Dynamic pricing based electric vehicle charging station location strategy using reinforcement learning

Li, Yanbin; Wang, JiaNi; Wang, Weiye; Liu, Chang; Li, Yun

doi:10.1016/j.energy.2023.128284

Cited by 11 publications

(3 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, a substantial amount of research has been dedicated to exploiting RL to tackle complex optimization problems [24,25]. The intrinsic flexibility of RL, its capacity to handle high-dimensional and continuous spaces, and its proficiency in balancing exploration and exploitation render it a unique advantage in solving optimization challenges [26][27][28]. RL algorithms, such as Q-Learning, Deep Q-Network (DQN), and Proximal Policy Optimization (PPO) [9], have found applications in logistics, supply chain management, resource allocation, and other optimization-intensive areas [24,26,29].…”

Section: Reinforcement Learning and Attention Mechanismmentioning

confidence: 99%

Optimal Placement of Charging Stations in Road Networks: A Reinforcement Learning Approach with Attention Mechanism

2023

View full text Add to dashboard Cite

With the aim of promoting energy conservation and emission reduction, electric vehicles (EVs) have gained significant attention as a strategic industry in many countries. However, the insufficiency of accessible charging infrastructure remains a challenge, hindering the widespread adoption of EVs. To address this issue, we propose a novel approach to optimize the placement of charging stations within a road network, known as the charging station location problem (CSLP). Our method considers multiple factors, including fairness in charging station distribution, benefits associated with their placement, and drivers’ discomfort. Fairness is quantified by the balance in charging station coverage across the network, while driver comfort is measured by the total time spent during the charging process. Then, the CSLP is formulated as a reinforcement learning problem, and we introduce a novel model called PPO-Attention. This model incorporates an attention layer into the Proximal Policy Optimization (PPO) algorithm, enhancing the algorithm’s capacity to identify and understand the intricate interdependencies between different nodes in the network. We have conducted extensive tests on urban road networks in Europe, North America, and Asia. The results demonstrate the superior performance of our approach compared to existing baseline algorithms. On average, our method achieves a profit increase of 258.04% and reduces waiting time by 73.40%, travel time by 18.46%, and charging time by 40.10%.

show abstract

Section: Reinforcement Learning and Attention Mechanismmentioning

confidence: 99%

Optimal Placement of Charging Stations in Road Networks: A Reinforcement Learning Approach with Attention Mechanism

2023

View full text Add to dashboard Cite

show abstract

“…Existing studies on DS and EVCS pricing have sufficient preliminary work. Literature [8] constructed a three-level location model considering dynamic pricing, including user decision, EVCS pricing, and EVCS location decision, and trained the optimal pricing strategy for EVCS using a soft actorcritic (SAC) reinforcement learning algorithm. Literature [9] uses multiplicative weighted Voronoi diagrams to model and analyze the electricity demand of EVCS.…”

Section: Introductionmentioning

confidence: 99%

Stackelberg Game-based Coordinative Dispatch of EV Charging Stations and Urban Distribution Systems Considering Temporal-spatial Dynamic Traffic Flow

Zuo

2024

jes

View full text Add to dashboard Cite

This paper proposes a Stackelberg Game-based coordinative dispatch model of electric vehicle charging stations (EVCSs) and urban distribution systems (UDS) considering temporal-spatial dynamic traffic flow. The model is formulated hierarchically and consists of an upper-level problem and two lower-level problems. Firstly, a detailed EVCS dispatching model considering both electricity prices and charging service prices is developed in the upper-level. Then the electricity pricing model of UDS and travel decision model of EV users are proposed in the lower model. Particularly, a temporal-spatial dynamic model is developed to capture the traffic flow evolution in urban transport network preciously. EVCS, UDS operator (DSO) and EV users can make decisions independently as different stakeholders. Finally, a multi-layer iterative framework is designed to capture the tripartite benefit equilibrium of distribution grid, EV charging stations, and EV users, and to realize the effective solution of the model. Numerical studies based on a modified IEEE 33-bus system demonstrate the effectiveness and accuracy of our proposed approach.

show abstract

“…Their service scope research is mainly in target with airports (Anna et al, 2019), logistics parks (Wu et al, 2016), and urban economic zones (Dai, 2018). Notably, an inevitable market competition exists among multiple CSs in the region (Li et al, 2023a), and this competition also leads to an uneven market distribution. At present, most present facility planning methods are based on the Wilson model or breaking point theory by the regularized circle or the weighted Voronoi diagram (Chen et al, 2017;Li et al, 2023b), which can only divide the market area within a fixed range.…”

Section: Introductionmentioning

confidence: 99%

Charging station service scope division and real-time pricing strategy based on the strongest occupation method

Yang,

Tang,

Chen

et al. 2024

Front. Energy Res.

View full text Add to dashboard Cite

With the rapid construction of charging stations (CSs), charging station operators need to enhance their core competitiveness by precisely planning their service areas and formulating reasonable and effective pricing strategies. However, the regional competition among multiple charging station operators is generally ignored. In the traditional model, the service scope of CSs appears as regular circles, which is inconsistent with the market distribution law. In response to the irregular relationship between the dynamic service scope of CSs and the real-time charging price, a charging station service scope (CSSS) model is proposed by introducing the variable service field strength (SFS). First, the competitiveness of CSs is evaluated quantitatively, and the SFS of CSs is defined to describe the service scope of CSs by the strongest occupation method. Second, the impact of the charging price on the charging demand is analyzed based on the CSSS division model. In addition, the revenue of charging station operators and the stability of the power grid are considered to establish a real-time pricing optimization model. Finally, the numerical simulation is operated in Furong District of Changsha. It is shown that the proposed method effectively achieves more profits for charging stations and decreases the average power deviation of the whole region.

show abstract

Dynamic pricing based electric vehicle charging station location strategy using reinforcement learning

Cited by 11 publications

References 42 publications

Optimal Placement of Charging Stations in Road Networks: A Reinforcement Learning Approach with Attention Mechanism

Optimal Placement of Charging Stations in Road Networks: A Reinforcement Learning Approach with Attention Mechanism

Stackelberg Game-based Coordinative Dispatch of EV Charging Stations and Urban Distribution Systems Considering Temporal-spatial Dynamic Traffic Flow

Charging station service scope division and real-time pricing strategy based on the strongest occupation method

Contact Info

Product

Resources

About