Russell Bent

Constraint-informed active learning for end-to-end ACOPF optimization proxies

Miao Li, Michael Klamkin, Pascal Van Hentenryck, Russell Bent et autres

This paper studies optimization proxies–machine learning (ML) models trained to efficiently predict optimal solutions for AC Optimal Power Flow (ACOPF) problems. While promising, optimization proxy performance heavily depends on training data quality. To address this limitation, this paper introduces a novel active …

us (code pays fourni par la source)

Load Block Modeling in Distribution Systems: Network Reconfiguration for Load Restoration

David M. Fobes, Harsha Nagarajan, Manuel Garcia, Robert Ferrando et autres

The distribution system restoration (DSR) problem has received considerable attention over the last decade or more. Solutions to the DSR problem identify the best set or sequence of actions to perform on a distribution circuit to restore service after a disruption. The …

Load Block Modeling in Distribution Systems: Network Reconfiguration for Load Restoration

David M. Fobes, Harsha Nagarajan, Manuel Garcia, Robert Ferrando et autres

The distribution system restoration (DSR) problem has received considerable attention over the last decade or more. Solutions to the DSR problem identify the best set or sequence of actions to perform on a distribution circuit to restore service after a disruption. The …

us (code pays fourni par la source)

MathOptAI.jl: Embed Trained Machine-Learning Predictors into JuMP Models

Oscar Dowson, Robert Parker, Russell Bent

We present MathOptAI.jl, an open-source Julia library for embedding trained machine-learning predictors into a JuMP model. MathOptAI.jl can embed a wide variety of neural networks, decision trees, and Gaussian Processes into a larger mathematical optimization model. MathOptAI.jl supports a range of Julia-based …

nz, us (code pays fourni par la source)

Code and Data Repository for MathOptAI.jl: Embed trained machine learning predictors into JuMP models

Oscar Dowson, Robert Parker, Russell Bent

The software and data in this repository are a snapshot of the software and data that were used in the research reported on in the paper MathOptAI.jl: Embed trained machine learning predictors into JuMP models by Oscar Dowson, Robert B. Parker, and …

A Hybrid Decomposition Approach for Stochastic Unit Commitment with Combined-Cycle Generators

Rosemary Barrass, Harsha Nagarajan, Mathieu Tanneau, Russell Bent et autres

The U.S. power grid is undergoing a paradigm shift as energy demand grows in scale and volatility. In response to this growing need, the U.S. has increased adoption of combined-cycle generators (CCs). CCs are fast-ramping generators that utilize variable configurations of combustion …

A Hybrid Decomposition Approach for Stochastic Unit Commitment with Combined-Cycle Generators

Rosemary Barrass, Harsha Nagarajan, Mathieu Tanneau, Russell Bent et autres

The U.S. power grid is undergoing a paradigm shift as energy demand grows in scale and volatility. In response to this growing need, the U.S. has increased adoption of combined-cycle generators (CCs). CCs are fast-ramping generators that utilize variable configurations of combustion …

E-Globe: Scalable $ε$-Global Verification of Neural Networks via Tight Upper Bounds and Pattern-Aware Branching

Wenting Li, Saif R. Kazi, Russell Bent, Duo Zhou et autres

Neural networks achieve strong empirical performance, but robustness concerns still hinder deployment in safety-critical applications. Formal verification provides robustness guarantees, but current methods face a scalability-completeness trade-off. We propose a hybrid verifier in a branch-and-bound (BaB) framework that efficiently tightens both upper …

E-Globe: Scalable $ε$-Global Verification of Neural Networks via Tight Upper Bounds and Pattern-Aware Branching

Wenting Li, Saif R. Kazi, Russell Bent, Duo Zhou et autres

Neural networks achieve strong empirical performance, but robustness concerns still hinder deployment in safety-critical applications. Formal verification provides robustness guarantees, but current methods face a scalability-completeness trade-off. We propose a hybrid verifier in a branch-and-bound (BaB) framework that efficiently tightens both upper …

Studying a Sequential Black Start Restoration Method Using PowerModelsONM.jl

Irfan Ullah, Karen L. Butler-Purry, Russell Bent, Harsha Nagarajan et autres

Black Start Restoration (BSR) in power distribution networks is a critical yet complex process, which may be accomplished through the coordination of microgrids, prioritized load recovery, and system stability maintenance. This research aims to study a BSR method using the PowerModelsONM (ONM) …

us (code pays fourni par la source)

FORWARD: A Feasible Radial Reconfiguration Algorithm for Multi-Source Distribution Networks

Joan Vendrell Gallart, Russell Bent, Solmaz S. Kia

This paper considers an optimal radial reconfiguration problem in multi-source distribution networks, where the goal is to find a radial configuration that minimizes quadratic distribution costs while ensuring all sink demands are met. This problem arises in critical infrastructure systems such as …

Learning to accelerate tightening of convex relaxations of the AC optimal power flow problem

Fatih Cengil, Harsha Nagarajan, Russell Bent, Sandra D. Ekşioğlu et autres

Abstract We propose a novel machine learning (ML)-based approach to significantly reduce the run times of the optimality-based bound tightening (OBBT) algorithm for strengthening the convex relaxations of the non-convex Alternating Current Optimal Power Flow (AC-OPF) problem. While OBBT can yield near-global …

us (code pays fourni par la source)