Berlin urged to remove barriers to PV

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

Ontario Electricity Demand 2020 shows a rare decline amid COVID-19, with higher residential peak load, lower commercial usage, hot-weather air conditioning, nuclear baseload constraints, and smart meter data shaping grid operations and forecasting.

Key Points

It refers to 2020 power use in Ontario: overall demand fell, while residential peaks rose and commercial loads dropped.

✅ Peak load shifted to homes; commercial usage declined.

✅ Hot summers raised peaks; overall annual demand still fell.

✅ Smart meters aid forecasting; grid must balance nuclear baseload.

Demand for electricity in Ontario last year fell to levels rarely seen in decades amid shifts in usage patterns caused by pandemic measures, with Ottawa’s electricity consumption dropping notably, new data show.

The decline came despite a hot summer that had people rushing to crank up the air conditioning at home, the province’s power management agency said, even as the government offered electricity relief to families and small businesses.

“We do have this very interesting shift in who’s using the energy,” said Chuck Farmer, senior director of power system planning with the Independent Electricity System Operator.

“Residential users are using more electricity at home than we thought they would and the commercial consumers are using less.”

The onset of the pandemic last March prompted stay-home orders, businesses to close, and a shuttering of live sports, entertainment and dining out. Social distancing and ongoing restrictions, even as the first wave ebbed and some measures eased, nevertheless persisted and kept many people home as summer took hold and morphed into winter, while the province prepared to extend disconnect moratoriums for residential customers.

System operator data show peak electricity demand rose during a hot summer spell to 24,446 megawatts _ the highest since 2013. Overall, however, Ontario electricity demand last year was the second lowest since 1988, the operator said.

In all, Ontario used 132.2 terawatt-hours of power in 2020, a decline of 2.9 per cent from 2019.

With more people at home during the lockdown, winter residential peak demand has climbed 13 per cent above pre-pandemic levels, even as Hydro One made no cut in peak rates for self-isolating customers, while summer peak usage was up 19 per cent.

“The peaks are getting higher than we would normally expect them to be and this was caused by residential customers _ they’re home when you wouldn’t expect them to be home,” Farmer said.

Matching supply and demand _ a key task of the system operator _ is critical to meeting peak usage and ensuring a stable grid, and the operator has contingency plans with some key staff locked down at work sites to maintain operations during COVID-19, because electricity cannot be stored easily. It is also difficult to quickly raise or lower the output from nuclear-powered generators, which account for the bulk of electricity in the province, as demand fluctuates.

READ MORE: Ontario government extends off-peak electricity rates to Feb. 22

Life patterns have long impacted overall usage. For example, demand used to typically climb around 10 p.m. each night as people tuned into national television newscasts. Livestreaming has flattened that bump, while more energy-efficient lighting led to a drop in provincial demand over the holiday season.

The pandemic has now prompted further intra-day shifts in usage. Fewer people are getting up in the morning and powering up at home before powering down and rushing off to work or school. The summer saw more use of air conditioners earlier than normal after-work patterns.

Weather has always been a key driver of demand for power, accounting for example for the record 27,005 megawatts of usage set on a brutally hot Aug. 1, 2006. Similarly, a mild winter and summer led to an overall power usage drop in 2017.

Still, the profound social changes prompted by the COVID-19 pandemic _ and whether some will be permanent _ have complicated demand forecasting.

“Work patterns used to be much more predictable,” the agency said. “The pandemic has now added another element of variability for electricity demand forecasting.”

Some employees sent home to work have returned to their offices and other workplaces, and many others are likely do so once the pandemic recedes. However, some larger companies have indicated that working from home will be long term.

“Companies like Facebook and Shopify have already stated their intention to make work from home a more permanent arrangement,” the operator said. “This is something our near-term forecasters would take into account when preparing for daily operation of the grid.”

Aggregated data from better smart meters, which show power usage throughout the day, is one method of improving forecasting accuracy, the operator said.

Related News

• Electricity Forum News

• Utility Operations News

Quebec Ice Storm 2025 disrupted power across Laurentians and Lanaudiere as freezing rain downed lines; Hydro-QuE9bec crews accelerated grid restoration, emergency response, and infrastructure resilience amid ongoing outages and severe weather alerts.

