Multi-Class Stackelberg Games for the Co-Design of Networked Systems (2505.03468v2)

Abstract: We investigate a co-design problem, encompassing simultaneous design of system infrastructure and control, through a game-theoretical framework. To this end, we propose the co-design problem as a two-layer hierarchical strategic interaction. At the upper layer, a leader (or multiple leaders) determines system design parameters, while at the lower layer, a follower (or multiple followers) optimizes the control strategy. To capture this hierarchy, we propose four novel classes of Stackelberg games that integrate diverse strategic behaviors, including combinations of cooperative and non-cooperative interactions across two different layers. Notably, the leaders' interactions are represented using a normal-form game, whereas the followers' interactions are modeled by different games (dynamic games in discrete time). These distinct game structures result in a Stackelberg game that accommodates different game types per layer, and/or supports heterogeneous strategic behaviors involving cooperation and non-cooperation simultaneously. Learning algorithms using the best-response dynamics are used to solve the game problems when considering a discrete strategic space for the leaders. The efficacy of the proposed approach is demonstrated through an application to the co-design of the Barcelona drinking water network.