I'M ON FIRE

Today's blog post references the "Fire" song by Kasabian. Of course, there is also an amazing song, "I'm on fire", by Bruce Springsteen, which I love as well. But today "I'm on FIIIIIIIIIIIIRE", as in the style of Kasabian, because: I am getting on with my evidence portfolio write-up for my apprenticeship, solving lots of challenges from my technical lead, and getting on with my blog posts as well.

Yet another beautiful photos from my beautiful friends in the Czech Republic, near Prague. 💜

I think angels surround ya

I have found (discovered, uncovered...) an abundance of articles about renewable energy and AI. It's as though the internet can't keep itself from sharing all of them with me. I love it and it's so so beautiful. It's just beautiful, and I love it, I love it, thanks.

As such my plan to write a blog post about just sensors today won't go ahead. I will push on with my current article.

P.S. I found a YouTube video. That could be a cool one to watch next!!! Thanks. 😍

I'm on FIIIIIIIIIIIIIRE

And so it's time for "Chapter 1: How AI is transforming renewable energy".

This is huge so let me just start with the first paragraph. 

Predicting power capacity levels

Predicting power capacity levels has become harder than ever, just due to the fact that more and more energy is coming from renewable energy resources, and yet these renewable energy sources are the most unpredictable of all and so we need to find a way to manage them all. And yet, this required, in order to ensure "a stable and efficient grid." With renewables making up more of the energy that is provided by the grid, there is greater uncertainty here, as renewables are intermittent and less predictable sources of energy.

The risk of instability

When we have more coal and gas-powered electricity (for example) in the system, then we can turn these on as reliable sources of back-up energy when the supply of power from renewables is intermittent. This is known as "grid inertia".

Without this "grid inertia", losing out on it, could mean that we are more susceptible to blackouts, and that there is greater instability in our grids.

The Good News

Sensor technology can be used on wind and solar power energy in order to "provide an enormous amount of real-time data", therefore "allowing AI to predict capacity levels." Um, okay then. Yes, yes, yes. WOW.

Move on, you've got to move on...

Prior to AI's involvement in the renewable energy transition, and its role in energy forecasting, "most forecasting techniques relied on individual weather models that offered a narrow view of the variables that affect the availability of renewable energy." 

Now, AI programs have been developed to help with the forecasting and generation of renewable energy.

They combine "self-learning weather models, datasets of historical weather data, real-time measurement from local weather stations, sensor networks and cloud information derived from satellite imagery and sky cameras."

Wow! That's a lot to break down here. So all of the different things that they use are:

• self-learning weather models
• datasets of historical weather data
• real-time measurement from local weather stations
• sensor networks
• cloud information derived from satellite imagery and sky cameras

I mean this is incredible! There is so much information combined here! Wow.

The Results

One example of this - the SunShot Initiative by the US Department of Energy - has resulted in "a 30% improvement in accuracy and solar forecasting". This has led "to gains on multiple fronts." Specifically, this initiative "'decreased operational electricity generation costs, decreased start and shutdown costs of conventional generators, and reduced solar power curtailment'". Wow! That is loads.

I'd better leave it there as I am getting tired now.