JXJunfeng Xie

Junfeng Xie

*This is an algorithmically generated author record based on publicly available information.

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


Junfeng Xie has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Energy-Efficient Intelligence Sharing in Intelligence Networking-Empowered Edge Computing: A Deep Reinforcement Learning Approach

    by Junfeng Xie, Qingmin Jia, Youxing Chen

    Advanced artificial intelligence (AI) and multi-access edge computing (MEC) technologies facilitate the development of edge intelligence, enabling the intelligence learned from remote cloud to network edge. To achieve automatic decision-making, the training efficiency and accuracy of AI models are crucial for edge intelligence. However, the collected data volume of each network edge node is limited, which may cause the over-fitting of AI models. To improve the training efficiency and accuracy of AI models for edge intelligence, intelligence networking-empowered edge computing (INEEC) is a promising solution, which enables each network edge node to improve its AI models quickly and economically with the help of other network edge nodes’ sharing of their learned intelligence. Sharing intelligence among network edge nodes efficiently is essential for INEEC. Thus in this paper, we study the intelligence sharing scheme, which aims to maximize the system energy efficiency while ensuring the latency tolerance via jointly optimizing intelligence requesting strategy, transmission power control and computation resource allocation. The system energy efficiency is defined as the ratio of model performance to energy consumption. Taking into account the dynamic characteristics of edge network conditions, the intelligence sharing problem is modeled as a Markov decision process (MDP). Subsequently, a twin delayed deep deterministic policy gradient (TD3)-based algorithm is designed to automatically make the optimal decisions. Finally, by extensive simulation experiments, it is shown that: 1) compared with DDPG and DQN, the proposed algorithm has a better convergence performance; 2) jointly optimizing intelligence requesting strategy, transmission power control and computation resource allocation helps to improve intelligence sharing efficiency; 3) under different parameter settings, the proposed algorithm achieves better results than the benchmark algorithms.


  • Open Access

    Computation Offloading and Resource Allocation in Satellite-Terrestrial Integrated Networks: A Deep Reinforcement Learning Approach

    by Junfeng Xie, Qingmin Jia, Youxing Chen, Wei Wang

    Satellite networks can enhance global network coverage without geographical restrictions. By applying edge computing paradigm to satellite networks, they can provide communication and computation services for Internet of Remote Things (IoRT) mobile devices (IMDs) at any time. Thus, in 6G mobile systems, satellite networks serve as a complement to terrestrial networks. This paper places its emphasis on satellite-terrestrial integrated networks (STINs). Computation offloading and resource allocation (CORA) play a crucial role in STINs given the limited communication and computation resources of satellites. In this paper, we investigate the CORA to minimize system energy consumption while ensuring the latency tolerance via jointly optimizing the offloading decision and the allocation of radio and computation resources. Taking into account the dynamic characteristics of network conditions, the CORA problem is formulated as a Markov decision process (MDP). Subsequently, an algorithm based on twin delayed deep deterministic policy gradient (TD3) is designed to automatically determine the optimal decisions. Finally, the convergence and superiority of the proposed algorithm in terms of energy efficiency are evaluated through extensive simulation experiments.


  • Open Access

    An Energy-Efficient Intelligence Sharing Scheme in Intelligence Networking-Empowered Edge Computing

    by Junfeng Xie, Qingmin Jia, Fengliang Lu

    Advanced artificial intelligence (AI) and multi-access edge computing (MEC) technologies facilitate the development of edge intelligence, which enables the intelligence learned from remote cloud to network edge. To realize automatic decision-making, the accuracy of AI models and training efficiency are crucial for edge intelligence. However, the data volume collected by each network edge node from various sensors is limited, which may cause the over-fitting of AI models. To improve the accuracy of AI models and training efficiency for edge intelligence, intelligence networking-empowered edge computing (INEEC) is emerging as a promising solution, which enables each network edge node to improve its AI models quickly and economically with the help of other network edge nodes’ sharing of their learned intelligence. Sharing intelligence among network edge nodes efficiently is essential for INEEC. Thus in this paper, we study the intelligence sharing scheme, which aims to maximize the system energy efficiency while ensuring the latency tolerance via jointly optimizing intelligence requesting strategy, transmission power control and computation resource allocation. The system energy efficiency is defined as the ratio of model performance to energy consumption. To solve this complex optimization problem, a hybrid algorithm that integrates GA and PSO is proposed to make the optimal intelligence sharing decision. Finally, the convergence and superiority of the proposed scheme in terms of intelligence sharing efficiency are evaluated through extensive simulation experiments.


