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

2022/10/06 by Erhan Bayraktar, Asaf Cohen, Bayraktar, Erhan +3 · 1 citation
Engineering · #60H10 #65C30 #91G60 #91G80 #93E20 #Electric Power System Optimization #FOS: Mathematics #Optimization and Control (math.OC)

paper · pdf · doi:10.48550/arxiv.2210.03045

openalex publication_date 2022/10/06 · openalex created_date 2022/10/08 · openalex updated_date 2026/07/28

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.

Cited by

• On the Effectiveness of Classical Regression Methods for Optimal Switching Problems

Related

• A Deep Learning Approach to Renewable Capacity Installation under Jump Uncertainty
• Accelerating Underground Pumped Hydro Energy Storage Scheduling with Decision-Focused Learning
• Learning-Assisted Competitive Algorithms for Peak-Aware Energy Scheduling
• DER Day-Ahead Offering: A Neural Network Column-and-Constraint Generation Approach
• Combinatorial Auctions and Graph Neural Networks for Local Energy Flexibility Markets