Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Energy-efficient User Clustering for UAV-enabled Wireless Networks Using EM Algorithm

Salim Janji, Adrian Kliks

TL;DR

The paper tackles energy-efficient deployment of UAV-based drone small cells for ground users by formulating a joint clustering and placement problem. It introduces DUCEM, a modified EM algorithm operating on Gaussian Mixture Models to produce initial user clustering and drone locations, with constrained covariance updates that reflect limited transmit power and user caps per drone. Empirical results show substantial gains in energy efficiency (~$25\%$) and link reliability (~$18.3\%$) over a K-means baseline, validating the approach as a solid initialization for subsequent optimization. The work has practical relevance for rapid, energy-aware UAV deployments in hotspot or disaster scenarios and points to future enhancements in interference management and propulsion energy considerations.

Abstract

Unmanned Aerial Vehicles (UAVs) can be used to provide wireless connectivity to support the existing infrastructure in hot-spots or replace it in cases of destruction. UAV-enabled wireless provides several advantages in network performance due to drone small cells (DSCs) mobility despite the limited onboard energy. However, the problem of resource allocation has added complexity. In this paper, we propose an energy-efficient user clustering mechanism based on Gaussian mixture models (GMM) using a modified Expected-Maximization (EM) algorithm. The algorithm is intended to provide the initial user clustering and drone deployment upon which additional mechanisms can be employed to further enhance the system performance. The proposed algorithm improves the energy efficiency of the system by 25% and link reliability by 18.3% compared to other baseline methods.

Energy-efficient User Clustering for UAV-enabled Wireless Networks Using EM Algorithm

TL;DR

The paper tackles energy-efficient deployment of UAV-based drone small cells for ground users by formulating a joint clustering and placement problem. It introduces DUCEM, a modified EM algorithm operating on Gaussian Mixture Models to produce initial user clustering and drone locations, with constrained covariance updates that reflect limited transmit power and user caps per drone. Empirical results show substantial gains in energy efficiency (~) and link reliability (~) over a K-means baseline, validating the approach as a solid initialization for subsequent optimization. The work has practical relevance for rapid, energy-aware UAV deployments in hotspot or disaster scenarios and points to future enhancements in interference management and propulsion energy considerations.

Abstract

Unmanned Aerial Vehicles (UAVs) can be used to provide wireless connectivity to support the existing infrastructure in hot-spots or replace it in cases of destruction. UAV-enabled wireless provides several advantages in network performance due to drone small cells (DSCs) mobility despite the limited onboard energy. However, the problem of resource allocation has added complexity. In this paper, we propose an energy-efficient user clustering mechanism based on Gaussian mixture models (GMM) using a modified Expected-Maximization (EM) algorithm. The algorithm is intended to provide the initial user clustering and drone deployment upon which additional mechanisms can be employed to further enhance the system performance. The proposed algorithm improves the energy efficiency of the system by 25% and link reliability by 18.3% compared to other baseline methods.
Paper Structure (11 sections, 12 equations, 4 figures, 1 table, 2 algorithms)

This paper contains 11 sections, 12 equations, 4 figures, 1 table, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Problem Formulation
  4. Expected-Maximization Algorithm
  5. Drone Users Clustering Expected Maximization Algorithm (DUCEM)
  6. Simulation and Results
  7. Users Mobility Model
  8. Simulation Parameters
  9. K-means Clustering
  10. Results
  11. Conclusion

Figures (4)

  • Figure 1: Scenario of users served by DSCs.
  • Figure 2: Comparison of clustering overlap for a given set of test points with different $d\Sigma_{max}$ values.
  • Figure 3: System energy efficiency (EE) against the maximum allowed number of users per cluster ($U_{max}$).
  • Figure 4: Link reliability ($L_{rel}$) against SINR threshold ($\Gamma_{Th}$). $U_{max}=1500$.