5G Traffic Management Balancing PDCCH and PDSCH Loads
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication systems face challenges in managing signal traffic across control and data channels, leading to overloading and inefficient resource utilization, particularly due to inadequate consideration of control channel overload, which affects network performance and user equipment (UE) experience.
Innovation Solution
The implementation of a traffic management system that incorporates deep reinforcement learning and multi-access edge computing to dynamically balance PDCCH and PDSCH resources across cells, using artificial neural networks to optimize channel allocation and predict handovers, thereby reducing overloading and signaling overhead.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing traffic management approaches are used to allocate wireless connection point resources, then resource allocation can be performed, but control channel overloading occurs and network performance deteriorates
Solution Approach 1:
The system performs preliminary actions by predicting future control channel load and UE handover patterns using machine learning models before overloading occurs. This allows proactive resource allocation adjustments and preventive handover management, avoiding the harmful effects of control channel overloading while maintaining reliable network performance.
2Productivity
If traffic management approaches differentiate between control channels and data channels, then resource allocation can be performed, but significant factors impacting network performance are not incorporated
Solution Approach 1:
The system implements a unified traffic management framework that simultaneously handles control channels, data channels, and UE handover management through integrated machine learning models. This multi-functional approach incorporates all significant factors affecting network performance into a single adaptive system, improving both resource allocation efficiency and overall network optimization.
Solution Approach 2:
The system continuously monitors network state, control channel load, and UE behavior patterns, then uses this feedback to dynamically adjust resource allocation decisions. The machine learning models are trained on historical network data and adapt to changing conditions in real-time, enabling the system to incorporate all significant performance factors into its decision-making process.
Data Source
AI summary
The technologies described herein are generally directed toward managing signal traffic in a wireless network. Example operations can include receiving, for a group of cells, a control channel utilization value for a control channel and a data channel utilization value for a data channel. The operations can further include generating, based on the control channel utilization value and a threshold, for a first cell of the group of cells, a channel allocation that can increase the balance of use of control channel resources and data channel resources for the first cell, and configuring the first cell of the group of cells to allocate control channel resources and data channel resources of the first cell based on the channel allocation.