Best Innovation Award
Lingxiao Yang
School of Artificial Intelligence, Anhui University, China
The Best Innovation Award article presents an academic overview of Lingxiao Yang, a researcher whose work integrates machine learning, artificial intelligence, and modern power systems to address emerging challenges in renewable energy, microgrids, and intelligent distribution networks. Her scholarly activities emphasize data-driven decision making, digital twin technologies, diffusion probabilistic models, and sustainable energy management while contributing to reliable and low-carbon electricity infrastructures.[1]
Abstract
Lingxiao Yang obtained her bachelor’s degree from Henan Normal University before completing master’s and doctoral studies at Northeastern University, Shenyang. She currently serves as a postdoctoral research scholar at Anhui University. Her research combines artificial intelligence with electrical engineering to improve state estimation, carbon flow analysis, renewable integration, and intelligent energy management. The interdisciplinary nature of her work reflects contemporary advances in engineering and sustainable power systems.[2]
Keywords
Machine Learning; Digital Twin; Power Systems; Microgrids; Energy Internet; Renewable Energy; Distribution Networks; Carbon Flow; Deep Reinforcement Learning; Artificial Intelligence.
Introduction
Modern electrical infrastructure increasingly depends upon intelligent algorithms capable of interpreting complex operational data. Yang’s research explores physics-informed machine learning, graph-based modeling, and probabilistic diffusion methods to enhance monitoring accuracy and operational reliability within renewable-integrated power systems. These studies align with global efforts toward digital transformation and carbon neutrality.[3]
Research Profile
According to the supplied academic profile, the researcher has authored 102 indexed publications, accumulated 5,388 citations, and achieved an h-index of 24. Her investigations span intelligent power distribution, energy internet applications, explainable artificial intelligence, renewable integration, and computational optimization. These indicators demonstrate sustained scholarly productivity and research visibility across engineering disciplines.[1]
Research Contributions
Her contributions include diffusion-based state estimation, graph Laplacian source decomposition for carbon flow estimation, digital twin-guided monitoring frameworks, and interpretable deep reinforcement learning for community energy management. These approaches integrate physical constraints with advanced artificial intelligence techniques, supporting resilient and sustainable power distribution networks.[4]
Publications
- A fine estimation method of carbon flow in distribution networks based on conditional denoising diffusion implicit model and graph Laplacian source decomposition (2026).
- Digital Twin-Guided Multi-Source State Estimation via Physics-Constrained DDPM for Renewable-Integrated Distribution Networks (2026).
- Power system state estimation using denoising diffusion probability model data generation and multi-source data fusion (2026).
- Interpretable Hybrid Deep Reinforcement Learning-Based Energy Management in Low-Carbon Community Energy Systems (2026).
Research Impact
Yang’s research contributes to the advancement of intelligent energy infrastructures by combining machine learning with engineering knowledge. Applications include improved operational awareness, enhanced renewable integration, carbon accounting, and interpretable decision support for power distribution systems. These developments are relevant to sustainable infrastructure planning and next-generation smart grids.[5]
Award Suitability
Considering the documented publication record, citation metrics, interdisciplinary engineering research, and continued development of AI-enabled solutions for sustainable energy systems, the research profile demonstrates characteristics commonly associated with innovation-oriented academic recognition. Evaluation for the Best Innovation Award would appropriately consider originality, scientific contribution, publication quality, and broader engineering relevance.[6]
Conclusion
Lingxiao Yang’s academic portfolio illustrates the integration of artificial intelligence and electrical engineering to address practical challenges within renewable energy and smart power systems. Her contributions to diffusion modeling, digital twins, and intelligent energy management represent ongoing developments supporting efficient, reliable, and sustainable electrical infrastructures while maintaining a consistent scholarly publication record.
External Links
References
- Elsevier. (n.d.). Scopus author details: Lingxiao Yang, Author ID 55793872200.
https://www.scopus.com/authid/detail.uri?authorId=55793872200
- Yang, L. (2026). A fine estimation method of carbon flow in distribution networks.
https://doi.org/10.1016/j.segan.2026.102363
- Yang, L. (2026). Digital Twin-Guided Multi-Source State Estimation.
https://doi.org/10.3390/su18136877
- Yang, L. (2026). Power system state estimation using DDPM.
https://doi.org/10.1016/j.epsr.2025.112302
- Yang, L. (2026). Interpretable Hybrid Deep Reinforcement Learning-Based Energy Management.
https://doi.org/10.1109/TCSS.2026.3670031