Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Cell Switching in HAPS-Aided Networking: How the Obscurity of Traffic Loads Affects the Decision

Berk Çiloğlu, Görkem Berkay Koç, Metin Ozturk, Halim Yanikomeroglu

TL;DR

Results confirm that the estimation error is capable of changing cell switching decisions, yielding performance divergence compared to no-error scenarios, and two different <inline-formula><tex-math notation="LaTeX">$Q$</tex-math></inline-formula>-learning algorithms perform well.

Abstract

This study aims to introduce the cell load estimation problem of cell switching approaches in cellular networks specially-presented in a high-altitude platform station (HAPS)-assisted network. The problem arises from the fact that the traffic loads of sleeping base stations for the next time slot cannot be perfectly known, but they can rather be estimated, and any estimation error could result in divergence from the optimal decision, which subsequently affects the performance of energy efficiency. The traffic loads of the sleeping base stations for the next time slot are required because the switching decisions are made proactively in the current time slot. Two different Q-learning algorithms are developed; one is full-scale, focusing solely on the performance, while the other one is lightweight and addresses the computational cost. Results confirm that the estimation error is capable of changing cell switching decisions that yields performance divergence compared to no-error scenarios. Moreover, the developed Q-learning algorithms perform well since an insignificant difference (i.e., 0.3%) is observed between them and the optimum algorithm.

Cell Switching in HAPS-Aided Networking: How the Obscurity of Traffic Loads Affects the Decision

TL;DR

Results confirm that the estimation error is capable of changing cell switching decisions, yielding performance divergence compared to no-error scenarios, and two different <inline-formula><tex-math notation="LaTeX"></tex-math></inline-formula>-learning algorithms perform well.

Abstract

This study aims to introduce the cell load estimation problem of cell switching approaches in cellular networks specially-presented in a high-altitude platform station (HAPS)-assisted network. The problem arises from the fact that the traffic loads of sleeping base stations for the next time slot cannot be perfectly known, but they can rather be estimated, and any estimation error could result in divergence from the optimal decision, which subsequently affects the performance of energy efficiency. The traffic loads of the sleeping base stations for the next time slot are required because the switching decisions are made proactively in the current time slot. Two different Q-learning algorithms are developed; one is full-scale, focusing solely on the performance, while the other one is lightweight and addresses the computational cost. Results confirm that the estimation error is capable of changing cell switching decisions that yields performance divergence compared to no-error scenarios. Moreover, the developed Q-learning algorithms perform well since an insignificant difference (i.e., 0.3%) is observed between them and the optimum algorithm.
Paper Structure (20 sections, 1 theorem, 12 equations, 5 figures, 1 table)

This paper contains 20 sections, 1 theorem, 12 equations, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Notation
  3. System Model
  4. Network Model
  5. Propagation Model
  6. User-Cell Association
  7. Data Traffic Model
  8. Power Consumption Model
  9. Problem Formulation
  10. Cell Load Estimation Problem
  11. Inter-Time-Slot Load Estimation Problem
  12. Intra-Time-Slot Load Estimation Problem
  13. Methodology
  14. Proposed $Q$-learning Designs
  15. Cost Function
  16. ...and 5 more sections

Key Result

Theorem 1

The error caused by the traffic load estimation, $\varepsilon \in \mathbb R$, can change the policy, $\pmb \eta$, in the optimization process, which is based on the cell loads; i.e., the objective function of the optimization problem is a function of cell loads.

Figures (5)

  • Figure 1: A typical VHetNet model containing SBSs, HAPS-SMBS, and UEs.
  • Figure 2: The architectural commonalities and differences between the designs.
  • Figure 3: Energy consumption for $n=4$ SBSs with three different $\varepsilon$ values.
  • Figure 4: Energy consumption for $n=8$ SBSs with three different $\varepsilon$ values.
  • Figure 5: Elapsed time comparison between FSD and LSD for different number of time slots when $n=4$. Results are averages of 10 runs (Monte Carlo).

Theorems & Definitions (2)

  • Theorem 1
  • proof