Short-term Forecasting of Price-responsive Loads Using Inverse Optimization

TL;DR

This paper presents a data-driven inverse optimization approach to accurately forecast short-term electricity demand of price-responsive loads, incorporating weather and time variables, and overcoming nonconvex challenges with a novel solution method.

Contribution

It introduces a new inverse optimization method that handles nonconvexities via linear problems with penalty terms, improving demand forecasting accuracy.

Findings

Successfully captures aggregate demand of HVAC systems

Outperforms traditional models in short-term forecasting

Effectively incorporates weather and time regressors

Abstract

We consider the problem of forecasting the aggregate demand of a pool of price-responsive consumers of electricity. The price-response of the aggregation is modeled by an optimization problem that is characterized by a set of marginal utility curves and minimum and maximum power consumption limits. The task of estimating these parameters is addressed using a generalized inverse optimization scheme that, in turn, requires solving a nonconvex mathematical program. We introduce a solution method that overcomes the nonconvexities by solving instead two linear problems with a penalty term, which is statistically adjusted by using a cross-validation algorithm. The proposed methodology is data-driven and leverages information from regressors, such as time and weather variables, to account for changes in the parameter estimates. The power load of a group of heating, ventilation, and air conditioning systems in buildings is simulated, and the results show that the aggregate demand of the group can be successfully captured by the proposed model, making it suitable for short-term forecasting purposes.