AI Transforming Transmission Line Ratings in the Post-FERC Order 881 Era

The Federal Energy Regulatory Commission (FERC) Order 881 has ushered in a new era in the energy world. It represents a profound shift in how we perceive and manage transmission line ratings. In this blog, I will delve into the significance of the order, its challenges, and the pivotal role that artificial intelligence plays in reshaping the energy industry.

FERC Order 881 — A New Dawn for Transmission Line Ratings:

At its core, the order requires transitioning from traditional static to the dynamic concept of ambient-adjusted ratings (AARs) for transmission lines. Its objective is to improve line ratings’ accuracy and adaptability in an ever-evolving energy landscape.

Order №881 concluded that relying on conservative assumptions regarding worst-case, long-term air temperature, and other weather conditions for line ratings can underutilize the transmission grid. As a result, mandating the use of AARs by all transmission providers will optimize grid utilization, reduce curtailment, and contribute to consumer cost savings.

Amidst this transformative shift, it’s essential to mention the concept of Dynamic Line Ratings (DLRs) as a significant precursor. The Commission clarified that adopting DLR can identify instances where flow reductions are necessary to ensure safe and dependable grid operation while preventing undue strain on transmission equipment. DLRs are real-time assessments of line capacity, accounting for variables like wind, weather, and conductor temperature. They served as an important stepping stone towards dynamic rating systems.

One of the critical benefits of DLR is its ability to accommodate the variable output of renewable energy sources, such as wind and solar. These sources are highly dependent on weather conditions and can experience fluctuations in generation. DLR helps mitigate curtailment by allowing transmission lines to carry more electricity during high renewable energy production periods. That means that excess renewable energy can be efficiently transported to where it is needed most, reducing the need to curtail generation when there is no available capacity on the grid.

Moreover, DLR enhances grid reliability by preventing overloading of transmission lines during peak demand periods. Operating lines closer to their capacity based on real-time conditions reduces the risk of line failures and power outages. That improves grid stability and minimizes the need for curtailment as a preventive measure to avoid grid instability.

In addition to reducing curtailment, DLR offers cost savings by optimizing the utilization of existing infrastructure. It can defer the need for expensive transmission line upgrades or expansions, which can be financially and environmentally costly.

In a recent publication from MIT titled “Exploring the Impacts of Dynamic Line Ratings on the ERCOT Transmission System,” researchers investigated the potential advantages of incorporating DLR by comparing it to AAR and Static Line Ratings (SLR) within a simulated Electric Reliability Council of Texas (ERCOT) grid. The study holds significant relevance when our power grid faces the challenge of accommodating an additional 47,000 GW miles of transmission infrastructure by 2035. Furthermore, the interconnection queue is expanding, with over 2 Terawatts of total generation and storage capacity currently seeking connection to the grid, with more than 95% of this capacity attributed to zero-carbon resources such as solar, wind, and battery storage.

The study utilized simulations for SLR, AAR, and DLR implementations, revealing significant cost reductions. While SLR costs $10.3 billion annually, AAR and DLR lowered expenses. AAR reduced costs by 35%, saving $356 million, while DLR achieved a remarkable 77% cost reduction, saving $776 million, mainly due to decreased congestion expenses.

Furthermore, the study highlighted the crucial role of DLRs in facilitating renewable energy integration into the grid. Given the variability and unpredictability of renewable generation, DLR can effectively manage transmission capacity, reducing the need to curtail renewable resources. Additionally, the research showed that AAR adoption in ERCOT could enable an extra dispatch of 160 MW of solar and 800 MW of wind. In contrast, introducing DLR led to an even more substantial increase, with 360 MW of solar and 2.25 terawatts of wind. Implementing DLR would avoid 2.83 million metric tons of CO2 emissions in this context.

AI’s Impact on the Grid:

Artificial Intelligence wields transformative power when processing vast volumes of real-time data with unparalleled speed and precision. In the context of the power grid, AI algorithms are poised to revolutionize how we handle temperature data and make real-time adjustments to line ratings, providing an elegant solution to the intricate challenge of implementing Dynamic Line Rating.

AI’s potential benefits to this arena are nothing short of extraordinary. Here’s a glimpse of what we stand to gain by harnessing AI’s capabilities for power grid management:

• Enhanced Grid Resilience: AI fortifies the grid’s resilience through real-time line rating adjustments. It acts as a vigilant guardian, preventing overheating and mitigating the risk of line failures, power outages, and costly equipment damage.
• Optimized Grid Capacity: AI doesn’t just crunch numbers; it optimizes the use of existing grid infrastructure by dynamically adjusting line ratings. That means we can ramp up capacity utilization without the immediate need for costly physical upgrades, translating into significant cost savings.
• Improved Grid Efficiency: AI’s Real-time temperature-driven line rating adjustments translate into enhanced grid efficiency. Minimizing transmission and distribution losses reduces energy wastage, lowering operational costs.
• Integration of Renewable Energy: Renewable energy sources like solar and wind are often at the mercy of weather conditions. AI’s real-time line rating adjustments enable seamless integration of these sources. When the weather shifts, so does the grid, ensuring a stable power supply.
• Cost Savings: AI-driven line rating adjustments empower utilities to make data-driven decisions, avoiding premature equipment replacements or unnecessary grid expansions. Investment in infrastructure upgrades becomes judicious and precisely timed.
• Enhanced Grid Safety: Beyond optimizing efficiency, AI contributes to grid safety by averting the overheating of power lines. That reduces the risk of wildfires, often triggered by overheated power lines, and safeguards the grid and surrounding environment.
• Accurate Load Forecasting: AI algorithms don’t just focus on real-time data; they delve into historical temperature and load data to provide precise load forecasting. This invaluable capability helps utilities plan for peak demand periods, ensuring a reliable power supply even during extreme weather conditions.
• Compliance with Environmental Regulations: AI’s real-time adjustments align perfectly with environmental regulations. Minimizing the likelihood of grid failures and their associated ecological hazards aids utilities in complying with stringent environmental standards.
• Data-Driven Decision-Making: AI’s rapid temperature and operational data processing give grid operators actionable insights. This data-driven approach empowers decision-makers to navigate the complex intricacies of grid management with precision and confidence.
• Scalability and Adaptability: The beauty of AI systems lies in their adaptability. They can effortlessly adjust to evolving grid conditions and accommodate the ever-changing landscape of technology and energy demand. This scalability is the bedrock of a resilient, future-ready grid.

The Importance of Testing AI-Powered Technology in Utility Companies

Testing AI-powered technology before implementation is of paramount importance for utility companies. This process is crucial in evaluating the technology’s suitability for their specific needs. It allows for a comprehensive assessment of the AI system’s performance, ensuring it can effectively address the unique challenges and requirements within the utility sector.

Furthermore, working with companies that allow their solutions to be trialed before implementation is precious. It provides an opportunity to thoroughly test the technology in a real-world context, helping utility companies make informed decisions about its viability and fit for their operations. This collaborative approach fosters a deeper understanding of how the AI solution can be customized and fine-tuned to align with the utility company’s goals, ensuring a more tailored and effective implementation.

Additionally, this testing phase helps mitigate risk by identifying potential issues, operational disruptions, or inaccuracies in a controlled environment, enabling companies to take preemptive measures. It also aids in evaluating data compatibility, operational integration, and cost-benefit analysis, providing valuable insights into the technology’s feasibility and return on investment. Moreover, testing ensures regulatory compliance, facilitates employee training, and gathers user feedback, ultimately contributing to a smoother and more successful adoption of AI-powered solutions in the utility industry.

Bridging the Gap — AI’s Contribution to a Smarter Grid:

AI acts as the bridge between traditional and ambient-adjusted line ratings. It fills the gap in achieving a brighter, more efficient grid. AI is transforming how we approach transmission line ratings by improving grid efficiency and enabling smarter energy management.

Numerous case studies and success stories demonstrate AI’s capabilities in action. From predicting line failures to optimizing energy flow, AI is revolutionizing the industry, one algorithm at a time.

For example, a utility organization aiming to minimize or eliminate the curtailment of renewable energy due to transmission congestion can rely on a digital automation scheme that monitors various grid variables in real time and can directly manage assets in case of failure. Some of our customers at Splight have doubled their transmission capacity and eliminated between 90% to 100% of renewable energy curtailments by implementing our AI-powered controls for the grid.

Looking Ahead: The Promise of AI in a Post-FERC Order 881 World:

FERC Order 881 is a pivotal moment in the energy industry, signifying a profound shift in managing and optimizing our power grids. The successful implementation of this order is propelled by the incredible potential of AI, which empowers us to harness data-driven insights and adapt transmission line ratings in real-time.

As we navigate this transformative era in energy, staying well-informed and actively engaging with the ongoing developments becomes more critical than ever. On October 5th, Splight will be speaking on the webinar “FERC Order 881: Leveraging AI to improve the accuracy of transmission line ratings” hosted by Logic2020, where we will delve deeper into the influence of AI on transmission line ratings, exploring the innovative solutions and strategies that are shaping the future of the energy sector. You can sign up to attend it here.

About the author:

With two decades of leadership in the energy industry, Fernando Llaver set out to transform the electric sector, emphasizing cutting-edge technology and the scalability of clean energy solutions. His comprehensive knowledge spanning project finance, executive roles, and grid operations equips him with a distinct vantage point. That enables him to meticulously optimize Splight’s technology, ensuring it meets the flexible interconnection demands of power generators and optimizes the efficiency of transmission and distribution networks.