Governor Sebelius vetoes coal plant measure

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

Wisconsin Solar and Wind Energy advances as rooftop solar, utility-scale farms, and NREL perovskite solar cells improve efficiency; wind turbines gain via wake modeling, yaw control, and grid-scale battery storage to cut carbon emissions.

Key Points

It is Wisconsin's growth in rooftop and utility-scale solar plus optimized wind turbines to cut carbon emissions.

✅ Perovskite solar cells promise higher efficiency, need longevity

✅ Wake modeling and yaw control optimize wind farm output

✅ Batteries and bids can offset reliance on natural gas

Solar energy in Wisconsin continued to grow in 2019, as more homeowners had rooftop panels installed and big utilities started building multi-panel solar farms.

Wind power is increasing more slowly in the state. However, renewable power developers are again coming forward with proposals for multiple turbines.

Nationally, researchers are working on ways to get even more energy from solar and wind, with the U.S. moving toward 30% electricity from wind and solar in coming years, as states like Wisconsin aim to reduce their carbon emissions over the next few decades.

One reason solar energy is growing in Wisconsin is due to the silicon panels becoming more efficient. But scientists haven't finished trying to improve panel efficiency. The National Renewable Energy Laboratory (NREL) in Golden, Col., is one of the research facilities experimenting with brushing a lab-made solution called perovskite onto a portion of a panel called a solar cell.

In a demonstration video supplied by NREL, senior scientist Maikel van Hest said that, in the lab anyway, the painted cell and its electrical connections called contacts, produce more energy:

"There you go! That's how you paint a perovskite solar cell. And you imagine that ultimately what you could do is you could see a company come in with a truck in front of your house and they would basically paint on the contacts first, dry those, and paint the perovskite over it. That you would have photovoltaic cells on the side of your house, put protective coating on it, and we're done."

Another NREL scientist, David Moore, says the new solar cells could be made faster and help meet what's expected to be a growing global demand for energy. However, Moore says the problem has been lack of stability.

"A solar cell with perovskites will last a couple years. We need to get that to 20-25 years, and that's the big forefront in perovskite research, is getting them to last longer," Moore told members of the Society of Environmental Journalists during a recent tour of NREL.

Another part of improving renewable energy is making wind turbines more productive. At NREL's Insight Center, a large screen showing energy model simulations dominates an otherwise darkened room. Visualization scientist Nicholas Brunhart-Lupo points to a display on the screen that shows how spinning turbines at one edge of a wind farm can cause an airflow called a wake, which curtails the power generation of other turbines.

"So what we find in these simulations is these four turbines back here, since they have this used air, this low-velocity wake being blown to their faces, they're only generating about 20% of the energy they should be generating," he explains.

Brunhart-Lupo says the simulations can help wind farm developers with placement of turbines as well as adjustments to the rotor and blades called the yaw system.

Continued progress with renewables may be vital to any state or national pledges to reduce use of fossil fuels and carbon emissions linked to climate change, including Biden's solar expansion plan as a potential pathway. Some scientists say to limit a rise in global temperature, there must be a big decline in emissions by 2050.

But even utilities that say they support use of more renewables, as why the grid isn't 100% renewable yet makes clear, aren't ready to let go of some energy sources. Jonathan Adelman of Xcel Energy, which serves part of Western Wisconsin, says Xcel is on track to close its last two coal-fired power plants in Minnesota. But he says the company will need more natural gas plants, even though they wouldn't run as often.

"It's not perfect. And it is in conflict with our ultimate goal of being carbon-free," says Adelman. "But if we want to facilitate the transition, we still need resources to help that happen."

Some in the solar industry would like utilities that say they need more natural gas plants to put out competitive bids to see what else might be possible. Solar advocates also note that in some states, energy regulators still favor the utilities.

Meanwhile, solar slowly marches ahead, including here in southeastern Wisconsin, as Germany's solar power boost underscores global momentum.

On the roof of a ranch-style home in River Hills, a work crew from the major solar firm Sunrun recently installed mounting brackets for solar panels.

Sunrun Public Policy Director Amy Heart says she supports research into more efficient renewables. But she says another innovation may have to come in the way regulators think.

"Instead of allowing and thinking about from the perspective of the utility builds the power plant, they replace one plant with another one, they invest in the infrastructure; is really thinking about how can these distributed solutions like rooftop solar, peer-to-peer energy sharing, and especially rooftop solar paired with batteries how can that actually reduce some of what the utility needs?

Large-scale energy storage batteries are already being used in some limited cases. But energy researchers continue to make improvements to them, too, with cheap solar batteries beginning to make widespread adoption more feasible as scientists race to reduce the expected additional harm of climate change.

