Edge-Cloud Traffic Management via Data Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems face challenges in managing traffic effectively due to the vast amount of data generated by vehicles, which leads to significant storage and communication resource requirements, making real-time processing and analysis cumbersome.
Innovation Solution
A method that pre-filters vehicle-related data before transmission to an AI system, using machine learning to infer vehicle actions and generate compensation instructions, reducing the data exchanged and processed, thereby optimizing traffic management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If all vehicle data is transmitted to cloud for processing, then processing accuracy is improved, but communication resource consumption increases significantly
Solution Approach 1:
The system segments vehicle data into two categories: raw sensor data processed locally by edge computing devices, and processed results transmitted to cloud. This segmentation allows accurate local processing while minimizing communication bandwidth consumption by only transmitting essential processed information rather than all raw data.
Solution Approach 2:
Edge computing devices serve as intermediaries between vehicles and cloud servers. These edge devices perform preliminary data processing and filtering, transforming raw vehicle data into condensed processed results before transmission to the cloud, thereby reducing communication resource consumption while maintaining processing accuracy.
2Loss of information
If all vehicle data is stored locally, then data availability is improved, but storage resource requirements increase enormously
Solution Approach 1:
The system segments data storage responsibilities between edge computing devices and cloud servers. Edge devices store processed results and essential vehicle data locally to ensure data availability, while less critical raw data is stored in the cloud, thereby balancing local data availability with reduced storage requirements at the edge.
Solution Approach 2:
The system creates selective copies of essential vehicle data at edge computing devices rather than storing all raw data. This copying approach ensures that critical data remains locally available for real-time processing while reducing the storage burden on both edge devices and cloud infrastructure.
3Loss of time
If edge computing devices process all data locally, then response time is improved, but device complexity increases
Solution Approach 1:
The system segments computational tasks between edge computing devices and cloud servers. Edge devices handle time-critical processing tasks that require fast response times, while less time-sensitive complex computations are offloaded to the cloud, thereby achieving fast response times without excessive edge device complexity.
Solution Approach 2:
The system implements partial local processing at edge devices, focusing only on the essential data processing needed for timely responses. Rather than attempting to process all data locally, the edge devices perform selective processing of critical information, reducing device complexity while maintaining acceptable response times for urgent operations.
Data Source
AI summary
Systems and methods are provided for implementing traffic management techniques in connected, but not necessarily autonomous vehicles. In accordance with one embodiment, a method comprises determining a first vehicle instruction based on vehicle-related data; transmitting the first vehicle instruction to a first vehicle; when the first vehicle performs an action, inferring whether the action is in response to the first vehicle instruction; and based on the inference, transmitting a second vehicle instruction with a compensation action to a second vehicle.