Statistical Relational AI for PV Multi-Timescale Uncertainty Modeling: Theory, Case Analysis, and Engineering Practice - Tapa dura

Acerca del autor

Xueqian Fu, PhD, is an Associate Professor with the College of Information and Electrical Engineering at the China Agricultural University. He has been recognized as one of the Stanford/Elsevier Top 2% Scientists (Career-long Impact) in the field of energy in both the 2024 and 2025 rankings. He is a IEEE Senior Member and currently serves as the Vice President of the IEEE Smart Village China Committee. He received his B.S. and M.S. degrees from North China Electric Power University in 2008 and 2011, respectively, and his Ph.D. degree from South China University of Technology in 2015. He was a Postdoctoral Researcher at Tsinghua University from 2015 to 2017. He serves as the Deputy Editor-in-Chief of Information Processing in Agriculture and is the founding chair of the IEEE International Symposium on the Application of Artificial Intelligence in Electrical Engineering (AAIEE).

De la contraportada

A unified framework for photovoltaic multi-timescale uncertainty modeling

Research on photovoltaic uncertainty remains fragmented: physical models lack interpretability, deep learning sacrifices generalizability, and no end-to-end solutions exist for real grid scenarios. Statistical Relational AI for PV Multi-Timescale Uncertainty Modeling: Theory, Case Analysis, and Engineering Practice delivers a unified framework integrating real-world PV power data with complete workflows for grid planning, operation, and uncertainty-aware decision-making.

The book systematically addresses how weather conditions, seasonal patterns, and time-of-day effects drive generation variability across multiple time scales. Case studies drawn from operational PV plants and real power system environments demonstrate a complete workflow from problem formulation through solution development. Practical datasets, executable code, and engineering examples show how proposed approaches translate into implementable solutions.

Readers will also find:

• Concrete implementation guidance for statistical relational AI methods applied to data organization, pattern discovery, and supporting analytical tasks
• Probabilistic techniques for quantifying PV output variability for stochastic optimization and electricity market operations
• A complete end-to-end technical pipeline spanning data acquisition, preprocessing, modeling, forecasting, and engineering deployment
• A structured perspective on future development trajectories for AI-driven photovoltaic uncertainty research and applications
• Solutions designed specifically for real PV grid scenarios rather than idealized or purely simulated environments

Designed for university faculty, academic researchers, power-system engineers, and graduate students, this book provides structured methodologies and reproducible tools for modeling PV uncertainty across time scales. Grid planners and renewable energy technology practitioners will also find directly applicable workflows for operational decision-making.