Key Points

Quebec Ice Storm 2025 brought freezing rain, outages, and grid damage, hitting Laurentians and Lanaudiere hardest.

✅ Peak: 62,000 Hydro-QuE9bec customers without electricity

✅ Most outages in Laurentians and Lanaudiere regions

✅ Crews repairing lines; restoration updates ongoing

A significant weather event struck Quebec in late March 2025, as a powerful ice storm caused widespread power outages across the province. The storm led to extensive power outages, affecting tens of thousands of residents, particularly in the Lanaudière and Laurentians regions. ​

Impact on Power Infrastructure

The freezing rain accumulated on power lines and vegetation, leading to numerous power outages across the network. Hydro-Québec reported that at its peak, over 62,000 customers were without electricity, with the majority of outages concentrated in the Laurentians and Lanaudière regions. By the afternoon, the number decreased to approximately 30,000, and further to just under 18,500 by late afternoon. 

Comparison with Previous Storms

While the March 2025 ice storm caused significant disruptions, it was less severe compared to the catastrophic ice storm of April 2023, which left 1.1 million Hydro-Québec customers without power. Nonetheless, the 2025 storm's impact was considerable, leading to the closure of municipal facilities and posing challenges for local economies, a pattern echoed when Toronto outages persisted for hundreds after a spring storm.

Ongoing Challenges

As of April 1, 2025, some areas continued to experience power outages, and incidents such as a manhole fire left thousands without service in separate cases. Hydro-Québec and municipal authorities worked diligently to restore services and address the aftermath of the storm, while Hydro One crews restored power to more than 277,000 customers after damaging storms in Ontario. Residents were advised to stay updated through official channels for restoration timelines and safety information.

Future Preparedness

The recurrence of such severe weather events highlights the importance of robust infrastructure and emergency preparedness, as seen in BC Hydro's storm response to an 'atypical' event that demanded extensive coordination. Both utility companies and residents must remain vigilant, especially during seasons prone to unpredictable weather patterns, with local utilities like Sudbury Hydro crews working to reconnect service after regional storms.

Related News

• Electricity Forum News

• Utility Operations News

Thermoelectric Materials convert waste heat into electricity via the Seebeck effect; quantum computations and semiconductors accelerate discovery, enabling clean energy, higher efficiency, and scalable heat-to-power conversion from abundant, non-toxic, cost-effective compounds.

Key Points

Thermoelectric materials turn waste heat into electricity via the Seebeck effect, improving energy efficiency.

✅ Convert waste heat to electricity via the Seebeck effect

✅ Quantum computations rapidly identify high-performance candidates

✅ Target efficient, low-thermal-conductivity, non-toxic, abundant compounds

The need to transition to clean energy is apparent, urgent and inescapable. We must limit Earth’s rising temperature to within 1.5 C to avoid the worst effects of climate change — an especially daunting challenge in the face of the steadily increasing global demand for energy and the need for reliable clean power, with concepts that can generate electricity at night now being explored worldwide.

Part of the answer is using energy more efficiently. More than 72 per cent of all energy produced worldwide is lost in the form of heat, and advances in turning thermal energy into electricity could recover some of it. For example, the engine in a car uses only about 30 per cent of the gasoline it burns to move the car. The remainder is dissipated as heat.

Recovering even a tiny fraction of that lost energy would have a tremendous impact on climate change. Thermoelectric materials, which convert wasted heat into useful electricity, can help, especially as researchers pursue low-cost heat-to-electricity materials for scalable deployment.

Until recently, the identification of these materials had been slow. My colleagues and I have used quantum computations — a computer-based modelling approach to predict materials’ properties — to speed up that process and identify more than 500 thermoelectric materials that could convert excess heat to electricity, and help improve energy efficiency.

Making great strides towards broad applications
The transformation of heat into electrical energy by thermoelectric materials is based on the “Seebeck effect.” In 1826, German physicist Thomas Johann Seebeck observed that exposing the ends of joined pieces of dissimilar metals to different temperatures generated a magnetic field, which was later recognized to be caused by an electric current.

Shortly after his discovery, metallic thermoelectric generators were fabricated to convert heat from gas burners into an electric current. But, as it turned out, metals exhibit only a low Seebeck effect — they are not very efficient at converting heat into electricity.

