Transmission congestion across PJM reached approximately $444 million in August 2026, continuing to demonstrate the significant economic impact of bottlenecks across North America’s largest electricity market.

E-REDES in Portugal completed a year-long assessment of Dynamic Line Rating solutions and published its findings in CIRED conference proceedings in June 2026. The assessment included a validation of Gridraven’s dynamic line ratings against conductor temperature measurements on a 60 kV distribution overhead line.

Transmission congestion across PJM remained elevated in June, resulting in $777.8 million in congestion costs. While down from the exceptional $1.0 billion recorded during May's heatwave, congestion continued to affect major transmission corridors across Pennsylvania, Maryland, Northern Virginia and New Jersey.

France suffered a major power outage as temperatures spiked to 44 degrees Celsius, and grid operators across the continent fired up gas power plants to keep powering air conditioning units.

The release comes as PJM congestion costs rose from approximately $1.8 billion in 2024 to $3.2 billion in 2025, highlighting growing pressure on the grid as electricity demand rises from data centers, industrial load growth and electrification.

The U.S. transmission system needs to at least double by 2050 to keep up with growing electricity demand, according to the Department of Energy. That means building roughly 5,000 miles of new high-capacity transmission lines each year.

As Europe pushes ahead on offshore wind amid project delays and political debates, most of the talk has focused on wind turbines. But, there’s a quieter wind story unfolding on the grid itself.

So, after Part 3, I was deep in the ERCOT data mines. The data is huge, but it is also a mess. The constraint names are just cryptic strings like "HARGRO_TWINBU1_1". No coordinates, no topology, just text.

After doing the PJM analysis, I was asked if it’s possible to do a similar thing in ERCOT since they also share a huge amount of data and use AAR.

After my first experiment (Harwood–Susquehanna 230kV DLR prediction) I’ve been digging deep into the 2025 PJM market data, and the numbers are staggering.

Gridraven is a small, highly efficient team working toward a clear goal: accelerating affordable and clean energy globally. Efficiency, in our case, isn’t about doing more with less, it’s about doing the right things with clarity and ownership.

I was looking at the US grid map and had a random idea. Can Gridraven Claw accurately predict the rating of a line where we have zero internal data and the operator is not using our solution?

We just shipped something our on-premise customers have been asking for: MSSQL support in Gridraven Claw. MSSQL is the default database in energy grid operations, and now, Claw on-premise installations can be made with either the Postgres or MSSQL database.

Gridraven’s new study on a key transmission line in south-central Texas shows that grid congestion raised power prices this summer — and that sensorless dynamic line rating (DLR) could have saved ratepayers $2–3 million, potentially up to $10 million, between May and August. Scaled statewide, the same AI-driven approach could cut into Texas’ $2 billion annual congestion costs.

System Operators face the challenge of balancing grid reliability with the increasing integration of renewable energy and fluctuating demand. Dynamic Line Rating (DLR) offers a transformative solution by leveraging hyper-local weather forecasts to optimize power line capacity in real-time and during planning. Unlike traditional static or seasonal ratings, which rely on conservative assumptions, DLR uses accurate weather data to calculate line ampacity dynamically, enabling System Operators to maximize grid efficiency. This post explores how DLR can be integrated into System Operator operations and planning, drawing on practical implementation strategies.

Gridraven and AST are piloting sensorless DLR in Latvia

Gridraven started a research project financed by the European Space Agency investigating the potential of satellite-derived DEMs in improving wind forecasts.

We can operate smarter with software-based operational intelligence to reduce curtailment, ease congestion and lower consumer costs.

Estonian energy tech startup moves to Texas, aims to boost electric grid. Gridraven's software helps lower power prices by optimizing grid capacity

Dynamic Line Ratings (DLR) promise to boost capacity, support load growth and reduce power prices. Yet, despite years of hype, DLR adoption remains limited. Why? Legacy solutions are plagued by inaccuracies, high costs, and slow deployment. At Gridraven, we have solved this with our breakthrough AI-based approach that's accrate, scalable, and ready to deploy today.

We’ve all been stuck in traffic—crawling along a highway, wondering why everything’s at a standstill. Now imagine this: what if traffic lights, speed limits, and lane access were all set based on the worst weather in history? A summer storm from five years ago. A snowy day from 2011. That’s exactly how we run our electricity grids.

Energy tech company Gridraven has won a public tender by Finnish TSO Fingrid to deploy dynamic line rating (DLR) across the country’s high-voltage transmission network.

Gridraven, the energy tech company redefining grid intelligence, won a public tender by Fingrid, Finland’s national transmission system operator, to deploy Dynamic Line Rating (DLR) across the country’s high-voltage transmission network.

