DRL-Derived Coverage Zones for Closed-Loop Uplink Power Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing 5G uplink power control mechanisms, such as open and closed-loop power control, struggle to efficiently manage UE transmit power in diverse propagation environments, leading to suboptimal performance in terms of power efficiency and throughput.
Innovation Solution
Employing an AI-based deep reinforcement learning (DRL) system to dynamically determine optimal coverage zones and target SINR values within a base station's coverage area, using unsupervised learning to adjust UE transmission power via closed-loop power control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If closed-loop power control algorithms are used to manage UE transmit power, then power efficiency and throughput can be improved, but the system complexity increases due to the need for configurable algorithms to handle different propagation environments
Solution Approach 1:
The system employs deep reinforcement learning agents that autonomously learn optimal power control strategies without requiring manual configuration. The agents self-adjust TPC commands based on observed network conditions and rewards, eliminating the need for complex vendor-specific algorithm configurations while improving throughput and power efficiency
2Use of energy by moving object
If deep reinforcement learning is used to dynamically determine coverage zones and target SINR values, then power efficiency and throughput are enhanced, but the computational complexity increases
Solution Approach 1:
The base station coverage area is divided into multiple coverage zones with different target SINR values, allowing differentiated power control strategies for different spatial regions. This segmentation enables the DRL system to optimize power efficiency locally in each zone while managing overall computational complexity through structured zone management
Solution Approach 2:
The system dynamically adjusts target SINR values and coverage zone configurations based on real-time network conditions learned by the DRL agent. By changing these parameters adaptively rather than using fixed configurations, the system achieves superior power efficiency while the DRL framework manages computational complexity through learned parameter transformations
3Adaptability or versatility
If fixed power control configurations are used, then device complexity is reduced, but the system cannot adapt to varying propagation environments and user mobility
Solution Approach 1:
The system replaces fixed power control configurations with dynamic, learnable control mechanisms. The DRL agent continuously adapts coverage zone boundaries and target SINR values in response to changing propagation conditions and user mobility patterns, enabling the system to handle diverse deployment scenarios without increasing operational complexity
Data Source
AI summary
The technology described herein is directed towards dynamically determining, based on current environment state data, a number of coverage zones within a base station's coverage area, and physical uplink shared channel (PUSCH) closed-loop power control-related data for user equipment in each zone. In one implementation, a deep reinforcement learning (DRL)-based system includes a first DRL agent that, based on the current environment state, outputs the optimal number of zones. Based on the current environment state data and the number of zones, a second DRL agent outputs optimal per-zone target signal-to-interference-plus-noise ratio (SINR) values. The SINR values are used in outputting transmit power control data to the UEs in each coverage zone. Also described is deep reinforcement learning by the system based on a reward function that can balance enhanced power efficiency with enhanced throughput to determine the optimal number of zones and SINR values for various current environment state data.