Learning Driven Mobility Control of Airborne Base Stations in Emergency Networks

Rui Li 1 Chaoyun Zhang 1 Paul Patras 1 Razvan Stanica 2 Fabrice Valois 2
2 AGORA - ALGorithmes et Optimisation pour Réseaux Autonomes
Inria Grenoble - Rhône-Alpes, CITI - CITI Centre of Innovation in Telecommunications and Integration of services
Abstract : Mobile base stations mounted on unmanned aerial vehicles (UAVs) provide viable wireless coverage solutions in challenging landscapes and conditions, where cellular/WiFi infrastructure is unavailable. Operating multiple such airborne base stations, to ensure reliable user connectivity, demands intelligent control of UAV movements, as poor signal strength and user outage can be catastrophic to mission critical scenarios. In this paper, we propose a deep reinforcement learning based solution to tackle the challenges of base stations mobility control. We design an Asynchronous Advantage Actor-Critic (A3C) algorithm that employs a custom reward function, which incorporates SINR and outage events information, and seeks to provide mobile user coverage with the highest possible signal quality. Preliminary results reveal that our solution converges after 4 × 10 5 steps of training, after which it outperforms a benchmark gradient-based alternative, as we attain 5dB higher median SINR during an entire test mission of 10,000 steps.
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/hal-01927252
Contributor : Razvan Stanica <>
Submitted on : Monday, November 19, 2018 - 5:00:38 PM
Last modification on : Wednesday, November 20, 2019 - 7:33:35 AM
Long-term archiving on: Wednesday, February 20, 2019 - 4:26:45 PM

File

WAIN_CameraReady.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01927252, version 1

Collections

Citation

Rui Li, Chaoyun Zhang, Paul Patras, Razvan Stanica, Fabrice Valois. Learning Driven Mobility Control of Airborne Base Stations in Emergency Networks. WAIN 2018 - Workshop on Artificial Intelligence in Networks, Dec 2018, Toulouse, France. ⟨hal-01927252⟩

Share

Metrics

Record views

109

Files downloads

276