Selectively Linearized Neural Network based RoCoF-Constrained Unit Commitment in Low-Inertia Power Systems

TL;DR

This paper introduces a novel selectively linearized neural network approach for unit commitment in low-inertia power systems, effectively predicting and managing RoCoF constraints amid increasing inverter-based resources.

Contribution

It develops a RoCoF predictor trained on high-fidelity data and implements a ReLU linearization to enhance computational efficiency in unit commitment.

Findings

Accurately predicts system-wide RoCoF using neural networks.

Improves computational efficiency through selective ReLU linearization.

Demonstrates effectiveness on IEEE 24-bus system with simulation results.

Abstract

Conventional synchronous generators are gradually being replaced by inverter-based resources, such transition introduces more complicated operation conditions. And the reduction in system inertia imposes challenges for system operators on maintaining system rate-of-change-of-frequency (RoCoF) security. This paper presents a selectively linearized neural network (SNLNN) based RoCoF-constrained unit commitment (SLNN-RCUC) model. A RoCoF predictor is first trained to predict the system wide highest locational RoCoF based on a high-fidelity simulation dataset. Instead of incorporating the complete neural network into unit commitment, a ReLU linearization method is implemented on active selected neurons to improve the algorithm computational efficiency. The effectiveness of proposed SLNN-RCUC model is demonstrated on the IEEE 24-bus system by conducting time domain simulation on PSS/E