European gas prices fall to pre-Ukraine war level

AI Load Forecasting for Utilities leverages machine learning, smart meters, and predictive analytics to balance energy demand during COVID-19 disruptions, optimize grid reliability, support demand response, and stabilize rates for residential and commercial customers.

Key Points

AI predicts utility demand with ML and smart meters to improve reliability and reduce costs.

✅ Adapts to rapid demand shifts with accurate short term forecasts

✅ Optimizes demand response and distributed energy resources

✅ Reduces outages risk while lowering procurement and operating costs

The spread of the novel coronavirus that causes COVID-19 has prompted state and local governments around the U.S. to institute shelter-in-place orders and business closures. As millions suddenly find themselves confined to their homes, the shift has strained not only internet service providers, streaming platforms, and online retailers, but the utilities supplying power to the nation’s electrical grid, which face longer, more frequent outages as well.

U.S. electricity use on March 27, 2020 was 3% lower than it was on March 27, 2019, a loss of about three years of sales growth. Peter Fox-Penner, director of the Boston University Institute for Sustainable Energy, asserted in a recent op-ed that utility revenues will suffer because providers are halting shutoffs and deferring rate increases. Moreover, according to research firm Wood Mackenzie, the rise in household electricity demand won’t offset reduced business electricity demand, mainly because residential demand makes up just 40% of the total demand across North America.

Some utilities are employing AI and machine learning for the energy transition to address the windfalls and fluctuations in energy usage resulting from COVID-19. Precise load forecasting could ensure that operations aren’t interrupted in the coming months, thereby preventing blackouts and brownouts. And they might also bolster the efficiency of utilities’ internal processes, leading to reduced prices and improved service long after the pandemic ends.

Innowatts
Innowatts, a startup developing an automated toolkit for energy monitoring and management, counts several major U.S. utility companies among its customers, including Portland General Electric, Gexa Energy, Avangrid, Arizona Public Service Electric, WGL, and Mega Energy. Its eUtility platform ingests data from over 34 million smart energy meters across 21 million customers in more than 13 regional energy markets, while its machine learning algorithms analyze the data to forecast short- and long-term loads, variances, weather sensitivity, and more.

Beyond these table-stakes predictions, Innowatts helps evaluate the effects of different rate configurations by mapping utilities’ rate structures against disaggregated cost models. It also produces cost curves for each customer that reveal the margin impacts on the wider business, and it validates the yield of products and cost of customer acquisition with models that learn the relationships between marketing efforts and customer behaviors (like real-time load).

Innowwatts told VentureBeat that it observed “dramatic” shifts in energy usage between the first and fourth weeks of March. In the Northeast, “non-essential” retailers like salons, clothing shops, and dry cleaners were using only 35% as much energy toward the end of the month (after shelter-in-place orders were enacted) versus the beginning of the month, while restaurants (excepting pizza chains) were using only 28%. In Texas, conversely, storage facilities were using 142% as much energy in the fourth week compared with the first.

Innowatts says that throughout these usage surges and declines, its clients took advantage of AI-based load forecasting to learn from short-term shocks and make timely adjustments. Within three days of shelter-in-place orders, the company said, its forecasting models were able to learn new consumption patterns and produce accurate forecasts, accounting for real-time changes.

Innowatts CEO Sid Sachdeva believes that if utility companies had not leveraged machine learning models, demand forecasts in mid-March would have seen variances of 10-20%, significantly impacting operations.

“During these turbulent times, AI-based load forecasting gives energy providers the ability to … develop informed, data-driven strategies for future success,” Sachdeva told VentureBeat. “With utilities and energy retailers seeing a once-in-a-lifetime 30%-plus drop in commercial energy consumption, accurate forecasting has never been more important. Without AI tools, utilities would see their forecasts swing wildly, leading to inaccuracies of 20% or more, placing an enormous strain on their operations and ultimately driving up costs for businesses and consumers.”

