EV Power Prediction Model Error Feedback Loop
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electric vehicle power consumption prediction models struggle to accurately calculate power usage due to unaccounted factors like driver skill and other difficult-to-quantify variables, leading to inaccurate predictions.
Innovation Solution
An information processing apparatus that calculates power consumption predictions using a prediction model incorporating error data from past movements, allowing for more accurate forecasting by adjusting for factors not initially considered.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If a mathematical model using observation values (traveling distance, speed, temperature) is used to predict power consumption, then the prediction can be calculated in advance, but the prediction accuracy deteriorates due to unaccounted factors like driver skill
Solution Approach 1:
The system collects actual power consumption data from past movements and uses it to update the prediction model through error calculation. The error between predicted and actual values is fed back into the model to improve future predictions, allowing the system to account for factors like driver skill that were initially unquantified.
Solution Approach 2:
The prediction model is updated in advance using historical data before new predictions are made. By pre-calculating errors from past movements and incorporating them into the model, the system prepares improved prediction capabilities ahead of time, maintaining both advance prediction timing and improved accuracy.
2Device complexity
If traditional mathematical models are used, then the model structure remains simple, but the ability to reflect difficult-to-quantify factors deteriorates
Solution Approach 1:
The system transforms unquantifiable factors into usable parameters by calculating prediction errors from actual data. Instead of directly measuring difficult-to-quantify factors like driver skill, the system uses the difference between predicted and actual power consumption as a parameter that captures their effect, maintaining model simplicity while improving reliability.
Solution Approach 2:
The prediction error serves as an intermediary that bridges the gap between simple mathematical models and complex real-world factors. Rather than directly incorporating difficult-to-measure variables, the error metric mediates their influence on the prediction model, allowing simple models to reflect complex realities.
Data Source
AI summary
According to an embodiment, an information processing apparatus includes one or more hardware processors configured to calculate a prediction value of an amount of electric power consumed for a movement to be predicted, based on a prediction model in which the amount of electric power consumed by a moving object is an objective variable, one or more factor values that affect the amount of electric power consumed for the movement of the moving object to be predicted, and an error between the prediction value obtained by the prediction model and an actual measured value.