Please wait a minute...

Current Issue

    20 January 2024, Volume 40 Issue 1
    Research and development of backscatter communications technology
    Yinghui YE, Rui XU, Yujia TIAN, Guangyue LU
    2024, 40(1):  1-23.  doi:10.11959/j.issn.1000-0801.2024001
    Asbtract ( 213 )   HTML ( 92)   PDF (777KB) ( 132 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    As an important technology for the deployment of Internet of things (IoT), backscatter communication performs low-power passive communication and energy harvesting by applying the incident signals, which is expected to achieve energy self-sustainability of the IoT node.In order to deepen its understanding and promote the development of related fields, a review of existing research was conducted and the future development prospects were presented.Firstly, the basic principle of backscatter communication and its architecture evolution were elaborated.Secondly, in terms of different communication architectures, the existing research works were surveyed.On this basis, the hybrid active-passive mutualistic symbiotic backscatter communication was proposed, and preliminary research and simulation analysis were conducted.Finally, future research directions of the proposed communication architecture were explored based on the existing research.

    Research and Development
    Research on deterministic networking technology for space-ground integrated
    Yuman ZHANG, Xia ZHU, Guoxin LIANG, Jiaen ZHOU, Yafei ZHAO, Mugen PENG
    2024, 40(1):  24-34.  doi:10.11959/j.issn.1000-0801.2024010
    Asbtract ( 127 )   HTML ( 44)   PDF (817KB) ( 193 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Satellite communication is a critical technology in the future of the communication field.Low earth orbit Internet constellations is a strategic infrastructure for the 6G integrated space-air-ground-maritime networks, which is capable of expanding the current communication network to the global near-earth region.Deterministic networking technology is a key component of space-based network, compared with the traditional best-effort packet network, it has the advantages of low latency, low jitter, low packet loss rate, and high reliability.Firstly, the current research background and status of deterministic networking were summarized, and then a deterministic networking architecture for satellite communications was proposed and its key technologies were described.Finally, the outlook for future research directions was discussed.

    Deep learning-based prediction of multi-level just noticeable distortion
    Haifeng XU, Hongkui WANG, Haibing YIN, Chuqiao CHEN
    2024, 40(1):  35-47.  doi:10.11959/j.issn.1000-0801.2024015
    Asbtract ( 49 )   HTML ( 13)   PDF (953KB) ( 53 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Visual just noticeable distortion (JND) directly reflects the sensitivity of the human visual system to visual signal noise, and is widely used in image and video processing.Aiming at the multilevel prediction problem of video JND threshold, it was transformed into the prediction problem of satisfied user ratio (SUR) curve, and a feature fusion-based SUR curve prediction model was proposed.The model was mainly divided into key frame extraction module, feature extraction and fusion module, and SUR score regression module.In the key frame extraction module, according to the visual perception mechanism, the spatial-temporal domain perception complexity was proposed and used as the video key frame judgment index.In the feature extraction and fusion module, a multi-scale dense residual network was proposed based on dense residual block (RDB) to realize image feature extraction and multi-scale fusion.The experimental results show that the proposed SUR curve prediction model is overall better than the existing models in terms of JND prediction accuracy and reduces the time cost by 8.1% on average in terms of operational efficiency.Meanwhile, the model can also be used to predict other layers of JND thresholds, which can be directly applied to video multilevel perceptual coding optimization.

    Research on a complaint prediction model utilizing joint neural networks
    Xiaoliang MA, Ying LIU, Jie GAO
    2024, 40(1):  48-58.  doi:10.11959/j.issn.1000-0801.2024006
    Asbtract ( 139 )   HTML ( 60)   PDF (739KB) ( 103 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    By conducting in-depth exploration on the key factors affecting repeat complaints of telecom operators, this study aimed to improve service quality and construct a risk prediction model.Based on the operator’s customer service data, the study employed Logistic regression, BP neural network, and their combined modeling methods.The Logistic regression model identified five major influencing factors, predicting the probability of repeat complaints with an accuracy of 80.0%.The BP neural network selected 81 influencing factors, achieving a prediction accuracy of 90.6%.On this basis, a combined model was constructed with an accuracy rate of up to 92.8%.After practical application in a provincial telecom operator, the repeat complaint rate decreased by 3.2%, demonstrating a significant impact.Strong support is provided for improving the service quality of telecom operators and reducing repeat complaints, which is of great significance for the development of the telecom industry in China.