Autogrid
Autogrid works with over 50 customers in 10 countries — including Energy Australia, Florida Power & Light, and Southern California Edison — to deliver AI-informed power usage insights. Its platform makes 10 million predictions every 10 minutes and optimizes over 50 megawatts of power, which is enough to supply the average suburb.

Flex, the company’s flagship product, predicts and controls tens of thousands of energy resources from millions of customers by ingesting, storing, and managing petabytes of data from trillions of endpoints. Using a combination of data science, machine learning, and network optimization algorithms, Flex models both physics and customer behavior, automatically anticipating and adjusting for supply and demand patterns through virtual power plants that coordinate distributed assets.

Autogrid also offers a fully managed solution for integrating and utilizing end-customer installations of grid batteries and microgrids. Like Flex, it automatically aggregates, forecasts, and optimizes capacity from assets at sub-stations and transformers, reacting to distribution management needs while providing capacity to avoid capital investments in system upgrades.

Autogrid CEO Dr. Amit Narayan told VentureBeat that the COVID-19 crisis has heavily shifted daily power distribution in California, where it’s having a “significant” downward impact on hourly prices in the energy market. He says that Autogrid has also heard from customers about transformer failures in some regions due to overloaded circuits, which he expects will become a problem in heavily residential and saturated load areas during the summer months (as utilities prepare for blackouts across the U.S. when air conditioning usage goes up).

“In California, [as you’ll recall], more than a million residents faced wildfire prevention-related outages in PG&E territory in 2019,” Narayan said, referring to the controversial planned outages orchestrated by Pacific Gas & Electric last summer. “The demand continues to be high in 2020 in spite of the COVID-19 crisis, as residents prepare to keep the lights on and brace for a similar situation this summer. If a 2019 repeat happens again, it will be even more devastating, given the health crisis and difficulty in buying groceries.”

AI making a difference
AI and machine learning isn’t a silver bullet for the power grid — even with predictive tools at their disposal, utilities are beholden to a tumultuous demand curve and to mounting climate risks across the grid. But providers say they see evidence the tools are already helping to prevent the worst of the pandemic’s effects — chiefly by enabling them to better adjust to shifted daily and weekly power load profiles.

“The societal impact [of the pandemic] will continue to be felt — people may continue working remotely instead of going into the office, they may alter their commute times to avoid rush hour crowds, or may look to alternative modes of transportation,” Schneider Electric chief innovation officer Emmanuel Lagarrigue told VentureBeat. “All of this will impact the daily load curve, and that is where AI and automation can help us with maintenance, performance, and diagnostics within our homes, buildings, and in the grid.”

Related News

• Electricity Forum News

• Grid Technologies News

US Nuclear Generating Costs 2017 show USD33.50/MWh for nuclear energy, the lowest since 2008, as capital expenditures, fuel costs, and operating costs declined after license renewals and uprates, supporting a reliable, low-carbon grid.

Key Points

The 2017 US nuclear average was USD33.50/MWh, lowest since 2008, driven by reduced capital, fuel, and operating costs.

✅ Average cost USD33.50/MWh, lowest since 2008

✅ Capital, fuel, O&M costs fell sharply since 2012 peak

✅ License renewals, uprates, market reforms shape competitiveness

Average total generating costs for nuclear energy in 2017 in the USA were at their lowest since 2008, according to a study released by the Nuclear Energy Institute (NEI), amid a continuing nuclear decline debate in other regions.

The report, Nuclear Costs in Context, found that in 2017 the average total generating cost - which includes capital, fuel and operating costs - for nuclear energy was USD33.50 per megawatt-hour (MWh), even as interest in next-generation nuclear designs grows among stakeholders. This is 3.3% lower than in 2016 and more than 19% below 2012's peak. The reduction in costs since 2012 is due to a 40.8% reduction in capital expenditures, a 17.2% reduction in fuel costs and an 8.7% reduction in operating costs, the organisation said.

