Current Issue

20 January 2023, Volume 39 Issue 1

Previous Issue    Next Issue

Review

A survey on AI algorithms applied in communication and computation in Internet of vehicles

Yu KANG, Yaqiong LIU, Tongyu ZHAO, Guochu SHOU

2023, 39(1):  1-19.  doi:10.11959/j.issn.1000-0801.2023019

Asbtract ( 622 )   HTML ( 104)   PDF (2390KB) ( 883 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In the 5G era, the development of communication and computing in the Internet of vehicles has been limited by the rapidly increasing amount of information.New breakthroughs in communication and computing in Internet of vehicles can be achieved by applying AI algorithms to the Internet of vehicles.Firstly, the application of AI algorithms in communication security, communication resource allocation, computation resource allocation, task offloading decision, server deployment, communication-computation integration were investigated.Secondly, the achievements and shortcomings of the present AI algorithms in different scenarios were analyzed.Finally, combined with the Internet of vehicle development trend, some future research directions for AI algorithms applied in the Internet of vehicles were discussed.

Research and Development

Service-based network as a platform: research on a new information communication network architecture

Xiaoyun WANG, Xiaodong DUAN, Tao SUN

2023, 39(1):  20-29.  doi:10.11959/j.issn.1000-0801.2023008

Asbtract ( 165 )   HTML ( 33)   PDF (3003KB) ( 361 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The deployment of 5G enables the network to expand from serving individuals to the industry.The evolution of mobile communication system was analyzed, and a new architecture development direction-service-based network as a platform was proposed.Facing the fundamental challenge of diversified requirements of industrial scenarios, the new architecture employed “platform” to address the generalization and scalability obstacles, and employed “service” to address heterogeneous characteristics of the network.The network service level assurance could also be guaranteed.The definition, overall architecture and mathematical model of “service-based network as a platform” were given.Based on the innovative practice of 5G service-based architecture (SBA) design, the principles of service design were proposed, and then the hierarchical design ideas were given.

Exploration and prospect of the key technologies of the new generation mobile communication of intelligent railway

Yulong LU, Haiyan SHEN, Junyao ZHANG, Xinglei YANG, Yalong XIE, Lingling YANG

2023, 39(1):  30-41.  doi:10.11959/j.issn.1000-0801.2023002

Asbtract ( 308 )   HTML ( 25)   PDF (2206KB) ( 459 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The progress of mobile communication technology drives industrial changes in all walks of life.The carrying capacity of the existing railway mobile communication system is increasingly difficult to meet the rapid growth of modern railway networks even after decades of development.Based on the requirements of intelligent railway applications for mobile communication bandwidth, delay, coverage and other challenges faced by the new generation of mobile communication, the critical technologies of new-generation mobile communication were focused on, such as the new generation of communication spectrum technology, channel coding technology, and multi-functional integrated radio frequency technology.Additionally, an “air-space-vehicle-ground integration” network aiming at seamless collaborative interaction of information among “vehicle-ground, vehicle-vehicle, and vehicle-person” was constructed.Furthermore, the application of communication-navigation integration, and communication-computing- storage integration were studied and prospected in intelligent railways.It will play a vital role in improving the service capability and efficiency of railway mobile communication and enable the development of China’s railway intelligence.

Spectrum sensing algorithm based on stochastic resonance and non-central F-distribution

Yuanmeng FAN, Shunlan LIU

2023, 39(1):  42-50.  doi:10.11959/j.issn.1000-0801.2023003

Asbtract ( 84 )   HTML ( 15)   PDF (1040KB) ( 110 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

To solve the problem that the detection probability of the spectrum sensing algorithm is low and the number of samples required for detection is large at low signal-to-noise ratio (SNR), a spectrum sensing algorithm based on stochastic resonance and non-central F-distribution (SRNF) was proposed.By introducing direct-current stochastic resonance noise, the system model of SRNF was established, and the expression of test statistic, false alarm probability and detection probability, and the expression of decision threshold obeying non-central F-distribution were deduced, and the optimal stochastic resonance noise parameter was solved by numerical method.The simulation results show that the detection performance of the proposed SRNF algorithm is better than that of energy detection (ED) algorithm and blind spectrum sensing based on F-distribution (BSF) algorithm at a low SNR.When the false alarm probability is 5%, the SNR is -12 dB, and the number of samples is 200, the detection probability of the proposed algorithm is 95%, which is 34% and 67% higher than BSF algorithm and ED algorithm, respectively.When the SNR is -12 dB, and the detection probability reaches 95%, the number of samples required by the proposed algorithm is 210, which saves 340 samples compared to the BSF algorithm.Furthermore, the proposed algorithm is less affected by noise uncertainty than ED algorithm.

