A Lightweight Machine Learning Approach for Delay-Aware Cell-Switching in 6G HAPS Networks

TL;DR

This work tackles energy-efficient cell-switching in 6G by integrating a HAPS-SMBS into a delay-aware, best-effort QoS framework. It develops a lightweight Q-learning method, Reduced Action-State Pair (RASP), to solve a combinatorial CS optimization in a VHetNet comprising SBSs, MBS, and HAPS-SMBS, while accounting for delay profiles and interference. Key contributions include a comprehensive system model, a reduced-complexity RL approach, and a detailed performance evaluation showing energy savings and QoS viability across interference scenarios. The results indicate that the proposed RASP approach can closely approximate exhaustive search performance at a fraction of the computational cost, enabling scalable delay-aware energy optimization for NTN-enabled 6G networks.

Abstract

This study investigates the integration of a high altitude platform station (HAPS), a non-terrestrial network (NTN) node, into the cell-switching paradigm for energy saving. By doing so, the sustainability and ubiquitous connectivity targets can be achieved. Besides, a delay-aware approach is also adopted, where the delay profiles of users are respected in such a way that we attempt to meet the latency requirements of users with a best-effort strategy. To this end, a novel, simple, and lightweight Q-learning algorithm is designed to address the cell-switching optimization problem. During the simulation campaigns, different interference scenarios and delay situations between base stations are examined in terms of energy consumption and quality-of-service (QoS), and the results confirm the efficacy of the proposed Q-learning algorithm.

Figures (3)

• Figure 1: A VHetNet containing SBSs, MBS, and HAPS-SMBS.
• Figure 2: Energy consumption of different algorithms and comparison for different scenarios.
• Figure 3: Data rate figures for all scenarios and $D = 30\%$ case.