Socio-Physical Human Orchestration in Smart Cities

The efficient management of a smart city and the improvement of the quality of humans' every-day life are becoming challenging problems due to smart cities' increased heterogeneity and complexity. In this paper, we present a novel socio-physical human orchestration framework to deal with the aforementioned issues, by capitalizing on recent advances in game theory and reinforcement learning. Initially, each human selects, in a distributed manner, a Point of Interest (PoI) that it wants to visit, by acting as stochastic learning automaton, exploiting the socio-physical conditions of the environment while learning from its previous experiences. As a result, those humans that have selected a specific PoI to visit, "compete" with each other in order to finally perform their visit. The humans' behavior is studied as a non-cooperative game among them, via adopting the theory of minority games, while the concluding Nash equilibrium point identifies the humans that will finally visit each PoI. A low complexity algorithm is introduced to realize the overall framework, while the performance of the proposed approach is evaluated through modeling and simulation under several scenarios, and its superiority is demonstrated.