Low-power transmission method for uplink millimeter-wave massive MIMO-NOMA system based on GSIC

Hui WANG, Qixin TAI, Liu LIU, Hong WANG, Rongfang SONG

2023, 39(1):  51-59.  doi:10.11959/j.issn.1000-0801.2023010

Asbtract ( 139 )   HTML ( 13)   PDF (1637KB) ( 377 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The combination of non-orthogonal multiple access (NOMA) and millimeter-wave (mmWave) massive multiple-input multiple-output (MIMO) can meet the requirements for huge throughput and massive connectivity in future wireless communication network.The total system power minimization for uplink mmWave massive MIMO-NOMA was studied, and a novel framework for a hybrid beamforming mmWave massive MIMO-NOMA uplink transmission system was proposed based on group-level successive interference cancellation (GSIC).Specifically, users were grouped according to channel gain, intergroup users being served by NOMA and intra group users being served by space division multiple access.By designing analog beamforming matrices for different groups and performing joint optimization for digital beamforming and power control, a parallel iterative algorithm was proposed to solve the optimization problem.Simulation results show that the proposed method outperforms the conventional mmWave massive MIMO-NOMA based on clustering and user-level SIC in terms of total power consumption.

Digital twin-assisted multi-mode communication resource management methods for smart buildings

Cheng SHI, Pengju LIU, Zhigang DU, Sunxuan ZHANG, Zhenyu ZHOU, Huifeng BAI, Guoqing HE, Wenwen SUN, Yue MA

2023, 39(1):  60-71.  doi:10.11959/j.issn.1000-0801.2023017

Asbtract ( 152 )   HTML ( 13)   PDF (1596KB) ( 435 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The multi-mode communication network provides communication support for the collection, transmission, and processing of energy regulation data and the training of energy regulation models for smart buildings.Digital twin can provide state estimation of computing resources and channel characteristics, assist in the multi-mode communication resource optimization management, and improve the training precision of energy regulation models.However, the digital twin-assisted multi-mode communication resource management of smart buildings still face challenges such as large training error of energy regulation model, coupling of multi-timescale resource allocation, and contradictions between training precision improvement of energy regulation model and energy consumption optimization.Aiming at the above challenges, a multi-timescale communication resource management optimization algorithm based on digital twin and empirical matching learning was proposed.The weighted sum of global model loss function and energy consumption was minimized by jointly optimizing the large-timescale gateway selection and small-timescale channel allocation and power control.Simulation results show that the proposed algorithm can improve the performance of weighted sum of global model loss function and energy consumption, ensure the precise energy regulation requirement and promote the low-carbon operation of smart buildings.

Synthetic spoofing speech detection method based on center-symmetric local binary pattern

Jia XU, Zhihua JIAN, Honghui JIN, Chao WU, Lin YOU, Yingxiao WU

2023, 39(1):  72-78.  doi:10.11959/j.issn.1000-0801.2023005

Asbtract ( 114 )   HTML ( 21)   PDF (1247KB) ( 201 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In view of the fact that the local binary pattern (LBP) based speech spoofing detection method has low detection accuracy when detecting synthetic speech, a spoofing speech detection method based on center-symmetric local binary pattern (CSLBP) was proposed.In this method, the spectrogram of the speech signal was obtained through short-time Fourier transform (STFT), and then the texture feature was extracted from the spectrogram using the CSLBP.The random forest classifier was trained by the extracted texture feature to realize the discrimination of genuine and spoofing speech.The CSLBP-based method comprehensively considered the value and position relationship of pixels in the spectrogram so as to contain more texture information, and reduced the feature dimension to 16 beneficial to decrease the amount of computation.Experimental results on the ASVspoof 2019 dataset show that, compared with the LBP-based spoofing detection method, the proposed method reduced the tandem detection cost function (t-DCF) of synthetic spoofing speech by 16.98% and increased the detection speed by 89.73%.

