In-Vehicle Network Selection Using Predicted QoS for Seamless Handover
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Vehicle network devices experience reconnection delays due to switching between networks, which disrupts seamless connectivity, and there is a need to predict connectivity quality to facilitate smooth handovers.
Innovation Solution
A method using machine learning to predict Quality of Service (QoS) metrics for available networks based on external factors and network performance characteristics, enabling seamless handovers by selecting optimal networks for in-vehicle devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If network devices switch between networks to meet QoS constraints, then connectivity quality is improved, but reconnection delay increases
Solution Approach 1:
The system performs preliminary actions by predicting future network QoS metrics before actual connectivity issues occur. The machine learning model forecasts network performance based on historical data and patterns, allowing the system to proactively switch networks before degradation happens, thereby avoiding reconnection delays while maintaining quality.
Solution Approach 2:
The system continuously monitors actual network performance and compares it against predicted QoS metrics. This feedback loop allows the system to adjust its network switching decisions in real-time, ensuring that switches are triggered at optimal moments to maintain connectivity quality while minimizing disruption.
2Reliability
If network switching is performed to maintain QoS constraints, then service quality is improved, but connection stability deteriorates
Solution Approach 1:
By predicting future network conditions in advance, the system can plan network switches beforehand, ensuring that transitions occur during optimal moments when connectivity disruption is minimized. This preliminary planning maintains service quality while preserving connection stability during transitions.
Solution Approach 2:
The system prepares for potential connectivity issues by having predictive models ready to forecast network degradation. This cushioning approach allows for smooth, pre-planned transitions rather than reactive switching, thereby maintaining stability while ensuring service quality constraints are met.
3Reliability
If real-time network monitoring is implemented, then connectivity quality is improved, but system complexity increases
Solution Approach 1:
The system uses feedback mechanisms to monitor network performance and compare actual QoS against predicted values. This feedback-driven approach simplifies decision-making by automatically triggering network switches based on predefined thresholds and predictions, reducing the need for complex manual control systems while maintaining high connectivity quality.
Solution Approach 2:
The system performs self-service by using its own monitored data to feed into predictive models, which then automatically guide network switching decisions. This self-contained loop eliminates the need for external complex control systems, maintaining connectivity quality while keeping the overall system architecture relatively simple.
Data Source
AI summary
A method for smart guided selection of networks includes detecting a wireless connectivity issue between. The in-vehicle network device is inside a vehicle, and the network access device may be inside or outside the vehicle. The method further includes receiving network data. The network data includes a list of available networks and network performance characteristics of each of the available networks. The method includes predicting, using machine learning, quality of service (QoS) metrics of the available networks along a trip of a vehicle and selecting a one or more networks from the list of available networks for one or more in-vehicle network devices based constraint solving on the predicted QoS metrics of the list available networks and QoS constraints.