You take a stand when you wanna make it right

"You take a stand when you wanna make it right,

Constantly mistaken that I can't say why enough" - Bayonne, I Know

Bayonne is definitely one of my favourite artists in the world. This is definitely one of my favourite songs in the world, too. I often quote it on here. There are a lot of lines that I like, from this song, and from others too, that I wanna quote today:

• "I think I got it right"; - hopefully that reflects the fact that I made the right decision to become a software engineer. That I might the right decision to pursue this life path in renewable energy.
• "Daniel, when I first saw you, I knew that you had, a flame in your heart." - This last one is from a song called "Daniel" by Bat for Lashes. And this is me. This is me. That is me, that is me. 

I have a flame in my heart. I have a flame in my heart. 🔥

A lone church stands at the foot of the mountains at the edge of a lone lake in the Vosges. 

This lake is called the Lac de Longemer.

It is one of my most healing spots in the world. Today, I could really use some healing.

I have a flame in my heart

Right, now it's time to focus on the next 4 paragraphs of this article. 

Oh my God. I just love the wind farms and the wind turbines and the hydroelectric dams and the energy. And I just want to do this. I want to do this. So, so much.

So, so, so much. I can feel them. I can feel them. The wind turbines and the electricity towers and the energy. I can feel them. I can feel them so, so much.

Whoa, whoa, I'm radioactive

Increasingly larger datasets are becoming available for renewable energy forecasting. This is where the role of AI comes in as well - AI can calculate far more on these topics than only human can. 

With the data that we have, we can now train AIs so that "predictions go far beyond the weather to train algorithms to predict more remarkable outcomes." I repeat that: predictions can now go far beyond the weather to train algorithms to predict more remarkable outcomes. 

For instance, when it comes to renewable energy generation forecasting, we can now predict such things as: 

• how much additional power is used during festive holidays
• how much additional power is used during a large-scale international event
• how much altitude impacts a community's energy usage.

The initial data forecasting was done on things like the speed of the wind, the "global horizontal irradiance" (please don't ask me what this is, this is so, so complicated), and the "resulting predicted power output" which allowed us to forecasting for minutes, hours, days, and months, ahead. 

"More accurate forecasting of variable energy at shorter timescales allows" us to forecast our energy production, consumption, and sales. As well as that, and anyway, forecasting has been historically useful for optimising plant availability, scheduling maintenances and repairs, and for maintaining grid stability and dispatching resources. Energy traders also have a lot to gain from this too as better predictions, means better outcomes for their wholesale and balancing bidding efforts.

The article says it all here in this quote: "'The earlier and more accurately you can predict, the more efficient it is for energy traders to rebalance their position.'".

"'I see AI providing a way of dealing with a lot more sites and using more granular and diverse data than historic forecast methods'", they quote someone important as saying.

So therefore AI allows us to deal with more complex and "granular" data. "'Ultimately, this means making a better financial return'". Ultimately, this means making a better financial return.

Better forecasting "output and to bid to the wholesale and balancing markets" also allows you to do so, "while avoiding penalties."  

Daniel, when I first saw you, I knew that you had, a flame in your heart

And so again, we have more data than ever with which to do our forecasting and predict our renewable supply, demand, and consumption.

Unfortunately, this data is just far too much for the naked human eye - this is where AI can step in, and do a better job of predicting, calculating, and breaking down these things than any human can.

When predicting for electricity consumption, we have traditionally not taken into account some of the most important things, like:

• holiday seasons and how that changes and affects power and consumption
• (for example, Christmas lights!!! When they all come on, on the inside and the outside, then this most certainly must affect the power grid!!!!). 💜
• large scale international events - say like the Olympics or something? Or the World Cup maybe? 
• Surely that's got to have some kind of an impact on the grid?
• altitudes - have you ever thought about what kind of an impact the Himalayas might have on the electricity grid? What about the Vosges? The Alps? The Andes? (Er... what other mountain ranges are there...? I don't know what other mountain ranges there are... sorry 🤣).

Made a wish on elevens

With the increase and the introduction of new data, we can go way beyond just predicted the electricity output over the coming few days, months, weeks and hours and even minutes. We can go as far as making comparisons relative to holidays, major international events, and comparing the electricity grid prediction even across altitudes.

The use of AI can help us to make predictions for different sites.

We can make a better financial return on our energy predictions as well as a result of this.

AI forecasting also helps those who are involved in "wholesale and balancing markets" to "avoid penalties". 

Made a wish on an eyelash

I don't know how to do anything else than what I love.

I only ever know how to be me.

All I ask is for the privilege to continue, to be able to keep on doing what I do.