Online Decision Making for Trading Wind Energy

TL;DR

This paper introduces an online learning algorithm for trading wind energy in electricity markets, combining adaptive gradient descent with newsvendor models to improve adaptability and economic outcomes in nonstationary environments.

Contribution

It presents a novel online trading algorithm that integrates adaptive gradient methods with feature-driven newsvendor models for wind energy markets.

Findings

Enhanced adaptability to nonstationary parameters

Significant economic gains demonstrated in numerical experiments

Reduced computational burden compared to existing methods

Abstract

We propose and develop a new algorithm for trading wind energy in electricity markets, within an online learning and optimization framework. In particular, we combine a component-wise adaptive variant of the gradient descent algorithm with recent advances in the feature-driven newsvendor model. This results in an online offering approach capable of leveraging data-rich environments, while adapting to the nonstationary characteristics of energy generation and electricity markets, also with a minimal computational burden. The performance of our approach is analyzed based on several numerical experiments, showing both better adaptability to nonstationary uncertain parameters and significant economic gains.