Federated Learning in Competitive EV Charging Market

TL;DR

This paper models the strategic interactions in EV charging markets with federated learning, revealing that while FL enhances QoS, it can intensify price competition and reduce profits, depending on data similarity.

Contribution

It introduces a multi-stage game model analyzing the impact of federated learning on EV charging stations' pricing and profit strategies.

Findings

FL improves QoS but may decrease profits due to increased price competition.

Stations participate in FL when data distributions are mildly dissimilar.

The equilibrium is characterized by decomposing a non-concave problem into a piece-wise concave program.

Abstract

Federated Learning (FL) has demonstrated a significant potential to improve the quality of service (QoS) of EV charging stations. While existing studies have primarily focused on developing FL algorithms, the effect of FL on the charging stations' operation in terms of price competition has yet to be fully understood. This paper aims to fill this gap by modeling the strategic interactions between two charging stations and EV owners as a multi-stage game. Each station first decides its FL participation strategy and charging price, and then individual EV owners decide their charging strategies. The game analysis involves solving a non-concave problem and by decomposing it into a piece-wise concave program we manage to fully characterize the equilibrium. Based on real-world datasets, our numerical results reveal an interesting insight: even if FL improves QoS, it can lead to smaller profits for both stations. The key reason is that FL intensifies the price competition between charging stations by improving stations' QoS to a similar level. We further show that the stations will participate in FL when their data distributions are mildly dissimilar.