Optimal Clustered, Multi-modal CO₂ Transport Considering Non-linear Costs - a Path-planning Approach

An important measure to achieve global reduction in CO₂ emissions is CO₂ capture, transport, and storage. The deployment of CO₂ capture requires the development of a shared CO₂ transport infrastructure, where CO₂ can be transported with different transport modes. Furthermore, the cost of CO₂ transport can be subject to significant economies of scale effects with respect to the amount of CO₂ transported, also mentioned as clustering effects. Therefore, optimizing the shared infrastructure of multiple CO₂ sources can lead to significant reductions in infrastructure costs. This paper presents a novel formulation of the clustered CO₂ transport network. The Markov Decision Process formulation defined here allows for more detailed modeling of non-linear, discrete transport costs and increased geographical resolution. The clustering effects are modeled through cooperative multi-agent interactions. A multi-agent, reinforcement learning-based algorithm is proposed to optimize the shared transportation network, with examples illustrating the results of the method.