FedParking: A Federated Learning Based Parking Space Estimation With Parked Vehicle Assisted Edge Computing

As a distributed learning approach, federated learning trains a shared learning model over distributed datasets while preserving the training data privacy. We extend the application of federated learning to parking management and introduce FedParking in which Parking Lot Operators (PLOs) collaborate to train a long short-term memory model for parking space estimation without exchanging the raw data. Furthermore, we investigate the management of Parked Vehicle assisted Edge Computing (PVEC) by FedParking. In PVEC, different PLOs recruit PVs as edge computing nodes for offloading services through an incentive mechanism, which is designed according to the computation demand and parking capacity constraints derived from FedParking. We formulate the interactions among the PLOs and vehicles as a multi-lead multi-follower Stackelberg game. Considering the dynamic arrivals of the vehicles and time-varying parking capacity constraints, we present a multi-agent deep reinforcement learning approach to gradually reach the Stackelberg equilibrium in a distributed yet privacy-preserving manner. Finally, numerical results are provided to demonstrate the effectiveness and efficiency of our scheme.

I. Introduction

Nowadays, federated learning has been envisioned as a distributed learning framework in which devices cooperate to build and update a globally shared learning model by supporting training the global model over distributed datasets [1], [2]. Federated learning enables each device as a data owner to locally train the global model with individually collected data. This approach exchanges model parameters instead of the actual training data and preserves data privacy of the devices. Due to the significant privacy-friendly characteristic, federated learning is applied to diverse domains, e.g., mobile keyboard prediction [3], wearable activity recognition [4] and content caching placement [5]. The promising approach is also integrated into vehicular networks to forecast traffic information such as traffic flow [6] and traffic speed [7] while guaranteeing reliable data privacy preservation during the forecast. Motivated by the current works, we extend the application of federated learning to parking management in smart cities, and develop a federated learning based parking space estimation scheme named by FedParking.