Data Correlation-Aware Resource Management in Wireless Virtual Reality (VR): An Echo State Transfer Learning Approach

Abstract

Providing seamless connectivity for wireless virtual reality (VR) users has emerged as a key challenge for future cloud-enabled cellular networks. In this paper, the problem of wireless VR resource management is investigated for a wireless VR network in which VR contents are sent by a cloud to cellular small base stations (SBSs). The SBSs will collect tracking data from the VR users, over the uplink, in order to generate the VR content and transmit it to the end-users using downlink cellular links.For this model, the data requested or transmitted by the users can exhibit correlation, since the VR users may engage in the same immersive virtual environment with different locations and orientations. As such, the proposed resource management framework can factor in such spatial data correlation, so as to better manage uplink and downlink traffic. This potential spatial data correlation can be factored into the resource allocation problem to reduce the traffic load in both uplink and downlink. In the downlink, the cloud can transmit 360 • contents or specific visible contents (e.g., user field of view) that are extracted from the original 360 • contents to the users according to the users' data correlation so as to reduce the backhaul traffic load. In the uplink, each SBS can associate with the users that have similar tracking information so as to reduce the tracking data size. This data correlation-aware resource management problem is formulated as an optimization problem whose goal is to maximize the users' successful A preliminary version of this work was published in [1].

Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial

“…ANNs have two major applications for wireless VR. First, ANNs can be used to predict the users' movement as well as their future interactions with the VR [95] • Resource management ⇒ DNN-based RL algorithm • UAV detection [93] • Limited time for data collection • Channel modeling for air-to-ground ⇒ SNN-based algorithm • Deployment and caching [92], [96], and [97] • Errors in training data • Handover for UE UAVs ⇒ RNN-based algorithm • Design multi-hop aerial network ⇒ CNN-based algorithm • UE UAV trajectory prediction ⇒ SNN-based algorithm VR • Resource allocation [103], [104] • Errors in collected data • VR users' movement ⇒ RNNs prediction algorithm • Head movement prediction [105] • Limited computational resources • Content correlation ⇒ CNN-based algorithm • Gaze prediction [106] • Limited time for training ANNs • VR video coding and decoding ⇒ CNN-based algorithm • Content caching and transmission [107] • Correction of inaccurate VR images ⇒ CNN-based algorithm • Viewing video prediction ⇒ SNN-based algorithm • Joint wireless and VR user environment prediction ⇒ RNNs prediction algorithm • Manage computational resources and video formats ⇒ DNN-based RL algorithm…”

“…In [106], a decision forest learning algorithm is proposed for gaze prediction. The work in [103] developed a neural network based transfer learning algorithm for data correlation aware resource allocation. 360 • content caching and transmission is optimized in [107] using an ESN and SSN based deep RL algorithm.…”

Motion-Aware Interplay between WiGig and WiFi for Wireless Virtual Reality

“…Elbamby et al [18] discussed the challenges and enablers for ultrareliable and low-latency wireless VR, including edge computing and proactive caching in millimeter wave (mmWave) cellular networks. Chen et al [19] solved a resource management problem in cellular networks for wireless VR, which exploited the potential spatial data correlations among users due to their engagement in the same VR environment to reduce the traffic load in both uplink and downlink. The problem was solved using a machine learning algorithm, which used echo state networks with transfer learning.…”

Distribution of Landscape Architecture Based on 3D Images and Virtual Reality Rationality Study

“…The continuous innovation of computer application technology has made the traditional landscape planning and design that require drawings have been unable to meet the needs of the times. The traditional drawing work of design schemes has begun to rely on VR (Virtual Reality) in the space environment and has gradually become a popular application direction [3]. The computer-aided technology used in the landscape planning and design process can be divided into AutoCAD technology, ArcGIS technology and VR technology.…”