EV Range Prediction Using Fleet Energy Confidence Intervals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing range prediction algorithms for electric vehicles are inaccurate due to dynamic and uncertain factors such as traffic congestion and driver behavior, leading to unreliable energy consumption estimates.
Innovation Solution
A computer system that estimates energy consumption and variance for vehicle routes using reference data from secondary vehicles, calculates a confidence interval, and controls vehicle operation based on present energy levels to switch between different modes of travel, including charging stops if necessary, to improve range prediction and route planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If range prediction algorithms use past information such as recently travelled range and power used, then the algorithm is simple to implement, but the prediction accuracy deteriorates due to dynamic and uncertain factors like traffic congestion and driver behavior
Solution Approach 1:
The system performs preliminary actions by collecting and storing reference energy consumption data from multiple secondary vehicles before making predictions. This pre-collected data from fleet vehicles is used to establish baseline consumption patterns, allowing the algorithm to account for dynamic factors without requiring complex real-time processing during actual range prediction
Solution Approach 2:
The system introduces an intermediary layer of reference data from secondary vehicles that mediates between simple past-performance algorithms and complex real-time analysis. This reference data acts as a buffer that captures dynamic factors like traffic and weather effects without requiring the prediction algorithm itself to be complex
2Measurement precision
If the system collects reference energy consumption data from multiple secondary vehicles and calculates confidence intervals, then the energy consumption estimation accuracy is improved, but the data processing complexity increases
Solution Approach 1:
The system segments the data processing into distinct modules: data collection from secondary vehicles, statistical analysis to calculate mean and standard deviation, and confidence interval computation. This segmentation allows each processing step to be handled independently and efficiently, reducing overall complexity while maintaining high estimation accuracy
Solution Approach 2:
The system uses reference data copied from multiple secondary vehicles that have traversed similar routes. By copying and analyzing this existing fleet data rather than collecting new data in real-time, the system achieves high accuracy without requiring complex real-time sensing and processing infrastructure
3Reliability
If the vehicle controls operation mode based on present energy level relative to confidence interval, then the vehicle ensures sufficient energy for destination, but the control system complexity increases
Solution Approach 1:
The control system dynamically adjusts vehicle operation modes based on the comparison between present energy level and confidence interval boundaries. When energy falls below the lower bound, the system automatically switches to energy-saving modes or suggests charging stops, providing adaptive control that ensures energy sufficiency without requiring overly complex decision-making algorithms
Solution Approach 2:
The system implements feedback control by continuously monitoring present energy level against the statistically-derived confidence interval. This feedback mechanism automatically triggers appropriate control actions (mode switching, charging suggestions) when energy boundaries are approached, ensuring reliable energy management through a relatively simple threshold-based control logic
Data Source
AI summary
A computer system is configured to receive a start position and a planned destination position for an electric vehicle of a vehicle type, estimate energy consumption and variance for at least one route between the start position and the destination position for the vehicle type, based on reference energy consumption vehicle data collected from secondary vehicles, calculate a confidence interval for the estimated energy consumption and variance at a predetermined confidence level, determine a present energy level in the electrical energy storage system, in response to the present energy level being below the confidence interval upper limit, control the vehicle according to a first mode, the first mode including a first route between the start position and the destination position, and in response to the present energy level exceeding or being equal to the confidence interval upper limit, control the vehicle according to a second mode, the second mode including a second route between the start position and the destination position.