Zelin Ji
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zelin Ji has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Zhijin Qin
Tsinghua University
7 shared publications - Xiaoming Tao
Tsinghua University
4 shared publications - Zhijin Qin
Tsinghua University
2 shared publications - Zhu Han
University of Houston
2 shared publications Adnan K. Kiani
University of Essex, Colchester, Essex, UK
1 shared publication- Clive G. Parini
School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K.
1 shared publication
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74, 16345-16357
Efficient Signals Denoising Under Imperfect Channels: A Noise-to-Noise Learning Approach
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74, 16345-16357
Efficient Signals Denoising Under Imperfect Channels: A Noise-to-Noise Learning Approach
- 25 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 18 (7) , 1235-1248
Computational Offloading in Semantic-Aware Cloud-Edge-End Collaborative Networks
The trend of massive connectivity pushes forward the explosive growth of end devices. The emergence of various applications has prompted a demand for pervasive connectivity and more efficient computing paradigms. On the other hand, the lack of computational capacity of the end devices restricts the implementation of the intelligent applications, and becomes a bottleneck of the multiple access for supporting massive connectivity. Mobile cloud computing (MCC) and mobile edge computing (MEC) techniques enable end devices to offload local computation-intensive tasks to servers by networks. In this paper, we consider the cloud-edge-end collaborative networks to utilize distributed computing resources. Furthermore, we apply task-oriented semantic communications to tackle the fast-varying channel between the end devices and MEC servers and reduce the communication cost. To minimize long-term energy consumption on constraints queue stability and computational delay, a Lyapunov-guided deep reinforcement learning hybrid (DRLH) framework is proposed to solve the mixed integer non-linear programming (MINLP) problem. The long-term energy consumption minimization problem is transformed into the deterministic problem in each time frame. The DRLH framework integrates a model-free deep reinforcement learning algorithm with a model-based mathematical optimization algorithm to mitigate computational complexity and leverage the scenario information, so that improving the convergence performance. Numerical results demonstrate that the proposed DRLH framework achieves near-optimal performance on energy consumption while stabilizing all queues.
- 25 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 18 (7) , 1235-1248
Computational Offloading in Semantic-Aware Cloud-Edge-End Collaborative Networks
The trend of massive connectivity pushes forward the explosive growth of end devices. The emergence of various applications has prompted a demand for pervasive connectivity and more efficient computing paradigms. On the other hand, the lack of computational capacity of the end devices restricts the implementation of the intelligent applications, and becomes a bottleneck of the multiple access for supporting massive connectivity. Mobile cloud computing (MCC) and mobile edge computing (MEC) techniques enable end devices to offload local computation-intensive tasks to servers by networks. In this paper, we consider the cloud-edge-end collaborative networks to utilize distributed computing resources. Furthermore, we apply task-oriented semantic communications to tackle the fast-varying channel between the end devices and MEC servers and reduce the communication cost. To minimize long-term energy consumption on constraints queue stability and computational delay, a Lyapunov-guided deep reinforcement learning hybrid (DRLH) framework is proposed to solve the mixed integer non-linear programming (MINLP) problem. The long-term energy consumption minimization problem is transformed into the deterministic problem in each time frame. The DRLH framework integrates a model-free deep reinforcement learning algorithm with a model-based mathematical optimization algorithm to mitigate computational complexity and leverage the scenario information, so that improving the convergence performance. Numerical results demonstrate that the proposed DRLH framework achieves near-optimal performance on energy consumption while stabilizing all queues.
- 24 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 23 (9) , 12284-12296
Resource Optimization for Semantic-Aware Networks With Task Offloading
The limited capabilities of user equipment restrict the local implementation of computation-intensive applications. Edge computing, especially the edge intelligence system, enables local users to offload the computation tasks to the edge servers to reduce the computational energy consumption of user equipment and accelerate fast task execution. However, the limited bandwidth of upstream channels may increase the task transmission latency and affect the computation offloading performance. To overcome the challenge arising from scarce wireless communication resources, we propose a semantic-aware multi-modal task offloading system that facilitates the extraction and offloading of semantic task information to edge servers. To cope with the different tasks with multi-modal data, a unified quality of experience (QoE) criterion is designed. Furthermore, a proximal policy optimization-based multi-agent reinforcement learning algorithm (MAPPO) is proposed to coordinate the resource management for wireless communications and computation in a distributed and low computational complexity manner. Simulation results verify that the proposed MAPPO algorithm outperforms other reinforcement learning algorithms and fixed schemes in terms of task execution speed and the overall system QoE.
