It’s Not Like Bill Gates Isn’t Trying, But Building an SMR Industry is Hard

February 11, 2023

Great work by Jonathan Rauch in the Atlantic, but a little slow coming around. People like Amory Lovins, and, well, me – recognized this no later than 1977.
Above, Bill Gate’s sunny projections for his small modular nuclear reactor, as he related in 2016. (spoiler, his schedule as slipped)

And let’s just review. This is one of the richest and most influential men in the world, who has joined with a bunch of other rich and influential men, women, foundations, corporations, and the US Government to work on this, and hired, I’m sure the best and brightest engineers and others, and their schedule has slipped by at least 8 years, and counting.
There is no possibility of a significant new nuclear contribution in this decade, and probably before 2035 at the very earliest.

Jonathan Rauch in the Atlantic:

The Real Obstacle to Nuclear Power – it’s not environmentalists—it’s the nuclear-power industry itself.

And so environmentalists, I thought, were betraying the environment by stigmatizing nuclear power. But I had to revise my view. Even without green opposition, nuclear power as we knew it would have fizzled—today’s environmentalists are not the main obstacle to its wide adoption.

As I recently pointed out, It isn’t about “pro nuclear” or “anti nuclear”. It’s about what’s possible, and what’s not.

Institute for Energy Economics and Financial Analysis:

Last week, NuScale and the Utah Associated Municipal Power Systems (UAMPS) announced what many have long expected. The construction cost and target price estimates for the 462-megawatt (MW) small modular reactor (SMR) are going up, way up.

From 2016 to 2020, they said the target power price was $55/megawatt-hour (MWh). Then, the price was raised to $58/MWh when the project was downsized from 12 reactor modules to just six (924MW to 462MW). Now, after preparing a new and much more detailed cost estimate,  the target price for the power from the proposed SMR has soared to $89/MWh.

Remarkably, the new $89/MWh price of power would be much higher if it were not for more than $4 billion in subsidies NuScale and UAMPS expect to get from U.S. taxpayers through a $1.4 billion contribution from the Department of Energy and the estimated $30/MWh subsidy in the Inflation Reduction Act (IRA). 

It also is important to remember that the $89/MWh target price is in 2022 dollars and substantially understates what utilities and their ratepayers actually will pay if the SMR is completed. For example, assuming a modest 2% inflation rate through 2030, utilities and ratepayers would pay $102 for each MWh of power from the SMR—not the $89 NuScale and UAMPS want them to believe they will pay.

The 53% increase in the SMR’s target power price since 2021 has been driven by a dramatic 75% jump in the project’s estimated construction cost, which has risen from $5.3 billion to $9.3 billion. The new estimate makes the NuScale SMR about as expensive on a dollars-per-kilowatt basis ($20,139/kW) as the two-reactor Vogtle nuclear project currently being built in Georgia, undercutting the claim that SMRs will be cheap to build.

NuScale and UAMPS attribute the construction cost increase to inflationary pressure on the energy supply chain, particularly increases in the prices of the commodities that will be used in nuclear power plant construction.

For example, UAMPS says increases in the producer price index in the past two years have raised the cost of:

  • Fabricated steel plate by 54%  
  • Carbon steel piping by 106%  
  • Electrical equipment by 25%  
  • Fabricated structural steel by 70%  
  • Copper wire and cable by 32%

In addition, UAMPS notes that the interest rate used for the project’s cost modeling has increased approximately 200 basis points since July 2020. The higher interest rate increases the cost of financing the project, raising its total construction cost.

Assuming the commodity price increases cited by NuScale and UAMPS are accurate, the prices of building all the SMRs that NuScale is marketing—and, indeed, of all of the SMR designs currently being marketed by any company—will be much higher than has been acknowledged, and the prices of the power produced by those SMRs will be much more expensive.

Finally, as we’ve previously said, no one should fool themselves into believing this will be the last cost increase for the NuScale/UAMPS SMR. The project still needs to go through additional design, licensing by the U.S. Nuclear Regulatory Commission, construction and pre-operational testing. The experience of other reactors has repeatedly shown that further significant cost increases and substantial schedule delays should be anticipated at any stages of project development.

