A5004399713- Software-Defined Networks and 5G
- IoT and Edge/Fog Computing
- Advanced MIMO Systems Optimization
- Cooperative Communication and Network Coding
- Blockchain Technology Applications and Security
- Advanced Optical Network Technologies
- Network Security and Intrusion Detection
- Caching and Content Delivery
- UAV Applications and Optimization
- Transportation and Mobility Innovations
- Traffic control and management
- Indoor and Outdoor Localization Technologies
- Topic Modeling
- Advanced Memory and Neural Computing
- Energy Harvesting in Wireless Networks
- Artificial Intelligence in Healthcare
- Sharing Economy and Platforms
- Smart Parking Systems Research
- Video Surveillance and Tracking Methods
- Service-Oriented Architecture and Web Services
- Telecommunications and Broadcasting Technologies
- Distributed Control Multi-Agent Systems
- Robotics and Sensor-Based Localization
- Speech and Audio Processing
- Complex Network Analysis Techniques
University of Electronic Science and Technology of China
2018-2025
Xi’an Jiaotong-Liverpool University
2025
Khalifa University of Science and Technology
2025
Quzhou University
2024
Yibin University
2022-2023
Science and Technology Department of Sichuan Province
2023
The Internet of Things (IoT) edge network has connected lots heterogeneous smart devices, thanks to unmanned aerial vehicles (UAVs) and their groundbreaking emerging applications. Limited computational capacity energy availability have been major factors hindering the performance user equipment (UE) IoT devices in networks. Besides, base station (BS) with computation server is allowed massive traffic vulnerable disasters. UAV a promising technology that provides stations (ABSs) assist...
In the fifth-generation (5G) wireless networks, Edge-Internet-of-Things (EIoT) devices are envisioned to generate huge amounts of data. Due limitation computation capacity and battery life devices, all tasks cannot be processed by these devices. However, mobile-edge computing (MEC) is a very promising solution enabling offloading nearby MEC servers improve quality service. Also, during emergency situations in areas where network failure exists, unmanned aerial vehicles (UAVs) can deployed...
The elastic reconstruction of 5G network services is expected to provide the capability slice orchestration access on demand, guarantee service experience and construct demand as well basic with lower costs. It challenging have different applications served independently a proper resource allocation mechanism according their own requirements. In this paper, we propose dynamic reservation deep reinforcement learning-based autonomous virtual slicing framework for next generation radio network....
Network slicing has been introduced in fifth-generation (5G) systems to satisfy requirements of diverse applications from various service providers operating on a common shared infrastructure. However, heterogeneous characteristics slices have not widely explored. In this paper, we investigate dynamic network strategies with mixed traffics virtualized radio access (RAN). Considering versatile users' quality (QoS) transmission delay and rate, coarse resource provisioning scheme deep...
Considering bandwidth-hungry and low latency requirement of vehicular communications applications, we propose a novel dynamic reinforcement learning-based slicing framework optimization solutions for efficient resource provisioning in virtualized network D2D-based vehicle-to-vehicle (V2V) communication. The aim is to balance utilization quality service (QoS) satisfaction levels multiple slices. designed as three-stage layered framework. In the first stage, deep virtual allocation scheme...
Wireless positioning in environments where global system (GPS) signals are unavailable—such as indoors, underground, and underwater—has become a research hotspot the Internet of Things (IoT). However, most existing traditional wireless technologies can only achieve desirable results with guaranteed line-of-sight (LoS) paths. In contrast, magnetoquasistatic (MQS) technology has demonstrated strong competitiveness these due to its robust penetration capabilities. Based on recent...
Network slicing (NS) is envisioned as an emerging paradigm for accommodating different virtual networks on a common physical infrastructure. Considering the integration of blockchain and NS, secure decentralized spectrum trading platform can be established autonomous radio access network (RAN) slicing. Moreover, realization proper incentive mechanisms fair crucial effective RAN This paper proposes novel hierarchical framework blockchain-empowered NS in RAN. Specifically, we deploy consortium...
The advent of radio access network (RAN) slicing is envisioned as a new paradigm for accommodating different virtualized networks on single infrastructure in 5G and beyond. Consequently, providers (InPs) desire to share their subleased resources effective resource management. Nonetheless, security privacy challenges the wireless deter operators from collaborating with one another trading. Lately, blockchain technology has received overwhelming attention secure trading thanks its features....
With the proliferation of smart mobile devices, there is now an ever increasing craving for higher bandwidth end user satisfaction. Increasing traffic leads to congestion backhaul networks. One promising solution this problem edge network and consequently caching. There emerging paradigm shift toward use unmanned aerial vehicles (UAVs) assist traditional cellular networks also provide connectivity in places where are no small base stations or faulty ones as a result some natural disaster...
Indoor localization utilizing received signal strength (RSS) fingerprint has garnered significant attention over the past decade because it is readily captured from MAC layer of ubiquitous hardware devices. However, accuracy RSS fingerprint-based methods notably influenced by two primary factors: 1) disparities between offline and online data distributions induced dynamic environmental changes device heterogeneity 2) inconsistencies among hetero-measure samples (different collected at same...
Fifth-generation (5G) wireless networks enable gigabit-per-second data speeds, minimal latency, and reliable Internet of Things (IoT) connectivity. Thus, network slicing (NS) has gained enormous interest due to its ability improve resource allocation. Due the exponential growth IoT data, it is difficult for infrastructure providers (InPs) determine appropriate allocate mobile virtual operators (MVNOs). In addition, MVNOs devices may use self-serving tactics that cause violate service level...
Non-line-of-sight (NLOS) identification is the key technique to improve accuracy of channel impulse response (CIR) based ultrawideband (UWB) positioning system. However, most existing NLOS approaches are tailored static environments and often encounter difficulties in dynamic settings with both temporal spatial variations, particularly when dealing limited hard samples. This paper introduces a sample meta-learning (HSML) approach address issues across different scenarios domains. HSML...
The fifth generation (5 G) mobile cellular network relies on slicing (NS) to satisfy the diverse quality of service (QoS) requirements various providers operating a standard shared infrastructure. However, synchronization radio access (RAN) and core (CN) has not been well-studied as an interdependent resource allocation problem. This work proposes novel slice-to-node factor (SNAF)-based end-to-end (E2E) slice provisioning scheme deep reinforcement learning (DRL)-based real-time algorithm for...
Radio Access Network (RAN) slicing enables resource sharing among multiple tenants and is an essential feature for next-generation mobile networks. Usually, a centralized controller aggregates available pools from to increase spectrum availability. In dynamic allocation, tenant could behave strategically by adjusting its preferences based on perceived conditions maximize utility. Slice may lie about the resources needed gain greater Such behavior lead poor utilization due excess acquired...
Vehicle dispatching in the mobility-as-a-service (MaaS) market has gradually become a situation of multi-service provider competition and coexistence. However, most existing research on vehicle with dynamic pricing for MaaS is still limited to single-service scenarios. In this paper, we propose an economic model that analyzes service demand interactions between multiple mobility providers (MSPs) passengers, respectively. We formulate problem as two-stage Stackelberg game under different...
The fifth generation (5G) wireless technology is envisioned to support different applications or services on a common substrate infrastructure. To achieve this objective, network virtualization needed partition the physical into various slices with each slice providing unique service in network. In networks mixed traffics, operators are required provide isolation since has its own defined objective. such achieving an efficient and effective resource allocation challenging issue. paper, we...
Nowadays, the unprecedented growth of mobile traffic is only rivaled by demands for a better quality service and faster data delivery. Caching content closer to end users one solution cope with these demands, but when providers share common physical infrastructure, managing limited cache resources becomes more challenging. With this increased complexity, deep reinforcement learning (DRL) presents itself as an optimal solution. In work, we propose dynamic DRL-based management framework...