Machine learning is revolutionizing the integration of renewable energy sources into power grids, boosting stability and efficiency. As the world races towards achieving a net-zero future, renewable energy sources like solar and wind power are emerging as crucial players in the fight against climate change. However, the transition from traditional synchronous generators to inverter-based renewable energy systems poses a challenge to grid stability due to low inertia.
Xingpeng Li, an assistant professor of electrical and computer engineering at the University of Houston, has received a National Science Foundation CAREER Award for his innovative solution. His project, Frequency-Constrained Energy Scheduling for Renewable-Dominated Low-Inertia Power Systems, aims to seamlessly integrate renewable energy sources into the power grid while maintaining stability and reliability. Inertia, which is the kinetic energy stored in rotating generators, plays a vital role in ensuring system stability, especially during disruptions.
With the increasing penetration of wind and solar power in the grid, the need to maximize their use while reducing reliance on traditional generators becomes crucial. Li’s research team is leveraging machine learning to develop dynamic performance models that will enhance the scheduling of generating resources for efficient and stable grid operations. By merging machine learning and optimization models, they aim to ensure grid stability while supporting the growing share of renewable energy sources.
In addition to his groundbreaking research, Li is also focused on inspiring future generations to pursue careers in power engineering. His team is developing an open-source tool for the research community and creating a new course called Applied Machine Learning in Power Systems to educate students on advanced concepts. By bridging the gap between machine learning and power systems, Li hopes to address the workforce needs in the rapidly evolving energy sector.
Li’s work extends beyond academia, with a focus on energy security, transition, and transmission in both onshore and offshore energy systems. His research at the Renewable Power Grid Lab at UH aims to promote renewable energy integration and improve the efficiency and security of energy systems. With a commitment to advancing net-zero energy systems, Li’s contributions are shaping the future of sustainable power grids.
Having garnered multiple awards and recognition for his research, Li continues to make significant strides in the field of power engineering. His expertise and dedication to advancing clean energy technologies highlight the importance of innovative solutions in transitioning towards a sustainable energy future. Li’s holistic approach to grid integration, research, and education underscores the critical role of machine learning in shaping the future of power systems.
