Cong Chen: Advancing the Energy Transition through Computation & Collaboration

Cong Chen, assistant professor of engineering and faculty member in the Master of Energy Transition program is teaching Data Analytics for Energy & Climate this term. (Photo by Katie Lenhart)

For Cong Chen, assistant professor of engineering and faculty member in the Master of Energy Transition (MET) program, this convergence defines both her research and her teaching. Chen's research focuses on optimization, electricity market, power systems engineering, and AI agents, frequently blending fields and sectors to advance the energy transition. This term, she is teaching the MET course, Data Analytics for Energy & Climate (ENTR 140).

Bringing real-world data into the MET classroom

Chen's interdisciplinary approach is embedded in her MET course, where students are using real-world datasets to examine areas such as electricity load, electricity price fluctuations, and data center costs.

"It's like cooking—you have all of these ingredients—the raw data," Chen says. "You need to prepare it; you need to use the right mathematical model to understand and analyze the data. Finally, you get your dish. You can present this to your customer: this is data visualization."

The course equips MET students with the quantitative tools for careers across the energy landscape. Chen notes that roles in consulting, finance, engineering, data science, and policy all require a strong foundation in data analytics. By grounding analytics in real operational and market challenges, Chen connects classroom learning directly to industry relevance.

Modeling electricity market real-time pricing with AI agents

The same impact-driven focus Chen teaches in the classroom underpins her research, which centers on electricity market pricing under uncertainty, large-scale DER aggregation, energy storage integration in wholesale electricity markets, and the use of large language models (LLMs) to model energy consumer behavior.

In a recent paper co-authored with Kuang Xu and Omer Karaduman during her Stanford postdoctoral energy fellowship, Behavioral Generative Agents for Energy Operations, Chen investigates how LLMs can simulate energy customer responses to price signals and operational approaches.

She is a recipient of a 2025 Amazon Research Award, and is using the award resources to study storage and renewable integration in electricity market operations—particularly how computational tools can better account for uncertainty and human decision-making.

"In my current research, we ask AI agents powered by LLM to role-play energy customers," Chen explains. "Some may have rooftop solar, electric vehicles, or home batteries. How will they respond to dynamic prices? How will they operate the system? We use LLMs to simulate those decisions."

That work extends into the electricity market's real-time pricing challenges. Chen is also examining California's ongoing effort to integrate storage into its grid, which presents both financial and operational obstacles.

"They have many big batteries, charging and discharging in the real-time electricity market," she says. "Just like people buy stock at a low price and sell at a high price, people are buying electricity at a low price to charge the batteries and selling that stored electricity at a high price."

While the financial dynamics are straightforward, it's unclear how to integrate energy storage time-based dynamics with real-time power system and electricity market operations.

"We want to make sure a good real-time electricity price improves system efficiency and incentivizes storage adoption," she says. "So, we need a better algorithm to integrate storage in power systems and electricity market operations. To create a better algorithm, you need to understand battery physics and power grid physics."

Chen develops new real-time pricing methods to integrate storage in power systems and electricity market operations, using LLMs to simulate how customers respond under different price signals and incentive structures under uncertainty.

In Chen's course, students work with practical datasets related to electricity markets, power system operations, and climate. (Photo by Beam Lertbunnaphongs '25)

Optimizing grid interconnections, both small and large

Alongside utility-scale storage integration, households and businesses are increasingly integrating DERs with the grid, including rooftop solar, electric vehicles, and batteries. Chen is collaborating with Lijun Ding, a mathematician at the University of California San Diego, and her Thayer postdoctoral researcher, Bohang Fang, to address grid interconnection and operational challenges spurred by DERs.

"All those distributed small-scale resources can be aggregated as a virtual power plant in the power system," she notes, highlighting the potential for DERs to increase grid flexibility when customers are enabled to offload stored energy back to the grid. "But if they are not coordinated properly, they can also create imbalances and inefficiency in the power networks."

Chen's team is using computational models to design more efficient ways of connecting DERs to the grid.

The interconnection challenge spans small-scale technologies to large-load data centers. Across the US, many data centers have completed construction but face long wait times for grid interconnection due to transmission constraints and queue backlogs. Chen's team is studying these wait times and designing new approaches to calibrate power flow and accelerate the queuing process.

Industry engagement and interdisciplinary impact

Chen's work has been recognized by the IEEE Power and Energy Society (PES), which awarded her the 2025 IEEE PES Outstanding Doctoral Dissertation Award.

"The award confirmed that there is strong alignment between industry needs and research frontiers," Chen says.

Chen saw beneficial research-industry collaboration in her PhD internship with ISO New England, where doctoral students are paired with mentors to tackle real-world operational challenges. There, Chen was supported by her mentors from the Advanced Technology Solutions (ATS) department in proposing new methods and algorithms to improve grid operational efficiency.

Chen is an active member of the IEEE PES PSOPE—Power System Operation, Planning, and Economics Committee, where operations and economics researchers and industry practitioners examine electricity grid and market issues.

"We talk about emerging issues, such as resource adequacy, hydrogen integration, data centers, renewable energy, and storage," Chen explains. "With a task force, the knowledge is dynamic and growing; through discussion, we shape the direction of research and industry thinking."

Across her research, teaching, and industry engagement, Chen has observed growing alignment between interdisciplinary academic research and industry collaboration, and she shares gratitude for the support, suggestions, and feedback she has received from colleagues in both areas.

"People have a passion to push energy research forward. It can be difficult to communicate across interdisciplinary fields at first—it's like learning a new language—but with time, we can gain that ability," she says. "Collaboration is essential to designing better energy systems."

By bridging fields and sectors with her research and teaching, Chen is advancing practical solutions for a rapidly evolving grid while preparing MET students to lead with creativity and impact.