Boyang Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Boyang Guo has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Youjia Chen
College of Physics and Information Engineering, Fuzhou University, Fuzhou, China
5 shared publications - Jinsong Hu
Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information, College of Physics and Information Engineering, Fuzhou University, Fuzhou, China
4 shared publications - Haifeng Zheng
Fuzhou University
3 shared publications - Chaoping Deng
State Grid Fujian Electric Power Research Institute, Fuzhou 350007, China
1 shared publication - David Lopez-Perez
Universitat Politcnica de Valncia, Valencia, Spain
1 shared publication - Guodong Lin
State Grid Fujian Electric Power Research Institute, Fuzhou 350007, China
1 shared publication
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74 (00906778) , 2941-2952
FoV-Based Hierarchical Rate Splitting for Statistical QoS-Driven VR Streaming in Cell-Free Networks
Virtual reality (VR) streaming demands both high data rates and low latency, requiring advanced transmission strategies to enhance system performance in wireless networks. This paper proposes a hierarchical rate-splitting multiple access-based cell-free (HRS-CF) VR transmission strategy, which integrates field of view (FoV)-based user grouping, scalable video coding (SVC)-based message design, and message-centric base station selection. Moreover, to characterize the statistical data rate of VR services under a given delay constraint, we investigate the effective capacity (EC) of the VR video streaming under HRS-CF strategy. Furthermore, we jointly optimize the precoding matrix, rate splitting coefficients, and BS selection using the proximal policy optimization (PPO) algorithm, where a power threshold-based BS selection is introduced to reduce computational complexity. Simulation results show that the proposed HRS-CF strategy outperforms the conventional rate splitting and CF transmission schemes, achieving at least a 16% performance improvement.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74 (00906778) , 2941-2952
FoV-Based Hierarchical Rate Splitting for Statistical QoS-Driven VR Streaming in Cell-Free Networks
Virtual reality (VR) streaming demands both high data rates and low latency, requiring advanced transmission strategies to enhance system performance in wireless networks. This paper proposes a hierarchical rate-splitting multiple access-based cell-free (HRS-CF) VR transmission strategy, which integrates field of view (FoV)-based user grouping, scalable video coding (SVC)-based message design, and message-centric base station selection. Moreover, to characterize the statistical data rate of VR services under a given delay constraint, we investigate the effective capacity (EC) of the VR video streaming under HRS-CF strategy. Furthermore, we jointly optimize the precoding matrix, rate splitting coefficients, and BS selection using the proximal policy optimization (PPO) algorithm, where a power threshold-based BS selection is introduced to reduce computational complexity. Simulation results show that the proposed HRS-CF strategy outperforms the conventional rate splitting and CF transmission schemes, achieving at least a 16% performance improvement.
- Open Access
- 18 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 7, 169-181
Data-Driven Inter-Cell Interference Coordination for Mobile Cellular Networks
Compared with traditional fixed frequency reuse patterns or optimization relying on channel information, artificial intelligence (AI)-based approaches using mobile big data provide another effective and efficient way for interference management. This paper proposes a data-driven interference coordination framework. First, Graphormer is adopted to model the inter-cell interference, where the node features capture the cell’s parameters, like power and allocated spectrum, and the edge features capture the interference relationships between neighboring cells. Second, a performance evaluation module is designed to establish a comprehensive understanding between network performance and wireless resource allocation, traffic requirement, interference, and so on. Then, proximal policy optimization (PPO) is utilized to dynamically optimize the spectrum allocation to enhance network performance while meeting dynamic traffic demands. Experimental results demonstrate that: i) the Graphormer-based interference modeling outperforms other algorithms in estimation accuracy; ii) the proposed approach effectively reduces inter-cell interference and improves network performance compared to other benchmark algorithms.
