Machine Learning-Based Deployment Strategy for HAP-Enabled Mobile Base Stations in Wireless Network 


Vol. 51,  No. 4, pp. 769-777, Apr.  2026
10.7840/kics.2026.51.4.769


PDF Full-Text
  Abstract

This study proposes an optimized deployment strategy for high altitude platform (HAP)-enabled mobile base stations by combining user density prediction with reinforcement learning. Using the Geolife GPS Trajectories dataset from the Beijing area, we preprocessed and divided the data into three regions based on building density, then employed a GRU model to predict 10-minute interval user density. Based on the predicted density information, a Deep Q-Network (DQN) was applied to learn the optimal deployment policy for mobile base stations. We compared the performance between single and dual base station scenarios. Experimental results show that the proposed approach effectively covers major high-density areas in every scenario, and improves performance through appropriate adjustment of the number of base stations and learning strategies compared to real-time greedy methods in scenario with high-density urban environments.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

H. Shin and H. Jeon, "Machine Learning-Based Deployment Strategy for HAP-Enabled Mobile Base Stations in Wireless Network," The Journal of Korean Institute of Communications and Information Sciences, vol. 51, no. 4, pp. 769-777, 2026. DOI: 10.7840/kics.2026.51.4.769.

[ACM Style]

Hyeji Shin and Hong-Bae Jeon. 2026. Machine Learning-Based Deployment Strategy for HAP-Enabled Mobile Base Stations in Wireless Network. The Journal of Korean Institute of Communications and Information Sciences, 51, 4, (2026), 769-777. DOI: 10.7840/kics.2026.51.4.769.

[KICS Style]

Hyeji Shin and Hong-Bae Jeon, "Machine Learning-Based Deployment Strategy for HAP-Enabled Mobile Base Stations in Wireless Network," The Journal of Korean Institute of Communications and Information Sciences, vol. 51, no. 4, pp. 769-777, 4. 2026. (https://doi.org/10.7840/kics.2026.51.4.769)
Vol. 51, No. 4 Index

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880