Comparison of heuristic methods for achieving minimum-cost capacitated networks with a new metaheuristic based on node valency
Designing low-cost networks is an essential step in planning linked infrastructure. For the case of capacitated trees, such as oil or gas pipeline networks, the cost is usually a function of both pipeline thickness (i.e. capacity) and pipeline length. Minimizing cost becomes particularly difficult as network topology itself dictates local flow material balances, rendering the optimization space non-linear. The combinatorial nature of potential trees requires the use of graph optimization heuristics to achieve good solutions in reasonable time. In this work we perform a comparison of known literature network optimization heuristics and metaheuristics, and propose novel algorithms, including a metaheuristic based on transferring edges of high valency nodes. Our metaheuristic achieves performance above similar algorithms studied, especially for larger graphs, usually producing a significantly higher proportion of optimal solutions, while remaining in line with time-complexity of algorithms found in the literature. Data points for graph node positions and capacities are first randomly generated, and secondly obtained from the German emissions trading CO2 source registry. Driven by the increasing necessity to find applications and storage for industry CO2 emissions, finding minimum-cost networks increases the business case for large-scale CO2 transportation pipeline infrastructure.