Emission-Aware Optimization of Gas Networks: Input-Convex Neural Network Approach
This addresses emission-aware optimization for gas network operators, offering a practical solution to a domain-specific problem with incremental improvements in method.
The paper tackled the problem of optimizing gas network planning under emission constraints by developing an input-convex neural network (ICNN) aided optimization routine to approximate complex gas flow equations, demonstrating that it outperforms non-convex and relaxation-based solvers with larger optimality gains for stricter emission targets and provides feasible solutions when others fail.
Gas network planning optimization under emission constraints prioritizes gas supply with the least CO$_2$ intensity. As this problem includes complex physical laws of gas flow, standard optimization solvers cannot guarantee convergence to a feasible solution. To address this issue, we develop an input-convex neural network (ICNN) aided optimization routine which incorporates a set of trained ICNNs approximating the gas flow equations with high precision. Numerical tests on the Belgium gas network demonstrate that the ICNN-aided optimization dominates non-convex and relaxation-based solvers, with larger optimality gains pertaining to stricter emission targets. Moreover, whenever the non-convex solver fails, the ICNN-aided optimization provides a feasible solution to network planning.