NONINTRUSIVE LOAD MONITORING: ENHANCEMENTS OF DEFINITIONS, FORMULATIONS AND SOLUTION APPROACHES

Date

2025-1

Author

Kollar, Şakir Buğra

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

281
views

243
downloads

Cite This

Nonintrusive Load Monitoring (NILM) is the problem of identifying the power consumption of individual appliances based on the aggregate power consumption. Hidden Markov Models (HMMs) are popular models that are used in solving NILM. In this thesis, the definitions, formulations and solution approaches regarding NILM are enhanced. A loss-based formulation is considered for the problem. The loss in consideration can be directly associated with the performance measures of the problem. Besides, methods that does not require disaggregation to determine how much electricity an appliance is consumed are proposed. Moreover, a new post-processing approach is proposed. In the proposed approach, the solutions are adjusted in a way that aims to match the estimated aggregate power consumption with the actual aggregate power consumption. Numerical results based on a real dataset used in the literature as well as synthetic data show that the proposed approaches would be an alternative of the existing algorithms under certain conditions.

Subject Keywords

Hidden Markov Models, Energy Disaggregation, Nonintrusive Load Monitoring

URI

https://hdl.handle.net/11511/113395

Collections

Graduate School of Natural and Applied Sciences, Thesis