ZZZijie Zheng

Zijie Zheng

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zijie Zheng has a total of 25 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Multi-Layer Radio Network Slicing for Heterogeneous Communication Systems

    by Jingzhi Hu, Zijie Zheng, Boya Di, Lingyang Song

    In this paper, we consider the radio access network (RAN) slicing in heterogeneous communication systems. Typically, the infrastructure provider (InP) allocates the radio resources to the mobile virtual network operators (MVNOs) as RAN slices, and then the MVNOs use the allocated resources to provide services for their users. As the RAN being heterogeneous, the users are generally with different quality of service (QoS) requirements. Besides, the MVNOs also have different intrinsic interests in terms of collecting revenue and satisfying users QoS demand and thus require different amount of resources. In this regard, it is challenging for the InP to determine the resource allocation strategy. To deal with this issue, we propose a three-layer Stackelberg game (TLSG) to jointly solve the frequency and power allocation for the InP. We derive the unique equilibrium for the special case where each MVNO uniform users and propose a bi-level differential evolution algorithm for more general cases. Simulation results reveal that both users and the InP can be better off when the RAN is sliced for different types of users, and that the MVNOs focusing more on revenue collecting result in the InP and the users obtaining less payoff.


  • HetMEC: Latency-Optimal Task Assignment and Resource Allocation for Heterogeneous Multi-Layer Mobile Edge Computing

    by Pengfei Wang, Zijie Zheng, Boya Di, Lingyang Song

    Driven by great demands on low-latency services of the edge devices (EDs), mobile edge computing (MEC) has been proposed to enable the computing capacities at the edge of the radio access network. However, conventional MEC servers suffer some disadvantages such as limited computing capacity, preventing computation-intensive tasks to be processed on time. To relief this issue, we propose the heterogeneous multi-layer MEC (HetMEC) where data that cannot be timely processed at the edge are allowed to be offloaded to the upper-layer MEC servers, and finally to the cloud center (CC) with more powerful computing capacity. We aim to minimize the system latency, i.e., the total computing and transmission time on all layers for the data generated by the EDs. We design the latency minimization algorithm by jointly coordinating the task assignment, computing and transmission resources among the EDs, multi-layer MEC servers, and the CC. Simulation results indicate that our proposed algorithm can achieve a lower latency and higher processing rate than the conventional MEC scheme.


  • Open Access

    Playing Card-Based RTS Games with Deep Reinforcement Learning

    by Tianyu Liu, Zijie Zheng, Hongchang Li, Kaigui Bian, Lingyang Song

    Game AI is of great importance as games are simulations of reality. Recent research on game AI has shown much progress in various kinds of games, such as console games, board games and MOBA games. However, the exploration in RTS games remains a challenge for their huge state space, imperfect information, sparse rewards and various strategies. Besides, the typical card-based RTS games have complex card features and are still lacking solutions. We present a deep model SEAT (selection-attention) to play card-based RTS games. The SEAT model includes two parts, a selection part for card choice and an attention part for card usage, and it learns from scratch via deep reinforcement learning. Comprehensive experiments are performed on Clash Royale, a popular mobile card-based RTS game. Empirical results show that the SEAT model agent makes it to reach a high winning rate against rule-based agents and decision-tree-based agent.


  • Open Access

    HetMEC: Latency-optimal Task Assignment and Resource Allocation for Heterogeneous Mobile Edge Computing

    by Pengfei Wang, Zijie Zheng, Boya Di, Lingyang Song

    Driven by great demands on low-latency services of the edge devices (EDs), mobile edge computing (MEC) has been proposed to enable the computing capacities at the edge of the radio access network. However, conventional MEC servers suffer disadvantages such as limited computing capacity, preventing the computation-intensive tasks to be processed in time. To relief this issue, we propose the heterogeneous MEC (HetMEC) where the data that cannot be timely processed at the edge are allowed be offloaded to the upper-layer MEC servers, and finally to the cloud center (CC) with more powerful computing capacity. We design the latency minimization algorithm by jointly coordinating the task assignment, computing and transmission resources among the EDs, multi-layer MEC servers, and the CC. Simulation results indicate that our proposed algorithm can achieve a lower latency and higher processing rate than the conventional MEC scheme.

  • Joint Task Assignment, Transmission, and Computing Resource Allocation in Multilayer Mobile Edge Computing Systems

    by Pengfei Wang, Chao Yao, Zijie Zheng, Guangyu Sun, Lingyang Song

    In our paper, we propose a multi-layer data flow processing system, i.e., EdgeFlow, to integrally utilize the computing capacity throughout the whole network, i.e., the cloud center (CC) on the top layer, the mobile edge computing (MEC) servers on the middle layer, and the edge devices (EDs) on the bottom layer. To realize the efficient data processing in EdgeFlow, we optimally assign the tasks to multiple layers, and allocate the wireless transmission resources between the MEC servers and EDs as well as the wired transmission resources between the CC and MEC servers. We prove that the system is naturally classified into two states, the non-blocking state and the blocking state, according to various data generation speed at the EDs. The system latency is minimized for the non-blocking state even though the problem is non-convex. As for the blocking state, the recovery time is minimized through solving a min-max problem. Based on the analytical results, The EdgeFlow system is implemented on the universal software radio peripheral (USRP) and the Intel Next Units of Computing (Intel NUC). A typical IoT application, photo recording and face recognition, is used for the simulation and the experiment, and indicates that the EdgeFlow can achieve a low latency and recovery time than the previous distributed frameworks, e.g. Cloudlet and the Markov Decision Process.