- 24 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 23 (9) , 12284-12296
Resource Optimization for Semantic-Aware Networks With Task Offloading
The limited capabilities of user equipment restrict the local implementation of computation-intensive applications. Edge computing, especially the edge intelligence system, enables local users to offload the computation tasks to the edge servers to reduce the computational energy consumption of user equipment and accelerate fast task execution. However, the limited bandwidth of upstream channels may increase the task transmission latency and affect the computation offloading performance. To overcome the challenge arising from scarce wireless communication resources, we propose a semantic-aware multi-modal task offloading system that facilitates the extraction and offloading of semantic task information to edge servers. To cope with the different tasks with multi-modal data, a unified quality of experience (QoE) criterion is designed. Furthermore, a proximal policy optimization-based multi-agent reinforcement learning algorithm (MAPPO) is proposed to coordinate the resource management for wireless communications and computation in a distributed and low computational complexity manner. Simulation results verify that the proposed MAPPO algorithm outperforms other reinforcement learning algorithms and fixed schemes in terms of task execution speed and the overall system QoE.
- Open Access
Resource Optimization for Semantic-Aware Networks with Task Offloading
The limited capabilities of user equipment restrict the local implementation of computation-intensive applications. Edge computing, especially the edge intelligence system, enables local users to offload the computation tasks to the edge servers to reduce the computational energy consumption of user equipment and accelerate fast task execution. However, the limited bandwidth of upstream channels may increase the task transmission latency and affect the computation offloading performance. To overcome the challenge arising from scarce wireless communication resources, we propose a semantic-aware multi-modal task offloading system that facilitates the extraction and offloading of semantic task information to edge servers. To cope with the different tasks with multi-modal data, a unified quality of experience (QoE) criterion is designed. Furthermore, a proximal policy optimization-based multi-agent reinforcement learning algorithm (MAPPO) is proposed to coordinate the resource management for wireless communications and computation in a distributed and low computational complexity manner. Simulation results verify that the proposed MAPPO algorithm outperforms other reinforcement learning algorithms and fixed schemes in terms of task execution speed and the overall system QoE.
Open AccessResource Optimization for Semantic-Aware Networks with Task Offloading
The limited capabilities of user equipment restrict the local implementation of computation-intensive applications. Edge computing, especially the edge intelligence system, enables local users to offload the computation tasks to the edge servers to reduce the computational energy consumption of user equipment and accelerate fast task execution. However, the limited bandwidth of upstream channels may increase the task transmission latency and affect the computation offloading performance. To overcome the challenge arising from scarce wireless communication resources, we propose a semantic-aware multi-modal task offloading system that facilitates the extraction and offloading of semantic task information to edge servers. To cope with the different tasks with multi-modal data, a unified quality of experience (QoE) criterion is designed. Furthermore, a proximal policy optimization-based multi-agent reinforcement learning algorithm (MAPPO) is proposed to coordinate the resource management for wireless communications and computation in a distributed and low computational complexity manner. Simulation results verify that the proposed MAPPO algorithm outperforms other reinforcement learning algorithms and fixed schemes in terms of task execution speed and the overall system QoE.
- Open Access
- 29 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 23 (7) , 7865-7876
Meta Federated Reinforcement Learning for Distributed Resource Allocation
In cellular networks, resource allocation is usually performed in a centralized way, which brings huge computation complexity to the base station (BS) and high transmission overhead. This paper introduces a distributed resource allocation method that aims to maximize energy efficiency (EE) while ensuring quality of service (QoS) for users. Specifically, to address the challenge of fast-varying wireless channel conditions, we propose a robust meta federated reinforcement learning ( MFRL ) framework that enables local users to optimize transmit power and assign channels using locally trained neural network models. This approach offloads the computational burden from the cloud server to the local users, reducing transmission overhead associated with local channel state information. The BS performs the meta-learning procedure to initialize a general global model, enabling rapid adaptation to different environments and improved EE performance. The federated learning technique, based on decentralized reinforcement learning, promotes collaboration and mutual benefits among users. Analysis and numerical results demonstrate that the proposed MFRL framework accelerates the reinforcement learning process, decreases transmission overhead, and offloads computation, while outperforming the conventional decentralized reinforcement learning algorithm in terms of convergence speed and EE performance across various scenarios.
- 29 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 23 (7) , 7865-7876
Open AccessMeta Federated Reinforcement Learning for Distributed Resource Allocation
In cellular networks, resource allocation is usually performed in a centralized way, which brings huge computation complexity to the base station (BS) and high transmission overhead. This paper introduces a distributed resource allocation method that aims to maximize energy efficiency (EE) while ensuring quality of service (QoS) for users. Specifically, to address the challenge of fast-varying wireless channel conditions, we propose a robust meta federated reinforcement learning ( MFRL ) framework that enables local users to optimize transmit power and assign channels using locally trained neural network models. This approach offloads the computational burden from the cloud server to the local users, reducing transmission overhead associated with local channel state information. The BS performs the meta-learning procedure to initialize a general global model, enabling rapid adaptation to different environments and improved EE performance. The federated learning technique, based on decentralized reinforcement learning, promotes collaboration and mutual benefits among users. Analysis and numerical results demonstrate that the proposed MFRL framework accelerates the reinforcement learning process, decreases transmission overhead, and offloads computation, while outperforming the conventional decentralized reinforcement learning algorithm in terms of convergence speed and EE performance across various scenarios.
