Yifu Ding is a doctoral candidate in the Department of Engineering Science at the University of Oxford. During her DPhil, she has been a visiting student at Alan Turing Institute, London, and Johns Hopkins University, USA (Prof. Benjamin Hobbs group). She is an active member at Wolfson College and The Oxford Student.
She holds a BEng degree in Electrical and Electronics Engineering from the University of Edinburgh and MSc degree in Sustainable Energy Futures at Imperial College London, where she was awarded the best master thesis. Before her DPhil in Oxford, Yifu worked for one year in Deutsche Gesellschaft für Internationale Zusammenarbeit (GIZ) and government energy research institute in China.
The reliability of the power system under the impact of increasing renewable penetration and extreme weather conditions is a rising concern globally. Enriched by learning experiences in different institutes and countries, my research focuses on machine learning applications and advanced chance-constrained optimizations for power system reliability. My works aim to find appealing solutions in both system design and short-term operations. I have specific research interests in:
- Machine learning probabilistic forecasting
- Chance-constrained optimization
- Optimal power flow analysis
- Microgrid design and control under extreme conditions
Recent publications are listed below. To access a full list of my publications and pre-prints, please visit my ResearchGate or email me directly.
- Y. Ding, T. Morstyn and M. D. McCulloch, "Distributionally Robust Joint Chance-Constrained Optimization for Networked Microgrids Considering Contingencies and Renewable Uncertainty," in IEEE Transactions on Smart Grid, doi: 10.1109/TSG.2022.3150397.
- Y. Ding and M. D. McCulloch, "Distributionally robust optimization for networked microgrids considering contingencies and renewable uncertainty," 2021 60th IEEE Conference on Decision and Control (CDC), 2021, pp. 2330-2335, doi: 10.1109/CDC45484.2021.9683658.
- Y. Ding, M.D. McCulloch, Additive Gaussian process prediction for electrical loads compared with deep learning models, The 12th ACM International Conference on Future Energy Systems, June 2021, doi: 10.1145/3447555.3466592