Neural networks for multi-horizon stochastic programming

TL;DR

This paper introduces a neural network-based framework to efficiently approximate solutions for multi-horizon stochastic programs, significantly reducing computation time while maintaining solution quality, demonstrated on UK power system planning.

Contribution

It extends surrogate modeling to multi-horizon stochastic programs with continuous decisions, providing a scalable neural network embedding approach and comprehensive computational validation.

Findings

Neural networks perform well across different architectures.

Approach is up to 34.72 times faster than traditional methods.

Surrogate solutions show better out-of-sample performance.

Abstract

This paper proposes a machine-learning-based solution approach for solving multi-horizon stochastic programs. The approach embeds a deep learning neural network into a multi-horizon stochastic program to approximate the recourse operational objective function. The proposed approach is demonstrated on a UK power system planning problem with uncertainty at investment and operational timescales. The results show that (1) the surrogate neural network performs well across three different architectures, (2) the proposed approach is up to 34.72 times faster than the direct solution of the monolithic deterministic equivalent counterpart, (3) the surrogate-based solutions yield comparable in-sample stability and improved out-of-sample performance relative to the deterministic equivalent, indicating better generalisation to unseen scenarios. The main contributions of the paper are: (1) we propose a machine-learning-based framework for solving multi-horizon stochastic programs, (2) we introduce a neural network embedding formulation tailored to multi-horizon stochastic programs with continuous first-stage decisions and fixed scenario sets, extending existing surrogate modelling approaches from two-stage to multi-horizon settings, and (3) we provide an extensive computational study on a realistic UK power system planning problem, demonstrating the trade-off between approximation accuracy, computational efficiency, and solution robustness for different neural network architectures and scenario set sizes.