Gridraven is participating in a DLR pilot with E-REDES in Portugal

The U.S. almost flunked a critical energy exam. Last week, the American Society of Civil Engineers (ASCE) rated America’s energy infrastructure a D+, down from a C- in 2021. This alarming grade should be a wake-up call for the industry.

Among the many conversations I’ve had the past few weeks in Houston around CERAWeek and at DISTRIBUTECH in Dallas, a consistent theme has emerged: electricity prices are surging, and geopolitical shifts are complicating energy security.

If power lines could better account for actual weather conditions, they would be able to transmit more electricity. Henri Manninen co-founded the technology company Gridraven, which specifically enhances electricity transmission capacity.

Our CEO, Georg Rute, recently wrote an op-ed for POWER magazine, talking about the power grid's actual potential and sharing his thoughts on how Gridraven can help solve the pressing issue of growing global energy needs.

Imagine unlocking 30% more power from our existing grid overnight. That’s the potential we’re ignoring, and it’s costing us billions.

From bitter cold and flash flooding to wildfire threats, last week brought extreme weather to Texas, leading to concerns about the reliability of its grid. Since the winter freeze of 2021, the state’s leaders and lawmakers have more urgently wrestled with how to strengthen the resilience of the grid while also supporting immense load growth.

A smarter, more efficient energy future starts with the right people. At Gridraven, we bring together experts from different fields, all working toward the goal of helping solve the global energy bottlenecks.

The Raven is our quarterly magazine, delivering insights on DLR, machine learning, and the technology shaping the future of energy. Published in print and online, it brings news, expert takes, and real-world impact—fast, clear, and always ahead of the curve.

Gridraven, whose AI-driven Dynamic Line Rating technology addresses grid bottlenecks and unlocks up to 30% more grid capacity annually, proudly announces its official expansion into the United States with the registration of Gridraven Inc. This strategic move underscores the company’s commitment to scaling operations and serving a growing international clientele.

Establishing a presence in the United States is a crucial step in our expansion. Electricity consumption in the US is rising rapidly due to economic development, electrification, and AI data centers. However, the grid is becoming overwhelmed and struggling to keep up with this demand, as building a new transmission line takes a decade.

The energy industry stands at a pivotal crossroads. With increasing demands for renewable energy integration and grid optimization, the sector is buzzing with innovation. In recent months, media outlets worldwide have spotlighted one transformative technology: Dynamic Line Rating (DLR). Let's delve into the latest topics, trends, and innovations as seen in the media, shaping the energy landscape and highlighting the critical role DLR plays in this evolution.

Henri and I attended CEATI's annual transmission and distribution conference in Palm Springs, California, this November. CEATI is one of the main power industry networks where utility engineers produce technical reports and guidance documents. During the event there are engineering working groups, parallel conference-style presentations, as well as an exhibition floor.

Gridraven's machine learning model improves wind speed forecast accuracy by 50% in the Golden State compared to the existing large scale numerical weather predictions. These improvements are fully leveraged in our software-based Dynamic Line Rating solution, leading to increased safety and efficiency in grid operations.

Gridraven’s 2024 has been a year of growth, learning, and validating our technology, but most importantly, it has set the stage for scaling up in 2025.

By harnessing machine learning and cutting-edge technology, Gridraven is optimizing energy infrastructure, increasing transmission line capacity, and paving the way for a more efficient energy future. Our Co-Founder and CTO's story underscores the importance of interdisciplinary collaboration and innovation in reshaping the global energy landscape.

We brought together experts from Estonia’s energy sector to discuss electricity prices in Estonia and nearby, what drives them, and how they can be reduced. The expert panel featured Ignitis Estonia CEO Timo Tatar, Member of the Management Board and Chief Development Officer at Enefit Green Andres Maasing, Baltic Energy Partners CEO Marko Allikson, and Professor Ivo Palu, moderated by Gridraven's CEO, Georg Rute.

Power grids are under pressure. Electricity demand is rising, yet infrastructure expansion is slow and costly. The good news? We don’t always need more power lines—we just need to use the ones we have more efficiently. Dynamic Line Rating (DLR) makes this possible by adjusting transmission capacity in real-time. But for DLR to work, we need highly accurate wind forecasts at the exact location of power lines. That’s where Gridraven’s machine learning (ML) model comes in.