    Research on green light compensation model for emergency preemption in C-V2X environment
    Changlong ZHANG, Farong HAN, Jimin WEI, Jingang DAI, Xiaodong YANG, Shibo QU
    2024, 40(1):  59-70.  doi:10.11959/j.issn.1000-0801.2024003
    Asbtract ( 37 )   HTML ( 10)   PDF (920KB) ( 48 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    To reduce the impact of the emergency vehicle preemption strategy on vehicles in non-priority phases at intersections, an emergency preemption green light compensation model in C-V2X environment was proposed.The proposed model doesn’t affect the emergency vehicle preemption strategy.The green time of the non-priority phases was calculated according to the real-time traffic demand to minimize the adverse impact on vehicles in non-priority phases.The proposed model was verified with simulation using an emergency vehicle.The results demonstrate that the proposed method can effectively decrease the queue lengths and reduce the average delay in non-priority phases after applying the emergency vehicle preemption strategy.The proposed method can improve traffic efficiency by optimizing the signal timing after the emergency vehicle passes through an intersection.

    Multi-adversarial domain adaptation method based on feature correction
    Yong ZHANG, Haoshuang LIU, Qi ZHANG, Wenzhe LIU
    2024, 40(1):  71-82.  doi:10.11959/j.issn.1000-0801.2024014
    Asbtract ( 28 )   HTML ( 4)   PDF (704KB) ( 30 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Domain adaptation can transfer labeled source domain information to an unlabeled but related target domain by aligning the distribution of source domain and target domain.However, most existing methods only align the low-level feature distributions of the source and target domains, failing to capture fine-grained information within the samples.To address this limitation, a feature correction-based multi-adversarial domain adaptation method was proposed.An attention mechanism to highlight transferable regions was introduced in this method and a feature correction module was deployed to align the high-level feature distributions between the two domains, further reducing domain discrepancies.Additionally, to prevent individual classifiers from overfitting their own noisy pseudo-labels,dual classifier co-training was proposed and the feature aggregation property of graph neural networks was utilized to generate more accurate source domain labels.Extensive experiments on three benchmark datasets for transfer learning demonstrate the effectiveness of the proposed method.

    A new method for reducing 5G overlapping coverage of urban grid roads
    Yejiang ZHANG, Jie CHEN, Yi LIU, Xingzheng LI, Fuyang LI, Jian HU
    2024, 40(1):  83-91.  doi:10.11959/j.issn.1000-0801.2024011
    Asbtract ( 29 )   HTML ( 5)   PDF (822KB) ( 34 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    The 5G network for urban grid road scenes has entered a new stage of refined operation and maintenance.The main contradiction has also shifted from insufficient coverage to severe overlapping coverage of some road sections.5G overlapping coverage will have a significant impact on users’ basic services such as internet access and voice.The optimization of traditional road overlapping coverage has many problems, such as inconsistent standards, recurring problems, and low work efficiency.The concept of overlapping coverage contribution was proposed, and an algorithm for root cause analysis of overlapping coverage was designed based on expert experience.An IT platform for optimizing overlapping coverage problems was also developed.The practice has proven that this method can effectively reduce the 5G overlapping coverage rate of urban grid roads, help enterprises save network optimization costs, and truly achieve the goal of cost reduction and efficiency increase.

    A single flow detection enabled method for DDoS attacks in IoT based on traffic feature reconstruction and mapping
    Lixia XIE, Bingdi YUAN, Hongyu YANG, Ze HU, Xiang CHENG, Liang ZHANG
    2024, 40(1):  92-105.  doi:10.11959/j.issn.1000-0801.2024012
    Asbtract ( 46 )   HTML ( 8)   PDF (822KB) ( 102 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    To address the slow response time of existing detection modules to Internet of things (IoT) distributed denial of service (DDoS) attacks, their low feature differentiation, and poor detection performance, a single flow detection enabled method based on traffic feature reconstruction and mapping (SFDTFRM) was proposed.Firstly, SFDTFRM employed a queue to store previously arrived flow based on the first in, first out rule.Secondly, to address the issue of similarity between normal communication traffic of IoT devices and DDoS attack traffic, a multidimensional reconstruction neural network model more lightweight compared to the baseline model and a function mapping method were proposed.The modified model loss function was utilized to reconstruct the quantitative feature matrix of the queue according to the corresponding index, and transformed into a mapping feature matrix through the function mapping method, enhancing the differences between different types of traffic, including normal communication traffic of IoT devices and DDoS attack traffic.Finally, the frequency information was extracted using a text convolutional network and information entropy calculation and the machine learning classifier was employed for DDoS attack traffic detection.The experimental results on two benchmark datasets show that SFDTFRM can effectively detect different DDoS attacks, and the average metrics value of SFDTFRM is a maximum of 12.01% higher than other existing methods.

