Proactive Downlink Scheduling Validation for Unusable Predicted Traffic
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing 5G wireless communication systems face challenges in managing varying resource demands and ensuring efficient delivery of downlink traffic due to unpredictable user behavior and traffic patterns, particularly in scenarios requiring ultrareliable and low latency communications (URLLC) and enhanced mobile broadband (eMBB).
Innovation Solution
User equipment employs a learning model to predict traffic patterns and transmit prediction reports to the radio network node, allowing proactive scheduling of resources based on confidence level criteria, and avoids transmitting acknowledgement for unusable traffic to optimize resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the user equipment transmits acknowledgement for all received downlink traffic, then the radio network node can maintain accurate scheduling information, but unnecessary resource allocation occurs for unusable traffic
Solution Approach 1:
The patent extracts the acknowledgement transmission for unusable traffic from the general acknowledgement mechanism. When the learning model determines that predicted traffic will not be usable by the application, the system selectively excludes acknowledgement transmission for that specific traffic, separating it from the normal ACK/NACK feedback loop. This prevents wasted scheduling resources while maintaining accuracy for usable traffic.
Solution Approach 2:
The system implements a feedback mechanism where the learning model's prediction results directly influence acknowledgement transmission behavior. The learning model continuously monitors traffic patterns and provides feedback to the MAC layer about which downlink traffic is likely to be unusable, creating a closed-loop system that adapts feedback transmission based on predicted utility.
2Reliability
If the learning model predicts traffic with high confidence threshold, then false scheduling predictions are reduced, but legitimate traffic predictions may be missed
Solution Approach 1:
The patent makes the confidence threshold dynamic rather than static. The threshold adapts based on the specific traffic flow characteristics, application requirements, and historical prediction accuracy. For time-sensitive applications, the threshold may be lower to capture more predictions, while for less critical traffic, the threshold remains higher to ensure accuracy. This dynamic adjustment resolves the contradiction between being too conservative and too aggressive.
Solution Approach 2:
The system changes the confidence threshold parameter based on multiple factors including application QoS requirements, traffic flow characteristics, and network conditions. By adjusting this critical parameter dynamically, the system optimizes the balance between prediction reliability and traffic delivery efficiency for different scenarios.
3Productivity
If proactive scheduling is enabled based on traffic prediction, then resource allocation efficiency improves, but system complexity increases due to learning model integration
Solution Approach 1:
The patent introduces a learning model as an intermediary component between the MAC layer and the application layer. This intermediary analyzes traffic patterns and provides prediction insights without requiring complex modifications to the core scheduling algorithms. The learning model acts as a bridge that translates application behavior into scheduling-relevant information, simplifying the overall system architecture.
Solution Approach 2:
The learning model operates autonomously at the user equipment, self-training on local traffic patterns without requiring centralized coordination or complex network-side processing. This self-service approach enables proactive scheduling capabilities while keeping the additional complexity localized to the device rather than propagating through the entire network infrastructure.
Data Source
AI summary
A user equipment may use a learning model to predict user behavior, or traffic corresponding thereto, and may transmit, to a radio network node, a prediction report indicative of the predicted behavior/traffic. Based on the prediction report the node may proactively schedule predicted downlink resources to facilitate delivery, to the user equipment, of predicted downlink traffic that may correspond to the indicated predicted behavior/traffic. The user equipment may indicate that successfully decoded downlink traffic, received from the node according to the scheduled predicted downlink resources, is invalid, or not usable, by avoiding transmission of HARQ feedback corresponding to the received traffic or by transmitting an invalid scheduled resource indication. The user equipment may analyze a confidence level corresponding to the learning model with respect to a confidence level threshold, which may be dynamically increased by the node in response to invalid traffic, to determine whether to transmit a prediction report.