Wangkun Xu
  • Home
  • Research
  • Software
  • Teaching
  • Supervision
  • News
  • Blog
  • About

Wangkun Xu

Portrait of Wangkun Xu

Wangkun Xu

Research Associate · Imperial College London

I develop learning and optimisation methods for efficient, robust, and secure power-system operation under high penetrations of renewable energy.

Learning-augmented optimisation Decision-focused learning Power-system security System dynamics

Imperial Scholar GitHub ORCID LinkedIn About / CV

Selected publications

Recent work spanning learning-augmented decision-making including efficient differentiable optimization for power system decision-focused learning and constraint learning for stability-constrained power system optimizations.

DiffAPQP

Structured Differentiable Optimization for Efficient Decision-focused Learning in Power Systems

2026

Wangkun Xu and Fei Teng

arXiv preprint arXiv:2608.04189

Preprint Code · Power systems Code · DiffAPQP
ICNN

Input Convex Neural Network as a Surrogate in Stability-Constrained Optimization for IBR-Dominated Power Systems

2026

Wangkun Xu, Hongyang Jia, Yi Wang, Ning Zhang, and Fei Teng

IEEE Transactions on Power Systems

Paper Preprint Code
FLOW-PCE

Flow-based Polynomial Chaos Expansion for Uncertainty Quantification in Power System Dynamic Simulation

2026

Le Fang, Wangkun Xu*, and Fei Teng

* Corresponding author

arXiv preprint arXiv:2603.20472

Preprint
LAPSO

Learning-Augmented Power System Operations: A Unified Optimization View

2026

Wangkun Xu, Zhongda Chu, and Fei Teng

IEEE Transactions on Power Systems

Paper Preprint Code Software
No matching items

View all publications →

Latest news

2026-09-02 Teaching

Delivered the guest lecture An Open-Source Toolbox for Embedding Neural Stability Surrogates in Stability-Constrained Optimization at the University of Strathclyde, Glasgow. Course details.

2026-09-02 Software

Open-sourced NCET, a toolbox for embedding neural stability surrogates in stability-constrained optimization. NCET package.

2026-09-02 Paper

Paper · Preprint.

2026-08-28 Event

Presented Input Convex Neural Network as a Surrogate in Stability-Constrained Optimization for IBR-dominated Power Systems.

2026-08-07 Event

Presented Structured Differentiable Optimization for Efficient Decision-Focused Learning in Power Systems at the EPICS Bimonthly Meeting, covering theory, software, and IEEE 118-bus evidence. Slides.

2026-08-01 Paper

Paper · Preprint.

No matching items

All news →

Featured software

Reusable scientific packages, research implementations, and open teaching resources.

NCET

NCET

NCET (Neural-network Constraint Embedding Toolkit) converts supported PyTorch neural networks into exact mixed-integer linear constraints compiled by CVXPY.

Neural stability surrogates · Stability-constrained optimization

GitHub Documentation Install Application
APQP

DiffAPQP

Differentiable PyTorch layers for affine-parametric quadratic and linear programs expressed directly in CVXPY.

Differentiable optimisation · Decision-focused learning

GitHub Documentation Install Application
GRID

GridForge

Build optimisation-ready power-system cases with profile dataset from PYPOWER or MATPOWER grids, YAML configurations, and bus-level time-series data.

Power-system testbeds · Data pipelines · CVXPY

GitHub Documentation Install
ML

Introduction to ML coding tutorial

Hands-on examples covering SVMs, PCA, k-means, and zero-shot energy-price forecasting with Amazon Chronos.

Python tutorial · MSc teaching

GitHub Related course
No matching items

Explore all software →

Current teaching

ELEC97077 · Smart Grid Technology

Machine Learning and Data Science for Power Systems

MSc Future Power Networks · Department of Electrical and Electronic Engineering, Imperial College London

Guest Lecturer · Lecturing, coursework, demonstrations, tutorials, and marking · 5 hours of lectures + 1-hour tutorial

2024–2026

Details Notes

MECH70039 · Data Science and Digitalisation

Introduction to Machine Learning for Energy Systems

MSc Sustainable Energy Futures · Energy Futures Lab, Imperial College London

Guest Lecturer · Lecture and hands-on tutorial · 2-hour lecture + 2-hour tutorial

2025–2026

Details Notes Tutorial
No matching items

Teaching and course materials →

Back to top

© 2026 Wangkun Xu ·

 

Built with Quarto