    Attention aware edge-node exchange graph neural network
    Ruiqin WANG, Yimin HUANG, Qishun JI, Chaoyi WAN, Zhifeng ZHOU
    2024, 40(1):  106-114.  doi:10.11959/j.issn.1000-0801.2024017
    Asbtract ( 34 )   HTML ( 10)   PDF (755KB) ( 43 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    An attention aware edge-node exchange graph neural network (AENN) model was proposed, which used edge-node switched convolutional graph neural network method for graph encoding in a graph structured data representation framework for semi supervised classification and regression analysis.AENN is an universal graph encoding framework for embedding graph nodes and edges into a unified latent feature space.Specifically, based on the original undirected graph, the convolution between edges and nodes was continuously switched, and during the convolution process, attention mechanisms were used to assign weights to different neighbors, thereby achieving feature propagation.Experimental studies on three datasets show that the proposed method has significant performance improvements in semi-supervised classification and regression analysis compared to existing methods.

    Edge computing smart grid resource scheduling algorithm based on reinforcement learning
    Jinghang YU, Yichen ZHAO, Hu SONG
    2024, 40(1):  115-122.  doi:10.11959/j.issn.1000-0801.2024005
    Asbtract ( 64 )   HTML ( 24)   PDF (642KB) ( 86 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    A smart grid is a power network capable of intelligent management and optimization.Network virtualization technology can effectively improve the resource utilization and reliability of smart grids and meet the differentiated needs of different users.In the case of limited resources, traditional virtual network embedding algorithms cannot dynamically adjust the allocation and mapping of virtual resources according to the resource usage and user needs of the power system.To solve this problem, edge computing and virtualization technology was combined and a virtual network resource scheduling algorithm based on reinforcement learning was introduced.The simulation results show that the proposed virtual resource scheduling algorithm is better than the other three scheduling algorithms in improving power grid reliability and resource utilization.

    Research on dual process theory based telecom augmented cognition
    Xiaoxing LIAN, Yong SONG, Jun ZHU, Shuling WANG, Xiaozhou YE, Ye OUYANG
    2024, 40(1):  123-135.  doi:10.11959/j.issn.1000-0801.2024007
    Asbtract ( 48 )   HTML ( 17)   PDF (925KB) ( 63 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Incorporating the current works in augmented large language models (LLM), a dual process theory based telecom augmented cognition architecture (TACA) was proposed.This architecture addressed challenges faced by LLM in the field of telecom, such as lack of domain-specific knowledge and limited reasoning capabilities.It aims to enhance cognitive reasoning, knowledge integration, tooling, and autonomous decision-execution capabilities for complex telco-scenarios.Technical application references for different telco-scenarios were provided, and the effectiveness and feasibility of the augmented cognition solution were preliminarily validated in addressing complex problems through experiments.The proposed TACA can serve as a future reference architecture for the application of LLMs in the telecom industry.