The year-on-year decline in capital costs over the past five years reflects the completion by most plants of efforts to prepare for operation beyond their initial 40-year licence. A few major items - a series of vessel head replacements; steam generator replacements and other upgrades as companies prepared for continued operation, and power uprates to increase output from existing plants - caused capital investment to increase to a peak in 2012. "As a result of these investments, 86 of the [USA's] 99 operating reactors in 2017 have received 20-year licence renewals and 92 of the operating reactors have been approved for uprates that have added over 7900 megawatts of electricity capacity. Capital spending on uprates and items necessary for operation beyond 40 years has moderated as most plants are completing these efforts," it says.

Since 2013, seven US nuclear reactors have shut down permanently, with the Three Mile Island debate highlighting wider policy questions, and another 12 have announced their permanent shutdown. The early closure for economic reasons of reliable nuclear plants with high capacity factors and relatively low generating costs will have long-term economic consequences, the report warns: replacement generating capacity, when needed, will produce more costly electricity, fewer jobs that will pay less, and, for net-zero emissions objectives, more pollution, it says.

NEI Vice President of Policy Development and Public Affairs John Kotek said the "hardworking men and women of the nuclear industry" had done an "amazing job" reducing costs through the institute's Delivering the Nuclear Promise campaign and other initiatives, in line with IAEA low-carbon lessons from the pandemic. "As we continue to face economic headwinds in markets which do not properly compensate nuclear plants, the industry has been doing its part to reduce costs to remain competitive," he said.

"Some things are in urgent need of change if we are to keep the nation's nuclear plants running and enjoy their contribution to a reliable, resilient and low-carbon grid. Namely, we need to put in place market reforms that fairly compensate nuclear similar to those already in place in New York, Illinois and other states," Kotek added.

Cost information in the study was collected by the Electric Utility Cost Group with prior years converted to 2017 dollars for accurate historical comparison.

Related News

• Electricity Forum News

• Power Generation News

Canada 100% Renewable Power by 2035 envisions a decentralized grid built on wind, solar, energy storage, and efficiency, delivering zero-emission, resilient, low-cost electricity while phasing out nuclear and gas to meet net-zero targets.

Key Points

Zero-emission, decentralized grid using wind, solar, and storage, plus efficiency, to retire fossil and nuclear by 2035.

✅ Scale wind and solar 18x with storage for reliability.

✅ Phase out nuclear and gas; no CCS or offsets needed.

✅ Modernize grids and codes; boost efficiency, jobs, and affordability.

A powerful derecho that left nearly a million people without power in Ontario and Quebec on May 21 was a reminder of the critical importance of electricity in our daily lives.

Canada’s electrical infrastructure could be more resilient to such events, while being carbon-emission free and provide low-cost electricity with a decentralized grid powered by 100 per cent renewable energy, according to a new study from the David Suzuki Foundation (DSF), a vision of an electric, connected and clean future if the country chooses.

This could be accomplished by 2035 by building a lot more solar and wind, despite indications that demand for solar electricity has lagged in Canada, adding energy storage, while increasing the energy efficiency in buildings, and modernizing provincial energy grids. As this happens, nuclear energy and gas power would be phased out. There would also be no need for carbon capture and storage nor carbon offsets, the modeling study concluded.

“Solar and wind are the cheapest sources of electricity generation in history,” said study co-author Stephen Thomas, a mechanical engineer and climate solutions policy analyst at the DSF.

“There are no technical barriers to reaching 100 per cent zero-emission electricity by 2035 nationwide,” Thomas told The Weather Network (TWN). However, there are considerable institutional and political barriers to be overcome, he said.

Other countries face similar barriers and many have found ways to reduce their emissions; for example, the U.S. grid's slow path to 100% renewables illustrates these challenges. There are enormous benefits including improved air quality and health, up to 75,000 new jobs annually, and lower electricity costs. Carbon emissions would be reduced by 200 million tons a year by 2050, just over one quarter of the reductions needed for Canada to meet its overall net zero target, the study stated.

