Mobility Sharing Fleet Relocation via RNN Prediction and MCMF Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional mobility sharing systems face challenges in implementing a one-way service due to high parking costs and vehicle concentration issues, necessitating an efficient mobility location strategy.
Innovation Solution
A mobility sharing system utilizing a deep learning algorithm, comprising a first vehicle determination unit, a prediction unit, a second vehicle determination unit, and a route setting unit, to optimize vehicle location and routing through unit area division, bidirectional RNN prediction, and MCMF algorithm application.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a one-way service is implemented in a conventional mobility sharing system, then user convenience is improved, but parking costs increase and vehicle concentration problems occur
Solution Approach 1:
The service area is divided into multiple unit areas, and vehicle relocation is performed at the unit area level rather than city-wide. This segmentation reduces the scale of each relocation task, lowering parking costs while enabling one-way service convenience for users.
Solution Approach 2:
The system performs preliminary vehicle relocation before peak demand periods by predicting future vehicle distribution patterns. Vehicles are proactively moved to anticipated high-demand areas, preventing vehicle concentration during critical times and reducing emergency relocation costs.
2Adaptability or versatility
If vehicle relocation is performed to prevent vehicle concentration, then service coverage is improved, but relocation costs increase
Solution Approach 1:
By dividing the service area into unit areas and performing relocation at this granular level, the system achieves precise service coverage control. Only the necessary vehicles are relocated to specific unit areas, minimizing overall relocation costs while maintaining comprehensive service coverage where needed.
Solution Approach 2:
The system dynamically adjusts relocation parameters including timing, destination, and vehicle quantity based on predicted demand patterns. By optimizing these parameters, the system achieves effective service coverage with minimal relocation costs.
3Measurement precision
If a deep learning model is used for vehicle demand prediction, then prediction accuracy is improved, but computational time increases
Solution Approach 1:
The prediction task is segmented by unit area, with the deep learning model performing predictions independently for each unit area. This segmentation reduces the computational burden on each individual prediction task while maintaining high accuracy through the power of deep learning algorithms.
Solution Approach 2:
The system performs preliminary model training and parameter optimization before actual prediction tasks. By pre-training the deep learning model on historical data and optimizing its parameters, the system achieves high prediction accuracy with reduced computational time during actual vehicle demand prediction.
Data Source
AI summary
The present invention relates to a mobility sharing system that operates a mobility location strategy using a deep learning algorithm. A first vehicle determination unit divides an entire area into a plurality of unit areas and determines the number of vehicles to be located in each of the plurality of unit areas. A prediction unit, by inputting a prediction data set generated based on the number of vehicles departing from each of stations and the number of vehicles arriving at each of the stations into a bidirectional recurrent neural network (RNN) model, predicts the number of vehicles departing from each of the stations and the number of vehicles arriving at each of the stations during a target time interval. A second vehicle determination unit sets the number of location vehicles to be located at each of the stations in the target time interval. A route setting unit applies an MCMF algorithm to the number of location vehicles to be located at each of the stations to determine a mobility location route for placing vehicles at each of the stations.