Route-Section Energy Prediction for Variable Traffic Conditions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing energy prediction technologies struggle to accurately predict energy consumption on routes with varying traffic conditions due to the use of a single prediction model, leading to reduced accuracy.
Innovation Solution
An energy prediction device that divides travel routes into sections and constructs separate consumption prediction models for each section, using proximity of condition information to determine route section merging and employing various machine learning methods to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single prediction model is used for the entire route, then the device complexity is reduced, but the measurement precision of energy consumption prediction deteriorates
Solution Approach 1:
The travel route is divided into multiple route sections based on traffic conditions, and separate prediction models are constructed for each section. This segmentation allows the system to capture the diverse effects of different traffic conditions on energy consumption, thereby improving prediction accuracy without requiring a single overly complex model.
Solution Approach 2:
Different prediction models are applied to different route sections according to their specific traffic conditions. Each section receives a tailored prediction approach that matches its local characteristics, such as congestion levels and traffic patterns, rather than applying a uniform model across the entire route.
2Measurement precision
If separate prediction models are constructed for each route section, then the measurement precision of energy consumption prediction is improved, but the device complexity increases
Solution Approach 1:
The route is segmented into multiple sections based on traffic conditions, allowing separate prediction models to be constructed for each section. This segmentation improves prediction accuracy by capturing local traffic characteristics while keeping each individual model relatively simple.
Solution Approach 2:
The prediction system dynamically adapts to different traffic conditions by selecting or constructing appropriate models for each route section. The system can adjust the number and characteristics of prediction models based on the diversity of traffic conditions encountered along the route.
Data Source
AI summary
An energy prediction device includes a route setting unit configured to divide a travel route traveled by a vehicle and set route sections into which the travel route is divided and a model construction unit configured to construct a consumption prediction model for predicting an energy consumed by the vehicle for each route section.