Rolling Coal

[Jolly]

Remember what he said ...DOUBLE.

You can't solar the country into this. You can't windmill the country into this. You can go nuclear, but those plants take years, if not decades, to construct and come online.

So, what do you do?

[taiwan_girl]

I think that coal is past. Trying to reopen mines, restart coal power plants is also something that cannot be done overnight.

I don't know what the timeframe for the estimated double of electricity usage is.

EDIT: Lots of interesting data here from the US Energy Information Administration. In their outlook through 2050, they project an about 25% increase in consumption from now to 2050.

Coal production is projected to being negative growth. (assuming I am reading the report correctly. LOL)

https://www.eia.gov/analysis/projection-data.php

[Jolly]

Have they taken the rise of AI into consideration?

[taiwan_girl]

I think that the report is from 2023.

(But, consumption cannot double if production does not double. Maybe he meant to say that we need to double production.)

But I think natural gas is more possible than coal. I think that for example, Texas has a lot of excess natural gas. There was something recently on my desk that talked about negative pricing for Texas natural gas - the producers are almost paying for people to take their natural gas.

[Axtremus]

@Jolly said in Rolling Coal:

Have they taken the rise of AI into consideration?

Of all the people who offer opinions on AI driven energy consumption, you choose to listen to Trump?

Have you look into Trump's methodology on how he came up with the "DOUBLE" projection for AI driven electricity demand?

[Jolly]

@Axtremus said in Rolling Coal:

@Jolly said in Rolling Coal:

Have they taken the rise of AI into consideration?

Of all the people who offer opinions on AI driven energy consumption, you choose to listen to Trump?

Have you look into Trump's methodology on how he came up with the "DOUBLE" projection for AI driven electricity demand?

You know something Elon Musk does not?

[George K]

@Axtremus said in Rolling Coal:

Of all the people who offer opinions on AI driven energy consumption, you choose to listen to Trump?

https://www.popsci.com/technology/ai-more-energy/

By 2030, the report notes, data center energy requirements could account for anywhere between 4.6% and 9.1% of total US electricity generated by 2030. That’s compared to 4% today. The newfound demand isn’t limited to the US either. By 2026, The International Energy Agency (IEA) estimates data center energy demand globally could double by 2026.

[taiwan_girl]

Okay, so it is data center consumption may double, but overall energy consumption will increase much less. I think the EIA report backs this up.

[Copper]

@George-K said in Rolling Coal:

data center energy requirements could account for anywhere between 4.6% and 9.1% of total US electricity generated by 2030.

That assumes that TG and Jolly continue to post at the current rate.

[George K]

@taiwan_girl said in Rolling Coal:

Okay, so it is data center consumption may double, but overall energy consumption will increase much less. I think the EIA report backs this up.

Let's ask...AI!

How much electrical energy will AI consume in the next five years?

Estimates and Projections:

• Current Consumption: In 2020, it was estimated that data centers (a significant portion of which support AI workloads) consumed about 1% of global electricity, which could translate to around 200 terawatt-hours (TWh). AI’s share of this is growing as AI adoption increases.
• Future Consumption: If AI adoption and computational requirements continue to grow at the current pace, the energy consumption of AI could potentially double or triple over the next five years. Some estimates suggest that AI could consume several hundred TWh by 2030, but this is highly dependent on technological advancements and efficiency improvements.

How about 10 years?

• Exponential Growth Scenario: If AI adoption continues to grow exponentially without significant breakthroughs in energy efficiency, AI's energy consumption could increase by an order of magnitude or more. By 2033, AI could potentially consume several hundred TWh annually, or even exceed 1,000 TWh, depending on the scale of deployment and the types of models in use.
• Efficiency-Driven Scenario: If substantial progress is made in improving AI energy efficiency—through better hardware, optimized algorithms, and more sustainable practices—then the growth in energy consumption could be more modest. In this scenario, AI’s energy use might increase more linearly, potentially reaching 500-800 TWh annually by 2033.
• In a worst-case scenario, AI could become a significant driver of global electricity demand, potentially consuming over 1,000 TWh annually.

[taiwan_girl]

@George-K said in Rolling Coal:

By 2030, the report notes, data center energy requirements could account for anywhere between 4.6% and 9.1% of total US electricity generated by 2030. That’s compared to 4% today. The newfound demand isn’t limited to the US either. By 2026, The International Energy Agency (IEA) estimates data center energy demand globally could double by 2026.

To follow up on this:

A deal between Constellation Energy and Microsoft will restart Pennsylvania’s Three Mile Island, the site of the country’s worst nuclear power accident, to help power the tech giant’s growing artificial intelligence ambitions.

Under the agreement, Constellation would revive the plant’s undamaged reactor, which was too costly to run and closed in 2019, and sell the power to Microsoft. The plan signals the gargantuan amount of power needed for data centers for AI, along with the tech industry’s thirst for a carbon-free, round-the-clock electricity source needed to meet climate goals.

https://www.wsj.com/business/energy-oil/three-mile-islands-nuclear-plant-to-reopen-help-power-microsofts-ai-centers-aebfb3c8

[Mik]

You’re also not factoring in millions of electric vehicles.

[taiwan_girl]

https://www.wired.com/story/the-ai-boom-is-raising-hopes-of-a-nuclear-comeback/

It’s all part of an ongoing flirtation between Big Tech and nuclear power. In March, Amazon Web Services agreed to buy a data center powered by Susquehanna nuclear power station in Pennsylvania. At an event at Carnegie Mellon University on September 18, Alphabet CEO Sundar Pichai mentioned small modular nuclear reactors as one potential source of energy for data centers. The links don’t stop there either: OpenAI CEO Sam Altman chairs the boards of nuclear startups Oklo and Helion Energy.

The AI boom has left technology companies scrambling for low-carbon sources of energy to power their data centers. The International Energy Agency estimates that electricity demand from AI, data centers, and crypto could more than double by 2026. Even its lowball estimates say that the added demand will be equivalent to all the electricity used in Sweden or—in the high-usage case—Germany.

This surge in energy demand is music to the ears of the nuclear power industry. Electricity demand in the US has been fairly flat for decades, but the sheer scale and intensity of the AI boom is changing that dynamic. One December 2023 report from a power industry consultancy declared the era of flat power demand over, thanks to growing demand from data centers and industrial facilities. The report forecasts that peak electricity demand in the US will grow by 38 gigawatts by 2028, roughly equivalent to 46 times the output of reactor one at Three Mile Island.

[George K]

Nuclear, FTW!

It's worked in France - pretty well.

[Renauda]

Forget coal. Go natural gas!