  • Open Access

    Joint Content Caching, Recommendation, and Transmission for Layered Scalable Videos Over Dynamic Cellular Networks: A Dueling Deep Q-Learning Approach

    by Junfeng Xie, Qingmin Jia, Xinhang Mu, Fengliang Lu

    Scalable Video Coding (SVC) and edge caching are two techniques that hold the potential to improve user-perceived video viewing experience. Moreover, video recommendation can further enhance the caching gain by reshaping users’ video preferences. In this paper, we investigate the video caching, recommendation and transmission for layered SVC streaming in cache-enabled cellular networks. Considering the dynamic characteristics of video popularity distribution and wireless network environment, to improve energy efficiency by minimizing system energy consumption and ensure the average user preference deviation tolerance, we begin by formulating a long-term optimization problem that focuses on video caching, recommendation and user association (UA). The problem is then transformed into a Markov decision process (MDP), which is solved by designing a dueling deep Q-learning network (DDQN)-based algorithm. Using this algorithm, we can obtain the optimal video caching, recommendation and UA solutions. Since the action space of the MDP is huge, to cope with the “curse of dimensionality”, linear approximation is integrated into the designed algorithm. Finally, the proposed algorithm’s convergence and effectiveness in reducing long-term system energy consumption are demonstrated through extensive simulations.


  • Open Access

    Deep Q-Learning Aided Energy-Efficient Caching and Transmission for Adaptive Bitrate Video Streaming Over Dynamic Cellular Networks

    by Junfeng Xie

    Adaptive bitrate video streaming (ABRVS) and edge caching are two techniques that hold the potential to improve user-perceived video viewing experience. In this paper, we investigate the content caching, transcoding and transmission for ABRVS in cache-enabled cellular networks. Considering the dynamic characteristics of video popularity distribution and wireless network environment, to improve energy efficiency and minimize system energy consumption, we begin by formulating a long-term optimization problem that focuses on both video caching and user association (UA). The problem is then transformed into a Markov decision process (MDP), which is solved by designing a deep Q-learning network (DQN)-based algorithm. Using this algorithm, we can obtain the optimal video caching and UA solutions. Since the action space of the MDP is huge, to cope with the “curse of dimensionality”, linear approximation is integrated into the designed algorithm. Finally, the proposed algorithm’s convergence and effectiveness in reducing long-term system energy consumption are demonstrated through extensive simulations.


  • Open Access

    Joint Caching and User Association Optimization for Adaptive Bitrate Video Streaming in UAV-Assisted Cellular Networks

    by Junfeng Xie, Zhaoba Wang, Youxing Chen

    Edge caching and adaptive bitrate video streaming are two promising techniques to ensure a good video viewing experience. Edge caching can bring contents closer to users to alleviate redundant content transmissions, reduce user-perceived delay and improve transmission capability. Adaptive bitrate video streaming is able to adaptively adjust video quality based on time-varying network conditions and different users’ preference. Due to the strong coupled relationship between caching and user association, in this article, we focus on the issue of joint caching and user association optimization for adaptive bitrate video streaming in UAV-assisted cellular networks. First, we formulate the optimization problem as a non-linear integer programming (NLIP) to minimize the content delivery delay. To solve this challenging NP-hard problem, a heuristic algorithm based on quantum-inspired evolutionary algorithm (QEA) is proposed to obtain the best caching and user association solutions iteratively. Finally, simulations are conducted to demonstrate that compared with three benchmark algorithms without joint optimization of caching and user association, the proposed algorithm can greatly improve users’ video viewing experience and achieve better system performance in terms of reducing the total content delivery delay.


  • Top Cited Papers

    A Survey of Blockchain Technology Applied to Smart Cities: Research Issues and Challenges

    by Junfeng Xie, Helen Tang, Tao Huang, F. Richard Yu, Renchao Xie, Jiang Liu, Yunjie Liu


  • Top Cited Papers

    A Survey of Machine Learning Techniques Applied to Software Defined Networking (SDN): Research Issues and Challenges

    by Junfeng Xie, F. Richard Yu, Tao Huang, Renchao Xie, Jiang Liu, Chenmeng Wang, Yunjie Liu

    In recent years, with the rapid development of current Internet and mobile communication technologies, the infrastructure, devices and resources in networking systems are becoming more complex and heterogeneous. In order to efficiently organize, manage, maintain and optimize networking systems, more intelligence needs to be deployed. However, due to the inherently distributed feature of traditional networks, machine learning techniques are hard to be applied and deployed to control and operate networks. Software Defined Networking (SDN) brings us new chances to provide intelligence inside the networks. The capabilities of SDN (e.g., logically centralized control, global view of the network, software-based traffic analysis, and dynamic updating of forwarding rules) make it easier to apply machine learning techniques. In this paper, we provide a comprehensive survey on the literature involving machine learning algorithms applied to SDN. First, the related works and background knowledge are introduced. Then, we present an overview of machine learning algorithms. In addition, we review how machine learning algorithms are applied in the realm of SDN, from the perspective of traffic classification, routing optimization, Quality of Service (QoS)/Quality of Experience (QoE) prediction, resource management and security. Finally, challenges and broader perspectives are discussed.