On Enhancing Network Throughput using Reinforcement Learning in Sliced Testbeds
This work addresses network slicing orchestration for applications demanding high throughput, but it is incremental as it builds on existing RL methods in a specific domain.
The paper tackles the challenge of meeting Service-Level Agreements (SLAs) for network slicing throughput by introducing the eMBB-Agent, a Reinforcement Learning approach using Deep Q-Networks, which experimentally enhances throughput by adjusting reception windows based on application variables.
Novel applications demand high throughput, low latency, and high reliability connectivity and still pose significant challenges to slicing orchestration architectures. The literature explores network slicing techniques that employ canonical methods, artificial intelligence, and combinatorial optimization to address errors and ensure throughput for network slice data plane. This paper introduces the Enhanced Mobile Broadband (eMBB)-Agent as a new approach that uses Reinforcement Learning (RL) in a vertical application to enhance network slicing throughput to fit Service-Level Agreements (SLAs). The eMBB-Agent analyzes application transmission variables and proposes actions within a discrete space to adjust the reception window using a Deep Q-Network (DQN). This paper also presents experimental results that examine the impact of factors such as the channel error rate, DQN model layers, and learning rate on model convergence and achieved throughput, providing insights on embedding intelligence in network slicing.