  • EdgeFlow: Open-Source Multi-layer Data Flow Processing in Edge Computing for 5G and Beyond

    by Chao Yao, Xiaoyang Wang, Zijie Zheng, Guangyu Sun, Lingyang Song

    Edge computing has evolved to be a promising avenue to enhance system computing capability by offloading processing tasks from the cloud to edge devices. In this article, we propose a multi-layer edge computing framework called EdgeFlow. In this framework, different nodes ranging from edge devices to cloud data centers are categorized into corresponding layers and cooperate for data processing. EdgeFlow can deal with the trade-off between the computing and communication capabilities so that the tasks can be assigned to each layer optimally. At the same time, resources are carefully allocated throughout the whole network to mitigate performance fluctuation. The proposed open-source data flow processing framework is implemented on a platform that can emulate various computing nodes in multiple layers and corresponding network connections. Evaluated on the face recognition scenario, EdgeFlow can significantly reduce task finish time and perform more tolerance to run-time variations, compared with pure cloud computing, pure edge computing, and Cloudlet. Potential applications of EdgeFlow, including network function virtualization, Internet of Things, and vehicular networks, are also discussed at the end of this article.


  • UAV Offloading: Spectrum Trading Contract Design for UAV-Assisted Cellular Networks

    by Zhiwen Hu, Zijie Zheng, Lingyang Song, Tao Wang, Xiaoming Li

    Unmanned aerial vehicle (UAV) has been recognized as a promising way to assist future wireless communications due to its high flexibility of deployment and scheduling. In this paper, we focus on temporarily deployed UAVs that provide downlink data offloading in some regions under a macro base station (MBS). Since the manager of the MBS and the operators of the UAVs could be of different interest groups, we formulate the corresponding spectrum trading problem by means of contract theory, where the manager of the MBS has to design an optimal contract to maximize its own revenue. Such contract comprises a set of bandwidth options and corresponding prices, and each UAV operator only chooses the most profitable one from all the options in the whole contract. We analytically derive the optimal pricing strategy based on fixed bandwidth assignment, and then propose a dynamic programming algorithm to calculate the optimal bandwidth assignment in polynomial time. By simulations, we compare the outcome of the MBS optimal contract with that of a socially optimal one and find that a selfish MBS manager sells less bandwidth to the UAV operators.


  • A Stackelberg Game Approach to Proactive Caching in Large-Scale Mobile Edge Networks

    by Zijie Zheng, Lingyang Song, Zhu Han, Geoffrey Ye Li, H. Vincent Poor

    Caching popular files in the storage of edge networks, namely edge caching, is a promising approach for service providers (SPs) to reduce redundant backhaul transmission to edge nodes (ENs). It is still an open problem to design an efficient incentive mechanism for edge caching in 5G networks with a large number of ENs and mobile users. In this paper, an edge network with one SP, a large number of ENs and mobile users with time-dependent requests is investigated. A convergent and scalable Stackelberg game for edge caching is designed. Specifically, the game is decomposed into two types of sub-games, a storage allocation game (SAG) and a number of user allocation games (UAGs). A Stackelberg game-based alternating direction method of multipliers (Stackelberg gamebased ADMM) is proposed to solve either the SAG or each UAG in a distributed manner. Based on both analytical and simulation results, the convergence speed, the optimum of the entire game, and the amount of information exchange are linearly (or sublinearly) related to the network size, which indicates that this framework can potentially cope with large-scale caching problems. The proposed approach also requires less backhaul resource than the existed approaches.


  • Game Theory for Big Data Processing: Multileader Multifollower Game-Based ADMM

    by Zijie Zheng, Lingyang Song, Zhu Han, Geoffrey Ye Li, H. Vincent Poor

    In this paper, tradeoff and convergence issues for incentive mechanisms are addressed by combining optimization and game theory. Specifically, a multiple-leader multiple-follower (MLMF) game-based alternating direction method of multipliers (ADMM) is developed that incentivizes the agents to perform a group of controllers' tasks in order to satisfy their corresponding objectives. Both analytical and simulation results verify that the proposed method reaches a hierarchical social optimum and converges linearly. More importantly, the convergence rate is independent of the network size, which indicates that the MLMF game-based ADMM can be used in very large networks, such as highly virtualized communication networks with two-layer hierarchies, for big data processing.


  • Sensor Deployment Recommendation for 3D Fine-Grained Air Quality Monitoring Using Semi-Supervised Learning

    by Yuzhe Yang, Zijie Zheng, Kaigui Bian, Lingyang Song, Zhu Han

    Driven by the increasingly serious air pollution problem, the monitoring of fine-grained air quality index (AQI) in urban areas has drawn considerable attention. In this paper, we design a novel algorithm to recommend the placement of sensors for energy- efficient AQI monitoring in urban three-dimensional (3D) space. Specifically, we first propose an entropy- based semi-supervised learning (ESSL) model to estimate the AQI distribution of unobserved locations, using the sparse historical spatial-temporal data and other features, including 3D coordinates, wind speed and weather conditions. Based on ESSL, we then design an entropy minimization ranking (EMR) algorithm to recommend the best sensor locations for AQI monitoring. Through the emulation on a fine-grained AQI dataset, the results demonstrate our scheme can provide energy- efficient solutions by using the least number of sensors to achieve higher accuracy than other existing approaches.