Related News

• Electricity Forum News

• Renewable Energy News

Manitoba Hydro 3.5 Percent Rate Increase proposes a smaller electricity rate hike under Public Utilities Board oversight to bolster financial reserves, address debt and Bipole III costs, amid shifting export sales and water flow conditions.

Key Points

It is Manitoba Hydro's proposed 3.5% electricity rate hike for 2019-20 to shore up finances under PUB oversight.

✅ PUB review sought without lengthy hearing

✅ Revenue boost forecast at 59 million dollars

✅ Natural gas rates flat; class shifts adjust bills

Manitoba Hydro is scaling back its rate hike request for next year, instead of the annual 7.9 per cent hikes the Crown corporation previously said it would need until 2023-24 to address debt. 

Hydro is asking the Public Utilities Board for a 3.5 per cent rate increase next year, which would take effect on April 1.

In last week's application, Hydro said its new board is reviewing the corporation's financial picture. Once that is complete, the utility expects to submit a new multi-year rate plan in late 2019 that addresses the organization's long-term future.

"It's too speculative at this point to discuss any possible future rate increases," spokesperson Bruce Owen said in an email.

The proposed increase next year is similar to other jurisdictions and nearly in line with the Public Utilities Board's decision to allow an average 3.6 per cent jump in electricity rates in 2018-19, which began this summer.

"The requested 3.5 per cent rate increase … generates a modest level of net income under average water flow conditions that will assist in gradually building the revenue base and reduce the risk of the corporation incurring a loss" in 2019-20, the rate application said.

If approved, consumers would face their second rate increase from Hydro in under a year.

Crown Services Minister Colleen Mayer said she's sympathetic to customers bracing for another rate increase amid NL rate hike concerns that far exceeds the rate of inflation.

"I hear that, very clearly," she said. "The NDP left us with an insurmountable problem — we're trying to fix that."

Hydro goes to court over special rate class for First Nations residents in Manitoba

National Energy Board OK's Manitoba-Minnesota Transmission Project

Next year's rate increase is projected to bring in $59 million of revenue, boosting the Crown corporation's financial reserves by $31 million.

Without it, the utility would deal with a net loss, it said.

This time, Hydro officials are asking PUB to forgo a rate hearing, suggesting neither itself nor the board has the resources for a lengthy six- to nine-month process to review an application where not much has changed financially and would generate a "minimum level of net income," Hydro said in a letter to the board.

The short-term rate relief, the letter recommends, should be "awarded in a timely and cost-effective manner, recognizing that the corporation's long-term financial forecasts will be finalized and available for review" in late 2019.

Hydro's net income next year will be lower than projected, the rate application said, due to a reduction in export sales and increases in depreciation and financing costs from Bipole III.

"Even though they had a total implosion of their previous board, on this very issue, they haven't learned lessons and they continue to be cheerleaders for these rapid rate increases," Kinew said, referring to the exodus of every board member but one earlier this year.

Manitoba Hydro's burgeoning debt surpasses $19 billion

On natural gas, Manitoba Hydro is asking PUB for no rate increase for the next two years.

There will, however, be some changes in rates in different customer classes, Owen said, resulting in modest rate reductions for mainly residential customers and increases for customers who use a lot of natural gas.

The corporation also wants to stop collecting fees to support the furnace replacement program. The initiative will continue with existing fees.

Related News

• Electricity Forum News

• Energy Policy News

Inventoried Energy Program pays ISO-NE generators for fuel security to boost winter reliability, with FERC approval, covering fossil, nuclear, hydropower, and batteries, complementing capacity markets to enhance grid resilience during severe cold snaps.

Key Points

ISO-NE program paying generators to hold fuel or energy reserves for emergencies, boosting winter reliability.

✅ FERC-approved stopgap for 2023 and 2024 winter seasons

✅ Pays for on-site fuel or stored energy during cold-trigger events

✅ Open to fossil, nuclear, hydro, batteries; limited gas participation

Electricity ratepayers in New England will pay tens of millions of dollars to fossil fuel and nuclear power plants later this decade under a program that proponents say is needed to keep the lights on during severe winters but which critics call a subsidy with little benefit to consumers or the grid, even as Connecticut is pushing a market overhaul across the region.

Last week the Federal Energy Regulatory Commission said ISO-New England, which runs the six-state power grid, can create what it calls the Inventoried Energy Program or IEP. This basically will pay certain power plants to stockpile of fuel for use in emergencies during two upcoming winters as longer-term solutions are developed.

The federal commission called it a reasonable short-term solution to avoid brownouts which doesn’t favor any given technology.

Not all agree, however, including FERC Commissioner Richard Glick, who wrote a fiery dissent to the other three commissioners.

“The program will hand out tens of millions of dollars to nuclear, coal and hydropower generators without any indication that those payments will cause the slightest change in those generators’ behavior,” Glick wrote. “Handing out money for nothing is a windfall, not a just and reasonable rate.”