In 1929, the Russian scientist Abraham Ioffe revolutionized the field of thermoelectricity. He observed that semiconductors — materials whose ability to conduct electricity falls between that of metals (like copper) and insulators (like glass) — exhibit a significantly higher Seebeck effect than metals, boosting thermoelectric efficiency 40-fold, from 0.1 per cent to four per cent.

This discovery led to the development of the first widely used thermoelectric generator, the Russian lamp — a kerosene lamp that heated a thermoelectric material to power a radio.

Are we there yet?
Today, thermoelectric applications range from energy generation in space probes to cooling devices in portable refrigerators, and include emerging thin-film waste-heat harvesters for electronics as well. For example, space explorations are powered by radioisotope thermoelectric generators, converting the heat from naturally decaying plutonium into electricity. In the movie The Martian, for example, a box of plutonium saved the life of the character played by Matt Damon, by keeping him warm on Mars.

In the 2015 film, The Martian, astronaut Mark Watney (Matt Damon) digs up a buried thermoelectric generator to use the power source as a heater.

Despite this vast diversity of applications, wide-scale commercialization of thermoelectric materials is still limited by their low efficiency.

What’s holding them back? Two key factors must be considered: the conductive properties of the materials, and their ability to maintain a temperature difference, as seen in nighttime electricity from cold concepts, which makes it possible to generate electricity.

The best thermoelectric material would have the electronic properties of semiconductors and the poor heat conduction of glass. But this unique combination of properties is not found in naturally occurring materials. We have to engineer them, drawing on advances such as carbon nanotube energy harvesters to guide design choices.

Searching for a needle in a haystack
In the past decade, new strategies to engineer thermoelectric materials have emerged due to an enhanced understanding of their underlying physics. In a recent study in Nature Materials, researchers from Seoul National University, Aachen University and Northwestern University reported they had engineered a material called tin selenide with the highest thermoelectric performance to date, nearly twice that of 20 years ago. But it took them nearly a decade to optimize it.

To speed up the discovery process, my colleagues and I have used quantum calculations to search for new thermoelectric candidates with high efficiencies. We searched a database containing thousands of materials to look for those that would have high electronic qualities and low levels of heat conduction, based on their chemical and physical properties. These insights helped us find the best materials to synthesize and test, and calculate their thermoelectric efficiency.

We are almost at the point where thermoelectric materials can be widely applied, but first we need to develop much more efficient materials. With so many possibilities and variables, finding the way forward is like searching for a tiny needle in an enormous haystack.

Just as a metal detector can zero in on a needle in a haystack, quantum computations can accelerate the discovery of efficient thermoelectric materials. Such calculations can accurately predict electron and heat conduction (including the Seebeck effect) for thousands of materials and unveil the previously hidden and highly complex interactions between those properties, which can influence a material’s efficiency.

Large-scale applications will require themoelectric materials that are inexpensive, non-toxic and abundant. Lead and tellurium are found in today’s thermoelectric materials, but their cost and negative environmental impact make them good targets for replacement.

Quantum calculations can be applied in a way to search for specific sets of materials using parameters such as scarcity, cost and efficiency, and insights can even inform exploratory devices that generate electricity out of thin air in parallel fields. Although those calculations can reveal optimum thermoelectric materials, synthesizing the materials with the desired properties remains a challenge.

A multi-institutional effort involving government-run laboratories and universities in the United States, Canada and Europe has revealed more than 500 previously unexplored materials with high predicted thermoelectric efficiency. My colleagues and I are currently investigating the thermoelectric performance of those materials in experiments, and have already discovered new sources of high thermoelectric efficiency.

Those initial results strongly suggest that further quantum computations can pinpoint the most efficient combinations of materials to make clean energy from wasted heat and the avert the catastrophe that looms over our planet.

Related News

• Electricity Forum News

• Power Generation News

Middle Tennessee Power Outages disrupt 100,000+ customers as severe thunderstorms, straight-line winds, downed trees, and debris challenge Nashville crews, slow restoration amid COVID-19, and threaten more hail, flash flooding, and damaging gusts.

Key Points

Blackouts across Nashville after severe storms and winds, leaving customers without power and facing restoration delays.

