EV Charging Routing Under Power Distribution Constraints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing demand for electric vehicle charging poses challenges to power distribution systems, including increased rates, instability, and negative outcomes, which existing technologies struggle to address effectively by optimizing routing and power distribution management.
Innovation Solution
A computer system that routes electric vehicles to optimal charging stations based on battery levels, location, power distribution system attributes, and traffic data, using a Deep Reinforcement Learning approach with a feasibility diamond to ensure compliance with power system constraints, and modifies the exploration process and optimality criterion to guarantee feasibility and optimality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If electric vehicle charging demand increases, then more vehicles can be charged, but power distribution system stability deteriorates
Solution Approach 1:
The system performs preliminary routing decisions for electric vehicles to charging stations by considering power distribution constraints before charging occurs. The centralized controller predicts future power distribution states and pre-determines optimal charging station assignments, preventing stability issues before they arise rather than reacting after instability occurs.
Solution Approach 2:
The system dynamically adjusts routing decisions based on real-time power distribution conditions and predicted future states. The centralized controller continuously updates routing recommendations as power distribution constraints change, making the charging system adaptive to varying grid conditions rather than static.
2Productivity
If routing optimization is implemented, then charging efficiency improves, but system complexity increases
Solution Approach 1:
The centralized controller serves multiple functions simultaneously: it monitors power distribution conditions, predicts future states, determines optimal routing, and manages charging station assignments. By consolidating these diverse functions into a single control system, the patent achieves complex optimization without proportionally increasing overall system complexity.
Solution Approach 2:
The system implements feedback loops where the centralized controller continuously monitors actual power distribution conditions and compares them with predicted states. This feedback mechanism allows the system to self-correct and refine routing decisions based on actual system performance, reducing the need for complex manual intervention.
3Reliability
If power distribution constraints are strictly enforced, then system reliability improves, but charging flexibility decreases
Solution Approach 1:
The system adds the time dimension to routing decisions by considering not only current power distribution constraints but also predicted future states. This temporal dimension allows the system to find routing solutions that may temporarily approach constraint boundaries but ensure long-term compliance, thereby maintaining flexibility while guaranteeing reliability.
Solution Approach 2:
The centralized controller acts as an intermediary between power distribution constraints and vehicle routing decisions. Rather than directly imposing rigid constraints on routing, the controller translates complex power system requirements into flexible guidance recommendations that maintain reliability while preserving charging flexibility.
Data Source
AI summary
A computer system for real-time coordinated operation of power distribution systems and electric vehicles accesses vehicle location information for one or more vehicles. Additionally, the system accesses charging station locations for one or more charging stations within a power distribution system. The computer system also accesses power distribution information describing voltage and/or current flow limits for the power distribution system. Further, the computer system routes a vehicle selected from the one or more vehicles to a first charging station location for charging, wherein the routing of the vehicle accounts for a current battery charge level of the vehicle and the power distribution information.