Biying Shou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Biying Shou has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Chao Huang
Department of Computer Science, The University of California at Davis, Davis, CA, USA
1 shared publication - Chenxi Sun
Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China
1 shared publication Jianwei Huang
Shenzhen Research Institute of Big Data, School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, 518129, China
1 shared publication- Jianwei Huang
The Chinese University of Hong Kong
1 shared publication Qian Ma
School of Intelligent Systems Engineering, Sun Yat‐sen University, Shenzhen, Guangdong, 518107, China
1 shared publicationTamer Başar
Department of Electrical and Computer Engineering, and Coordinated Science Laboratory, University of Illinois at Urbana‐Champaign, Urbana, Illinois, 61801, USA
1 shared publication
Latest Publications
- Open Access
Federated Learning in Competitive EV Charging Market
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.
Open AccessFederated Learning in Competitive EV Charging Market
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.
- 11 June 2021
- Published by SAGE Publications in Production and Operations Management
- Vol. 30 (11) , 4004-4022
Monopoly Pricing with Participation‐Dependent Social Learning About Quality of Service
The quality of many online services (such as online games, video streaming, cloud services) depends not only on the service capacity but also on the number of users using the service simultaneously. For a new online service, the potential users are often uncertain about both the capacity and congestion level of the service, and hence are uncertain about the quality of service (QoS). In this study, we consider users’ participation‐dependent social learning (PDSL), that is, learning of the QoS through participants’ online reviews. The key difference from the traditional social learning mechanism is that the learning object (QoS) is not a fixed value, but instead, it depends on the number of review participants. We study how such a new learning process affects the service provider's dynamic pricing strategy in four different market scenarios, depending on whether the decisions are for two periods or infinite periods and whether users are aware of the congestion effect or not. Our analysis yields several key insights. First, the presence of PDSL significantly affects the provider's optimal pricing policy. In a two‐period market with congestion‐unaware users, the provider would always set a flat price when there is no PDSL; in contrast, when there is PDSL, the optimal price can either increase or decrease, depending on the capacity and the prior mean QoS belief. Second, users’ congestion‐awareness causes the provider to set a non‐decreasing pricing policy in the two‐period market, while the provider's steady‐state pricing policy in the infinite‐period market increases with the capacity and the prior QoS belief. Third, the existence of PDSL increases the provider's profit in all four market scenarios as long as the provider's capacity is larger than users’ prior mean QoS belief.
- 11 June 2021
- Published by SAGE Publications in Production and Operations Management
- Vol. 30 (11) , 4004-4022
Monopoly Pricing with Participation‐Dependent Social Learning About Quality of Service
The quality of many online services (such as online games, video streaming, cloud services) depends not only on the service capacity but also on the number of users using the service simultaneously. For a new online service, the potential users are often uncertain about both the capacity and congestion level of the service, and hence are uncertain about the quality of service (QoS). In this study, we consider users’ participation‐dependent social learning (PDSL), that is, learning of the QoS through participants’ online reviews. The key difference from the traditional social learning mechanism is that the learning object (QoS) is not a fixed value, but instead, it depends on the number of review participants. We study how such a new learning process affects the service provider's dynamic pricing strategy in four different market scenarios, depending on whether the decisions are for two periods or infinite periods and whether users are aware of the congestion effect or not. Our analysis yields several key insights. First, the presence of PDSL significantly affects the provider's optimal pricing policy. In a two‐period market with congestion‐unaware users, the provider would always set a flat price when there is no PDSL; in contrast, when there is PDSL, the optimal price can either increase or decrease, depending on the capacity and the prior mean QoS belief. Second, users’ congestion‐awareness causes the provider to set a non‐decreasing pricing policy in the two‐period market, while the provider's steady‐state pricing policy in the infinite‐period market increases with the capacity and the prior QoS belief. Third, the existence of PDSL increases the provider's profit in all four market scenarios as long as the provider's capacity is larger than users’ prior mean QoS belief.