Artificial intelligence-based methods for renewable power system operation

Y Li, Y Ding, S He, F Hu, J Duan, G Wen… - Nature Reviews …, 2024 - nature.com
Carbon neutrality goals are driving the increased use of renewable energy (RE). Large-
scale use of RE requires accurate energy generation forecasts; optimized power dispatch …

End-to-end learning of user equilibrium with implicit neural networks

Z Liu, Y Yin, F Bai, DK Grimm - Transportation Research Part C: Emerging …, 2023 - Elsevier
This paper intends to transform the transportation network equilibrium modeling paradigm
via an “end-to-end” framework that directly learns travel choice preferences and the …

E2E-AT: A Unified Framework for Tackling Uncertainty in Task-Aware End-to-End Learning

W Xu, J Wang, F Teng - Proceedings of the AAAI Conference on …, 2024 - ojs.aaai.org
Successful machine learning involves a complete pipeline of data, model, and downstream
applications. Instead of treating them separately, there has been a prominent increase of …

Optimization with Neural Network Feasibility Surrogates: Formulations and Application to Security-Constrained Optimal Power Flow

Z Kilwein, J Jalving, M Eydenberg, L Blakely… - Energies, 2023 - mdpi.com
In many areas of constrained optimization, representing all possible constraints that give rise
to an accurate feasible region can be difficult and computationally prohibitive for online use …

[HTML][HTML] Constraint-driven deep learning for nk security constrained optimal power flow

BN Giraud, A Rajaei, JL Cremer - Electric Power Systems Research, 2024 - Elsevier
The transition to green energy is reshaping the energy landscape, marked by increased
integration of renewables, distributed resources, and the electrification of other energy …

A Bayesian approach to breaking things: efficiently predicting and repairing failure modes via sampling

C Dawson, C Fan - arXiv preprint arXiv:2309.08052, 2023 - arxiv.org
Before autonomous systems can be deployed in safety-critical applications, we must be able
to understand and verify the safety of these systems. For cases where the risk or cost of real …

An Auto-Tuned Robust Dispatch Strategy for Virtual Power Plants to Provide Multi-Stage Real-Time Balancing Service

N Gu, J Cui, C Wu - IEEE Transactions on Smart Grid, 2023 - ieeexplore.ieee.org
To fully exploit the flexible potential of distributed energy resources (DERs) in providing
balancing service to the power system, Virtual Power Plants (VPPs) act as control centers to …

Deep-learning-aided voltage-stability-enhancing stochastic distribution network reconfiguration

W Huang, C Zhao - IEEE Transactions on Power Systems, 2023 - ieeexplore.ieee.org
Power distribution networks are approaching their voltage stability boundaries due to the
severe voltage violations and the inadequate reactive power reserves caused by the …

Fast and Reliable Contingency Screening with Input-Convex Neural Networks

N Christianson, W Cui, S Low, W Yang… - arXiv preprint arXiv …, 2024 - arxiv.org
Power system operators must ensure that dispatch decisions remain feasible in case of grid
outages or contingencies to prevent cascading failures and ensure reliable operation …

RADIUM: Predicting and Repairing End-to-End Robot Failures using Gradient-Accelerated Sampling

C Dawson, A Parashar, C Fan - arXiv preprint arXiv:2404.03412, 2024 - arxiv.org
Before autonomous systems can be deployed in safety-critical applications, we must be able
to understand and verify the safety of these systems. For cases where the risk or cost of real …