Hui Liang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Hui Liang has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Xiaohui Zhao
Jilin University
6 shared publications - Wei Zhang
The University of New South Wales
4 shared publications - Zan Li
Jilin University
3 shared publications - Long Shi
Nanjing University of Science and Technology
2 shared publications - Nan Cheng
Xidian University
2 shared publications - Qihao Li
College of Communication Engineering, Jilin University, Changchun, China
2 shared publications
Latest Publications
- 25 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74 (00906778) , 1594-1607
Secure Access Strategy for SatMEC Systems: Risk-Aware Service Selection in the Presence of Eavesdropping Satellites
Satellite communications have been considered a key part of global connectivity, effectively supporting diverse applications such as the Internet of Things (IoT) and real-time communication services. However, security-sensitive devices face significant challenges due to the threat of eavesdropping satellites, which compromise data confidentiality. Existing approaches often rely on deterministic models and fail to account for the stochastic nature of eavesdropping threats and the dynamic demands of satellite networks, limiting their applicability in practical scenarios. To address these challenges, this work proposes a novel secure access strategy for satellite mobile edge computing (SatMEC) systems, integrating a stochastic risk assessment model and an evolutionary game-theoretic framework. The proposed solution leverages a probabilistic model to evaluate the spatial distribution of eavesdropping satellites, quantifies the eavesdropping risk via the concept of eavesdropping capacity, and incorporates a dynamic service selection strategy that balances secrecy capacity and queuing delay.Furthermore, a distributed algorithm is developed to enable IoT devices to select service satellites based on real-time utility optimization adaptively. Extensive simulation experiments validate the effectiveness of the proposed strategy, demonstrating its ability to improve system security, balance the network load, and enhance overall performance in large-scale and dynamic satellite network environments. The results highlight the reliability and scalability of the proposed solution, making it a practical approach for secure and efficient access in LEO satellite networks.
- 25 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74 (00906778) , 1594-1607
Secure Access Strategy for SatMEC Systems: Risk-Aware Service Selection in the Presence of Eavesdropping Satellites
Satellite communications have been considered a key part of global connectivity, effectively supporting diverse applications such as the Internet of Things (IoT) and real-time communication services. However, security-sensitive devices face significant challenges due to the threat of eavesdropping satellites, which compromise data confidentiality. Existing approaches often rely on deterministic models and fail to account for the stochastic nature of eavesdropping threats and the dynamic demands of satellite networks, limiting their applicability in practical scenarios. To address these challenges, this work proposes a novel secure access strategy for satellite mobile edge computing (SatMEC) systems, integrating a stochastic risk assessment model and an evolutionary game-theoretic framework. The proposed solution leverages a probabilistic model to evaluate the spatial distribution of eavesdropping satellites, quantifies the eavesdropping risk via the concept of eavesdropping capacity, and incorporates a dynamic service selection strategy that balances secrecy capacity and queuing delay.Furthermore, a distributed algorithm is developed to enable IoT devices to select service satellites based on real-time utility optimization adaptively. Extensive simulation experiments validate the effectiveness of the proposed strategy, demonstrating its ability to improve system security, balance the network load, and enhance overall performance in large-scale and dynamic satellite network environments. The results highlight the reliability and scalability of the proposed solution, making it a practical approach for secure and efficient access in LEO satellite networks.
- 10 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 14 (7) , 1949-1953
A Cybertwin-Based Trading Mechanism for Personalized Transmission Services in Cloud Native Networks
The Cybertwin-based cloud native network (CCNN) with a cloud-edge-end architecture is to provide personalized user services, which includes both wireless access networks and cloud networks. However, the limited availability of resources and intense user competition present significant challenges. While prior studies have contributed to this issue, they overlook the feasibility of using resources as the trading object in a user-centric approach, particularly in wireless networks. To address this gap, this letter proposes a Cybertwin-based Personalized Transmission Service Trading Mechanism (CPTSTM), employing a one-to-many concurrent bilateral negotiation model for dynamic multi-provider trading. An optimization problem is formulated to minimize user costs by modeling the negotiation as a sequential decision-making process, accounting for individual rationality and system uncertainties. Given restricted and hybrid action spaces, we introduce a Constrained Parameterized Deep Q-learning Network (CPDQN)-based negotiation strategy integrating offer evaluation, acceptance, and bidding strategies. Simulation results confirm the feasibility of the proposed mechanism and demonstrate that the CPDQN-based algorithm outperforms existing methods in terms of trade success rate (nearly 100%) and the number of negotiation rounds (reduced by 75%) while maintaining comparable user utility across various scenarios.