A Fisco-Bcos platform based accurate performance analysis model of blockchain system

Mingrui XU, Yucai YAO, Xiaorong ZHU

2023, 39(1):  79-91.  doi:10.11959/j.issn.1000-0801.2023013

Asbtract ( 152 )   HTML ( 11)   PDF (1950KB) ( 253 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In order to solve the problems such as difficult to estimate the performance of blockchain system and determine the requirement of hardware facilities, an accurate model of blockchain TPS based on model and data was established under different network structures.Considering the network architecture, the consensus algorithm, the communication of nodes and other elements, the precise model of TPS was established based on the blockchain transaction model of Fisco-Bcos platform and a large amount of actual data fitting.Through the TPS test of the actual blockchain system, the results show that the prediction TPS model established can maintain high prediction accuracy under different network architecture.

A method for locating fault sections of power optical communication network intelligent operation and maintenance equipment off-grid based on Dijkstra algorithm

Hailong ZHANG, Bo LI, Najuan JIA

2023, 39(1):  92-99.  doi:10.11959/j.issn.1000-0801.2023012

Asbtract ( 113 )   HTML ( 10)   PDF (1632KB) ( 160 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In order to determine the mapping relationship between the off grid fault section and the fault current distribution, and find the shortest path between the off grid fault section and the fault current distribution, an off grid fault section location method based on Dijkstra algorithm was designed for the intelligent O＆amp;M equipment of the electro-optical communication network.The LightGBM algorithm in the data-driven method was selected to determine the mapping relationship between the off grid fault section and the fault current distribution through a large number of samples.Based on Dijkstra algorithm, the shortest path of mapping relationship was found, and the off network fault section was searched.The location platform for off grid fault section of intelligent operation and maintenance equipment of power optical communication network was designed to realize the location and alarm of off grid fault point, namely, signal loss of intelligent operation and maintenance equipment.The comparison experiment shows that the location result of this method was the closest to the actual location and the most accurate in the off network fault section location caused by the interruption of optical cable in the SDH ring network circuit area, the off network fault section location caused by the fault of optical cable in the multi way bus section, and the off network fault section location scenario caused by the fault of optical cable in the multi way bus section in the ring power area.It effectively improved the accuracy of fault location and has good applicability.

Research on the application of site value evaluation model

Chuanbing GONG, Mingshuai YANG, Song WU, Haiping GE, Shouguo ZHANG, Lei LIU, Yunshan QI, Hui XU

2023, 39(1):  100-107.  doi:10.11959/j.issn.1000-0801.2023001

Asbtract ( 121 )   HTML ( 17)   PDF (790KB) ( 308 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The value evaluation and benefit analysis of newly built sites have always been a problem that plagues operators’ network construction.Compared with the traditional evaluation methods based on coverage and complaints, a brand-new site value evaluation model was constructed from the dimensions of cost, revenue, adjacent base station load, and regional traffic development potential.The composition and calculation method of the specific index of the evaluation model were given, and the value score of the site was obtained by combining the weights of each index.Finally, suggestions were given for the applicable scenarios of the model, and practical application methods were illustrated with examples.

Research on POI quality prediction based on KPCA-GA-BP neural network

Lu LIU, Dan YANG, Ruijie CHEN, Jia LI, Xi ZHOU

2023, 39(1):  108-116.  doi:10.11959/j.issn.1000-0801.2023004

Asbtract ( 120 )   HTML ( 14)   PDF (1259KB) ( 104 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

At present, in network optimization, network quality evaluation and prediction are generally based on communities, and a flexible evaluation system for POI network quality was proposed following the research idea of “research on dimensionality increase and implementation of dimensionality reduction”.However, it involves many network KPI, resulting in a relatively complex evaluation system for POI network comprehensive quality and low prediction accuracy.In order to improve the prediction accuracy of POI network quality, KPCA was used to compress the correlation of input variables of BP neural network, the structure of BP neural network was simplified, and then the connection weights and threshold parameters of BP neural network were optimized through GA.Compared with the prediction results of traditional BP neural network, the prediction accuracy is improved by 10.9%, and the mean square error performance is significantly reduced, it can play a better supporting role in the prediction of POI network quality.