Building a net-zero carbon electricity system by 2035 is a key part of Canada’s 2030 Emissions Reduction Plan. Currently over 80 per cent of the nation’s electricity comes from non-carbon sources including a 15 per cent contribution from nuclear, with solar capacity nearing a 5 GW milestone nationally. How the final 20 per cent will be emission-free is currently under discussion.

The Shifting Power study envisions an 18-fold increase in wind and solar energy, with the Prairie provinces expected to lead growth, along with a big increase in Canada’s electrical generation capacity to bridge the 20 per cent gap as well as replacing existing nuclear power.

The report does not see a future role for nuclear power due to the high costs of refurbishing existing plants, including the challenges with disposal of radioactive wastes and decommissioning plants at their end of life. As for the oft-proposed small modular nuclear reactors, their costs will likely “be much more costly than renewables,” according to the report.

There are no technical barriers to building a bigger, cleaner, and smarter electricity system, agrees Caroline Lee, co-author of the Canadian Climate Institute’s study on net-zero electricity, “The Big Switch” released in May. However, as Lee previously told TWN, there are substantial institutional and political barriers.

In many respects, the Shifting Power study is similar to Lee’s study except it phases out nuclear power, forecasts a reduction in hydro power generation, and does not require any carbon capture and storage, she told TWN. Those are replaced with a lot more wind generation and more storage capacity.

“There are strengths and weaknesses to both approaches. We can do either but need a wide debate on what kind of electricity system we want,” Lee said.

That debate has to happen immediately because there is an enormous amount of work to do. When it comes to energy infrastructure, nearly everything “we put in the ground has to be wind, solar, or storage” to meet the 2035 deadline, she said.

There is no path to net zero by 2050 without a zero-emissions electricity system well before that date. Here are some of the necessary steps the report provided:

Create a range of skills training programs for renewable energy construction and installation as well as building retrofits.

Prioritize energy efficiency and conservation across all sectors through regulations such as building codes.

Ensure communities and individuals are fully informed and can decide if they wish to benefit from hosting energy generation infrastructure.

Create a national energy poverty strategy to ensure affordable access.

Strong and clear federal and provincial rules for utilities that mandate zero-emission electricity by 2035.

For Indigenous communities, make sure ownership opportunities are available along with decision-making power.

Canada should move as fast as possible to 100 per cent renewable energy to gain the benefits of lower energy costs, less pollution, and reduced carbon emissions, says Stanford University engineer and energy expert Mark Jacobson.

“Canada has so many clean, renewable energy resources that it is one of the easier countries [that can] transition away from fossil fuels,” Jacobson told TWN.

For the past decade, Jacobson has been producing studies and technical reports on 100 per cent renewable energy, including a new one for Canada, even as Canada is often seen as a solar power laggard today. The Stanford report, A Solution to Global Warming, Air Pollution, and Energy Insecurity for Canada, says a 100 per cent transition by 2035 timeline is ideal. Where it differs from DSF’s Shifting Power report is that it envisions offshore wind and rooftop solar panels which the latter did not.

“Our report is very conservative. Much more is possible,” agrees Thomas.

“We’re lagging behind. Canadians really want to get going on building solutions and getting the benefits of a zero emissions electricity system.”

Related News

• Electricity Forum News

• Renewable Energy News

Greengen Misfeasance Ruling details a B.C. Supreme Court decision awarding $10.125 million over wrongfully denied Crown land and water licence permits for a Fries Creek run-of-river hydro project under a BC Hydro contract.

Key Points

A B.C. Supreme Court ruling awarding $10.125M for wrongful denial of Crown land and water licences on Greengen's project.

✅ $10.125M damages for misfeasance in public office

✅ Denial of Crown land tenure and water licence permits

✅ Tied to Fries Creek run-of-river and BC Hydro EPA

A B.C. Supreme Court judge has ordered the provincial government to pay $10.125 million after it denied permits to a company that wanted to build a run-of-the river independent power project near Squamish.