The program is the latest reaction by ISO-NE to the winter of 2013-14 when New England almost saw brownouts because of a shortage of natural gas to create electricity during a pair of week-long deep freezes.

ISO-New England says the situation is more critical now because of the possible retirement of the gas-fired Mystic Generating Station in Massachusetts. As with closed nuclear plants such as Vermont Yankee and Pilgrim in Massachusetts, power plant owners say lower electricity prices, partly due to cheap renewables and partly to stagnant demand, means they can’t be profitable just by selling power.

Programs like the IEP are meant to subsidize such plants – “incentivize” is the industry term – even though some argue there is no need to subsidize nuclear in deregulated markets so they’ll stay open if they are needed.

The IEP approved last week will be applied to the winters of 2023 and 2024, after a different subsidy program expires. It sets prices, despite warnings about rushing pricing changes from industry groups, for stocking certain amounts of fuel and payments during any “trigger” event, defined as a day when the average of high and low temperatures at Bradley International Airport in Connecticut is no more than 17 degrees Fahrenheit.

These payments will be made on top of a complex system of grid auctions used to decide how much various plants get paid for generating electricity at which times.

ISO-NE estimates the new program will cost between $102 million and $148 million each winter, depending on weather and market conditions.

It says the payments are open to plants that burn oil, coal, nuclear fuel, wood chips or trash; utility-scale battery storage facilities; and hydropower dams “that store water in a pond or reservoir.” Natural gas plants can participate if they guarantee to have fuel available, but that seems less likely because of winter heating contracts.

A major complaint and groups that filed petitions opposing the project is that ISO-NE presented little supporting evidence of how prices, amount and overall cost were determined. ISO-NE argued that there wasn’t time for such analysis before the Mystic shutdown, and FERC agreed.

“The proposal is a step in the right direction … while ISO-NE finishes developing a long-term market solution,” the commission said in its ruling.

The program is the latest example of complexities facing the nation’s electricity system evolves in the face of solar and wind power, which produce electricity so cheaply that they can render traditional power uneconomic but which can’t always produce power on demand, prompting discussions of Texas grid improvements among policymakers. Another major factor is climate change, which has increased the pressure to support renewable alternatives to plants that burn fossil fuels, as well as stagnant electricity demand caused by increased efficiency.

Opponents, including many environmental groups, say electricity utilities and regulators are too quick to prop up existing systems, as the 145-mile Maine transmission line debate shows, built when electricity was sent one way from a few big plants to many customers. They argue that to combat climate change as well as limit cost, the emphasis must be on developing “non-wire alternatives” such as smart systems for controlling demand, in order to take advantage of the current system in which electricity goes two ways, such as from rooftop solar back into the grid.

Related News

• Electricity Forum News

• Energy Policy News

Electric Field-Induced Glass Softening reveals a Joule heating anomaly in silicate glass, where anode-side nanoscale alkali depletion drives ionic conduction, localized thermal runaway, melting, and evaporation, challenging homogeneity assumptions and refining materials processing models.

Key Points

An effect where electric fields lower glass softening temperature via nanoscale ionic migration and structural change.

✅ Anode-side alkali depletion creates extreme, localized heating

✅ Thermal runaway melts glass near the anode despite uniform bulk

✅ Findings refine Joule heating models and enable new glass processing

A team of scientists working with electrical currents and silicate glass have been left gobsmacked after the glass appeared to defy a basic physical law, in a field that also explores electricity-from-air devices for novel energy harvesting.

If you pass an electrical current through a material, the way that current generates heat can be described by Joule's first law. It's been observed time and time again, with the temperature always evenly distributed when the material is homogeneous (or uniform).

But not in this recent experiment. A section - and only a section - of silicate glass became so hot that it melted, and even evaporated. Moreover, it did so at a much lower temperature than the boiling point of the material.

The boiling point of pure silicate glass is 2,230 degrees Celsius (4,046 degrees Fahrenheit). The hottest temperature the researchers recorded in a homogeneous piece of silicate glass during the experiment was 1,868.7 degrees Celsius.

Say whaaaat.

"The calculations did not add up to explain what we were seeing as simply standard Joule heating," said engineer and materials scientist Himanshu Jain of Lehigh University.

"Even under very moderate conditions, we observed fumes of glass that would require thousands of degrees higher temperature than Joule's law could predict!"

Jain and his colleagues from materials science company Corning Incorporated were investigating a phenomenon they had described in a previous paper. In 2015, they reported that an electric field could reduce the temperature at which glass softens, by as much as a few hundred degrees, a line of inquiry that parallels work on low-cost heat-to-electricity materials in energy research. They called this "electric field-induced softening."

