Analysis and Enhancement of Resource-hungry Applications

1 online resource (172 pages) : PDF

2022

University of North Carolina at Charlotte

Resource-hungry applications play a very important role in people's daily lives, such as real-time video streaming applications and mobile augmented reality applications. However, there are several challenges to satisfy the user Quality-of-Experience (QoE) requirements of resource-hungry applications. First, these applications usually require a vast amount of network bandwidth resources to support the data communication of different functionalities. However, only limited network bandwidth resources can be assigned to these applications which leads to long network latency and poor user QoE. In addition, artificial intelligent (AI) and machine learning (ML) models are widely adopted in these applications which significantly increases the computation complexity of these applications. Because of the limited computing resource on mobile devices, computation-intensive tasks are offloaded to edge servers located at the edge of the core network. However, additional network latency and bandwidth usage are introduced which may degrade user QoE. Moreover, base stations (BSs) and edge servers may be densely deployed to provide high network capacity, thus resulting in ultra-dense wireless networks. However, a major challenge of the ultra-dense wireless network is the increased complexity of networking mechanisms.In this research, the characteristics of popular resource-hungry applications are first analyzed. Then, based on the analyzed characteristics, we propose several specifically designed algorithms to enhance the performance of each resource-hungry application. For real-time video streaming applications, a configuration adaptive video encoding scheme is proposed to improve the video visual quality of existing real-time video streaming applications. For ultra-high-definition (UHD) video delivery applications, we propose a cloud computing based deep compression framework named Pearl, which utilizes the power of deep learning and cloud computing to compress UHD videos and reduce the high network bandwidth resource usage of UHD video delivery. For mobile augmented reality (MAR) applications, a fast model updating algorithm and a smart task allocation decision algorithm are proposed to overcome the challenges brought by the high computation complexity and latency-sensitive tasks in MAR applications. Finally, a real-time network optimization algorithm is proposed to address the high complexity problem of networking design in ultra-dense wireless networks.In our proposed algorithms, deep learning techniques (e.g., neural networks, reinforcement learning, and incremental learning) and machine learning algorithms (e.g., clustering) are adopted. This research will provide important insights for the design of AI-powered optimization for resource-hungry applications and network management.

doctoral dissertations

Computer engineering
Electrical engineering

Ph.D.

Electrical Engineering

Xie, Jiang

Han, Tao
Wang, Pu
Lu, Aidong

Thesis (Ph.D.)--University of North Carolina at Charlotte, 2022.

This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s). For additional information, see http://rightsstatements.org/page/InC/1.0/.

Copyright is held by the author unless otherwise indicated.

HUANG_uncc_0694D_13060

http://hdl.handle.net/20.500.13093/etd:3012