Youping Zhao’s research while affiliated with Beijing Jiaotong University and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (9)


A Self-Learning Channel Modeling Approach Based on Explainable Neural Network
  • Article

July 2023

·

4 Reads

·

5 Citations

IEEE Wireless Communications Letters

Pengfei Xue

·

Youping Zhao

To improve the accuracy and generalization of channel modeling in complex scenarios, an explainable neural network (XNN)-enabled self-learning channel modeling approach is proposed. With the help of model visualization and feature importance analysis, it is shown that the XNN channel model can reveal the intrinsic relationship between the channel characteristics and system parameters. The output and input of the channel model can be represented by mathematical expressions, making the channel model more transparent and credible. The self-learning optimization training (SLOT) algorithm enables fine-tuning and self-optimization of the channel model to ensure scenario adaptation. Specifically, when predicting the path loss, the simulation results show that the root mean square error (RMSE) is consistently less than the predefined error threshold in various test scenarios at different buildings.


Fig. 1. Transaction processing of blockchain-based spectrum trading.
Fig. 3. Architecture of the proposed multiple-blockchain framework.
Fig. 4. Simulation scenario
A Multi-blockchain Scheme for Distributed Spectrum Sharing in CBRS System
  • Article
  • Full-text available

April 2023

·

255 Reads

·

15 Citations

IEEE Transactions on Cognitive Communications and Networking

·

Yifei Liang

·

Youping Zhao

·

[...]

·

To overcome the spectrum scarcity issues, the citizens broadband radio service (CBRS) presents a centralized spectrum management solution. The efficiency of spectrum utilization could be further improved by introducing spectrum trading. Blockchain-based spectrum trading has been considered as a decentralized, flexible, and secure approach. However, current studies rarely investigate the interference to incumbent users caused by spectrum trading between CBRS devices (CBSDs), and the scalability issues in blockchain-based spectrum trading are rarely discussed. To address the problems above, this paper develops the blockchain-based spectrum trading mechanisms for CBRS. Particularly, we propose a queuing mechanism for intra-coexistence group (CxG) trading, in which spectrum trading is leveraged to reduce the aggregated interference to incumbents. A new parameter termed “network feature" is proposed to prioritize spectrum transactions in different queues, which helps to achieve the trade-off between the interference to incumbents and resource requirements in spectrum transactions. Furthermore, we propose a multi-blockchain architecture and a corresponding cross-chain mechanism to improve the speed of inter-CxG spectrum trading. Simulation results show that the aggregated interference to incumbents can be reduced by adopting the proposed method. Meanwhile, when adopting the proposed cross-chain spectrum trading mechanism, the network throughput can be improved by up to 24% compared with the traditional CBRS spectrum management framework.

Download

Reducing the System Overhead of Millimeter-Wave Beamforming With Neural Networks for 5G and Beyond

December 2021

·

488 Reads

·

6 Citations

IEEE Access

To accommodate the rapid change of radio propagation environment for mobile communication scenarios, millimeter-wave beamforming requires instantaneous channel state information (CSI) to update its operational parameters in real time, resulting in heavy system overhead. As the number of antennas increases, the system overhead associated with beam management will increase dramatically. To address this overarching problem, a neural network-aided millimeter-wave beamforming algorithm is proposed in this paper. A new parameter, referred to as “beam adjustment interval”, is proposed to evaluate the beamforming performance. It is defined as the maximum time duration in which the signal-to-interference-plus-noise ratio (SINR) of the user equipment can be maintained above the predefined threshold. Besides, a predictive method of beam adjustment to maximize the beam adjustment interval is developed, which considers the SINR not only at the current location but also future possible locations. Simulation results show that the proposed algorithm can significantly increase beam adjustment interval and reduce the total number of beam adjustments for the moving user equipment, thus reducing the system overhead 41.4% on average over 10 randomly generated test traces.



