QoE Optimization for Live Video Streaming in UAV-to-UAV Communications via Deep Reinforcement Learning

Liyana Adilla Binti Burhanuddin,Xiaonan Liu,Ursula Challita,Yansha Deng,Andras Zahemszky

doi:10.1109/tvt.2022.3152146

Liyana Adilla Binti Burhanuddin, Xiaonan Liu + Show 3 more

Open Access

https://doi.org/10.1109/tvt.2022.3152146

Copy DOI

Abstract

A challenge for rescue teams when fighting against wildfire in remote areas is the lack of information, such as the size and images of fire areas. As such, live streaming from Unmanned Aerial Vehicles (UAVs), capturing videos of dynamic fire areas, is crucial for firefighter commanders in any location to monitor the fire situation with quick response. The 5G network is a promising wireless technology to support such scenarios. In this paper, we consider a UAV-to-UAV (U2U) communication scenario, where a UAV at a high altitude acts as a mobile base station (UAV-BS) to stream videos from other flying UAV-users (UAV-UEs) through the uplink. Due to the mobility of the UAV-BS and UAV-UEs, it is important to determine the optimal movements and transmission powers for UAV-BSs and UAV-UEs in real-time, so as to maximize the data rate of video transmission with smoothness and low latency, while mitigating the interference according to the dynamics in fire areas and wireless channel conditions. In this paper, we co-design the video resolution, the movement, and the power control of UAV-BS and UAV-UEs to maximize the Quality of Experience (QoE) of real-time video streaming. We applied the Deep Q-Network (DQN) and Actor-Critic (AC) to maximize the QoE of video transmission from all UAV-UEs to a single UAV-BS to learn the dynamic fire areas and communication environment. Simulation results show the effectiveness of our proposed algorithm in terms of the QoE, delay and video smoothness compared to the Greedy algorithm.

Highlights

Over the years, an increasing number of wildfires has inevitably created new challenges for firefighters to control and monitor fire in remote areas [1], [2]
According to the 3GPP guidelines [34], we consider fractional power control for all Unmanned Aerial Vehicles (UAVs) and the power transmitted by the kth UAV users (UAV-UEs) while communicating with the UAV-base stations (BSs) can be given by video, we propose the boundary flying area for UAV-UEs in each fire area, which can be written as Eq (5)
The target area is captured by K UAV-UE(s), i.e., K = 4 in the ith fire area Ai (i = 1, 2, and, 3)

Summary

Introduction

An increasing number of wildfires has inevitably created new challenges for firefighters to control and monitor fire in remote areas [1], [2]. The use of UAVs provides the fire commander with sufficient information of the overall situation of the fire and danger, such as explosions or human requiring rescue. It helps to reduce any imminent dangers and obstacles to firefighters. Existing wireless technologies, such as WiFi, Bluetooth, and radio wave, can only support UAVs’ communication within a short transmission range, which are inefficient for multi-UAV collaboration with limited multiUAV control [3]. To ensure the effectiveness of multi-tier UAVs, the optimal intensity, altitude of drones, and the specific network load conditions should be considered to ensure the deployment of multi-tier UAVs [10]

Objectives

Results

Conclusion