Charging Station Pricing Model for Balanced Demand Allocation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Public charging stations face issues of unbalanced battery charging demand and low utilization rates due to unified dynamic price adjustments, leading to a poor charging experience for drivers and hindering the expansion of rechargeable vehicles.

Innovation Solution

A method and apparatus for training an information adjustment model of charging stations using multi-agent reinforcement learning, employing a deep deterministic policy gradient algorithm to optimize charging station operations and enhance coordination among stations, thereby improving utilization rates.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If unified dynamic price adjustment at fixed time intervals is implemented, then charging station operations are simplified, but demand balance and utilization rate deteriorate

Engineering Contradiction:
Improvecharging station operation simplicityVSAvoidcharging station utilization rate
Core Design Contradiction:
Ease of operationVSProductivity

Solution Approach 1:

The patent implements dynamic pricing where charging stations adjust prices in real-time based on current demand conditions, vehicle battery states, and environmental factors, rather than using fixed time-interval adjustments. This dynamic approach allows the system to respond flexibly to changing conditions, optimizing utilization rates while maintaining operational simplicity through automated decision-making algorithms.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system incorporates feedback mechanisms that continuously monitor charging demand, station utilization, and vehicle states, then use this information to adjust pricing strategies. The feedback loop enables the system to learn from past performance and optimize future pricing decisions, resolving the contradiction between operational simplicity and utilization optimization.

Inventive Principle:
Principle #23Feedback

2Stability of the object's composition

If centralized control is used for price adjustment, then system coordination is improved, but system complexity and computational requirements increase

Engineering Contradiction:
Improvecharging station coordinationVSAvoidmulti-agent system complexity
Core Design Contradiction:
Stability of the object's compositionVSDevice complexity

Solution Approach 1:

The patent divides the centralized control system into multiple independent agent modules, each responsible for specific charging stations or regions. These agents operate semi-independently with defined interaction protocols, reducing overall system complexity while maintaining coordination through standardized communication interfaces and shared objective functions.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system transitions from traditional centralized-hierarchical control to a distributed multi-agent architecture that operates across multiple dimensions of autonomy and coordination. This dimensional shift allows complex coordination tasks to be distributed across numerous simple agents, reducing the computational burden on any single component while maintaining system-wide coherence.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentEP4220487B1Method and apparatus for training information adjustment model of charging station, storage medium and product
Publication Date: 2025.10.15 BEIJING BAIDU NETCOM SCI & TECH CO LTD
  • EP4220487B1 patent drawingFigure 1
  • EP4220487B1 patent drawingFigure 2
  • EP4220487B1 patent drawingFigure 3

AI summary

A method and apparatus for training an information adjustment model of a charging station, an electronic device, and a storage medium. An implementation comprises: acquiring a battery charging request, and determining environment state information corresponding to each charging station in a charging station set; determining, through an initial policy network, target operational information of the each charging station in the charging station set for the battery charging request, according to the environment state information; determining, through an initial value network, a cumulative reward expectation corresponding to the battery charging request according to the environment state information and the target operational information; training the initial policy network and the initial value network by using a deep deterministic policy gradient algorithm; and determining a trained policy network as an information adjustment model corresponding to the each charging station.