FIGURE 1. System model.
FIGURE 3. Boundary of each AP coverage generated by Voronoi (Note: each triangle represents an AP.).
FIGURE 4. Average packet loss rate vs. number of VCs by exhaustive search.
FIGURE 6. Network fitness generated by exhaustive search.
FIGURE 8. Optimal VC clustering scheme (Note: each triangle represents an AP, all triangles with same color belong to same VC, and triangle with circle is selected master AP.).
Flexible Virtual Cell Design for Ultradense Networks: A Machine Learning Approach

June 2021

·

66 Reads

·

5 Citations

IEEE Access

With the ever-growing demand for even higher throughput, ultradense networks (UDNs) are being deployed for the fifth generation (5G) mobile communications. Although massively distributed radio access points (APs) result in a considerable increase in throughput, they also cause some critical problems. When employing a wireless backhaul, the backhaul capacity becomes a limiting factor, which may result in a high packet loss rate. Furthermore, dense deployment of APs leads to more frequent handoffs for mobile user equipment, which results in heavy measurement and signaling overhead. For a better trade-off between the packet loss rate and the handoff overhead, a machine learning approach for flexible virtual cell (VC) design is proposed that leverages particle swarm optimization (PSO) to quickly find the optimal VC solution. To be responsive to the dynamic traffic demand and backhaul capacity of APs, a new parameter called “weighted distance” is employed in the modified K-means algorithm, which is nested in the PSO procedures for master AP selection and VC boundary determination. Compared with an exhaustive search, optimal VC solutions can be found efficiently through considerably fewer iterations. The proposed method is generic and applicable to disparate UDN application scenarios.


Interference-Based Consensus and Transaction Validation Mechanisms for Blockchain-Based Spectrum Management

June 2021

·

121 Reads

·

41 Citations

IEEE Access

The convergence of dynamic spectrum access (DSA) and blockchain has been regarded as the new paradigm of spectrum management. Because of the inherent properties of blockchain, such as decentralization and tamper-resistance, the deployment of blockchain in future networks has advantages to address problems exposed in traditional centralized spectrum management systems, such as high security risk and low allocation efficiency. In this article, we first compare blockchain-based spectrum management with the traditional centralized approach and then present a reference architecture for blockchain-based spectrum management. In particular, we propose an interference-based consensus mechanism, which can be employed to improve transaction efficiency and reduce system overhead while promoting spectrum sharing. The proposed consensus mechanism is based on the comparison of aggregated interference experienced by each node, such that the node that suffers the most aggregated interference will obtain the accounting right as a compensation. Furthermore, to avoid harmful interference caused by spectrum traders, an interference-based transaction validation mechanism is designed to validate the spectrum transactions stored in the blocks. Different from existing transaction validation mechanisms in which every transaction needs to be validated by all nodes, a “transaction validation area” is determined for each spectrum transaction, and only the nodes located in the validation area need to validate the transaction. The simulation results show that the system fairness and nodes’ signal-to-interference-and-noise power ratio (SINR) can be improved by adopting the proposed mechanisms while reducing the system overhead.


Adaptive Compressed Wideband Spectrum Sensing Based on Radio Environment Map Dedicated for Space Information Networks

May 2019

·

47 Reads

·

2 Citations

Lecture Notes of the Institute for Computer Sciences

Spectrum sensing is the basis of dynamic spectrum access and sharing for space information networks consisting of various satellite and terrestrial networks. The traditional spectrum sensing method, guided by the Nyquist-Shannon sampling theorem, might not be suitable for the emerging communication systems such as the fifth-generation mobile communications (5G) and space information networks utilizing spectrum from sub-6 GHz up to 100 GHz to offer ubiquitous broadband applications. In contrast, compressed spectrum sensing can not only relax the requirements on hardware and software, but also reduce the energy consumption and processing latency. As for the compressed measurement (low-speed sampling) process of the existing compressed spectrum sensing algorithms, the compression ratio is usually set to a fixed value, which limits their adaptability to the dynamically changing radio environment with different sparseness. In this paper, an adaptive compressed spectrum sensing algorithm based on radio environment map (REM) dedicated for space information networks is proposed to address this problem. Simulations show that the proposed algorithm has better adaptability to the varying environment than the existing compressed spectrum sensing algorithms.