In his Oct. 10 decision, Justice Kevin Loo said the plaintiff, Greengen Holdings Ltd., “lost an opportunity to achieve a completed and profitable hydro-electric project” after government representatives wrongfully exercised their legal authority, a transgression described in the ruling as “misfeasance,” with separate concerns reflected in an Ontario market gaming investigation reported elsewhere.

Between 2003 and 2009, the company sought to develop a hydro-electric project on and around Fries Creek, which sits opposite the Brackendale neighbourhood on the other side of the Squamish River. To do so, Greengen Holdings Ltd. required a water licence from the Minister of the Environment and tenure over Crown land from the Minister of Agriculture.

After a lengthy process involving extensive communications between Greengen and various provincial and other ministries and regulatory agencies, the permits were denied, according to Loo. Both decisions cited impacts on Squamish Nation cultural sites that could not be mitigated.

Elsewhere, an Indigenous-owned project in James Bay proceeded despite repeated denials, underscoring varied approaches to community participation.

40-year electricity plan relied on Crown land
The case dates back to December 2005, when BC Hydro issued an open call for power with Greengen. The company submitted a tender several months later.

On July 26, 2006, BC Hydro awarded Greengen an energy purchase agreement, amid evolving LNG electricity demand across the province, under which Greengen would be entitled to supply electricity at a fixed price for 40 years.

Unlike conventional hydroelectric projects, such as new BC generating stations recently commissioned, which store large volumes of water in reservoirs, and in so doing flood large tracts of land, a run of the river project often requires little or no water storage. Instead, from a high elevation, they divert water from a stream or river channel.

Water is then sent into a pressured pipeline known as a penstock, and later passed through turbines to generate electricity, Loo explained, as utilities pursue long-term plans like the Hydro-Québec strategy to reduce fossil fuel reliance. The system returns water to the original stream or river, or into another body of water. 

The project called for most of that infrastructure to be built on Crown land, according to the ruling.

All sides seemed to support the project
In early 2005, company principle Terry Sonderhoff discussed the Fries Creek project in a preliminary meeting with Squamish Nation Chief Ian Campbell.

“Mr. Sonderhoff testified that Chief Campbell seemed supportive of the project at the time,” Loo said.

Related News

• Electricity Forum News

• Power Generation News

U.S. Russian Uranium Import Ban reshapes nuclear fuel supply, bolstering energy security, domestic enrichment, and sanctions policy while diversifying reactor-grade uranium sources and supply chains through allies, waivers, and funding to sustain utilities and reliability.

Key Points

A U.S. law halting Russian uranium imports to boost energy security diversify nuclear fuel and revive U.S. enrichment.

✅ Cuts Russian revenue; reduces geopolitical risk.

✅ Funds U.S. enrichment; supports reactor fuel supply.

✅ Enables waivers to prevent utility shutdowns.

In a move aimed at reducing reliance on Russia and fostering domestic energy security for the long term, the United States has banned imports of Russian uranium, a critical component of nuclear fuel. This decision, signed into law by President Biden in May 2024, marks a significant shift in the U.S. nuclear fuel supply chain and has far-reaching economic and geopolitical implications.

For decades, Russia has been a major supplier of enriched uranium, a processed form of uranium used to power nuclear reactors. The U.S. relies on Russia for roughly a quarter of its enriched uranium needs, feeding the nation's network of 94 nuclear reactors operated by utilities which generate nearly 20% of the country's electricity. This dependence has come under scrutiny in recent years, particularly following Russia's invasion of Ukraine.

The ban on Russian uranium is a multifaceted response. First and foremost, it aims to cripple a key revenue stream for the Russian government. Uranium exports are a significant source of income for Russia, and by severing this economic tie, the U.S. hopes to weaken Russia's financial capacity to wage war.

Second, the ban serves as a national energy security measure. Relying on a potentially hostile nation for such a critical resource creates vulnerabilities. The possibility of Russia disrupting uranium supplies, either through political pressure or in the event of a wider conflict, is a major concern. Diversifying the U.S. nuclear fuel supply chain mitigates this risk.

