A Data-Driven Warm Start Approach for Convex Relaxation in Optimal Gas Flow

TL;DR

This paper introduces a neural network-based data-driven warm start method to improve the efficiency of convex relaxations in optimal gas flow problems, reducing iterations while maintaining solution quality.

Contribution

It presents a novel neural network approach to provide warm starts for convex relaxations in optimal gas flow, enhancing computational efficiency.

Findings

Significantly reduces the number of iterations in the convex-concave procedure

Maintains optimality and feasibility of solutions

Demonstrates effectiveness through case studies

Abstract

In this letter, we propose a data-driven warm start approach, empowered by artificial neural networks, to boost the efficiency of convex relaxations in optimal gas flow. Case studies show that this approach significantly decreases the number of iterations for the convex-concave procedure algorithm, and optimality and feasibility of the solution can still be guaranteed.