Jack Kelly

> It might be worth carrying out a quick literature search first yeah. I did a quick text search for "simulat" in my ref database and found 74 results :)...

Thanks Mario, I'll look into Gridlab-D in more detail. It does say it can do sub-second resolution, which is promising. I wonder if it provides household-level power demand, though? And...

Also see the [CBECC-Res Compliance Software Project](http://www.bwilcox.com/BEES/BEES.html)

A few other ideas for a simulator: Two separate "modules": - One for generating "appliance activity scripts". This module would learn statistical models of appliance activity patterns from real data;...

Would also be useful to be able to simulate "abnormal" (but physically plausible) behaviour. The sort of behaviour which _does_ occur in real homes and which would provide an excellent...

A few other quick notes on ideas which have come up during the NILM Workshop: - The simulator needs to be especially accurate at peak demand times. One use case...

I've started sketching out some very rough design ideas for the simulator on [this Google doc](https://docs.google.com/document/d/1xv7VcQWfVk32BBVOU5gL7LFuqcrSaO_OfLWRYs36slA/edit?usp=sharing). Comments welcome.

Thanks Oli, I've added Dong Chen's paper to [the list of references on the Google doc](https://docs.google.com/document/d/1xv7VcQWfVk32BBVOU5gL7LFuqcrSaO_OfLWRYs36slA/edit#heading=h.cpfdo5q2bmkj). And here's the full reference: Chen, D.; Irwin, D. & Shenoy, P. SmartSim: A...

Nilmtk doesn't have such an algorithm. But if you have the two time series then won't you also have the time stamps? If you have an activation which occurred on,...

So... supposedly, when we do training, we want to learn a model for each appliance _type_ in the dataset. Then, when we do metrics, we'll go through each appliance _type_...