Jianzhe Xue
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jianzhe Xue has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Haibo Zhou
School of Electronic Science and Engineering, Nanjing University, Nanjing, China
12 shared publications - Yunting Xu
College of Computing and Data Science, Nanyang Technological University, Singapore
8 shared publications - Tianqi Zhang
School of Electronic Science and Engineering, Nanjing University, Nanjing, China
7 shared publications - Xuemin Shen
University of Waterloo
7 shared publications - Lian Zhao
Toronto Metropolitan University
4 shared publications - Yu Sun
School of Electronic Science and Engineering, Nanjing University, Nanjing, China
4 shared publications
Latest Publications
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 7231-7245
Hybrid DRL-Based Uplink BS Selection and Power Control for Mobility Management in FD-RAN
Immersive communication in sixth-generation mobile networks (6G) demands ultra-high data rates, seamless connectivity, and consistent service quality, posing stringent requirements on mobility management in dynamic environments. Fully-decoupled radio access network (FD-RAN), as a promising 6G architecture, supports decoupled uplink/downlink access and multi-base-station cooperation, enabling uplink-intensive multi-connectivity mobility management. Realizing this capability in FD-RAN entails joint optimization of uplink base station (UBS) selection and user equipment (UE) power control, which is inherently challenging due to their mixed-variable nature. In this paper, we investigate the uplink mobility management problem in FD-RAN by formulating it as a mixed-variable optimization that minimizes the mismatch between network serving capability and dynamic QoS demands. To solve this efficiently, we propose a hybrid-action-space deep reinforcement learning (HDRL) framework and further design a dimension-reduced discrete action space to improve training efficiency. Based on the HDRL framework, we develop a hybrid proximal policy optimization (HPPO) algorithm with two independent sub-actors for discrete UBS association and continuous power control, jointly trained via a shared global critic. Simulation results validate the effectiveness of the HPPO algorithm in enabling seamless and demand-aware uplink services for mobile UEs.
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 7231-7245
Hybrid DRL-Based Uplink BS Selection and Power Control for Mobility Management in FD-RAN
Immersive communication in sixth-generation mobile networks (6G) demands ultra-high data rates, seamless connectivity, and consistent service quality, posing stringent requirements on mobility management in dynamic environments. Fully-decoupled radio access network (FD-RAN), as a promising 6G architecture, supports decoupled uplink/downlink access and multi-base-station cooperation, enabling uplink-intensive multi-connectivity mobility management. Realizing this capability in FD-RAN entails joint optimization of uplink base station (UBS) selection and user equipment (UE) power control, which is inherently challenging due to their mixed-variable nature. In this paper, we investigate the uplink mobility management problem in FD-RAN by formulating it as a mixed-variable optimization that minimizes the mismatch between network serving capability and dynamic QoS demands. To solve this efficiently, we propose a hybrid-action-space deep reinforcement learning (HDRL) framework and further design a dimension-reduced discrete action space to improve training efficiency. Based on the HDRL framework, we develop a hybrid proximal policy optimization (HPPO) algorithm with two independent sub-actors for discrete UBS association and continuous power control, jointly trained via a shared global critic. Simulation results validate the effectiveness of the HPPO algorithm in enabling seamless and demand-aware uplink services for mobile UEs.