    Engineering and Application
    Intelligent operation and maintenance of power communication network based on data perception fusion
    Huahui LYU, Zhe MING, Kai FAN, Qingming CHEN, Hongyu SHI, Wenjing ZOU, Dingbo WANG, Shengtao GUAN, Yong WU
    2024, 40(1):  136-143.  doi:10.11959/j.issn.1000-0801.2024016
    Asbtract ( 39 )   HTML ( 5)   PDF (647KB) ( 86 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Under the common influence of multiple factors and structural complexity in the power communication network, traditional operation and maintenance methods are vulnerable to the disturbance of abnormal voltage signal and abnormal transformer signal in the perception process, resulting in the global perception of the network and seriously affecting the overall operation and maintenance effect.In order to effectively solve the problem of perception bias caused by multiple factors, the data perception fusion algorithm was used to optimize the perception of the power parameters under the power communication network, so as to realize the effect of improving the perception accuracy and optimizing the overall quality of operation and maintenance.In the optimization scheme, the situational awareness scope of power communication network security was determined firstly.Secondly, the situational awareness of voltage security under power communication network operation was optimized.Thirdly, the security situational awareness parameters of power network transformer were defined based on the data perception fusion algorithm.Finally, the data perception fusion calculation of perception information was completed.The simulation comparison test shows that the data perception fusion algorithm has the ability to improve the overall quality of operation and maintenance, reduce the perception deviation in the process of operation and maintenance, and improve the perception sensitivity and accuracy.

    Exploration and application of autonomous network based on network events
    Weihong LI, Ying YANG, Kun HUANG, Chenglong ZHU, Tantao PAN, Xianzong HE
    2024, 40(1):  144-151.  doi:10.11959/j.issn.1000-0801.2024013
    Asbtract ( 36 )   HTML ( 14)   PDF (767KB) ( 59 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    In order to achieve the goal of autonomous networks and improve the automation of network operation, an autonomous network model was explored.The model introduced algorithms such as multidimensional data automatic clustering, adaptive sliding time window mechanism, user traffic loss assessment model based on spatiotemporal sequence correlation, fault propagation graph based on graph theory and spatiotemporal clustering, and builded automation capabilities through network event management, fault self-identification, self-positioning, self-scheduling, and intelligent quality inspection.The goal is achieving L4 advanced intelligent network by 2025.

    Architecture and verification of enhanced deterministic networking oriented large-scale
    Jun XU, Aihua LIU, Guoquan KONG, Quan XIONG
    2024, 40(1):  152-161.  doi:10.11959/j.issn.1000-0801.2024008
    Asbtract ( 54 )   HTML ( 13)   PDF (724KB) ( 116 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Comparison to the traditional “best-effort” QoS of IP-based network, deterministic networking had provided guaranteed QoS capabilities catering the requirements of differentiated increasing IP-based services.In the local Ethernet network and limited domain IP network, IEEE and IETF had approved the time-sensitive networking and deterministic working groups, which had published series standards.At present, the large-scale deterministic networking research has been carried out in the industry.There has being a consensus that the deterministic networking technology needs to be enhanced, and a new enhanced deterministic networking architecture needs to be developed.A three-dimension enhanced networking architecture was proposed, and the prototype devices verification based the architecture were provided.The results of verification show that it can meet the large-scale deterministic requirements with the well compatibilites for existed IP network.

    A study and practice of end-to-end quality of service analysis scheme for 5G services based on autonomous network
    Shicheng XU
    2024, 40(1):  162-170.  doi:10.11959/j.issn.1000-0801.2024002
    Asbtract ( 64 )   HTML ( 31)   PDF (745KB) ( 58 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Conducting end-to-end analysis of 5G service quality is the focus of operators to improve 5G user perception.Technical solutions such as rule engine, AI competency center, and intelligent scheduling were adopted to build a “fifth order closed-loop autonomous process” covering quality difference identification, quality difference definition, closed-loop management, effect analysis, and model iteration related to 5G service quality analysis.The process can make up for the shortage of the traditional end-to-end analysis of service quality that highly relies on solidified expert rules.According to this process, the end-to-end analysis scheme of 5G service quality of self-intelligent network was studied and practiced, achieving efficient autonomous collaboration and ensuring the perception of 5G service users.

Copyright Information
Authorized by: China Association for Science and Technology
Sponsored by: China Institute of Communications
Posts and Telecom Press Co., Ltd.
Publisher: Beijing Xintong Media Co., Ltd.
Editor-in-Chief: Chen Shanzhi
Editorial Director: Li Caishan
Address: F2, Beiyang Chenguang Building, Shunbatiao No.1 Courtyard, Fengtai District, Beijing, China
Postal Code: 100079
Tel: 010-53879277
Mailing Code: 2-397
ISSN 1000-0801
CN 11-2103/TN
Total visitors:
Visitors of today:
Now online: