Hello everyone! First post here, I signed up to ask a question about an optimisation formulation, but I thought I’d also take this opportunity to publicize my Julia package for selecting representative days.
The main reasons you would use this over e.g. clustering is ease of use (though there’s also TimeSeriesClustering.jl for that), the possibility of using optimisation to select periods. It’s not that optimisation >> clustering though, and generally I would say be careful when reducing the temporal scope of models (see my working paper on the subject if you’re interested.)
If you have any questions / issues please let me know 