- Open Access
Meta Federated Reinforcement Learning for Distributed Resource Allocation
In cellular networks, resource allocation is usually performed in a centralized way, which brings huge computation complexity to the base station (BS) and high transmission overhead. This paper explores a distributed resource allocation method that aims to maximize energy efficiency (EE) while ensuring the quality of service (QoS) for users. Specifically, in order to address wireless channel conditions, we propose a robust meta federated reinforcement learning (\textit{MFRL}) framework that allows local users to optimize transmit power and assign channels using locally trained neural network models, so as to offload computational burden from the cloud server to the local users, reducing transmission overhead associated with local channel state information. The BS performs the meta learning procedure to initialize a general global model, enabling rapid adaptation to different environments with improved EE performance. The federated learning technique, based on decentralized reinforcement learning, promotes collaboration and mutual benefits among users. Analysis and numerical results demonstrate that the proposed \textit{MFRL} framework accelerates the reinforcement learning process, decreases transmission overhead, and offloads computation, while outperforming the conventional decentralized reinforcement learning algorithm in terms of convergence speed and EE performance across various scenarios.
Open AccessMeta Federated Reinforcement Learning for Distributed Resource Allocation
In cellular networks, resource allocation is usually performed in a centralized way, which brings huge computation complexity to the base station (BS) and high transmission overhead. This paper explores a distributed resource allocation method that aims to maximize energy efficiency (EE) while ensuring the quality of service (QoS) for users. Specifically, in order to address wireless channel conditions, we propose a robust meta federated reinforcement learning (\textit{MFRL}) framework that allows local users to optimize transmit power and assign channels using locally trained neural network models, so as to offload computational burden from the cloud server to the local users, reducing transmission overhead associated with local channel state information. The BS performs the meta learning procedure to initialize a general global model, enabling rapid adaptation to different environments with improved EE performance. The federated learning technique, based on decentralized reinforcement learning, promotes collaboration and mutual benefits among users. Analysis and numerical results demonstrate that the proposed \textit{MFRL} framework accelerates the reinforcement learning process, decreases transmission overhead, and offloads computation, while outperforming the conventional decentralized reinforcement learning algorithm in terms of convergence speed and EE performance across various scenarios.
- Open Access
Federated Learning for Distributed Energy-Efficient Resource Allocation
In cellular networks, resource allocation is performed in a centralized way, which brings huge computation complexity to the base station (BS) and high transmission overhead. This paper investigates the distributed resource allocation scheme for cellular networks to maximize the energy efficiency of the system in the uplink transmission, while guaranteeing the quality of service (QoS) for cellular users. Particularly, to cope the fast varying channels in wireless communication environment, we propose a robust federated reinforcement learning (FRL_suc) framework to enable local users to perform distributed resource allocation in items of transmit power and channel assignment by the guidance of the local neural network trained at each user. Analysis and numerical results show that the proposed FRL_suc framework can lower the transmission overhead and offload the computation from the central server to the local users, while outperforming the conventional multi-agent reinforcement learning algorithm in terms of EE, and is more robust to channel variations.
Open AccessFederated Learning for Distributed Energy-Efficient Resource Allocation
In cellular networks, resource allocation is performed in a centralized way, which brings huge computation complexity to the base station (BS) and high transmission overhead. This paper investigates the distributed resource allocation scheme for cellular networks to maximize the energy efficiency of the system in the uplink transmission, while guaranteeing the quality of service (QoS) for cellular users. Particularly, to cope the fast varying channels in wireless communication environment, we propose a robust federated reinforcement learning (FRL_suc) framework to enable local users to perform distributed resource allocation in items of transmit power and channel assignment by the guidance of the local neural network trained at each user. Analysis and numerical results show that the proposed FRL_suc framework can lower the transmission overhead and offload the computation from the central server to the local users, while outperforming the conventional multi-agent reinforcement learning algorithm in terms of EE, and is more robust to channel variations.
- 21 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 70 (3) , 1808-1819
Reconfigurable Intelligent Surface Aided Cellular Networks With Device-to-Device Users
Reconfigurable intelligent surface (RIS) technology is promising to enhance wireless communications services by providing smart radio environment. In this paper, we investigate the RIS aided cellular networks with device-to-device (D2D) users, and maximize the sum of the transmission rate of the D2D communications and the cellular networks from a new perspective. In addition to solving the typical resource allocation problems for D2D communications, this paper further optimize the wireless environment by adjusting the position and phase shift of the RIS. To solve this non-convex problem, we propose a novel decentralized double deep Q-network (D3QN) framework for the resource allocation at users and a centralized DDQN for RIS optimization at the base station (BS), which are verified to achieve the near-optimal performance with lower complexity and enhanced robustness. Simulation results illustrate that the proposed framework can achieve higher transmission rates compared to benchmarks, meanwhile meeting the quality of service (QoS) requirements at the BS and D2D users.
- 21 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 70 (3) , 1808-1819
Reconfigurable Intelligent Surface Aided Cellular Networks With Device-to-Device Users
Reconfigurable intelligent surface (RIS) technology is promising to enhance wireless communications services by providing smart radio environment. In this paper, we investigate the RIS aided cellular networks with device-to-device (D2D) users, and maximize the sum of the transmission rate of the D2D communications and the cellular networks from a new perspective. In addition to solving the typical resource allocation problems for D2D communications, this paper further optimize the wireless environment by adjusting the position and phase shift of the RIS. To solve this non-convex problem, we propose a novel decentralized double deep Q-network (D3QN) framework for the resource allocation at users and a centralized DDQN for RIS optimization at the base station (BS), which are verified to achieve the near-optimal performance with lower complexity and enhanced robustness. Simulation results illustrate that the proposed framework can achieve higher transmission rates compared to benchmarks, meanwhile meeting the quality of service (QoS) requirements at the BS and D2D users.
- 4 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 10 (3) , 508-511
Power Optimization in Device-to-Device Communications: A Deep Reinforcement Learning Approach With Dynamic Reward
Device-to-Device (D2D) communication can be used to improve system capacity and energy efficiency (EE) in cellular networks. One of the critical challenges in D2D communications is to extend network lifetime by efficient and effective resource management. Deep reinforcement learning (RL) provides a promising solution for resource management in wireless communication systems. This letter aims to maximise the EE while satisfying the system throughput constraints as well as the quality of service (QoS) requirements of D2D pairs and cellular users in an underlay D2D communication network. To achieve this, a deep RL based dynamic power optimization algorithm with dynamic rewards is proposed. Moreover, a novel algorithm with two parallel deep Q networks (DQNs) is designed to maximize the EE of the considered network. The proposed deep RL based power optimization method with dynamic rewards achieves higher EE while satisfying the system throughput requirements.
- 4 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 10 (3) , 508-511
Power Optimization in Device-to-Device Communications: A Deep Reinforcement Learning Approach With Dynamic Reward
Device-to-Device (D2D) communication can be used to improve system capacity and energy efficiency (EE) in cellular networks. One of the critical challenges in D2D communications is to extend network lifetime by efficient and effective resource management. Deep reinforcement learning (RL) provides a promising solution for resource management in wireless communication systems. This letter aims to maximise the EE while satisfying the system throughput constraints as well as the quality of service (QoS) requirements of D2D pairs and cellular users in an underlay D2D communication network. To achieve this, a deep RL based dynamic power optimization algorithm with dynamic rewards is proposed. Moreover, a novel algorithm with two parallel deep Q networks (DQNs) is designed to maximize the EE of the considered network. The proposed deep RL based power optimization method with dynamic rewards achieves higher EE while satisfying the system throughput requirements.
- Open Access
Reconfigurable Intelligent Surface Enhanced Device-to-Device Communications
Reconfigurable intelligent surface (RIS) technology is a promising method to enhance the device-to-device (D2D) communications. To maximize the sum rate of the cellular and D2D networks, a joint optimization of the position and the phase shift of RIS in D2D communications is considered in this paper. To solve the non-convex sum rate maximum problem, we propose a novel convolutional neural network (CNN) based deep Q-network (DQN) that jointly optimizes the RIS position and its phase shift with lower complexity. Numerical results illustrate that the proposed algorithm can achieve higher sum rate compared to the benchmark algorithms, meanwhile meeting the quality of service (QoS) requirements at D2D receivers and the base station (BS).
Open AccessReconfigurable Intelligent Surface Enhanced Device-to-Device Communications
Reconfigurable intelligent surface (RIS) technology is a promising method to enhance the device-to-device (D2D) communications. To maximize the sum rate of the cellular and D2D networks, a joint optimization of the position and the phase shift of RIS in D2D communications is considered in this paper. To solve the non-convex sum rate maximum problem, we propose a novel convolutional neural network (CNN) based deep Q-network (DQN) that jointly optimizes the RIS position and its phase shift with lower complexity. Numerical results illustrate that the proposed algorithm can achieve higher sum rate compared to the benchmark algorithms, meanwhile meeting the quality of service (QoS) requirements at D2D receivers and the base station (BS).