Below, Jon Ball, an executive with GE/Hitachi Nuclear, which has its own Small Modular Reactor (SMR) design, states that a Levelized Cost of Energy or 60$ MWhr from their technology is “achievable”. A recent poll of industry experts predicted such a price by 2050.

For comparison, see Lazard’s Levelized Cost of Energy numbers for 2021, below the vid.


17 Responses to “It’s Not Like Bill Gates Isn’t Trying, But Building an SMR Industry is Hard”

  1. Anthony O'Brien Says:

    The nuclear industry talks of the mass produced small car sort of reactor, but builds the hand built McLarens of reactors. Purchasers have to blame themselves too, “we love the design BUUUTTT” When you buy a Dodge Ram do ask for it to be 6 inches longer and 2 inches wider?

    That aside, nuclear has long missed the boat. It will never get a chance to be competitive. It is just too far behind.

    • John Oneill Says:

      The reason Bill Gates’ optimistic forecast from 2016 ran off the rails was that he was building the prototype in China, and Donald Trump’s souring relations with China made the work untenable. When solar panels are all built in the US, instead of getting their silicon from China, with Uighur prison camps for labour and Mongolian coal for heat, they’ll probably be a bit more expensive too.
      The Lazard Levelised Cost of Energy is available online here
      It shows energy sources divided into ‘Renewable’ and ‘Conventional’, with a minimum and maximum. No mention of hydro, which is the by far largest power source usually considered ‘Renewable’ (except in California.) LCOE prices given are for new build, and are well above the median shown for existing plant, with gas combined cycle at $24 and nuclear at $29. Cost of gas is listed as $3.45/MMBTU in the US, up to $7.00 in Japan and India, and a capacity factor of only ten percent. Price peaks for gas over the last year have gone twice that high for the US, and over seven times that high for Europe and Japan. Fuel cost is the main determinant of fossil fuel electricity cost, but uranium prices are a minor factor in nuclear power prices – the largest factor is the interest on build cost. That’s one of the main reasons new Western reactors got so expensive – long build times, for the first reactors built in 30 years, plus high interest rates.
      Apart from LCOE, as environmentalists, you should be looking at net emissions. In Europe, the countries with the lowest emissions from power generation are Norway and Iceland, blessed with lots of mountains and rain, and not so much with people. Next are Sweden and France, with very low figures for CO2 per kilowatt hour, thanks to hydro and nuclear. Both have recently reversed course on nuclear, and pledged to build more. In North America, the lowest emissions again are from Quebec, and a few other thinly populated areas with well-harnessed rivers. Next is Ontario, the largest province in Canada, with 60% of its power from nuclear and again, planning for more.
      Mark Jacobson, the guru of 100% renewables, was recently hailing the beginning of a new 1.2 gigawatt power line from Quebec to New York, to supplement the latter’s renewables, hopefully by 2026. He shed no tears for the 2 GW of reliable power that Indian Point’s reactors used to supply the State, till former Governor Andrew Cuomo managed to have them closed in 2021. Unfortunately Quebec tends to run short of power in winter, and often has to import from Ontario – Hydro Quebec’s contract does not compel it to supply NY when its home customers need power.

  2. The price increases of steel plate, electrical equipment and such are much more of a problem for wind, solar and especially batteries. The main cost for nuclear is expertise.

    • Mark Mev Says:

      That is a 50% increase in $/MWh since 2021 without the IRA subsidy and 100% increase over the same time frame with the IRA subsidy. Maybe I missed it, but can you show me prices for utlility solar or wind farms where the $/MHr has increased the same or more over the same time frame?

      • Wind companies don’t raise and lower their rates. They make contracts and then lose money and try to weasel out of them like here:

        • Mark Mev Says:

          Corporations and utilities sign PPAs. In 2022 solar increased around 40%, wind was in the single digits. Again, show me your data that wind and utility solar prices have increased more than than nuclear. If your statement: “The price increases of steel plate, electrical equipment and such are much more of a problem for wind, solar and especially batteries.” is true where are the PPAs that show this.
          Just read that article. My opinion, the company saying that they can’t build that offshore wind farm because financially it would be profitable with the existing PPA should have arranged the contract like they did for Vogtle. All cost overruns would be paid by the consumers.

    • rhymeswithgoalie Says:

      “The main cost for nuclear is expertise.”

      My laugh for the day.

