AI-Driven PDCP Reordering Timer for Adaptive SDU Forwarding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication systems face inefficiencies in packet reordering due to fixed reordering timers, leading to increased power and memory usage, and reduced transmission throughput, as they do not adapt to varying conditions.
Innovation Solution
Implementing artificial intelligence (AI)-enabled learning models to predict optimal reordering timer durations based on packet arrival times, adjusting the reordering window dynamically to improve communication performance and reduce unnecessary delays.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a fixed reordering timer is used for packet reordering, then the reordering process is simple to implement, but transmission throughput is reduced and power consumption increases
Solution Approach 1:
The patent applies dynamics by transitioning from a fixed reordering timer to a dynamic timer whose duration is predicted using machine learning models. The system continuously learns from packet arrival patterns and adjusts the reordering window duration accordingly, allowing the timer to adapt to varying network conditions and optimize transmission throughput while maintaining implementation simplicity through automated prediction mechanisms
2Device complexity
If a fixed reordering timer is used, then device complexity is low, but power consumption increases
Solution Approach 1:
The system implements self-service by employing machine learning models that automatically learn from packet arrival patterns and predict optimal reordering timer durations without requiring manual configuration or complex control logic. The model continuously refines its predictions based on observed network behavior, enabling the system to optimize power consumption autonomously while maintaining relatively simple implementation architecture
Solution Approach 2:
The patent applies parameter changes by dynamically adjusting the reordering timer duration parameter based on predicted packet arrival patterns. Instead of using a fixed parameter, the system modifies the timer duration according to learned network conditions, which reduces unnecessary waiting time and power consumption while the machine learning framework manages the complexity of parameter adaptation
3Ease of operation
If a fixed reordering timer is used, then implementation is straightforward, but adaptability to varying network conditions is poor
Solution Approach 1:
The system implements feedback mechanisms where machine learning models continuously monitor packet arrival patterns and use this information to refine predictions of optimal reordering timer durations. The model processes feedback from actual packet transmission outcomes and adjusts its predictions accordingly, enabling the system to adapt to varying network conditions while maintaining straightforward implementation through automated learning and adjustment processes
Data Source
AI summary
Methods, systems, and devices for dynamically adjusting a reordering timer are described. A wireless device may receive control signaling indicating a configuration comprising a first set of one or more parameters associated with a reordering timer for a packet data convergence protocol (PDCP) entity of the wireless device, wherein the reordering timer is associated with reordering of a set of service data units (SDUs) by the PDCP entity of the wireless device. The wireless device may determine a duration for the reordering timer according to the first set of one or more parameters associated with the reordering timer, and the wireless device may forward one or more SDUs of the set of SDUs, based at least in part on an expiration of the reordering timer.