AI Fleet Charging and Yard Management for Dynamic EV Dispatch
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional fleet management systems for electric vehicles face challenges due to unique servicing and operational characteristics, inefficient charging management, reduced yard space, and suboptimal block assignments, leading to operational inefficiencies and increased costs.
Innovation Solution
A system utilizing AI and machine learning to manage electric vehicle charging, dispatch operations, and yard management, incorporating real-time data from various sources, including telematics, to optimize charging, block assignments, and fleet operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If electric vehicle chargers are introduced into fleet yards, then charging capability is improved, but yard space and vehicle mobility are reduced
Solution Approach 1:
The yard management system dynamically adjusts yard configurations and charging schedules based on real-time vehicle locations, charger availability, and operational needs. This allows the system to optimize space utilization and vehicle mobility while ensuring charging capability, rather than using static yard layouts that waste space.
Solution Approach 2:
The system enables vehicles to autonomously locate and connect to available chargers using GPS tracking and real-time charger status data. This self-service capability eliminates the need for dedicated fixed parking spots at each charger, allowing vehicles to access charging infrastructure throughout the yard and freeing up space.
2Ease of operation
If traditional block configurations are used, then operational simplicity is maintained, but adaptability to route changes and new vehicles is reduced
Solution Approach 1:
The block assignment system dynamically reconfigures vehicle blocks based on real-time operational data including route changes, vehicle availability, and driver schedules. This dynamic approach maintains operational simplicity through automated adjustments while achieving high adaptability to changing conditions, eliminating the need for manual block reconfiguration.
Solution Approach 2:
The system continuously monitors operational parameters such as vehicle locations, charger status, and route deviations, using this feedback to automatically adjust block assignments and charging schedules. This closed-loop control maintains simplicity by automating the adaptation process while achieving high versatility in responding to operational changes.
3Ease of operation
If charger communication protocols are relied upon, then charging control is achieved, but system reliability is reduced when communication fails
Solution Approach 1:
The system uses telematics data from vehicles as an intermediary source to track charging status when charger communication protocols fail. By monitoring vehicle battery levels and charging current through telematics, the system maintains charging control and reliability even when direct charger communication is unavailable.
Solution Approach 2:
Vehicles provide their own charging status information through onboard telematics systems, eliminating dependency on charger communication protocols. This self-service approach ensures that charging data can be tracked and controlled through alternative means when the primary communication channel fails.
Data Source
AI summary
A system and method that takes as input streamed and real-time data from the electric vehicle, from the charging station, from vehicle routes and scheduling systems, weather, traffic, and terrain from appropriate data streams, and uses Artificial Intelligence software using Machine Learning Technology on the Internet Cloud to manage electric vehicle charging, dispatch operations, and yard management for electric fleets is provided which combines data-driven decision making, deep learning, optimization, and statistical methods.