- 18 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 7, 169-181
Open AccessData-Driven Inter-Cell Interference Coordination for Mobile Cellular Networks
Compared with traditional fixed frequency reuse patterns or optimization relying on channel information, artificial intelligence (AI)-based approaches using mobile big data provide another effective and efficient way for interference management. This paper proposes a data-driven interference coordination framework. First, Graphormer is adopted to model the inter-cell interference, where the node features capture the cell’s parameters, like power and allocated spectrum, and the edge features capture the interference relationships between neighboring cells. Second, a performance evaluation module is designed to establish a comprehensive understanding between network performance and wireless resource allocation, traffic requirement, interference, and so on. Then, proximal policy optimization (PPO) is utilized to dynamically optimize the spectrum allocation to enhance network performance while meeting dynamic traffic demands. Experimental results demonstrate that: i) the Graphormer-based interference modeling outperforms other algorithms in estimation accuracy; ii) the proposed approach effectively reduces inter-cell interference and improves network performance compared to other benchmark algorithms.
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (6) , 11363-11376
Toward Requested VR QoE Using Multi-Objective Reinforcement Learning
Virtual reality (VR) has been viewed as an important application in the coming wireless networks. Nevertheless, it requires both broad bandwidth and low-latency transmission, which places significant pressure on limited wireless resources. Aiming for resource savings while satisfying the various QoE requirements, based on dedicated formulating VR QoE, i.e., the mean opinion score (MOS) of video quality and motion-to-photon (MTP) delay, a QoE-steering (QoE-STR) multi-objective reinforcement learning algorithm is proposed to jointly optimize the field of view (FoV) redundancy, provided video quality, computing resources, and communication resources. The algorithm is tailored to distinct user preferences through multiple basic policies. Then it introduces a QoE-STR policy selection mechanism based on the direction vector toward the requested QoE, making users' achieved QoE approach their respective requested QoE. To reduce the computing complexity, we further develop a distributed QoE-STR (Dist. QoE-STR) algorithm, which can independently allocate wireless resources to each user while guaranteeing the network's overall resource constraints. Simulation results demonstrate the effectiveness of both proposed algorithms and the Dist. QoE-STR performs better since it can independently design the direction vector for each user.
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (6) , 11363-11376
Toward Requested VR QoE Using Multi-Objective Reinforcement Learning
Virtual reality (VR) has been viewed as an important application in the coming wireless networks. Nevertheless, it requires both broad bandwidth and low-latency transmission, which places significant pressure on limited wireless resources. Aiming for resource savings while satisfying the various QoE requirements, based on dedicated formulating VR QoE, i.e., the mean opinion score (MOS) of video quality and motion-to-photon (MTP) delay, a QoE-steering (QoE-STR) multi-objective reinforcement learning algorithm is proposed to jointly optimize the field of view (FoV) redundancy, provided video quality, computing resources, and communication resources. The algorithm is tailored to distinct user preferences through multiple basic policies. Then it introduces a QoE-STR policy selection mechanism based on the direction vector toward the requested QoE, making users' achieved QoE approach their respective requested QoE. To reduce the computing complexity, we further develop a distributed QoE-STR (Dist. QoE-STR) algorithm, which can independently allocate wireless resources to each user while guaranteeing the network's overall resource constraints. Simulation results demonstrate the effectiveness of both proposed algorithms and the Dist. QoE-STR performs better since it can independently design the direction vector for each user.
- 22 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (5) , 7904-7917
Pareto-Optimal Multiagent Cooperative Caching Relying on Multipolicy Reinforcement Learning
Given the popularity of flawless telepresence and the resultants explosive growth of wireless video applications, besides handling the traffic surge, satisfying the demanding user requirements for video qualities has become another important goal of network operators. Inspired by this, cooperative edge caching intrinsically amalgamated with scalable video coding is investigated. Explicitly, the concept of a Pareto-optimal semi-distributed multiagent multipolicy deep reinforcement learning (SD-MAMP-DRL) algorithm is conceived for managing the cooperation of heterogeneous network nodes. To elaborate, a multipolicy reinforcement learning algorithm is proposed for finding the Pareto-optimal policies during the training phase, which balances the teletraffic versus the user experience tradeoff. Then the optimal policy/solution can be activated during the execution phase by appropriately selecting the associated weighting coefficient according to the dynamically fluctuating network traffic load. Our experimental results show that the proposed SD-MAMP- acrshort DRL algorithm: 1) achieves better performance than the benchmark algorithms and 2) obtains a near-complete Pareto front in various scenarios and selects the optimal solution by adaptively adjusting the above-mentioned pair of objectives.
