Charging Pile Recommendation Using Queue and Failure Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
New energy vehicles face challenges with long queues at public charging stations and potential charging pile failures, leading to inconvenience and inefficiency in charging processes.
Innovation Solution
An IoT system for new energy vehicles in smart cities that includes a user platform, service platform, and charging pile management platform, utilizing machine learning models to recommend the best charging piles based on travel demand, queuing information, location, environmental factors, and failure rates, thereby optimizing the charging experience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If users rely on public charging piles on the streets, then charging service coverage is improved, but waiting time increases due to long queues
Solution Approach 1:
The system performs preliminary actions by predicting charging pile status and queue lengths before users arrive. The recommendation model pre-calculates the most suitable charging piles based on historical data, current status, and predicted future states, allowing users to make informed decisions before traveling to charging locations, thereby reducing actual waiting time while maintaining broad service coverage
2Adaptability or versatility
If users use public charging piles, then charging accessibility is improved, but reliability deteriorates due to charging pile failures
Solution Approach 1:
The system implements continuous feedback mechanisms by collecting real-time status data from charging piles, user charging experiences, and failure information. This feedback is processed by the recommendation model to dynamically adjust recommendations, avoiding charging piles with high failure rates and prioritizing reliable charging infrastructure, thus maintaining accessibility while improving reliability through data-driven selection
Solution Approach 2:
The system enables self-service by allowing users to independently query charging pile reliability information and receive personalized recommendations without manual intervention. Users can access real-time status, historical performance, and predicted reliability of charging piles through the platform, empowering them to make informed choices and avoid unreliable charging locations
3Measurement precision
If comprehensive charging information is collected and processed, then recommendation accuracy is improved, but system complexity increases
Solution Approach 1:
The system applies segmentation by dividing the complex recommendation task into distinct processing stages: data collection from multiple sources, preliminary filtering of charging pile status, prediction of queue lengths and failure rates, and final recommendation generation. Each stage handles specific types of information with dedicated processing logic, reducing overall system complexity while maintaining comprehensive data analysis for high recommendation accuracy
Data Source
AI summary
The present disclosure provides a method of charging information recommendation for a new energy vehicle in a smart city. This method is executed by a charging pile management platform. This method includes: based on the service platform, obtaining a charging request of a user by the user platform; based on the charging request, determining candidate charging piles; based on queuing information of the candidate charging piles and time information for going to the candidate charging piles, sorting the candidate charging piles to determine an object charging pile; processing the travel demand information, location information, and the environmental information of the object charging pile based on a recommendation model to determine first sub-recommendation information; based on a failure rate of the object charging pile, determining second sub-recommendation information; based on the first sub-recommendation information and the second sub-recommendation information, determining recommendation information; and feeding back the recommendation information to the user.