The Coordinated Charging Pricing Approach for Charging Stations with Multi-agent Deep Reinforcement Learning

As the number of electric vehicles on the road increases, there is a corresponding rise in the number of charging facilities available. To entice electric vehicle owners to utilize their services, more operators are entering the market with competitive pricing incentives for charging. However, it is important to implement a pricing mechanism that strikes a balance between supply and demand and avoids the issues of under or oversupply, ultimately leading to rational utilization of resources. An appropriate pricing mechanism can also promote healthy and sustainable growth of the industry. To achieve the desired outcome and develop the synergy of charging facility operators in a competitive environment, we propose a multi-intelligence-based collaborative pricing mechanism for charging facility operators. This mechanism ensures a balance of revenue among multiple operators and prevents harmful price competition between charging facility operators. To learn the coordinated charging pricing strategy, we adopt the multi-agent deep deterministic policy gradient method. This approach incorporates the response pattern of mobility-on-demand vehicles to provide an optimal solution for charging pricing strategies.