Departure Time Model for Electric Vehicle Charging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining the departure time of electric vehicle batteries for intelligent charging are inaccurate, especially when users deviate from their routine, and require large datasets for reliable modeling, failing to account for irregular user behavior and deviations from normal consumption patterns.
Innovation Solution
A data-based departure time model that incorporates calendrical time specifications, consumption variable curves, and outlier detection using machine learning methods to predict the most probable departure time, allowing for adaptive charging strategies by analyzing usage patterns and detecting deviations from regular behavior.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional data-based departure time models are used, then large datasets are required for reliable modeling, but the accuracy deteriorates when users deviate from their routine behavior
Solution Approach 1:
The model dynamically adapts its prediction behavior based on the detected regularity of user behavior. When regular patterns are detected, it uses probabilistic predictions based on historical data. When irregularities or deviations are detected, it switches to alternative prediction strategies, making the system flexible and adaptive to changing user patterns without requiring extensive retraining datasets.
Solution Approach 2:
The system changes the parameters used for prediction based on the detected behavior pattern. It transitions between different prediction modes (probabilistic vs. alternative methods) depending on the regularity parameter of user behavior, allowing reliable predictions across both routine and irregular scenarios without compromising accuracy.
2Measurement precision
If probabilistic departure time models are used, then routine behavior can be predicted, but irregular user behavior and deviations from normal consumption patterns cannot be accounted for
Solution Approach 1:
The system continuously monitors consumption patterns and provides feedback on the regularity of user behavior. This feedback loop enables the system to detect deviations from normal patterns and switch prediction strategies accordingly, maintaining precision whether the user follows routine or exhibits irregular behavior.
Solution Approach 2:
The prediction approach dynamically adjusts between probabilistic modeling for routine behavior and alternative methods for irregular behavior, ensuring measurement precision is maintained across different user behavior scenarios without requiring the system to be rigidly fixed to one prediction method.
3Ease of operation
If simple charging control is used, then the charging process is straightforward, but opportunities for optimization through intelligent charging are lost
Solution Approach 1:
The system enables intelligent charging optimization through automated departure time prediction and charging strategy determination, allowing the charging process to self-optimize based on predicted user needs and energy prices without requiring complex manual intervention or user expertise in energy management.
Solution Approach 2:
The system performs preliminary departure time prediction and charging strategy planning before the actual charging process begins, enabling optimization of energy utilization by pre-determining the optimal charging schedule based on predicted departure times and energy price patterns, thus improving productivity without complicating the actual charging operation.
Data Source
AI summary
A method is disclosed for ascertaining a departure time specification, which indicates the most probable departure time specification of an electric vehicle from a building, in order to determine a charging strategy for an electric energy storage device of the electric vehicle. The method includes providing a data-based departure time model which is trained to provide a departure time specification on the basis of a calendrical time specification and on the basis of one or more temporal load variable curves of vehicle-external load variables within a specified period of time. The one or more variable curves characterizes the usage of one or more energy loads, in particular a domestic appliance and/or a heating and hot water system, of the building. The method further includes analyzing the data-based departure time model by specifying the calendrical time specification and the one or more load variable curves within the specified period of time in order to determine the departure time specification.