Cloud-Based Charge Route Estimation for Electric Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for electric vehicles (EVs) face challenges in accurately estimating optimized routes to high power charge stations due to the stochastic nature of charge station locations, efficiency, availability, and costs, exceeding the processing capabilities of on-board EV processors.
Innovation Solution
A cloud-based neural network remote server system aggregates real-time data from global EV fleets to predict optimal charge routes and times by analyzing vehicle and charging station performance, using deep-learning engines to discover patterns and provide continuously updated, accurate estimates to individual EVs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If on-board HEV processors are used to determine optimal charge routes, then real-time route adjustment is possible, but processing accuracy and capability are insufficient due to limited computational resources
Solution Approach 1:
A cloud-based server acts as an intermediary between HEVs and charging stations, performing complex analytical computations remotely. The server receives vehicle performance data, charge station data, and environmental data, then generates optimized route recommendations that are communicated back to vehicles, resolving the contradiction by moving processing capability from limited on-board processors to powerful external servers.
Solution Approach 2:
The system transitions from two-dimensional local processing to three-dimensional cloud-based processing by adding the spatial dimension of remote server computation. This allows vastly increased computational resources to be applied to route optimization problems while keeping on-board vehicle systems relatively simple.
2Measurement precision
If more variables and parameters are considered for route optimization, then accuracy improves, but computational complexity exceeds on-board processor capabilities
Solution Approach 1:
The cloud server serves as an intermediary that handles the computational burden of analyzing multiple variables including vehicle performance data, charge station capabilities, environmental conditions, and historical charging patterns. This enables comprehensive multi-parameter analysis without overloading on-board processors, maintaining both accuracy and processing speed.
Solution Approach 2:
The computational task is segmented into two parts: data collection and preliminary processing by on-board processors, and complex analytical computation by the cloud server. This segmentation allows each component to operate within its capability limits while achieving overall system optimization.
3Measurement precision
If real-time data from global fleet is aggregated and analyzed, then charge station selection accuracy improves, but data processing time and computational resources increase
Solution Approach 1:
The cloud server continuously aggregates and pre-processes data from the global HEV fleet, maintaining updated databases of vehicle performance, charge station status, and environmental conditions. This preliminary action ensures that when a specific route optimization query is received, the server can quickly retrieve and analyze pre-processed data rather than starting from scratch, reducing real-time processing time while maintaining high accuracy.
Solution Approach 2:
The system implements continuous data collection and analysis from the global fleet, with the cloud server constantly updating its models and databases. This continuous operation ensures that the most current and accurate information is always available for route optimization decisions, improving prediction accuracy without requiring intensive batch processing that would cause time delays.
Data Source
AI summary
A hybrid electric vehicle (HEV) that includes a communication unit configured to periodically respond to a charge signal, and to adjust a travel route and charge waypoint, according to an estimated charge station travel route and waypoint charge time received from a remote fleet server. The estimates are received in response to periodic operating conditions that are generated and communicated to the server. The operating conditions include one or more of charge station, environment, and location data, vehicle data, and battery performance data, among other data. The controller further configured to respond to travel route and/or charge complete signals, and to generate and store an estimate error as a difference between the actual and estimated optimal charge route and charge time. The controller readjusts at least one of the travel route and charge waypoint, responsive to the updated estimated optimal charge route and waypoint charge time received from the server.