Geospatial data science is an ever-evolving field that merges the complexity of environmental data with the power of technology. My journey began with a fascination for Earth Sciences and a newfound love for coding, and it has since grown into a full-fledged passion for transforming raw datasets into actionable insights. From my first steps at Planet OS to tackling real-world challenges at Gridraven, I’ve learned that working with geospatial data is equal parts puzzle-solving, perseverance, and impact-making. In this post, I’ll share how coding and data science have shaped my career and why geospatial insights are key to optimizing energy systems and building a greener future.

As the demand for energy grows, so does the need for a power grid capable of adapting to unpredictable weather and increased load without extensive new infrastructure. Markus Lippus and the team at GridRaven are rethinking grid potential through advanced AI solutions, using machine learning to unlock real-time flexibility in power transmission. By integrating environmental data with predictive models, they’re enabling the grid to safely handle more power when conditions allow—helping accelerate the shift toward sustainable energy while reducing costs and congestion.

Gridraven is working with Elering, the Estonian TSO, on a full-network DLR pilot covering 5500 km of 110 kV and 330 kV lines.

Introducing three key members who drive our projects forward: Eneli Toodu, Sten Buldas, and Juri Krainjukov.

GridRaven continues to grow, attracting top talent with a shared vision for a cleaner, smarter energy future.

Accurately predicting wind speed and direction is critical for grid operation. GridRaven has shown an improvement in accuracy from its machine learning weather model that makes it possible to roll out fully sensorless Dynamic Line Ratings on entire networks.

A quarter of 330 kV lines limit transmission capacity between Estonia and Latvia. Further, within each of those lines, nearly every span of each line might be limiting at some point in time. Dynamic Line Ratings need to cover a quarter of all spans in the network to maximize transmission capacity.

Safety is the number one concern for all transmission service providers. Unfortunately accidents do happen despite the best efforts to prevent them. One of the factors that contributes to accidents is the fact that transmission lines may dangerously overheat on hot, sunny, windless days. Accurate wind forecasting helps reduce this risk.

James Pearman, our data science intern, explores the inner workings of the deep learning models for downscaling wind. The model accounts with local features in the landscape one after the other, increasing or decreasing wind speeds in a 'white box' manner. Features of the terrain as well as air pressure appear to have the greatest effects on wind speed.

We are happy to welcome Mari and Ingvar to the team! Mari joins as our Senior Power Systems Expert and Ingvar joins as a Data Scientist.

GridRaven is accepted into the European Space Agency Business Incubator. During the year-long programme we'll collaborate with space experts to leverage satellite data for improving weather forecasting models.

FERC's intention with Ambient Adjusted Ratings is to increase grid capacity. However, a gain in capacity is not always guaranteed. Utilities have been optimizing their grids for decades and may have been knowingly using optimistic assumptions in the past. Dynamic Line Ratings are a more customized solution, helping increase capacity and maintain safety.

Gridraven's IEEE article on wind prediction with machine learning

Just like the proverbial chain an entire transmission line can be limited by its weakest link. But identifying the weakest link is not trivial, since it depends on the weather. Dynamic Line Rating solutions must account with the wind in each span individually.

The cost of grid congestion in Texas in 2022 was $3 billion. But much of this congestion is artificial and comes from outdated line rating methods. Dynamic Line Ratings increase capacity by a third on average, helping bring down energy prices for consumers. But as the example of a power line near San Antonio shows, there are also many hours in a year when line ratings should be reduced for safety reasons.

GridRaven and the Estonian Environment Agency, which is responsible for weather forecasting, have signed a cooperation agreement aimed at exploring the potential of machine learning for downscaling wind predictions.

It takes increasingly longer for new energy projects to connect to the grid. Already, 3,000GW of renewable capacity is awaiting a grid connection, which would double the world's renewable capacity. Making better use of the existing grid would enable more clean power projects to connect to the grid quicker.

GridRaven has been awarded €1.5 million by Enterprise Estonia. This funding will support hiring eight people into our technical team in Tallinn who will further refine our ML wind prediction and the digital twin of the grid.

We validated our prediction accuracy against measurements from Estonia's official weather stations. Grid Raven's machine learning model improves wind speed forecast accuracy by 39% compared to the existing forecast. Higher accuracy leads to increased safety and efficiency in Dynamic Line Rating applications.

Increasing grid capacity reduces the price of energy, but only if this additional capacity is available for tomorrow, in step with energy markets. DLR forecasting is required to reduce prices for consumers and accelerate the energy transition.

Power grids are starting to become a bottleneck in the transition to clean energy. Dynamic Line Rating (DLR) is a mature technology that can unlock up to 30% more capacity from the existing grid. Grid Raven is improving Dynamic Line Rating (DLR) technology by making it more accurate, resilient and scalable.