Appliance State Estimation based on Particle Filtering

The load disaggregation problem

Dominik Egarter will present his work on Appliance State Estimation based on Particle Filtering at  the 5th ACM Workshop on Embedded Systems for Energy-Efficient Buildings (BuildSys'13) which will take place in Rome, Italy at 13th and 14th October 2013.

Non-Intrusive Load Monitoring is a single-point metering approach to identify and to monitor household appliances according their appliance power characteristics. In this paper, we propose an unsupervised classification approach for appliance state estimation of on/off-appliances modeled by a Hidden Markov Model (HMM). To estimate the states of appliances, we use the sequential Monte Carlo or Particle Filtering (PF) method. The proposed algorithm is tested with MATLAB simulations and is evaluated according to correctly or incorrectly detected on/off events.
On other approaches for solving the NILM problem, see:

Particle filter method

Read more about the approach in:

D. Egarter, Venkata Pathuri Bhuvana, W. Elmenreich. Appliance State Estimation Based on Particle Filtering, 5th ACM Workshop on Embedded Systems For Energy-Efficient Buildings, Rome, Italy, 2013.

On other approaches for solving the NILM problem, see:

D. Egarter and W. Elmenreich. EvoNILM - Evolutionary appliance detection for miscellaneous household appliances. In Proceedings of the Green and Efficient Energy Applications of Genetic and Evolutionary Computation at the 2013 Genetic and Evolutionary Computation Conference (GECCO 2013 GreenGEC). ACM, July 2013.

D. Egarter, A. Sobe, and W. Elmenreich. Evolving non-intrusive load monitoring. In Proceedings of the 15th European Conference on the Applications of Evolutionary and bio-inspired Computation, pages 182–191, Vienna, Austria, April 2013.