Knowledge Transfer in Deep Reinforcement Learning for Slice-Aware Mobility Robustness Optimization

TL;DR

This paper introduces SAMRO, a deep reinforcement learning approach that enhances mobility robustness in network slicing by optimizing handover parameters for each slice, ensuring better service quality and seamless mobility.

Contribution

It presents a novel slice-aware reinforcement learning framework with a two-step transfer learning scheme for efficient online training in mobility management.

Findings

Significant improvement in slice-aware service continuity.

Enhanced handover performance compared to legacy algorithms.

Effective online fine-tuning with mixed experience replay.

Abstract

The legacy mobility robustness optimization (MRO) in self-organizing networks aims at improving handover performance by optimizing cell-specific handover parameters. However, such solutions cannot satisfy the needs of next-generation network with network slicing, because it only guarantees the received signal strength but not the per-slice service quality. To provide the truly seamless mobility service, we propose a deep reinforcement learning-based slice-aware mobility robustness optimization (SAMRO) approach, which improves handover performance with per-slice service assurance by optimizing slice-specific handover parameters. Moreover, to allow safe and sample efficient online training, we develop a two-step transfer learning scheme: 1) regularized offline reinforcement learning, and 2) effective online fine-tuning with mixed experience replay. System-level simulations show that compared against the legacy MRO algorithms, SAMRO significantly improves slice-aware service continuation while optimizing the handover performance.