      So Vogtle had billions of dollars worth of expertise, eh?

  3. Roger Walker Says:

    Just for fun, I put the question to ChatGPT:

    *summarize the current state of nuclear power*

    As of my knowledge cut off in 2021, the use of nuclear power globally has been declining in recent years due to the increasing competition from renewable energy sources, public concerns over safety and waste management, and high costs of building new nuclear plants. However, some countries still see nuclear power as a crucial part of their energy mix and are investing in research and development of advanced nuclear technologies. The overall trend in the energy sector has shifted towards decarbonization, and nuclear power, as a low-carbon source of energy, is being considered as a potential solution to reduce greenhouse gas emissions and address climate change.

    *what role can nuclear play in reducing gge over the next decade?*

    Nuclear power has the potential to play a significant role in reducing greenhouse gas emissions (GGEs) over the next decade as it is a low-carbon energy source. The continued operation of existing nuclear power plants and the construction of new advanced nuclear technologies, such as small modular reactors, could help to reduce GGEs by generating electricity without emitting carbon dioxide. Additionally, the use of nuclear power in conjunction with renewable energy sources could help to balance the grid and support the integration of variable renewables, such as wind and solar, into the energy mix.
    However, the deployment of nuclear power is not without challenges. The high costs of building new nuclear plants, public concerns over safety and waste management, and competition from cheaper renewable energy sources are some of the factors that could limit its growth in the coming years. Therefore, it will be important for the industry to address these challenges and ensure the safe, cost-effective, and sustainable deployment of nuclear power to play a role in reducing GGEs over the next decade.

    *”The continued operation of existing nuclear power plants” – OK. But “new advanced nuclear technologies, such as small modular reactors,” will not be on line within the coming decade and they are much, much more expensive than renewables.*

    Thank you for pointing that out. You are correct, it is unlikely that new advanced nuclear technologies, such as small modular reactors, will be online within the next decade due to the time required for their development and deployment. Additionally, you are correct that they are often more expensive than renewable energy sources, such as wind and solar, which have seen significant cost reductions in recent years.

    Therefore, the role of existing nuclear power plants in reducing greenhouse gas emissions over the next decade is likely to be more limited, and the focus will be on maximizing their operational efficiency and extending their lifespan where feasible. At the same time, the continued growth of renewable energy sources and the development of energy storage technologies will play a key role in reducing greenhouse gas emissions and addressing climate change in the coming years.

    *The IPCC says reducing emissions quickly and radically is crucial to avoid major tipping points. So what’s the point in throwing money at unproven technology that might, or might not, provide emissions-free energy somewhere down the road?*

    You raise a valid point. The Intergovernmental Panel on Climate Change (IPCC) has emphasized the need for rapid and deep reductions in greenhouse gas emissions to avoid the worst impacts of climate change. In this context, investing in unproven technologies that may or may not provide emissions-free energy in the future may not be the most effective use of resources.
    Instead, a more immediate and cost-effective approach would be to focus on scaling up proven technologies, such as renewable energy sources like wind and solar, and increasing energy efficiency. Additionally, investing in research and development of advanced energy storage systems and grid infrastructure can help to integrate these renewable sources into the energy mix and overcome the intermittency challenges associated with them.
    However, it is worth noting that the future energy mix will likely be diverse and will likely include a mix of low-carbon energy sources, including nuclear power. While the immediate priority is to reduce emissions quickly and radically, it may still be valuable to continue investing in research and development of advanced nuclear technologies for use in the long term, as long as it does not distract from or delay the deployment of proven and readily available low-carbon technologies.

    *So why did you tell me that nuclear power “has the potential to play a significant role in reducing greenhouse gas emissions (GGEs) over the next decade”?*

    I apologize for the confusion. You are correct, it is unlikely that nuclear power will play a significant role in reducing greenhouse gas emissions over the next decade due to the limitations and challenges I mentioned in my previous responses. The emphasis should be on scaling up proven low-carbon technologies, such as renewable energy sources, energy efficiency, and energy storage systems, to reduce emissions quickly and effectively in the near term. The future of energy will likely be diverse, and advanced nuclear technologies may play a role in the long-term, but the immediate focus should be on reducing emissions as rapidly as possible to address the pressing issue of climate change.