- 10 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 14 (7) , 1949-1953
A Cybertwin-Based Trading Mechanism for Personalized Transmission Services in Cloud Native Networks
The Cybertwin-based cloud native network (CCNN) with a cloud-edge-end architecture is to provide personalized user services, which includes both wireless access networks and cloud networks. However, the limited availability of resources and intense user competition present significant challenges. While prior studies have contributed to this issue, they overlook the feasibility of using resources as the trading object in a user-centric approach, particularly in wireless networks. To address this gap, this letter proposes a Cybertwin-based Personalized Transmission Service Trading Mechanism (CPTSTM), employing a one-to-many concurrent bilateral negotiation model for dynamic multi-provider trading. An optimization problem is formulated to minimize user costs by modeling the negotiation as a sequential decision-making process, accounting for individual rationality and system uncertainties. Given restricted and hybrid action spaces, we introduce a Constrained Parameterized Deep Q-learning Network (CPDQN)-based negotiation strategy integrating offer evaluation, acceptance, and bidding strategies. Simulation results confirm the feasibility of the proposed mechanism and demonstrate that the CPDQN-based algorithm outperforms existing methods in terms of trade success rate (nearly 100%) and the number of negotiation rounds (reduced by 75%) while maintaining comparable user utility across various scenarios.
- 9 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (13) , 25487-25499
Mixture of Gradient: A Unified Enhancing Approach for Deep-Learning-Based Wireless Network Optimization
Deep learning plays increasingly important role in future wireless network management and optimization. Existing training methods such as label-based supervised learning and label-free learning have inherent limitations. The performance of supervised learning is limited by labels, while label-free training methods require extensive exploration. To address these limitations, this article proposes a novel mixture of gradients (MoG) method, which integrates gradients from different sources within the training process in order to improve the convergence performance of neural networks (NNs). Particularly, MoG is a modular, plug-and-play solution requiring no structural modifications to existing NNs. Its implementation necessitates only minor modifications to the loss function, where the label-based supervised loss is combined with a label-free loss through weighted summation. The label-free loss can be either unsupervised loss or reinforcement learning loss. This flexibility allows seamless integration into nearly all NN-based methods, making it applicable to a wide range of wireless optimization problems with minimal implementation cost. Extensive simulations across multiple classic wireless scenarios demonstrate that MoG can significantly enhance the performance of NN decision-making, leading to higher transmission rates.
- 9 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (13) , 25487-25499
Mixture of Gradient: A Unified Enhancing Approach for Deep-Learning-Based Wireless Network Optimization
Deep learning plays increasingly important role in future wireless network management and optimization. Existing training methods such as label-based supervised learning and label-free learning have inherent limitations. The performance of supervised learning is limited by labels, while label-free training methods require extensive exploration. To address these limitations, this article proposes a novel mixture of gradients (MoG) method, which integrates gradients from different sources within the training process in order to improve the convergence performance of neural networks (NNs). Particularly, MoG is a modular, plug-and-play solution requiring no structural modifications to existing NNs. Its implementation necessitates only minor modifications to the loss function, where the label-based supervised loss is combined with a label-free loss through weighted summation. The label-free loss can be either unsupervised loss or reinforcement learning loss. This flexibility allows seamless integration into nearly all NN-based methods, making it applicable to a wide range of wireless optimization problems with minimal implementation cost. Extensive simulations across multiple classic wireless scenarios demonstrate that MoG can significantly enhance the performance of NN decision-making, leading to higher transmission rates.
