A neural network approach to high-dimensional optimal switching problems with jumps in energy markets

TL;DR

This paper introduces a neural network-based algorithm for solving high-dimensional optimal switching problems with jumps, specifically applied to energy markets, demonstrating accuracy and efficiency in complex, high-dimensional scenarios.

Contribution

The paper presents a novel backward-in-time machine learning algorithm using neural networks to solve high-dimensional energy switching problems with stochastic jumps.

Findings

Algorithm achieves accurate solutions in high dimensions

Performance scales linearly or sub-linearly with problem size

Effective for complex energy scheduling problems

Abstract

We develop a backward-in-time machine learning algorithm that uses a sequence of neural networks to solve optimal switching problems in energy production, where electricity and fossil fuel prices are subject to stochastic jumps. We then apply this algorithm to a variety of energy scheduling problems, including novel high-dimensional energy production problems. Our experimental results demonstrate that the algorithm performs with accuracy and experiences linear to sub-linear slowdowns as dimension increases, demonstrating the value of the algorithm for solving high-dimensional switching problems.