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

In this letter, we propose a data-driven warm start approach, empowered by an artificial neural network, 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, while optimality and feasibility of the solution can still be guaranteed. We also confirm the robustness of this algorithm, and show that this approach can be extended to the optimal dispatch of large-scale electricity-gas coupled integrated energy systems.