Vehicle Energy Prediction Algorithm Error Minimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle range prediction systems are inaccurate as they do not consider the full nature of the journey, leading to unreliable estimates, especially for vehicles with long refueling/recharging intervals or sparse refueling/recharging stations.
Innovation Solution
A system and method that obtain journey, vehicle, and non-vehicle data to predict energy requirements using an energy prediction algorithm, which adjusts by calculating errors from historical journeys to improve accuracy over time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If existing vehicle range prediction systems use simple extrapolation of recent consumption data, then the system complexity is low, but the measurement precision of energy requirement prediction deteriorates
Solution Approach 1:
The system changes parameters by incorporating multiple data dimensions (journey data, vehicle data, non-vehicle data) and using machine learning algorithms to dynamically adjust prediction models, transforming simple extrapolation into a multi-parameter prediction system that improves accuracy without excessive complexity
Solution Approach 2:
The patent replaces simple mechanical extrapolation methods with electronic computing and machine learning algorithms, using processor-based systems to analyze historical data and predict energy requirements, thereby achieving higher precision through computational methods
2Measurement precision
If the system uses comprehensive journey data, vehicle data and non-vehicle data with machine learning algorithms, then the measurement precision of energy requirement prediction improves, but the device complexity increases
Solution Approach 1:
The system achieves universality by creating a multi-functional prediction platform that handles various data types (journey, vehicle, non-vehicle data) and serves multiple vehicles and drivers, where a single machine learning model structure can be adapted to different prediction scenarios without requiring separate systems
Solution Approach 2:
The system implements self-service through automated machine learning model training and updating, where the system automatically learns from historical data and improves predictions without manual intervention, reducing operational complexity while maintaining high precision
3Reliability
If the energy prediction algorithm is adjusted using historical journey data and error minimization, then the reliability of energy requirement prediction improves, but the loss of time for data processing increases
Solution Approach 1:
The system applies preliminary action by pre-processing and storing historical journey data, vehicle data, and non-vehicle data in structured formats before actual prediction is needed. Machine learning models are trained in advance on historical data, so when real-time prediction is required, the system can quickly retrieve pre-processed data and generate predictions without extensive real-time computation
Solution Approach 2:
The system implements dynamics by adaptively adjusting the prediction model based on accumulated historical data. As more historical journeys are processed, the machine learning algorithm dynamically updates its parameters to improve reliability, balancing the trade-off between processing time and prediction accuracy over time
Data Source
AI summary
A system for determining an energy requirement of a vehicle for a journey. The system includes a predictor mechanism to predict, using an energy prediction algorithm, a vehicle energy requirement for the journey. The system includes an updater mechanism configured to refine the energy prediction algorithm for the vehicle by determining for each of a number of historical journeys undertaken by the vehicle, an error between an actual vehicle energy usage for the historical journey and a predicted energy usage derived using the energy prediction algorithm for the historical journey, each historical journey of the of the number of historical journeys being associated with a respective error of a set of errors. An aggregate error is calculated from the set of errors. The updater is arranged to adjust the energy prediction algorithm to reduce the aggregate error.