This study aims to introduce and address the problem of traffic load estimation in the cell switching concept within the evolving landscape of vertical heterogeneous networks (vHetNets). The problem is that the practice of cell switching faces a significant challenge due to the lack of accurate data on the traffic load of sleeping small base stations (SBSs). This problem makes the majority of the studies in the literature, particularly those employing load-dependent approaches, impractical due to their basic assumption of perfect knowledge of the traffic loads of sleeping SBSs for the next time slot. Rather than developing another advanced cell switching algorithm, this study investigates the impacts of estimation errors and explores possible solutions through established methodologies in a novel vHetNet environment that includes the integration of a high altitude platform (HAPS) as a super macro base station (SMBS) into the terrestrial network. In other words, this study adopts a more foundational perspective, focusing on eliminating a significant obstacle for the application of advanced cell switching algorithms. To this end, we explore the potential of three distinct spatial interpolation-based estimation schemes: random neighboring selection, distance-based selection, and clustering-based selection. Utilizing a real dataset for empirical validations, we evaluate the efficacy of our proposed traffic load estimation schemes. Our results demonstrate that the multi-level clustering (MLC) algorithm performs exceptionally well, with an insignificant difference (i.e., 0.8%) observed between its estimated and actual network power consumption, highlighting its potential to significantly improve energy efficiency in vHetNets.

翻译：摘要：本研究旨在引入并解决垂直异构网络（vHetNet）演进背景下小区切换概念中的流量负载估计问题。该问题的核心在于，由于缺乏对休眠小型基站（SBS）流量负载的准确数据，小区切换实践面临重大挑战。这使得现有文献中的大部分研究（尤其是采用负载依赖方法的研究）因基本假设（即完美掌握休眠SBS下一时隙的流量负载）而变得不切实际。本研究并未设计另一先进的小区切换算法，而是通过将高空平台（HAPS）作为超级宏基站（SMBS）集成到地面网络的新型vHetNet环境中，探究估计误差的影响并探索基于成熟方法的可行解决方案。换言之，本研究采取更基础的视角，聚焦于消除先进小区切换算法应用的主要障碍。为此，我们探索了三种基于空间插值的估计方案：随机邻域选择、距离基选择和聚类基选择。通过真实数据集的实证验证，我们评估了所提流量负载估计方案的有效性。结果表明，多级聚类（MLC）算法表现卓越，其估计的网络功耗与实际功耗差异极小（仅0.8%），凸显了其在提升vHetNet能效方面的巨大潜力。