Thesis Format
Integrated Article
Degree
Doctor of Philosophy
Program
Electrical and Computer Engineering
Supervisor
Xianbin Wang
Abstract
In recent years, a plethora of new wireless applications have emerged, each with its specific quality of service (QoS) requirements and quality of experience (QoE) perception mechanism. These developments pose significant challenges to resource management and network cooperation in future wireless networks. To overcome these challenges, this thesis focuses on the development of several intelligent and customized resource management and network cooperation techniques for beyond 5G and 6G networks.
First, for reducing power consumption in cloud radio access network (CRAN), a traffic prediction-enabled energy-efficient dynamic computing resource allocation scheme is proposed. Specifically, a novel wireless traffic prediction method based on two-dimensional convolution neural network (CNN) long short-term memory (LSTM) model with temporal aggregation is proposed. Moreover, a multi-start simulated annealing (MSA) algorithm is proposed for energy-efficient dynamic computing resource allocation in CRAN. Simulation results demonstrate that compared with fixed computing resource allocation, the proposed scheme could reduce the total power consumption by 52.18%.
Second, categorized QoS provisioning is a natural idea to satisfy the diverse QoS requirements of different categories of applications through a two-stage resource allocation scheme. To optimize the key QoS indicators of three different application categories and mitigate backhaul network congestion simultaneously, a decoupling-based iterative optimization (DBIO) algorithm is proposed for the first-stage resource allocation from radio access network (RAN) to tenants to achieve categorized QoS provisioning.
Third, in downlink 6G heterogeneous networks (HetNets), for achieving tailored QoS provisioning to ensure fairness among users with different QoS requirements, an interactive optimization algorithm (IOA) is proposed for joint user association and resource allocation.
Last, for achieving application-specific QoE enhancement, multi-user multi-application packet scheduling in downlink 6G RAN is investigated, which is formulated as a Markov decision process (MDP) problem. For solving this problem, a deep deterministic policy gradient (DDPG)-based solution is proposed. Moreover, to avoid resource waste and improve the performance of DDPG-based packet schedulers, a knowledge embedding method is proposed. Simulation results demonstrate that utilizing the proposed knowledge embedding method, the performance of the DDPG-based packet schedulers could be improved by at least 8.07% on the test dataset in terms of average reward per time slot.
Summary for Lay Audience
In recent years, a lot of new wireless applications have emerged with diverse requirements on data transmission rate, latency and so on. Moreover, the evaluation criteria of users' experience on these applications are different. These diverse requirements and different evaluation criteria bring critical challenges to resource management and cooperation among different base stations in future wireless networks. Therefore, in this thesis, several intelligent and customized resource management and network cooperation techniques are developed.
First, for reducing power consumption in cloud radio access network (CRAN), a traffic prediction-enabled energy-efficient dynamic computing resource allocation scheme is proposed. Specifically, a novel wireless traffic prediction method is proposed based on artificial intelligence (AI). Moreover, a multi-start simulated annealing (MSA) algorithm is proposed for dynamically allocating computing resource to reduce power consumption. Simulation results show that by using the proposed scheme, compared with fixed computing resource allocation, the total power consumption could be reduced by 52.18%.
Second, a natural idea to satisfy the diverse requirements of different categories of applications is to utilize a two-stage resource allocation scheme. In order to optimize the objectives of three different application categories and mitigate network congestion simultaneously, a decoupling-based iterative optimization (DBIO) algorithm is proposed for the first-stage resource allocation from radio access network (RAN) to tenants, each serving a specific category.
Third, considering the scenario where different types of base stations coexist in a network, for ensuring fairness among users with different requirements, an interactive optimization algorithm (IOA) is proposed for jointly deciding the set of users served by each base station and the allocation of base stations' resources to their served users.
Last, in 6G networks, to improve users' experiences in an application-specific way, a deep reinforcement learning (DRL) approach is proposed for deciding the set of data packets of applications to be transmitted in the next time slot. Moreover, in order to avoid resource waste and improve the performance of the DRL-based packet schedulers, a knowledge embedding method is proposed. Simulation results show that by using the proposed knowledge embedding method, the average reward per time slot of DRL-based packet schedulers on the test dataset could be improved by at least 8.07%.
Recommended Citation
Fu, Yongqin, "Intelligent and Customized Resource Management and Network Cooperation in Beyond 5G and 6G Networks" (2024). Electronic Thesis and Dissertation Repository. 10052.
https://ir.lib.uwo.ca/etd/10052
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.