# The New Frontier in RAN Heterogeneity: Multi-tier Drone-Cells

arXiv: https://arxiv.org/abs/1604.00381 · HTML: https://mlsanity.com/paper/1604.00381/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2016.

## Built on by (most cited first, 3 of 3)

- [Cooperative Multi-Agent Deep Reinforcement Learning for Reliable and Energy-Efficient Mobile Access via Multi-UAV Control](https://mlsanity.com/paper/2210.00945/) (2022)
- [Quantum Multi-Agent Actor-Critic Networks for Cooperative Mobile Access in Multi-UAV Systems](https://mlsanity.com/paper/2302.04445/) (2023)
- [UAV Base Station Trajectory Optimization Based on Reinforcement Learning in Post-disaster Search and Rescue Operations](https://mlsanity.com/paper/2202.10338/) (2022)

## Abstract (arXiv)

In cellular networks, the locations of the radio access network (RAN) elements are determined mainly based on the long-term traffic behaviour. However, when the random and hard-to-predict spatio-temporal distribution of the traffic (load,demand) does not fully match the fixed locations of the RAN elements (supply), some performance degradation becomes inevitable. The concept of multi-tier cells (heterogeneous networks, HetNets) has been introduced in 4G networks to alleviate this mismatch. However, as the traffic distribution deviates more and more from the long-term average, even the HetNet architecture will have difficulty in coping up with the erratic supply-demand mismatch, unless the RAN is grossly over-engineered (which is a financially non-viable solution). In this article, we study the opportunistic utilization of low-altitude unmanned aerial platforms equipped with base stations (BSs), i.e., drone-BSs, in 5G networks. In particular, we envisage a multi-tier drone-cell network complementing the terrestrial HetNets. The variety of equipment, and non-rigid placement options allow utilizing multitier drone-cell networks to serve diversified demands. Hence, drone-cells bring the supply to where the demand is, which sets new frontiers for the heterogeneity in 5G networks. We investigate the advancements promised by drone-cells, and discuss the challenges associated with their operation and management. We propose a drone-cell management framework (DMF) benefiting from the synergy among software defined networking (SDN), network functions virtualization (NFV), and cloud-computing. We demonstrate DMF mechanisms via a case study, and numerically show that it can reduce the cost of utilizing drone-cells in multitenancy cellular networks.