A Gaussian Process-based Price-Amount Curve Construction for Demand Response Provided by Internet Data Centers

TL;DR

This paper introduces a Gaussian Process Regression method to accurately construct the Price-Amount curve for demand response in internet data centers, accounting for operational uncertainties.

Contribution

The paper presents a novel Gaussian Process-based approach for constructing demand response curves that incorporate IDC operational uncertainties.

Findings

Effective estimation of the Price-Amount curve with uncertainty quantification

Demonstrated improved accuracy over traditional methods

Provides a probabilistic framework for demand response modeling

Abstract

For a Demand Response (DR) program with internet data centers (IDC), the Price-Amount curve that estimates how the potential DR amount depends on the DR price determined by power systems is crucial. Constructing this curve is challenging mainly due to the uncertainty in IDCs' operation. A novel Gaussian Process Regression-based estimation method is thus proposed. The variance of resulting curve reflecting the IDC operational uncertainty is also calculated.