Vehicular Edge Server Switching Using Digital Twin Latency Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The latency associated with accessing edge server resources in edge computing for connected vehicles can be excessive in certain situations, making it inefficient to always rely on these resources, and thus a mechanism is needed to determine when to use onboard resources instead.
Innovation Solution
A switching system that uses a combination of historical data and digital twin simulations to determine when to utilize onboard or edge server resources, by comparing the current driving context with historical and simulated latency data to make informed decisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If vehicles always access edge server resources, then computational ability is expanded and data sharing is enabled, but latency becomes excessive in certain situations
Solution Approach 1:
The system dynamically switches between onboard and edge server resources based on real-time conditions. The switching mechanism evaluates current driving context, historical performance data, and predicted latency to determine the optimal computing resource, making the system adaptive rather than static.
Solution Approach 2:
The system performs preliminary evaluation by comparing current driving context with historical data and digital twin simulations before actually switching resources. This predictive approach allows the system to anticipate latency issues and proactively select the best computing resource in advance.
2Loss of time
If vehicles use onboard resources, then latency is reduced, but computational ability is limited compared to edge server resources
Solution Approach 1:
The system is designed to perform multiple functions by utilizing both onboard computing resources and edge server resources. The switching mechanism enables the vehicle to leverage the computational power of edge servers when needed while maintaining the ability to operate independently using onboard resources, creating a multi-functional computing architecture.
3Productivity
If a switching mechanism is implemented, then optimal resource selection is achieved, but system complexity increases
Solution Approach 1:
The system uses digital twin simulations to create virtual copies of the vehicle's operating conditions and performance characteristics. By comparing real-world data with digital twin predictions, the system can evaluate potential switching decisions without requiring complex real-time simulations, reducing the actual computational burden.
Solution Approach 2:
The switching mechanism acts as an intermediary layer between the vehicle's onboard systems and edge server resources. It manages the complexity of resource selection by implementing a standardized evaluation framework that compares driving context, historical performance, and predicted outcomes, simplifying the decision-making process.
4Measurement precision
If historical data and digital twin simulations are used for switching decisions, then prediction accuracy is improved, but data processing requirements increase
Solution Approach 1:
The system applies partial action by selectively processing only the most relevant historical data and digital twin simulations for each switching decision. Rather than analyzing all available data comprehensively, the mechanism focuses on key parameters such as driving context similarity and predicted latency thresholds, reducing processing requirements while maintaining prediction accuracy.
Data Source
AI summary
The disclosure includes embodiments including a vehicular edge server switching mechanism based on historical data and digital twin simulations. A method includes causing a sensor set of a connected vehicle to determine a current driving context of the connected vehicle. A method includes comparing the current driving context to a set of digital twin data and a set of historical data to determine a predicted latency for using offboard computing resources of an edge server. The method includes determining that the predicted latency for using the offboard computing resources satisfies a threshold for the predicted latency. The method includes executing a switching decision that includes deciding to use the offboard computing resources of the edge server based on the comparing of the current driving context to the set of digital twin data and the set of historical data and the determining that the threshold for the predicted latency is satisfied.