21–30 of 38 posts
No paper, no code, no comparison to other models - hell, they didn't even label the graphs. This is just Google PR spam.
A demonstration of the astonishing value of a relatively small government program: weather observation and forecasting.
Actually, scratch that. On the scale of government, they're more medium size.
No paper, no code, no comparison to other models - hell, they didn't even label the graphs. This is just Google PR spam.
Well, keep an eye out for it here: https://deepmind.com/research/publications/
How exactly does this need machine learning? Naively I would assume that it's somewhat directly correlated with wind speed (and little more, maybe direction) and a very simple model based on that data will give you good predictions.
No paper, no code, no comparison to other models - hell, they didn't even label the graphs. This is just Google PR spam.
The optimization for their datacenters used a 3 layer neural network with 6 neurons. I wonder if this is much more complicated than that...
I have been working in the same field, quite a few years in my own forecasting company and then later on as a side project. Not wanting to steal the thunder of Deepmind, but I feel should mention my site which is currently beta as in "works for a few electricity power load and supply forecasting scenarios" and quite well so. Also, it's out there, cheap and fast. https://ausblick.cryptoport.net Unfortunately, it's onl…
How exactly does this need machine learning? Naively I would assume that it's somewhat directly correlated with wind speed (and little more, maybe direction) and a very simple model based on that data will give you good predictions.
Wind speed, power load nearby, wind forecast, storage capacity ...
Should I engage the alternator now, even if it's spinning? Could that use up more energy than if I let it spin on a flywheel and engage later?
Also repairs. What should I fix, and when? Does it make sense just to keep it offline in the winter when consumption is low? Then you get all the pricing data available.
It's also looking for variables not known. Perhaps there's a bad actor, and for whatever reason, when he's there, losses occur.
If anyone is interested in this type of work, our team at Amperon is hiring data engineers, data scientists, and front end engineers. We’re funded by SV Angel and Notation Capital and we’ve already got traction in ERCOT (Texas). More info: https://medium.com/@astanway/introducing-amperon-2cded368284...
Is remote (Texas) viable?