Third, the ban is intended to revitalize the domestic uranium mining and enrichment industry, building on earlier initiatives such as Trump's uranium order announced previously. The U.S. has historically been a major uranium producer, but environmental concerns and competition from cheaper foreign sources led to a decline in domestic production. The ban, coupled with $2.7 billion in federal funding allocated to expand domestic uranium enrichment capacity, aims to reverse this trend.

The transition away from Russian uranium won't be immediate. The law includes a grace period until mid-August 2024, and waivers can be granted to utilities facing potential shutdowns if alternative suppliers aren't readily available. Finding new sources of enriched uranium will require forging partnerships with other uranium-producing nations like Kazakhstan, Canada on minerals cooperation, and Australia.

The long-term success of this strategy hinges on several factors. First, successfully ramping up domestic uranium production will require overcoming regulatory hurdles and addressing environmental concerns, alongside nuclear innovation to modernize the fuel cycle. Second, securing reliable alternative suppliers at competitive prices is crucial, and supportive policy frameworks such as the Nuclear Innovation Act now in law can help. Finally, ensuring the continued safe and efficient operation of existing nuclear reactors is paramount.

The ban on Russian uranium is a bold move with significant economic and geopolitical implications. While challenges lie ahead, the potential benefits of a more secure and domestically sourced nuclear fuel supply chain are undeniable. The success of this initiative will be closely watched not only by the U.S. but also by other nations seeking to lessen their dependence on Russia for critical resources.

Related News

• Electricity Forum News

• Energy Policy News

Ontario Electricity COVID-19 Recovery Rate sets a fixed price of 12.8 cents/kWh, replacing time-of-use billing and aligning costs across off-peak, mid-peak, and on-peak periods per Ontario Energy Board guidance through Oct. 31.

Key Points

A flat 12.8 cents/kWh electricity price in Ontario that temporarily replaces time-of-use rates from June 1 to Oct. 31.

✅ Fixed 12.8 cents/kWh, all hours, June 1 to Oct. 31

✅ Higher than off-peak 10.1, lower than mid/on-peak

✅ Based on Ontario Energy Board average cost

Ontario residents will now have to pay a fixed electricity price that is higher than the off-peak hydro rate many in the province have been allowed to pay so far due to the pandemic. 

The announcement, which was made in a news release on Saturday, comes after the Ontario government suspended the normal “time-of-use” billing system on March 24 and as electricity rates are about to change across Ontario. 

The government moved all customers onto the lowest winter rate in response to the pandemic as emergency measures meant more people would be at home during the middle of the day when electricity costs are the highest. 

Now, the government has introduced a new “COVID-19 recovery rate” of 12.8 cents per kilowatt hour at all times of the day. The fixed price will be in place from June 1 to Oct. 31. 

The fixed price is higher than the winter off-peak price, which stood at 10.1 per kilowatt hour. However, it is lower than the mid-peak rate of 14.4 per kilowatt hour and the high-peak rate of 20.8 per kilowatt hour, even though typical bills may rise as fixed pricing ends for many households. 

“Since March 24, 2020, we have invested just over $175 million to deliver emergency rate relief to residential, farm and small business electricity consumers by suspending time-of-use electricity pricing,” Greg Rickford, the minister of energy, northern development and mines, said in a news release. 

“This investment was made to protect the people of Ontario from a marked increase in electricity rates as they did their part by staying home to prevent the further spread of the virus.”

Rickford said that the COVID-19 recovery rate is based on the average cost of electricity set by the Ontario Energy Board. 

“This fixed rate will continue to suspend time-of-use prices in a fiscally responsible manner,” he said. "Consumers will have greater flexibility to use electricity when they need it without paying on-peak and mid-peak prices, and some may benefit from ultra-low electricity rates under new time-of-use options."

Related News

• Electricity Forum News

• Energy Policy News