day. E.g. it is higher likelihood that the heater was turned on during colder temperature and late at night vs. an oven.

Once the itemized measurements (i.e. when each appliance was on and off) are generated then specific recommendations can be generated. For example: 1. Recommend an alternate appliance that could lower consumption based on historical usage patterns. 2. Recommend a different pricing approach (tier vs. peak) 3. Recommend using specific appliances at different times of day based on usage pattern.

Note: The application used excel to do the data analytics and then insert the data into the webpage to generate the visualizations. We did not have time to develop a complete application but wanted to focus on illustrating the concept. Extract zipfile into a folder and open EnergyUse.htm to see the application.

This uses the Green Data and is related to a winning idea of providing real time measurement data.

Submitted by Sri 4 months ago

Vote Activity Show

Comments (4)

  1. Sri Idea Submitter

    We would love to get feedback as to people's thoughts on this project. Please leave a comment if you can ! Thanks !

    4 months ago
    0 Agreed
  2. I have been using the green button data since PG&E launched it a couple of years ago. Before that, we could disaggregate a user's data to determine heating, cooling, and lighting loads based on seasonal data (monthly). With the hourly data, you can get the idle draw (vampire load) by taking an average of a few points during the early am hours. Knowing lighting, heating, cooling, and vampire load, the rest falls into the category of appliances and other, which is usually a hot tub or pool. You can see the pool on GIS systems. The challenge is getting the User to provide information about their appliances to take it to the next step.

    4 months ago
    1 Agreed
    1. Sri Idea Submitter

      Thanks for the comment Scott. Absolutely right. Getting the user's input is critical to improve the degree of accuracy of the prediction algorithm. Nevertheless, this is a one time input and as you said, we could provide an initial guess using real estate data. I also suspect that the large ticket appliances (HVAC, washer, dryer, pool motor, etc) tend to dominate most of the energy consumption. Also, these items are likely to be the items that hold the most potential for optimization since they are used in a regular fashion (e.g. recommend when to use it) and there are multiple alternative models (e.g. recommend a different appliance model).

      4 months ago
      0 Agreed
  3. I registered and answered the questions regarding my home. It would be helpful to be able to denote that the fuel for my dryer and my oven is gas, not electric. By far, my biggest electricity consumers are my two stage heat pump systems. The rest of my house uses less than 20 kWh per day, and costs very little on Dominion's Time of Use rate tariff.

    4 months ago
    1 Agreed