- 22 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (5) , 7904-7917
Pareto-Optimal Multiagent Cooperative Caching Relying on Multipolicy Reinforcement Learning
Given the popularity of flawless telepresence and the resultants explosive growth of wireless video applications, besides handling the traffic surge, satisfying the demanding user requirements for video qualities has become another important goal of network operators. Inspired by this, cooperative edge caching intrinsically amalgamated with scalable video coding is investigated. Explicitly, the concept of a Pareto-optimal semi-distributed multiagent multipolicy deep reinforcement learning (SD-MAMP-DRL) algorithm is conceived for managing the cooperation of heterogeneous network nodes. To elaborate, a multipolicy reinforcement learning algorithm is proposed for finding the Pareto-optimal policies during the training phase, which balances the teletraffic versus the user experience tradeoff. Then the optimal policy/solution can be activated during the execution phase by appropriately selecting the associated weighting coefficient according to the dynamically fluctuating network traffic load. Our experimental results show that the proposed SD-MAMP- acrshort DRL algorithm: 1) achieves better performance than the benchmark algorithms and 2) obtains a near-complete Pareto front in various scenarios and selects the optimal solution by adaptively adjusting the above-mentioned pair of objectives.
- Open Access
- 19 October 2022
- Published by MDPI AG in Electronics
- Vol. 11 (20) , 3385
Augmented Lagrangian-Based Reinforcement Learning for Network Slicing in IIoT
Network slicing enables the multiplexing of independent logical networks on the same physical network infrastructure to provide different network services for different applications. The resource allocation problem involved in network slicing is typically a decision-making problem, falling within the scope of reinforcement learning. The advantage of adapting to dynamic wireless environments makes reinforcement learning a good candidate for problem solving. In this paper, to tackle the constrained mixed integer nonlinear programming problem in network slicing, we propose an augmented Lagrangian-based soft actor–critic (AL-SAC) algorithm. In this algorithm, a hierarchical action selection network is designed to handle the hybrid action space. More importantly, inspired by the augmented Lagrangian method, both neural networks for Lagrange multipliers and a penalty item are introduced to deal with the constraints. Experiment results show that the proposed AL-SAC algorithm can strictly satisfy the constraints, and achieve better performance than other benchmark algorithms.
- 19 October 2022
- Published by MDPI AG in Electronics
- Vol. 11 (20) , 3385
Open AccessAugmented Lagrangian-Based Reinforcement Learning for Network Slicing in IIoT
Network slicing enables the multiplexing of independent logical networks on the same physical network infrastructure to provide different network services for different applications. The resource allocation problem involved in network slicing is typically a decision-making problem, falling within the scope of reinforcement learning. The advantage of adapting to dynamic wireless environments makes reinforcement learning a good candidate for problem solving. In this paper, to tackle the constrained mixed integer nonlinear programming problem in network slicing, we propose an augmented Lagrangian-based soft actor–critic (AL-SAC) algorithm. In this algorithm, a hierarchical action selection network is designed to handle the hybrid action space. More importantly, inspired by the augmented Lagrangian method, both neural networks for Lagrange multipliers and a penalty item are introduced to deal with the constraints. Experiment results show that the proposed AL-SAC algorithm can strictly satisfy the constraints, and achieve better performance than other benchmark algorithms.