A new approach for supervised power disaggregation by using a deep recurrent LSTM network

Bin Yang1, Lukas Mauch2

  • 1University of Stuttgart
  • 2Universität Stuttgart

Details

Category

Special Symposia

Theme

Signal Processing Applications in Smart Buildings

Sessions

11:00 - 12:20 | Mon 14 Dec | Ireland B | MbSB-L

Electricity Disaggregation: Algorithms

Abstract

This paper presents a new approach for supervised power disaggregation by using a deep recurrent long short term memory network. It is useful to extract the power signal of one dominant appliance or any subcircuit from the aggregate power signal. To train the network, a measurement of the power signal of the target appliance in addition to the total power signal during the same time period is required. The method is supervised, but less restrictive for practice since submetering of an important appliance or a subcircuit for a short time is feasible. The main advantages of this approach are: a) It is also applicable to variable load and not restricted to on-off and multi-state appliances. b) It is eventless and featureless, i.e. it does not require any event detection and feature extraction. c) By using multiple networks, it is possible to disaggregate multiple appliances or subcircuits at the same time. d) It also works with a low cost power meter as shown in the experiments with the REDD dataset (1/3Hz sampling frequency, only real power).

Additional Information

No information added

Video

No videos found