Cost Attribution And Risk-Averse Unit Commitment In Power Grids Using Integrated Gradient

TL;DR

This paper presents a novel method using Integrated Gradients to attribute costs and manage risks in power grid operations, enhancing reliability and reducing costs through risk-aware unit commitment.

Contribution

It introduces a new cost attribution algorithm based on Integrated Gradients for power system risk management, enabling better renewable capacity planning.

Findings

Improved grid reliability in simulations on RTS-GMLC.

Reduced operational costs through risk-aware adjustments.

Effective attribution of stochastic impacts on system costs.

Abstract

This paper introduces a novel approach to addressing uncertainty and associated risks in power system management, focusing on the discrepancies between forecasted and actual values of load demand and renewable power generation. By employing Economic Dispatch (ED) with both day-ahead forecasts and actual values, we derive two distinct system costs, revealing the financial risks stemming from uncertainty. We present a numerical algorithm inspired by the Integrated Gradients (IG) method to attribute the contribution of stochastic components to the difference in system costs. This method, originally developed for machine learning, facilitates the understanding of individual input features' impact on the model's output prediction. By assigning numeric values to represent the influence of variability on operational costs, our method provides actionable insights for grid management. As an application, we propose a risk-averse unit commitment framework, leveraging our cost attribution algorithm to adjust the capacity of renewable generators, thus mitigating system risk. Simulation results on the RTS-GMLC grid demonstrate the efficacy of our approach in improving grid reliability and reducing operational costs.