✅ Straight-line winds 60-80 mph toppled trees and power lines

✅ 130,000+ customers impacted; some outages may last 1-2 weeks

✅ Restoration slowed by debris, COVID-19 protocols, and new storms

Some middle Tennessee residents could be without electricity for up to two weeks after strong thunderstorms swept through the area Sunday, knocking out power for more than 100,000 customers, a scale comparable to Los Angeles outages after a station fire.

"Straight line winds as high as 60-80 miles per hour knocked down trees, power lines and power polls, interrupting power to 130,000 of our 400,000+ customers," Nashville Electric said in a statement Monday. The utility said the outage was one of the largest on record, though Carolina power outages recently left a quarter-million without power as well.

"Restoration times will depend on individual circumstances. In some cases, power could be out for a week or two" as challenges related to coronavirus and the need for utilities adapt to climate change complicated crews' responses and more storms were expected, the statement said. "This is unfortunate timing on the heels of a tornado and as we deal with battling COVID-19."

Metropolitan Nashville and Davidson County Mayor John Cooper also noted that the power outages were especially inconvenient, a challenge similar to Hong Kong families without power during Typhoon Mangkhut, as people were largely staying home to slow the spread of coronavirus. He also pointed out that the storms came on the two month anniversary of the Nashville tornado that left at least two dozen people dead.

"Crews are working diligently to restore power and clear any debris in neighborhoods," Cooper said.

He said that no fatalities were reported in the county but sent condolences to Spring Hill, whose police department reported that firefighter Mitchell Earwood died during the storm due to "a tragic weather-related incident" while at his home and off duty. He had served with the fire department for 10 years.

The Metro Nashville Department of Public Works said it received reports of more than 80 downed trees in Davidson County.

Officials also warn that copper theft can be deadly when electrical infrastructure is damaged after storms.

The National Weather Service Nashville said a 72 mph wind gust was measured at Nashville International Airport — the fifth fastest on record.

The weather service warned that strong storms with winds of up to 75 mph, large hail, record-long lightning bolt potential seen in the U.S., and isolated flash flooding could hit middle Tennessee again Monday afternoon and night.

"Treat Severe Thunderstorm Warnings the same way you would Tornado Warnings and review storm safety tips before you JUST TAKE SHELTER," the NWS instructs. "70 mph is 70 mph whether it's spinning around in a circle or blowing in a straight line."

Related News

• Electricity Forum News

• Overhead T&D News

Texas Energy Policy Debate centers on ERCOT and PUC directives, fossil fuels vs renewables, grid reliability, energy efficiency, battery storage, and blackout risks, shaping Texas power market rules, conservation alerts, and capacity planning.

Key Points

Policy fight over ERCOT/PUC rules weighing fossil fuels vs renewables and storage to bolster Texas grid reliability.

✅ ERCOT and PUC directives under political scrutiny

✅ Fossil fuel subsidies vs renewable incentives and storage

✅ Focus on grid reliability, efficiency, and blackout prevention

Earlier this week, Governor Abbott released a letter to the Public Utility Commission of Texas (PUC) and the Electric Reliability Council of Texas (ERCOT), demanding electricity market reforms that Abbott falsely claims will "increase power generation capacity and to ensure the reliability of the Texas power grid."

Unfortunately, Abbott's letter promotes polluting, unreliable fossil fuels, attacks safer clean energy options, and ignores solutions that would actually benefit everyday Texans.

"Governor Abbott, in a blatant effort to politicize Texans' energy security, wants to double down on fossil fuels, even though they were the single largest point of failure during both February's blackouts and June's energy conservation alerts," said Cyrus Reed, Interim Director & Conservation Director of the Lone Star Chapter of the Sierra Club.

"Many of these so-called solutions were considered and rejected most recently by the Texas Legislature. Texas must focus on expanding clean and reliable renewable energy, energy efficiency, and storage capacity, as voters consider funding to modernize generation in the months ahead.

"We can little afford to repeat the same mistakes that have failed to provide enough electricity where it is needed most and cost Texans billions of dollars. Instead of advocating for evidence-based solutions, Abbott wants to be a culture warrior for coal and gas, even as he touts grid readiness amid election season, even when it results in blackouts across Texas."

Related News

• Electricity Forum News

• Energy Policy News