Clustering time series of smart meter measurementsTeršek, Matija (Avtor) Štrumbelj, Erik (Mentor) time seriesrepresentationsclusteringrecurrent neural networksvariational autoencoderssimilarity measuresIn this thesis we provide a compact review of 8 time series representations in combination with 2 clustering algorithms and 2 indices for internal clustering validation. We analyse time series measured by smart meter devices and check how their representations affect clustering. We conclude that no representation can be directly used for the task and that more focus should be put on preprocessing. Additionally, we compare representations and 4 similarity measures on simulated time series. We find out that similarity measures outperform representations in most cases and that a variational autoencoder-based representation works the best for simulated time series.20202020-09-07 15:50:01Diplomsko delo/naloga119309VisID: 26492COBISS_ID: 28477443sl