It was certainly a peculiar phenomenon, so they set up another experiment. They put pieces of glass in a furnace, and applied 100 to 200 volts in the form of both alternating and direct currents.

Next, a thin wisp of vapour emanated from the spot where the anode conveying the current contacted the glass.

"In our experiments, the glass became more than a thousand degrees Celsius hotter near the positive side than in the rest of the glass, which was very surprising considering that the glass was totally homogeneous to begin with," Jain said.

This seems to fly in the face of Joule's first law, so the team investigated more closely - and found that the glass wasn't remaining as homogeneous as it started out. The electric field changed the chemistry and the structure of the glass on nanoscale, in just a small section close to the anode.

This region heats faster than the rest of the glass, to the point of becoming a thermal runaway - where an increase in temperature further increases temperature in a blistering feedback loop.

As it turned out, that spot of structural change and dramatic heat resulted in a small area of glass reaching melting point while the rest of the material remained solid.

"Unlike electronically conducting metals and semiconductors, with time the heating of ionically conducting glass becomes extremely inhomogeneous with the formation of a nanoscale alkali-depletion region, such that the glass melts near the anode, even evaporates, while remaining solid elsewhere," the researchers wrote in their paper.

In other words, the material wasn't homogeneous any more, which means the glass heating experiment doesn't exactly change how we apply Joule's first law.

But it's an exciting result, since until now we didn't know a material could actually lose its homogeneity with the application of an electrical current, with possible implications for thin-film heat harvesters in electronics. (The thing is, no one had tried electrically heating glass to these extreme temperatures before.)

So the physical laws of the Universe are still okay, as a piece of glass hasn't broken them. But Joule's first law may need a bit of tweaking to take this effect into account, a reminder that unconventional energy concepts like nighttime solar cells also challenge our intuitions.

And, of course, it's another piece of understanding that could help us in other ways too, including advances in thermoelectric materials that turn waste heat into electricity.

"Besides demonstrating the need to qualify Joule's law," Jain said, "the results are critical to developing new technology for the fabrication and manufacturing of glass and ceramic materials."

The research has been published in Scientific Reports.

Related News

• Electricity Forum News

• Power Generation News

GE Wind Turbine Collapse Brazil raises safety concerns at Omega Energia's Delta VI wind farm in Maranhe3o, with GE Renewable Energy probing root-cause of turbine failure after a worker injury and similar incidents in 2024.

Key Points

An SEO focus on the Brazil GE turbine collapse, its causes, safety investigation, and related 2024 incidents.

✅ Incident at Omega Energia's Delta VI, Maranhao; one worker injured

✅ GE Renewable Energy conducts root-cause investigation and containment

✅ Fifth GE turbine collapse in 2024 across Brazil and the United States

A GE Renewable Energy turbine collapsed at a wind farm in north-east Brazil, injuring a worker and sparking a probe into the fifth such incident this year, the manufacturer confirmed.

One of the manufacturer’s GE 2.72-116 turbines collapsed at Omega Energia’s Delta VI project in Maranhão, which was commissioned in 2018.

Three GE employees were on site at the time of the collapse on Tuesday (3 September), the US manufacturer confirmed, even as U.S. offshore wind developers signal growing competitiveness with gas. 

One worker was injured and is currently receiving medical treatment, GE added.

"We are working to determine the root cause of this incident and to provide proper support as needed," it said

The turbine collapse in Brazil is the fifth such incident involving GE turbines this year, even as the UK's biggest offshore windfarm begins power supply this week, underscoring broader sector momentum.

On 16 February, a turbine collapsed at NextEra Energy Resources’ Casa Mesa wind farm in New Mexico, US, while giant wind components were being transported to a project in Saskatchewan, Canada. The site uses GE’s 2.3-116 and 2.5-127 models.

The New Mexico incident was followed by another collapse in the US — as a Scottish North Sea wind farm resumed construction after Covid-19 — this time a GE 2.4-107 unit at Tradewind Energy’s Chisholm View 2 project in Oklahoma on 21 May.

Two GE turbines then collapsed at projects in July: a 2.5-116 unit at Invenergy’s Upstreamwind farm in Nebraska on 5 July, followed by a 1.7-103 model at the Actis Group-owned Ventos de São Clemente complex in Pernambuco, north-eastern Brazil, even as tidal power in Scotland generated enough electricity to power nearly 4,000 homes.

No employees were injured in the first four turbine collapses of the year, in contrast with concerns at a Hawaii geothermal plant over potential meltdown risk.

In response to the latest incident, GE Renewable Energy added: "It is too early to speculate about the root cause of this week’s turbine collapse.

"Based on our learnings from the previous turbine collapses, we have teams in place focused on containing and resolving these issues quickly, to ensure the safe and reliable operation of our turbines."

Related News

• Electricity Forum News

• Power Generation News