- 23 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. PP (08908044) , 1-8
Spatial-Temporal Generative AI for Traffic Flow Estimation With Sparse Data of Connected Vehicles
Traffic flow estimation (TFE) is crucial for intelligent transportation systems, which traditionally rely on extensive road sensors at significant cost. Sparse mobile crowdsensing (MCS) enables a cost-effective alternative by utilizing sparsely distributed probe vehicle data (PVD) collected from connected vehicles. However, according to the central limit theorem, the initial TFE results derived from sparse PVD by calculating the average vehicle speed for each road segment turn out to be inaccurate. To this end, this paper proposes a novel sparse MCS TFE approach and improves its accuracy with the spatial-temporal generative artificial intelligence (GAI) framework. Within this framework, the conditional encoder mines spatial-temporal correlations in the initial TFE results, and the generative decoder generates accurate TFE outputs, achieving similar results to those employing complete and sufficient PVD. Additionally, we discuss the design of the spatial-temporal neural network that serves as the backbone of the conditional encoder for effectively capturing spatial-temporal correlations. The effectiveness of the proposed TFE approach is demonstrated through evaluations based on real-world connected vehicle data. Experimental results demonstrate the feasibility of the proposed TFE approach and highlight the effectiveness of the spatial-temporal GAI framework in improving estimation accuracy.
- 23 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. PP (08908044) , 1-8
Spatial-Temporal Generative AI for Traffic Flow Estimation With Sparse Data of Connected Vehicles
Traffic flow estimation (TFE) is crucial for intelligent transportation systems, which traditionally rely on extensive road sensors at significant cost. Sparse mobile crowdsensing (MCS) enables a cost-effective alternative by utilizing sparsely distributed probe vehicle data (PVD) collected from connected vehicles. However, according to the central limit theorem, the initial TFE results derived from sparse PVD by calculating the average vehicle speed for each road segment turn out to be inaccurate. To this end, this paper proposes a novel sparse MCS TFE approach and improves its accuracy with the spatial-temporal generative artificial intelligence (GAI) framework. Within this framework, the conditional encoder mines spatial-temporal correlations in the initial TFE results, and the generative decoder generates accurate TFE outputs, achieving similar results to those employing complete and sufficient PVD. Additionally, we discuss the design of the spatial-temporal neural network that serves as the backbone of the conditional encoder for effectively capturing spatial-temporal correlations. The effectiveness of the proposed TFE approach is demonstrated through evaluations based on real-world connected vehicle data. Experimental results demonstrate the feasibility of the proposed TFE approach and highlight the effectiveness of the spatial-temporal GAI framework in improving estimation accuracy.
- 11 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (8) , 12874-12889
Spatial-Temporal Attention Model for Traffic State Estimation With Sparse Internet of Vehicles Data
The rapid growth of connected vehicles creates new opportunities to exploit internet of vehicles (IoV) data for traffic state estimation (TSE), which is a key enabler of intelligent transportation systems (ITS). In this paper, we propose a cost-effective TSE framework that leverages sparse IoV data, which significantly reducing the data collection overhead associated with large-scale IoV datasets. We further analyze the impact of data sparsification and show that the induced estimation errors can be well approximated by Gaussian noise, thereby reformulating sparse IoV-based TSE as a denoising problem. To enhance estimation accuracy, we develop a spatial-temporal attention model, termed the convolutional retentive network (CRNet), which integrates convolutional neural networks (CNNs) for spatial correlation learning with a retentive network (RetNet) for temporal dependency modeling. Extensive experiments conducted on a large-scale real-world IoV dataset validate the feasibility of TSE under sparse IoV sensing conditions. Notably, even when only 5% of the data is available, CRNet achieves a mean absolute error (MAE) below 5 km/h, demonstrating both the high accuracy of the proposed approach and its practical applicability in real-world scenarios.
- 11 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (8) , 12874-12889
Spatial-Temporal Attention Model for Traffic State Estimation With Sparse Internet of Vehicles Data
The rapid growth of connected vehicles creates new opportunities to exploit internet of vehicles (IoV) data for traffic state estimation (TSE), which is a key enabler of intelligent transportation systems (ITS). In this paper, we propose a cost-effective TSE framework that leverages sparse IoV data, which significantly reducing the data collection overhead associated with large-scale IoV datasets. We further analyze the impact of data sparsification and show that the induced estimation errors can be well approximated by Gaussian noise, thereby reformulating sparse IoV-based TSE as a denoising problem. To enhance estimation accuracy, we develop a spatial-temporal attention model, termed the convolutional retentive network (CRNet), which integrates convolutional neural networks (CNNs) for spatial correlation learning with a retentive network (RetNet) for temporal dependency modeling. Extensive experiments conducted on a large-scale real-world IoV dataset validate the feasibility of TSE under sparse IoV sensing conditions. Notably, even when only 5% of the data is available, CRNet achieves a mean absolute error (MAE) below 5 km/h, demonstrating both the high accuracy of the proposed approach and its practical applicability in real-world scenarios.
- 10 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (8) , 12439-12454
Experience-Centric Resource Management in ISAC Networks: A Digital Agent-Assisted Approach
In this paper, we propose a digital agent (DA)-assisted resource management scheme for enhanced user quality of experience (QoE) in integrated sensing and communication (ISAC) networks. Particularly, user QoE is a comprehensive metric that integrates quality of service (QoS), user behavioral dynamics, and environmental complexity. The novel DA module includes a user status prediction model, a QoS factor selection model, and a QoE fitting model, which analyzes historical user status data to construct and update user-specific QoE models. Users are clustered into different groups based on their QoE models. A Cramér-Rao bound (CRB) model is utilized to quantify the impact of allocated communication resources on sensing accuracy. A joint optimization problem of communication and computing resource management is formulated to maximize long-term user QoE while satisfying CRB and resource constraints. A two-layer data-model-driven algorithm is developed to solve the formulated problem, where the top layer utilizes an advanced deep reinforcement learning algorithm to make group-level decisions, and the bottom layer uses convex optimization techniques to make user-level decisions. Simulation results based on a real-world dataset demonstrate that the proposed DA-assisted resource management scheme outperforms benchmark schemes in terms of user QoE.
- 10 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (8) , 12439-12454
Experience-Centric Resource Management in ISAC Networks: A Digital Agent-Assisted Approach
In this paper, we propose a digital agent (DA)-assisted resource management scheme for enhanced user quality of experience (QoE) in integrated sensing and communication (ISAC) networks. Particularly, user QoE is a comprehensive metric that integrates quality of service (QoS), user behavioral dynamics, and environmental complexity. The novel DA module includes a user status prediction model, a QoS factor selection model, and a QoE fitting model, which analyzes historical user status data to construct and update user-specific QoE models. Users are clustered into different groups based on their QoE models. A Cramér-Rao bound (CRB) model is utilized to quantify the impact of allocated communication resources on sensing accuracy. A joint optimization problem of communication and computing resource management is formulated to maximize long-term user QoE while satisfying CRB and resource constraints. A two-layer data-model-driven algorithm is developed to solve the formulated problem, where the top layer utilizes an advanced deep reinforcement learning algorithm to make group-level decisions, and the bottom layer uses convex optimization techniques to make user-level decisions. Simulation results based on a real-world dataset demonstrate that the proposed DA-assisted resource management scheme outperforms benchmark schemes in terms of user QoE.
- 10 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 6927-6943
FD-RAN Empowered Multiple Base Stations Cooperative ISAC for Low-Altitude Networks
The fully-decoupled radio access network (FD-RAN) with multiple base stations (BS) networked cooperation is expected to provide high-quality communication coverage for aerial vehicles while sensing their locations accurately and efficiently. In this paper, we propose a novel multiple BSs cooperative passive integrated sensing and communication (ISAC) framework in FD-RAN for low-altitude aerial vehicles. It utilizes the Doppler shift information from uplink orthogonal frequency division multiplexing (OFDM) signals to achieve efficient localization without incurring additional sensing overhead. Specifically, the carrier frequency offset (CFO) compensation process at each BS captures Doppler shift resulting from the relative motion between the aerial vehicle and the BS. Considering the position and velocity of the aerial vehicle as unknown variables, the localization is achieved by formulating and solving a system of equations describing these Doppler shifts. Furthermore, to enable accurate trajectory tracking, we design a learning-based adaptive double-filter (LADF) algorithm, which leverages temporal correlations in both Doppler shift measurements and vehicle trajectories to improve the time-continuous localization. Extensive simulation results demonstrate the effectiveness of our proposed ISAC framework in low-altitude FD-RAN, which can enhance the coverage performance and efficiently provide accurate localization for aerial vehicles.
- 10 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 6927-6943
FD-RAN Empowered Multiple Base Stations Cooperative ISAC for Low-Altitude Networks
The fully-decoupled radio access network (FD-RAN) with multiple base stations (BS) networked cooperation is expected to provide high-quality communication coverage for aerial vehicles while sensing their locations accurately and efficiently. In this paper, we propose a novel multiple BSs cooperative passive integrated sensing and communication (ISAC) framework in FD-RAN for low-altitude aerial vehicles. It utilizes the Doppler shift information from uplink orthogonal frequency division multiplexing (OFDM) signals to achieve efficient localization without incurring additional sensing overhead. Specifically, the carrier frequency offset (CFO) compensation process at each BS captures Doppler shift resulting from the relative motion between the aerial vehicle and the BS. Considering the position and velocity of the aerial vehicle as unknown variables, the localization is achieved by formulating and solving a system of equations describing these Doppler shifts. Furthermore, to enable accurate trajectory tracking, we design a learning-based adaptive double-filter (LADF) algorithm, which leverages temporal correlations in both Doppler shift measurements and vehicle trajectories to improve the time-continuous localization. Extensive simulation results demonstrate the effectiveness of our proposed ISAC framework in low-altitude FD-RAN, which can enhance the coverage performance and efficiently provide accurate localization for aerial vehicles.
- 8 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 2355-2368
Predictive Beamforming for OTFS-Enabled URLLC in High-Mobility Vehicular Networks
Ultra reliable low latency communication (URLLC) in vehicular networks is pivotal for meeting the stringent requirements of transportation safety. However, achieving it is very challenging due to the high mobility of vehicles and the complex propagation environment. Orthogonal time frequency space (OTFS) modulation addresses these issues by modulating symbols into the delay-Doppler (DD) domain, which can leverage full time-frequency diversity by spreading each DD domain symbol across the entire time-frequency plane. In this paper, we propose a novel OTFS-enabled ultra reliable low latency vehicular network architecture for downlink transmission. To achieve low latency, we adopt frequency division duplex (FDD) mode to transmit data frames as soon as they arrive to minimize scheduling delays. Furthermore, to enhance the received signal strength at the receiver, beamforming is applied at the transmitter. Due to the channel state information (CSI) feedback delay in FDD systems, we design a deep learning algorithm, the DD-domain Convolutional Transformer (DDCT), for predictive beamforming based on historical DD-domain CSI. In DDCT, a convolutional neural network extracts spatial features from the DD domain, and a transformer captures their temporal correlations. Extensive simulation results demonstrate the effectiveness of the proposed vehicular network architecture and the superiority of the deep learning algorithm for predictive beamforming.
- 8 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 2355-2368
Predictive Beamforming for OTFS-Enabled URLLC in High-Mobility Vehicular Networks
Ultra reliable low latency communication (URLLC) in vehicular networks is pivotal for meeting the stringent requirements of transportation safety. However, achieving it is very challenging due to the high mobility of vehicles and the complex propagation environment. Orthogonal time frequency space (OTFS) modulation addresses these issues by modulating symbols into the delay-Doppler (DD) domain, which can leverage full time-frequency diversity by spreading each DD domain symbol across the entire time-frequency plane. In this paper, we propose a novel OTFS-enabled ultra reliable low latency vehicular network architecture for downlink transmission. To achieve low latency, we adopt frequency division duplex (FDD) mode to transmit data frames as soon as they arrive to minimize scheduling delays. Furthermore, to enhance the received signal strength at the receiver, beamforming is applied at the transmitter. Due to the channel state information (CSI) feedback delay in FDD systems, we design a deep learning algorithm, the DD-domain Convolutional Transformer (DDCT), for predictive beamforming based on historical DD-domain CSI. In DDCT, a convolutional neural network extracts spatial features from the DD domain, and a transformer captures their temporal correlations. Extensive simulation results demonstrate the effectiveness of the proposed vehicular network architecture and the superiority of the deep learning algorithm for predictive beamforming.
- 24 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 40 (2) , 130-137
Digital Twin Empowered Wireless Positioning: Prospects, Architecture, and Challenges
Achieving precise and reliable positioning in complex and dynamic environments is very challenging due to multipath propagation, environmental changes, and system limitations. This article explores the role of digital twin (DT) in wireless positioning and provides comprehensive study on the prospects of DT in enhancing positioning performance with respect to accuracy, coverage, latency, and reliability. Particularly, a general architecture for DT-empowered wireless positioning is proposed. The powerful simulation and prediction capabilities of DT are leveraged for fine-grained multi-path feature extraction, dynamic model update, seamless-transition, and system optimization. A case study based on fingerprinting positioning is presented to demonstrate the enhancement due to DT in feature extraction and model update. Some open research issues in DT-empowered wireless positioning are also discussed.
- 24 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 40 (2) , 130-137
Digital Twin Empowered Wireless Positioning: Prospects, Architecture, and Challenges
Achieving precise and reliable positioning in complex and dynamic environments is very challenging due to multipath propagation, environmental changes, and system limitations. This article explores the role of digital twin (DT) in wireless positioning and provides comprehensive study on the prospects of DT in enhancing positioning performance with respect to accuracy, coverage, latency, and reliability. Particularly, a general architecture for DT-empowered wireless positioning is proposed. The powerful simulation and prediction capabilities of DT are leveraged for fine-grained multi-path feature extraction, dynamic model update, seamless-transition, and system optimization. A case study based on fingerprinting positioning is presented to demonstrate the enhancement due to DT in feature extraction and model update. Some open research issues in DT-empowered wireless positioning are also discussed.
- 13 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (10) , 13144-13156
LOSEC: Local Semantic Capture Empowered Large Time Series Model for IoT-Enabled Data Centers
Deep learning methods for accurately predicting data center status, which are essential for addressing the exponential growth of energy consumption, have gained significant attention, driven by the vast amounts of data collected through the advancement of Internet of Things (IoT) technologies. However, conventional small models often face data scarcity issues in practical deployment. While large models show promise in addressing this challenge, they encounter obstacles, such as multivariate tasks, computational intensity, and ineffective information capture. Moreover, their applications in data centers remain largely unexplored. In this article, we investigate local semantic capture empowered large model for multivariate time series forecasting in IoT-enabled data centers. We first introduce time series tasks within data centers and propose the Point Lag (Plag)-Llama framework with the Lag-Llama backbone to support zero-shot forecasting and fine-tuning for multivariate point time series forecasting. To address computational intensity and enhance the capabilities of multivariate forecasting, we propose the local semantic capture (LOSEC) for adapter fine-tuning, which captures local semantic information across time and channel dimensions alternately with low-complexity. Specifically, time series are patched into tokens, and channels are clustered together, forming local semantic information that can be captured more effectively. Extensive experiments demonstrate that Plag-Llama exhibits superior zero-shot capability and that the LOSEC empowered adapter fine-tuning achieves state-of-the-art performance on real-world datasets collected from data centers, with ablation studies further validating the effectiveness of each module within the proposed models.