  4. sailrick Says:

    In 2020, China installed 72 GW of wind and 48 GW of solar generating capacity.
    I did some back of the envelope figuring with generating capacity factors for PV solar, wind and nuclear, to see what that is equivalent to in nuclear power. I used number I think are generous to nuclear.
    100% for nuclear, 30% for wind and 18% for PV solar utility scale.
    What I came up with is that the 72 GW of solar is equivalent to building about 21 single reactor nuclear plants of typical 1 GW capacity built IN ONE YEAR.
    The 48 GW of solar equivalent to building 8 such nuclear plants IN ONE YEAR.

    This article is what I’m referring to.
    A Decade Of Wind, Solar, & Nuclear In China Shows Clear Scalability Winners

    “China’s natural experiment in deploying low-carbon energy generation shows that wind and solar are the clear winners.”

    • John Oneill Says:

      72 GW of solar is in no way equivalent to 21 one-gigawatt nuclear reactors. The solar will provide power during the day, so coal will be kept around for nightfall. Even more so in winter, solar output wil suffer from short days, cloudy weather, and snow on the panels, while demand is highest. The smog from those busy coal plants will wreck the health of those living nearby, and not do the already low capacity factors of solar any good. Beijing smog is a result of low wind during winter, so wind turbines won’t be helping much then, either. In contrast, nuclear, when well run, has a 90 % capacity factor, but refuelling is timed for spring or autumn, so you can probably count on 100% – slightly more, even, since colder water in the heat sink increases efficiency. To sweeten the deal, that waste heat can be diverted to district heating, putting even more coal out of business. The Chinese have built four American-designed AP-1000 reactors (in much less time than the pair being built in Georgia, let alone the failed project in South Carolina.) The two plants near Haiyang city, in Shandong province, have been hooked up to the city’s district heating system, displacing coal. In summer, waste heat has also been proposed for desalination and hydrogen production.

      • sailrick Says:

        “72 GW of solar is in no way equivalent to 21 one-gigawatt nuclear reactors. The solar will provide power during the day”

        That’s why I used capacity factors to compare them, and adjust for the intermittency of solar and wind power.
        And you are not considering energy storage to firm up renewables.

        • John Oneill Says:

          China’s electricity production totalled 757,850 GWh in Dec 2022. That’s an average of 1000 GW (dividing by 31 days and 24 hours). Maximum demand is usually somewhere between 50 and 100% higher than the average – in fact, the country’s total generating capacity is over 2,500 GW, of which about 750GW are wind and solar.
          It’s just over a year since China commissioned the word’s largest pumped storage facility, with 3.6 GW output, and 40 GWh capacity.

          So for only about the equivalent of 6,000/40 = 150 times the storage capacity of Fengning pumped storage station, the Chinese could maybe get through four hours power of an evening – then cross their fingers that the wind would blow next day, to recharge all those dams. They could use batteries instead, but batteries are still much more expensive, and don’t last nearly as long.

          • sailrick Says:

            What batteries don’t last long? There are many kinds of batteries for backup, some for longer duration back up, like flow batteries.
            China’s percent of electricity generated by solar and wind is just slightly less than for the U.S, about 10% versus 12% for the U.S. But they are scaling up solar and wind faster.
            And there are other non-battery energy storage solutions. Thermal, compressed air, liquid air, etc.

            World’s largest compressed air grid “batteries” will store up to 10GWh

            California is set to be home to two new compressed-air energy storage facilities – each claiming the crown for the world’s largest non-hydro energy storage system. Developed by Hydrostor, the facilities will have an output of 500 MW and be capable of storing 4 GWh of energy.


            Construction begins on the world’s biggest liquid air battery

            “The project near Manchester, U.K., will use spare green energy to compress air into a liquid and store it. When demand is higher, the liquid air is released back into a gas, powering a turbine that puts the green energy back into the grid.

            The new liquid air battery, being developed by Highview Power, is due to be operational in 2022 and will be able to power up to 200,000 homes for five hours, and store power for many weeks. …….. Highview is developing other sites in the U.K., continental Europe, and the U.S., including in Vermont, but the Manchester project will be the first.”


          • sailrick Says:

            Closed loop pumped hydro is capital intensive, but efficient and cheap to run once it’s built.
            I don’t know if the one in China you referred to is closed loop.