- 19 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 23 (5) , 5006-5018
Trusted Mobile Edge Computing: DAG Blockchain-Aided Trust Management and Resource Allocation
The integration of directed acyclic graph (DAG) blockchain and mobile edge computing (MEC) has emerged as a promising means to enable computation-intensive, delay-sensitive, and secure task execution in Internet of Things (IoT) applications. However, off-chain task execution results are not credible even if the results have been recorded on the chain, since blockchain cannot extend the trust of on-chain data to off-chain. To make the off-chain and on-chain trust consistent, we first develop a trusted MEC (T-MEC) framework by employing a DAG blockchain-aided decentralized trust management (DAG-DTM) mechanism. Specifically, DAG-DTM evaluates the off-chain trust of edge nodes according to the quality of task execution results, and the trust can be further verified off the chain by any edge node under the same trust management rule. Moreover, the approval time for recording the execution result of the edge node on the chain is positively correlated with the verified off-chain trust, which can further promote on-chain transaction security of trusted edge node. Second, we jointly optimize the bandwidth and computation resource allocation to minimize the system latency that consists of off-chain task execution delay and on-chain transaction confirmation delay. Numerical results compare system latency and security performance between the optimized T-MEC and the benchmark schemes. In particular, the optimized T-MEC can achieve a 33.12% gain of computation delay and a 10.19% gain of system latency at an affordable cost of transaction confirmation delay (i.e., 3.21%) over T-MEC, while meeting the requirements of off-chain task execution latency and on-chain transaction security simultaneously.
- 19 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 23 (5) , 5006-5018
Trusted Mobile Edge Computing: DAG Blockchain-Aided Trust Management and Resource Allocation
The integration of directed acyclic graph (DAG) blockchain and mobile edge computing (MEC) has emerged as a promising means to enable computation-intensive, delay-sensitive, and secure task execution in Internet of Things (IoT) applications. However, off-chain task execution results are not credible even if the results have been recorded on the chain, since blockchain cannot extend the trust of on-chain data to off-chain. To make the off-chain and on-chain trust consistent, we first develop a trusted MEC (T-MEC) framework by employing a DAG blockchain-aided decentralized trust management (DAG-DTM) mechanism. Specifically, DAG-DTM evaluates the off-chain trust of edge nodes according to the quality of task execution results, and the trust can be further verified off the chain by any edge node under the same trust management rule. Moreover, the approval time for recording the execution result of the edge node on the chain is positively correlated with the verified off-chain trust, which can further promote on-chain transaction security of trusted edge node. Second, we jointly optimize the bandwidth and computation resource allocation to minimize the system latency that consists of off-chain task execution delay and on-chain transaction confirmation delay. Numerical results compare system latency and security performance between the optimized T-MEC and the benchmark schemes. In particular, the optimized T-MEC can achieve a 33.12% gain of computation delay and a 10.19% gain of system latency at an affordable cost of transaction confirmation delay (i.e., 3.21%) over T-MEC, while meeting the requirements of off-chain task execution latency and on-chain transaction security simultaneously.
- 9 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 10 (24) , 22080-22095
Stochastic-Stackelberg-Game-Based Edge Service Selection for Massive IoT Networks
Mobile edge computing is a promising technique to provide timely edge service for the Internet of Things. With a continuously expanding network scale, the number and types of devices in the IoT network are growing rapidly. Moreover, the total number of devices that need edge service actually in the network is uncertain because the devices are online or offline frequently. It is very critical to design an efficient service selection strategy for every device to access edge service providers (ESPs) in such a huge number of devices situation. To address the problem, this paper first formulates the access of IoT devices as a stochastic Stackelberg game model. Then, for the edge service selection of devices, a Poisson game is utilized to model the coordinated selection of edge services, we propose a distributed iterative algorithm to solve this game and give the optimal edge service selection strategy for each device group. Next, for the non-cooperative competition among ESPs with incomplete information, the service prices of other ESPs are first estimated through a Bayesian Neural Network (BNN). Then we model this stochastic non-cooperative game as a POMDP model, and finally obtain the optimal long-term pricing strategy through Bayesian deep Q-learning network (BDQN) algorithm. The experimental simulation results show that the proposed strategy can significantly improve the utilities of both ESPs and devices and effectively decrease the average queuing probability of all devices.
