0

i have a streamed power data in real time coming from my electric meter, and when i see the load with my eyes i can tell which kind of appliance is on. Currently i'm using a sliding window of ten points and calculating the standard deviation to detect appliances turning on or off. The aim is to know how much each appliance is consuming by an integral calculation. I need help to perform a signal disaggregation in real Time os i can calculate the inegral of each appliance and avoid having cross calculated consumption values that can happen like in this img

Thx in advance for any help you could provide!

ouss rom
  • 1
  • Do you have any code you could share? What have you tried? – ficuscr Jul 20 '18 at 15:08
  • what i've tried so far is: Whenever an event 'on' is detected i start recording the new incoming data until the next event. I'm using the amplitude of the change to know which element has turned off, but with only this input and all the appliances that i have in my home (some of them have the same power so the same changes in amplitude are registred), this solution can't silmply hadle it. – ouss rom Jul 20 '18 at 15:20
  • Questions about code will get more attention on SO if you provide code. Most are happy to help but not looking to write your solution from scratch. Just an FYI. Sounds interesting. Welcome to SO. – ficuscr Jul 20 '18 at 15:23

1 Answers1

0

If it's just about distinguish between on and off state, naive bayes classification might do the work (https://machinelearningmastery.com/naive-bayes-classifier-scratch-python/) there are several interesting links at the end.

If you want to disaggregate various consumers, an artificial neural network might be a possible solution using TensorFlow https://www.tensorflow.org/tutorials/

An issue here is to generate the labeled training data from scratch.

Performing a fast fourier analysis is used e.g. for detection of hifi equipment - as each device has a specific spectrum.

Oliver Prislan
  • 320
  • 4
  • 12