Low-hit frequency-hopping communication systems for power Internet of things random access

Shu DU, Mei MA, Bo ZHAO, Qi ZENG, Xing LIU

2023, 39(1):  117-125.  doi:10.11959/j.issn.1000-0801.2023018

Asbtract ( 131 )   HTML ( 9)   PDF (1793KB) ( 124 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The communication network is an essential component of the data acquisition and information transmission in power Internet of things (IoT).To meet the development requirements of multiple power service in the future, the wireless communication technique with flexible-access and high scalability is one of the development directions for power IoT.Due to the features of large-scale access, random access time, high security and reliability for information transmission of power IoT, a frequency-hopping (FH) technique with low-hit rate for random access was proposed.The construction algorithm of such FH pattern was based upon the combination and shift operation of conventional FH sequences.By the theoretical arithmetic and numerical simulation, the properties of the proposed FH pattern and the error-rate of the FH-based power IoT were evaluated.The analysis reveals that the new class of FH sequences and the system can meet the requirements of large-scale access and highly reliable communication for the power IoT, which has good application prospects.

Engineering and Application

Status quo, problem and promotion suggestions of 5G application in industrial field

Mengzhe ZHANG, Yijun XIA

2023, 39(1):  126-135.  doi:10.11959/j.issn.1000-0801.2023009

Asbtract ( 269 )   HTML ( 35)   PDF (1192KB) ( 307 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The great value of 5G is to support high-quality development of the real economy.Based on the status quo and bottleneck problem of 5G application in the industrial field, the “classified and targeted” development path was built.According to characteristics of typical 5G application scenarios in the industrial field, they were divided into 3 types—leading, exploring and lagging, and corresponding promotion suggestions were proposed.

Telecom-operators cryptography application system with quantum key distribution

Jun LUO, Chi LIU, Binglei WANG

2023, 39(1):  136-145.  doi:10.11959/j.issn.1000-0801.2023015

Asbtract ( 166 )   HTML ( 19)   PDF (1309KB) ( 320 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The communication network based on quantum key distribution (QKD) has the ability to realize “perfect secrecy”.At present, it cannot meet the needs of large-scale applications and needs to combine classical cryptography in practical applications.Firstly, the functional architecture model of the telecom-operators cryptography application system integrating quantum key distribution was proposed, and then the hierarchy, the core network elements, the functional modules, and the interface relationships of the model were described.Furthermore, the framework of the application system was given, and the main components of the framework were introduced.Finally, the typical application scenarios and workflow were illustrated.

Research on deployment of pooled vBRAS in cloud IP metropolitan area network

Xia GONG, Huanan CHEN, Yongqing ZHU, Shizhang YUAN, Bing YANG

2023, 39(1):  146-152.  doi:10.11959/j.issn.1000-0801.2023016

Asbtract ( 147 )   HTML ( 26)   PDF (1109KB) ( 246 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Cloud-network integration was the main development direction of IP carrier networks.As the closest network to users, IP MAN has rich service features and it is also an important test field for network cloudification.Facing the carrier requirements of multiple access and the changes of traffic direction, IP MAN was transformed from the traditional north-south tree architecture to the Spine-Leaf architecture to meet the service requirements, such as fixed-mobile convergence and multi-cloud access scenarios.Based on the evolution of the cloud IP MAN, the deployment scheme of pooled vBRAS and key technologies were introduced, and technical reference for the large-scale commercial deployment and technology evolution of vBRAS were provided.

Discussion on the evolution of architecture of the core network of cellular Internet of things

Hongyuan MA, Wei ZHOU, Yan FU, Yongping SHAO, Dan LI

2023, 39(1):  153-161.  doi:10.11959/j.issn.1000-0801.2023007

Asbtract ( 148 )   HTML ( 29)   PDF (2047KB) ( 295 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

At present, there are two Internet of things networks facing 2G, 4G, NB-IoT and facing toB core networks.In order to simplify the network, enhance the capability, enhance the benefit, and facilitate the operation and maintenance, it is necessary to define the target architecture of 5G-oriented Internet of things core network.Based on the existing network problems and combined with the driving force of network evolution, the network evolution target structure, evolution strategy and service solution were analyzed and discussed.It provides a reference for operators to plan and construct the Internet of things.