How advanced analytics and AI can save our grid from electric vehicle overload
Utility companies can leverage meter data and learning models to manage reliability.
Utility companies nationwide are facing an increased load on their circuits as more people choose to purchase and drive electric vehicles.
The already aging grid will continue to be tested as EV adoption is expected to grow from 4.5 million in 2023 to 78.5 million by 2035, according to a recent study from the Edison Electric Institute.
Several industry leaders have told Kforce that self-reporting of EV charging installations are likely only catching a small percentage of this growing population. And residential EV charging is projected to keep rising, due to factors such as lower cost of ownership and environmental impact.
To address this sharp increase in demand, utility companies must figure out how to accurately detect electric vehicles on the grid.
“If utilities are not proactive in detecting EVs on the distribution grid, they may find out too late that their circuits are overloaded,” said Steve Brown, energy and utilities industry principal for Kforce Consulting Solutions. “We’re hearing Distribution Operations leaders across the industry say that this is no longer a problem they can ignore.” For example, at an average of 7200 watt-hours per level 2 charger, it’s not hard to see how just a few chargers can threaten an already fully loaded 50 kVA transformer.
"When transformers are overloaded, the components can be damaged, leading to customer outages—which we're all trying hard to minimize," Brown said.
Utility leaders are looking to develop the strategy and technology expertise needed to properly detect electric vehicles. Advanced analytics and AI can solve this prevalent challenge, but only if the company’s data is ready.
“AI and advanced analytics have the power to transform EV detection, but without a strong data foundation, even the most sophisticated models will struggle to deliver real-world impact,” said Brad Boyd, Data and AI practice leader for Kforce Consulting Solutions. “Utility leaders should be prioritizing data readiness—ensuring completeness, governance and accessibility—before AI can truly drive operational intelligence and grid resilience.”
Leveraging advanced analytics and AI can unlock key insights, including learning which customers are attaching chargers, improving time-to-detection, increasing cost savings from load shifting, recognizing trends in attachment and identifying how many customers are charging during peak times.
“Discovering and studying these data points can help identify where enhancements are needed and how to influence customer behavior before catastrophic failure occurs,” Brown said. “Distribution leaders are learning there are a lot of benefits to this proactive approach.”
Ready to address the impact of electric vehicles on your power grid?
Connect with Steve Brown and the Kforce Consulting Solutions team to learn how data and AI solutions can drive operational intelligence and grid resilience. Talk with us today about finding the right path forward for your company.
Contact us
Contact us
Published MARCH 2025
Together Toward Tomorrow
Together Toward Tomorrow
Learn more
Learn more
Read how Kforce used AI to help an energy company enhance operational outcomes
What AI solution is best for your company?
What AI solution is best for your company?
Kforce survey: Quality and security dominate data and analytics concerns
Kforce survey: Quality and security dominate data and analytics concerns
Whitepaper: Preparing your organization for generative AI
Whitepaper: Preparing your organization for generative AI
Related content
representative customer consumption by behind-the-meter asset
Detection approaches and challenges
Identifying EV customers, especially those charging during peak times, allows the utility to conduct targeted campaigns to incentivize off-peak charging. This in turn helps companies manage both peak demand and the cost of power.
Utility companies have taken various approaches to detecting EVs, such as self-reporting and public vehicle registration data. The most reliable, and most generally actionable for utilities with automated meter infrastructure, is meter data.
With proper modeling and analysis techniques, utilities should be able to detect level 2 chargers at greater than 90% accuracy with 15-minute interval data.
However, it’s important to note that charging needs and frequency will vary by household, Brown said. Factors such as customer behaviors and car model can significantly impact charging activity.
Models will have to be sensitive to those variations, and a model that works well in one setting may not achieve the desired effectiveness in another.
Any model that attempts to interpret energy curves must account for events with a similar load profile. For example, large 220V appliances with sustained draw, such as a pool heater, can exhibit curves that might look similar to an EV charging cycle. It’s important to find signatures that fit an EV charging cycle, not just look for an amplitude spike.
A recent SEPA paper on this topic illustrates the varying usage spikes that can occur:
Challenges
Not all customers charge the same way. Companies that are leading in EV detection have shared that any detection work they do must account for variability in behavior.
This includes everything from lifestyle differences (remote vs on-site work) to classes of cars with unique charging characteristics (size of vehicle and battery pack).
Daily habits and lifestyle variances have big impacts on a charging curve. Some customers may only charge as soon as they return from work, resulting in a clear, sustained spike in usage. Others may charge at bedtime, which could push the charging curve across days even though it’s one charging event. Others may connect the charger every time they return home throughout the day, creating multiple random, and often short, charging cycles. Utility companies need to be prepared for all scenarios.
Behavioral Variability
Don’t fall into the fallacy of assuming a detection model that works well for a large urban area will work well for a smaller city or rural area. While still useful, they will likely be less effective.
Factors such as charging durations, times of day and predominant EV models may vary greatly by region.
“Each of these elements impacts a charging curve,” Brown said. “It is important to account for these variables and adapt the model to the local lifestyles and preferences of the service area.”
Location Variability
There are various approaches in the Data & AI world to address the challenges with false-positives, behavior variability and local variability.
Applying data & AI for improved detection
As previously described, false positives occur when energy spikes from non-EV sources trigger monitoring and detection algorithms. Data & AI capabilities can help prevent these scenarios by:
Identifying and extracting patterns such as ramp time, frequency of usage and charging duration. This identification will likely happen over the course of weeks/months based on the amount of charging a customer performs.
Ensuring similar load-heavy components and appliances have their characteristics and profiles accurately identified and provided to detection algorithms. Doing so allows for both positive and negative testing regarding EV detection.
Using deep learning models such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) to separate EV charging signals from other loads.
Reducing false positives
Energy usage varies significantly by user habits, charging frequency and time-of-day preferences. This makes pattern recognition more complex, and addressing behavioral variability can increase outcome confidence levels:
Develop user personas based on charging patterns—daily commuter, weekend charger, traveler, etc. Leverage unsupervised learning such as Graph Neural Networks (GNN) and Wavelet Transform Clustering and density-based spatial clustering (DBSCAN) to segment users into behavioral groups.
Implement adaptive machine learning models that adjust based on historical charging patterns. Apply long short-term memory (LSTM) or Bayesian Neural Networks (BNN) trained on energy consumption wavelets to identify and recognize trends. This also helps to address seasonal variations.
Implement a continuous learning pipeline that refreshes and retrains models with new data each month. Real-time feedback loops, such as opt-in confirmations, can be used to fine-tune false positive rates as it relates to behavior.
Addressing behavioral variability
There are significant variations in grid topology, infrastructure and regional EV adoption rates based on living locations—urban and rural, residential and commercial, and regulated and deregulated. Understanding this variability is crucial to appropriately interpreting analysis:
Build and train models separately based on geographic region to accommodate local grid conditions. Consider leveraging transfer learning to adapt pre-trained models to new regions or areas where limited data may be available.
Focus on integrating GIS data to build a spatial analytics layer that could be used to map EV charging density by area and circuit. This can then be overlayed with circuit configuration details to provide better overall capacity management.
Use interpretable ML models such as SHAP and LIME to explain why a charge event was classified as an EV session. This should enable utility teams to validate AI insights and adjust detection rules based on local variations.
Managing location variability
The pressure to invest in EV detection will only grow as EV buying trends continue. Utilities can benefit greatly by starting the foundational data and analytics projects that help them understand the impacts to the grid. By arming themselves with the right data and AI solutions, companies can stay ahead of the growth and ensure customer reliability.
“EV detection isn’t just about identifying charging patterns,” Boyd said. “It’s about building an adaptive, AI-driven energy grid that evolves with user behavior, market and regional trends.”
A recent SEPA paper
strong data foundation
study from the Edison Electric Institute
False positives
SPACE IN BETWEEN BUTTONS
SPACE IN BETWEEN MODULES/ Macros/ Sections
SPACE IN BETWEEN HEADER AND SUBHEAD + Subhead & Body
How to Optimize Your Professional Brand on LinkedIn
Stay Updated on Industry Trends with Twitter
How to Use Instagram During Your Job Search
Related articles
Connect with me
Steve Brown
MEET THE AUTHORS
Principal Industry Solutions
Connect with me
Brad Boyd
VP consulting solutions Data & AI
LET'S TALK CUSTOM SOLUTIONS
Contact us
Contact us
Learn more
Read how Kforce used AI to help an energy company enhance operational outcomes
Learn more