- 13 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (10) , 13144-13156
LOSEC: Local Semantic Capture Empowered Large Time Series Model for IoT-Enabled Data Centers
Deep learning methods for accurately predicting data center status, which are essential for addressing the exponential growth of energy consumption, have gained significant attention, driven by the vast amounts of data collected through the advancement of Internet of Things (IoT) technologies. However, conventional small models often face data scarcity issues in practical deployment. While large models show promise in addressing this challenge, they encounter obstacles, such as multivariate tasks, computational intensity, and ineffective information capture. Moreover, their applications in data centers remain largely unexplored. In this article, we investigate local semantic capture empowered large model for multivariate time series forecasting in IoT-enabled data centers. We first introduce time series tasks within data centers and propose the Point Lag (Plag)-Llama framework with the Lag-Llama backbone to support zero-shot forecasting and fine-tuning for multivariate point time series forecasting. To address computational intensity and enhance the capabilities of multivariate forecasting, we propose the local semantic capture (LOSEC) for adapter fine-tuning, which captures local semantic information across time and channel dimensions alternately with low-complexity. Specifically, time series are patched into tokens, and channels are clustered together, forming local semantic information that can be captured more effectively. Extensive experiments demonstrate that Plag-Llama exhibits superior zero-shot capability and that the LOSEC empowered adapter fine-tuning achieves state-of-the-art performance on real-world datasets collected from data centers, with ablation studies further validating the effectiveness of each module within the proposed models.
- 30 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 11 (2) , 1281-1296
Handover-Free Multi-Connectivity Mobility Management for Downlink FD-RAN: A Hierarchical DRL-Based Approach
Seamless connectivity and on-demand service provision are considered as the fundamental capabilities in next-generation mobile networks (6G). However, current configuration of single base station (BS) connection and increasingly denser BS deployment pose great challenges for mobile user equipment (UE), due to the frequent handover and limited communication serving capacity. To this end, we investigate the handover-free multi-connectivity mobility management problem in downlink over a novel 6G architecture, namely fully-decoupled radio access network (FD-RAN). Particularly, we formulate the problem as a two-layer task involving UE-BS association and link power control, whose objective is to minimize the long-term absolute difference between UE’s serving rate and rate demand. We propose a hierarchical deep reinforcement learning (HDRL)-based scheme to decompose the original problem into two subproblems for efficient resolution. Specifically, a double deep Q-network (DDQN) algorithm is employed to update the multi-connectivity BS cooperation set for each UE at the first layer of HDRL. Then at the second layer, we design a transformer-assisted soft actor-critic (TSAC) algorithm to jointly determine transmission power for all links associated with each UE. Extensive simulations validate the effectiveness of proposed scheme over benchmarks, which is capable of providing seamless connectivity and fine-grained on-demand service for mobile UEs.
- 30 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 11 (2) , 1281-1296
Handover-Free Multi-Connectivity Mobility Management for Downlink FD-RAN: A Hierarchical DRL-Based Approach
Seamless connectivity and on-demand service provision are considered as the fundamental capabilities in next-generation mobile networks (6G). However, current configuration of single base station (BS) connection and increasingly denser BS deployment pose great challenges for mobile user equipment (UE), due to the frequent handover and limited communication serving capacity. To this end, we investigate the handover-free multi-connectivity mobility management problem in downlink over a novel 6G architecture, namely fully-decoupled radio access network (FD-RAN). Particularly, we formulate the problem as a two-layer task involving UE-BS association and link power control, whose objective is to minimize the long-term absolute difference between UE’s serving rate and rate demand. We propose a hierarchical deep reinforcement learning (HDRL)-based scheme to decompose the original problem into two subproblems for efficient resolution. Specifically, a double deep Q-network (DDQN) algorithm is employed to update the multi-connectivity BS cooperation set for each UE at the first layer of HDRL. Then at the second layer, we design a transformer-assisted soft actor-critic (TSAC) algorithm to jointly determine transmission power for all links associated with each UE. Extensive simulations validate the effectiveness of proposed scheme over benchmarks, which is capable of providing seamless connectivity and fine-grained on-demand service for mobile UEs.