Location Prediction Network Scheduler for Wireless Traffic
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network communication systems fail to effectively manage dynamic user equipment (UE) mobility and traffic due to rapid changes in UE movements and network conditions, leading to inefficiencies in resource allocation and quality of service (QoS) delivery.
Innovation Solution
A location prediction-based network scheduler that predicts UE locations and available network resources for future time slots, determining weight values as priority parameters to optimize data forwarding, routing, and resource allocation, integrating with traffic engineering (TE) functions to dynamically select the best routes and time slots for data transmission.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If current network scheduling methods are used, then network resources are allocated based on current UE location, but the system cannot handle rapid or dynamic changes in UE movements or network conditions
Solution Approach 1:
The system performs preliminary actions by predicting UE location and network resource availability for future time slots before actual data transmission occurs. The network scheduler obtains location prediction information and available network resource prediction for multiple future time slots, then determines weight values in advance to optimize data forwarding decisions when they are needed.
Solution Approach 2:
The system implements dynamics by continuously updating location predictions and network resource assessments based on real-time conditions. The scheduler dynamically adjusts weight values and data forwarding decisions for each time slot based on the predicted UE trajectory and available network resources, enabling the system to adapt to rapid changes in UE movement and network state.
2Productivity
If location prediction for next time window is obtained, then future data forwarding can be optimized, but the system complexity increases
Solution Approach 1:
The system segments the future time window into multiple discrete time slots, allowing the scheduler to handle prediction and optimization in manageable increments. Instead of processing the entire future period at once, the scheduler obtains predictions and determines weight values for each time slot sequentially, reducing computational complexity while maintaining optimization effectiveness.
Solution Approach 2:
The system uses parameter changes by transforming complex multi-dimensional optimization problems into weight value determination. The scheduler converts location prediction information and network resource predictions into weight values that can be directly used for data forwarding decisions, simplifying the implementation while maintaining optimization capability.
3Reliability
If weight values are determined for multiple next time slots, then comprehensive resource allocation is achieved, but the computation time increases
Solution Approach 1:
The system performs preliminary computation by obtaining location prediction information and network resource predictions for future time slots in advance. The scheduler determines weight values for multiple time slots before actual data transmission occurs, allowing for comprehensive resource allocation planning while managing computation time through proactive scheduling decisions.
Data Source
AI summary
Embodiments are provided for traffic scheduling based on user equipment (UE) in wireless networks. A location prediction-based network scheduler (NS) interfaces with a traffic engineering (TE) function to enable location-prediction-based routing for UE traffic. The NS obtains location prediction information for a UE for a next time window comprising a plurality of next time slots, and obtains available network resource prediction for the next time slots. The NS then determines, for each of the next time slots, a weight value as a priority parameter for forwarding data to the UE, in accordance with the location prediction information and the available network resource prediction. The result for the first time slot is then forwarded from the NS to the TE function, which optimizes, for the first time slot, the weight value with a route and data for forwarding the data to the UE.