Citations (7)


... This transparency builds stakeholder trust and ensures compliance with regulatory standards, particularly in high-stakes industrial applications [13]. Combined with self-optimization capabilities, where systems autonomously adapt to changing conditions, XAI strengthens the utility of digital twins in dynamic IIoT settings [14]. ...

Reference:

A Blockchain-Assisted Federated Learning Framework for Secure and Self-Optimizing Digital Twins in Industrial IoT
A Self-Learning Channel Modeling Approach Based on Explainable Neural Network
  • Citing Article
  • July 2023

IEEE Wireless Communications Letters

... In addition, in [16], a blockchain-based queuing mechanism for intra-coexisting group (CxG) trading is proposed. Leveraging blockchain decentralization and smart contracts for spectrum transactions reduces aggregated interference to incumbents and improves transaction processing efficiency. ...

A Multi-blockchain Scheme for Distributed Spectrum Sharing in CBRS System

IEEE Transactions on Cognitive Communications and Networking

... 1) Model Input and Output: An apparent task for applying an AI model for BM is defining the input and output of the AI based BM system. In [18], we attempt to reduce number of beam switching for a moving UE. The training data is collected by selecting the beam that satisfies the performance requirement while having the highest dwelling time for the moving UE. ...

Reducing the System Overhead of Millimeter-Wave Beamforming With Neural Networks for 5G and Beyond

IEEE Access

... This guarantees a transparent and auditable history of spectrum access, making it more difficult for attackers to alter or tamper with previous transactions. Liang et al. 116 investigate the integration of blockchain with Dynamic Spectrum Access DSA to improve spectrum management by leveraging the decentralization and tamperresistance of blockchain technology. They propose a reference architecture that includes an interference-based consensus mechanism and a targeted validation system. ...

Interference-Based Consensus and Transaction Validation Mechanisms for Blockchain-Based Spectrum Management

IEEE Access

... Authors in [64] introduced a clustering algorithm that optimally determines fog node locations in 5G networks, enhancing network performance by optimizing node placement. Authors in [65] developed a customizable virtual cell design technique, leveraging machine learning to balance packet loss rates and handoff overheads effectively. In [66], a novel method for spectrum analysis in shared spectrum environments was proposed, utilizing unsupervised learning to improve channel detection. ...

Flexible Virtual Cell Design for Ultradense Networks: A Machine Learning Approach

IEEE Access

... Indeed,in [21], REMs were used to locate relevant PUs in a geographic region of interest, characterizing their positions, directivities, powers, and modulation types. Likewise, in [22], REMs were used to sense the spectrum based on an adaptive compressed spectrum-sensing algorithm, contributing spatial information to the network capable of adapting to the radio environment. REMs are very flexible tools, as shown in [23], where they are combined with ML to determine the effective coverage area perceived by a cognitive sensor network, correctly estimating it at around 92%. ...

Adaptive Compressed Wideband Spectrum Sensing Based on Radio Environment Map Dedicated for Space Information Networks
  • Citing Chapter
  • May 2019

Lecture Notes of the Institute for Computer Sciences

... Wang et al. [107] proposed the use of the AdaBoost algorithm to use path loss and variance of path loss to classify network links in an ultra dense millimetre band network. This approach allows contextual awareness to be applied to cognitive radio by identifying channel conditions or radio scenarios. ...

Machine Learning-Aided Radio Scenario Recognition for Cognitive Radio Networks in Millimeter-Wave Bands
  • Citing Chapter
  • February 2018

Lecture Notes of the Institute for Computer Sciences