Proactive Downlink Radio Resource Scheduling Using Traffic Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing 5G wireless communication systems face challenges in managing varying resource demands from mobile devices with different quality-of-service classes, particularly in handling ultrareliable and low latency communications (URLLC) and enhanced mobile broadband (eMBB), where resource loads and reliability vary significantly.
Innovation Solution
A radio network node uses a learning model to predict traffic patterns and proactively schedules resources based on prediction reports, adjusting confidence levels and scheduling strategies to optimize resource allocation and reduce unnecessary transmissions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If proactive resource scheduling based on traffic prediction is implemented, then resource utilization and delivery reliability are improved, but false predictions may cause unnecessary resource allocation and increased network complexity
Solution Approach 1:
The system performs preliminary actions by scheduling resources in advance based on predicted traffic patterns rather than waiting for actual traffic requests. The radio network node schedules downlink resources proactively based on prediction reports from user equipment, allowing resources to be allocated before traffic actually occurs, thereby improving delivery reliability and reducing latency.
Solution Approach 2:
The system implements feedback mechanisms where the radio network node receives prediction reports from user equipment, schedules resources accordingly, and then monitors actual traffic delivery. If predictions are inaccurate, the system can adjust future scheduling decisions based on observed performance, creating a closed-loop control system that improves accuracy over time.
2Measurement precision
If prediction confidence level criterion is increased to reduce false predictions, then scheduling accuracy is improved, but fewer resources are scheduled and latency increases
Solution Approach 1:
The system dynamically adjusts the prediction confidence level criterion based on current network conditions and prediction performance. Rather than using a fixed threshold, the criterion can be adapted in real-time to balance between scheduling accuracy and responsiveness, allowing the system to schedule more aggressively when confidence is high and be more conservative when uncertainty increases.
Solution Approach 2:
The system changes the parameter of prediction confidence level criterion based on operational context. Different traffic types, network conditions, and user requirements can lead to different confidence thresholds being applied, allowing optimization of the trade-off between scheduling frequency and accuracy for different scenarios.
3Speed
If resource scheduling is optimized for URLLC with stringent latency requirements, then low latency communication is improved, but resource allocation for other QoS classes becomes less efficient
Solution Approach 1:
The system applies different scheduling strategies and confidence criteria for different QoS classes. URLLC traffic receives proactive scheduling with lower confidence thresholds to ensure low latency, while other traffic types may use different parameters. This localized optimization allows each traffic type to receive appropriate scheduling treatment without compromising overall system efficiency.
Solution Approach 2:
The scheduling system segments different traffic flows based on their QoS requirements and applies separate prediction and scheduling parameters to each segment. This allows URLLC traffic to be handled with stringent latency requirements while other traffic classes are scheduled according to their own characteristics, improving overall resource utilization across diverse service types.
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.