- 9 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 10 (24) , 22080-22095
Stochastic-Stackelberg-Game-Based Edge Service Selection for Massive IoT Networks
Mobile edge computing is a promising technique to provide timely edge service for the Internet of Things. With a continuously expanding network scale, the number and types of devices in the IoT network are growing rapidly. Moreover, the total number of devices that need edge service actually in the network is uncertain because the devices are online or offline frequently. It is very critical to design an efficient service selection strategy for every device to access edge service providers (ESPs) in such a huge number of devices situation. To address the problem, this paper first formulates the access of IoT devices as a stochastic Stackelberg game model. Then, for the edge service selection of devices, a Poisson game is utilized to model the coordinated selection of edge services, we propose a distributed iterative algorithm to solve this game and give the optimal edge service selection strategy for each device group. Next, for the non-cooperative competition among ESPs with incomplete information, the service prices of other ESPs are first estimated through a Bayesian Neural Network (BNN). Then we model this stochastic non-cooperative game as a POMDP model, and finally obtain the optimal long-term pricing strategy through Bayesian deep Q-learning network (BDQN) algorithm. The experimental simulation results show that the proposed strategy can significantly improve the utilities of both ESPs and devices and effectively decrease the average queuing probability of all devices.
- 8 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 8 (22) , 16349-16358
A Combinatorial Auction Resource Trading Mechanism for Cybertwin-Based 6G Network
Cybertwin is a promising technique in the 6G network to cope with an exponentially increasing demand for the mobile data traffic and growing number of required network service appliances. Multiple resources are required to fulfil various personalized services of mobile users while protecting their privacy. In this article, we propose a progressive adaptive user selection environment (PAUSE)-based combinatorial auction resource trading mechanism to allocate the resource efficiently and securely. Cybertwins can request the various resources as a bid according to its corresponding user and proceed the auction in a fully distributed manner. Not only the user’s privacy can be well protected but also its cost can be saved due to the transparency of this mechanism. Simulation results validate the effectiveness of our mechanism in comparison with the centralized benchmark.
- 8 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 8 (22) , 16349-16358
A Combinatorial Auction Resource Trading Mechanism for Cybertwin-Based 6G Network
Cybertwin is a promising technique in the 6G network to cope with an exponentially increasing demand for the mobile data traffic and growing number of required network service appliances. Multiple resources are required to fulfil various personalized services of mobile users while protecting their privacy. In this article, we propose a progressive adaptive user selection environment (PAUSE)-based combinatorial auction resource trading mechanism to allocate the resource efficiently and securely. Cybertwins can request the various resources as a bid according to its corresponding user and proceed the auction in a fully distributed manner. Not only the user’s privacy can be well protected but also its cost can be saved due to the transparency of this mechanism. Simulation results validate the effectiveness of our mechanism in comparison with the centralized benchmark.
- 16 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 7 (9) , 9091-9102
Throughput Maximization by Deep Reinforcement Learning With Energy Cooperation for Renewable Ultradense IoT Networks
Ultra-dense network (UDN) is considered as one of the key technologies for the explosive growth of mobile traffic demand on the Internet of Things (IoT). It enhances network capacity by deploying small base stations in large quantities, but it simultaneously causes great energy consumption. In this paper, we use energy harvesting (EH) and energy cooperation technologies to maximize system throughput and save energy. Considering that the energy arrival process and channel information are not available a-priori, we propose an optimal deep reinforcement learning (DRL) algorithm to solve this average throughput maximization problem over finite horizon. We also propose a multi-agent deep reinforcement learning method to solve the dimensionality problem caused by the expansion of the state and action dimension. Finally, we compare these algorithms with two traditional algorithms, greedy algorithm and conservative algorithm. The numerical results show that the proposed algorithms are valid and effective in increasing system average throughput on long term.
- 16 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 7 (9) , 9091-9102
Throughput Maximization by Deep Reinforcement Learning With Energy Cooperation for Renewable Ultradense IoT Networks
Ultra-dense network (UDN) is considered as one of the key technologies for the explosive growth of mobile traffic demand on the Internet of Things (IoT). It enhances network capacity by deploying small base stations in large quantities, but it simultaneously causes great energy consumption. In this paper, we use energy harvesting (EH) and energy cooperation technologies to maximize system throughput and save energy. Considering that the energy arrival process and channel information are not available a-priori, we propose an optimal deep reinforcement learning (DRL) algorithm to solve this average throughput maximization problem over finite horizon. We also propose a multi-agent deep reinforcement learning method to solve the dimensionality problem caused by the expansion of the state and action dimension. Finally, we compare these algorithms with two traditional algorithms, greedy algorithm and conservative algorithm. The numerical results show that the proposed algorithms are valid and effective in increasing system average throughput on long term.
- 21 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 69 (7) , 7622-7633
Power Allocation Based on Reinforcement Learning for MIMO System With Energy Harvesting
This paper focuses on the use of a reinforcement learning (RL) approach to find two online power allocation policies in a point to point EH-MIMO wireless communication system. In our study, we train the power allocation policies in order to learn the map between the environment and the agent. Particularly, in order to avoid “dimension disaster” problem which may happen in our proposed SARSA power allocation policy, we introduce a linear approximation method to get an approximate SARSA power allocation policy. The linear approximation can handle infinite number of states and trade-off between complexity and performance of power allocation is significantly improved. The simulation results show that the proposed SARSA and approximate SARSA power allocation policies have a considerable throughput increase compared with the benchmark policies, such as greedy, random and conservative policies.
- 21 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 69 (7) , 7622-7633
Power Allocation Based on Reinforcement Learning for MIMO System With Energy Harvesting
This paper focuses on the use of a reinforcement learning (RL) approach to find two online power allocation policies in a point to point EH-MIMO wireless communication system. In our study, we train the power allocation policies in order to learn the map between the environment and the agent. Particularly, in order to avoid “dimension disaster” problem which may happen in our proposed SARSA power allocation policy, we introduce a linear approximation method to get an approximate SARSA power allocation policy. The linear approximation can handle infinite number of states and trade-off between complexity and performance of power allocation is significantly improved. The simulation results show that the proposed SARSA and approximate SARSA power allocation policies have a considerable throughput increase compared with the benchmark policies, such as greedy, random and conservative policies.
- 14 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 69 (6) , 6401-6414
Optimal Energy Cooperation Policy in Fusion Center-Based Sustainable Wireless Sensor Networks
In this paper, in order to maximize a long-term average system transmission rate, we propose an optimal energy cooperation policy for the sustainable wireless sensor network where each pair of nodes can harvest energy and transfer energy in the pair. We formulate this optimization problem into a Markov decision process (MDP). We define a node pairing metric—relative energy distance ratio (REDR)—to design a node pairing algorithm which can decouple the original MDP into a multiple low dimension MDP. Then, value iteration and relative value iteration algorithms are brought to find optimal energy cooperation policies over finite and infinite horizons for each pair of nodes respectively. Simulation results show that the system transmission rate of the proposed policy with REDR based pairing algorithm outperforms the non-cooperation policies as well as the policies with straightforward pairing algorithms.
- 14 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 69 (6) , 6401-6414
Optimal Energy Cooperation Policy in Fusion Center-Based Sustainable Wireless Sensor Networks
In this paper, in order to maximize a long-term average system transmission rate, we propose an optimal energy cooperation policy for the sustainable wireless sensor network where each pair of nodes can harvest energy and transfer energy in the pair. We formulate this optimization problem into a Markov decision process (MDP). We define a node pairing metric—relative energy distance ratio (REDR)—to design a node pairing algorithm which can decouple the original MDP into a multiple low dimension MDP. Then, value iteration and relative value iteration algorithms are brought to find optimal energy cooperation policies over finite and infinite horizons for each pair of nodes respectively. Simulation results show that the system transmission rate of the proposed policy with REDR based pairing algorithm outperforms the non-cooperation policies as well as the policies with straightforward pairing algorithms.