            Then there’s the potential for Vehicle to Grid, with EVs. (V2G) The first small V2G program in America is up and running in the New York grid.

            And when an EV needs a new battery, the old one is far from dead. It can be used by electric utilities for stationary grid backup.

            Battery Second Use for Plug-In Electric Vehicles


            All The Energy Storage The Grid Needs Will Soon Be Under Our Noses

            “The International Energy Agency’s most conservative estimate puts 130 million electric vehicles on the road by 2030, and Gorguinpour said those vehicles will contain almost ten times the amount of energy storage needed by the grid”


  5. Roger Walker Says:

    I’ve recently spent considerable time and energy ploughing through developments at Flamanville and Hinkley Point 2.

    All in all, it’s clear to me that nuclear power has no future in purely commercial terms. It cannot compete with renewables. It’s also clear that tax payers on both sides of the Channel are being shafted, especially in Britain where the bill will amount to hundreds of billions of pounds. Hundreds? Really? Well, yes – the gap between Strike Price and market price, determined by ever cheaper renewables, can only continue to grow, and that CfD is in place for 60 years! I have no idea how to calculate how much that works out at but hundreds of billions has to be in the right ball park. What I don’t understand is who gets the money and how. At first, I thought it must have to do with dividends, but that doesn’t make sense.

    As far as I can make out, EDF paid out about €2bn in dividends over the last five years. 80% of that went to the French treasury, which is also picking up the tab for at least 20bn – hardly an equitable exchange. If EDF is fully nationalized, the same argument holds. If EDF is re-privatized and if it goes on to make profits from Flamanville, it would be taxed in France and pay dividends to (some already rich) private investors (and to the French treasury which would certainly keep a sizeable stake). In the long term, then, the French might come out winners. But, as we’ve seen above, that is most unlikely.

    As for Hinkley (Hinkley/Sizewell?), if – miraculously – NNB survives and makes a profit, it has to ‘share’ that profit with the British treasury (does that mean it gets taxed?), and EDF’s share of that profit would presumably be subject to the same regime as for Flamanville. If not, the CfD comes into play and the British tax-payer is stuck with that horrendous bill – not forgetting the hundred billion or so already committed to cleaning up 17 other reactors, including the notorious Calder Hall (aka Windscale, aka Sellafield).

    Then there’s the time factor. All these scenarios play out over several decades of what promises to be an extraordinarily turbulent century. Who would bet their pension on the state of our already wobbly world and its financial institutions in 60 years’ time? Never mind 2338, the scheduled date for the end of the Hinkley Point C project.

    I cannot escape the conclusion that it’s all about vast sums of money. I’m even tempted to think there’s a tacit agreement between the super-rich and the governing classes to the effect that the plebs get screwed because… well, that’s what they’re there for.

  6. John Oneill Says:

    From the UK National Audit Office report on Hinkley Point C –
    ‘For HPC, NNBG will receive £92.50 (in 2012 prices) for each megawatt hour
    (MWh) of electricity from HPC that it sells into the market for 35 years. NNBG will receive top-up payments if the market price is lower, which are ultimately paid for by electricity bill-payers. Conversely, payments will flow in the opposite direction if wholesale prices rise above the strike price.’
    Recently, UK wholesale prices have risen well over 300 pounds per MWh, as high as 500. At that rate, Hinkley Point is a bargain, paying money back to the government and consumers. My brother and his wife recently returned from visiting another brother in Wales, and said they were cold the whole time they were there – power prices were so high, everyone was economising on heating their houses.
    I agree with some of the criticism of HPC – 9% rate of return for investors is far too high for such a long term asset, from a time when interest rates were rock bottom, and the EPR reactor design is unnecessarily complex. Instead of tying itself in knots to avoid investing in nuclear itself, while regulating and legislating the industry to death by a million paper cuts, the government should put skin in the game itself. A secure power system is as vital to society as a health system, or roads, or national defense.
    That said, HPC will make 7% of the UK’s power, no matter what the wind or the natural gas markets are doing. It’s training up hundreds of apprentices, who will be needed to replace the gas-cooled reactors currently producing about seventeen percent of the power, and that will need to be replaced within the decade. Unlike the gas-cooled reactors, it will last for sixty years or longer.

Leave a Reply

Please log in using one of these methods to post your comment: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: