Current Issue

20 October 2020, Volume 36 Issue 10

Previous Issue    Next Issue

Topic:Intelligent Communication Technology

Perspectives on coordinated satellite-terrestrial intelligent maritime communication network

Wei FENG,Rui TANG,Ning GE

2020, 36(10):  1-11.  doi:10.11959/j.issn.1000-0801.2020281

Asbtract ( 494 )   HTML ( 63)   PDF (975KB) ( 744 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

With the implementation of national marine strategy,economic activities such as maritime transport,marine resource exploitation become increasingly important,and the demand for maritime communications keeps growing.Although the terrestrial cellular network had entered the 5G era,existing maritime communications still mainly rely on marine satellites and shore-based base stations,which are far from meeting the demand in terms of communication rate,delay and reliability.The future 6G networks are expected to offer satellite-air-ground-sea full coverage.However,due to complex maritime environments and heterogeneous marine services,the 6G maritime communication networks still face unique challenges.After summarizing the current developing status of maritime communications,related key technologies were surveied from three aspects:transmission efficiency,network coverage,and information service.For the future development of 6G intelligent maritime communication networks,the technical methods and research directions of maritime environment-aware intelligent transmission,coordinated satellite-terrestrial dynamic networking and service-driven resource allocation were prospected.

Internet intelligent routing architecture and algorithm

Fei GUI,Yang CHENG,Dan LI,Sihong HONG

2020, 36(10):  12-20.  doi:10.11959/j.issn.1000-0801.2020285

Asbtract ( 515 )   HTML ( 48)   PDF (1565KB) ( 777 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Traffic bursts are common in networks, which have a significant impact on quality of user experience. In the case of traffic bursts, huge volumes of packets can overwhelm the physical links in a short time duration(i.e., milliseconds), resulting in congestion and frequent packet loss. However, traditional routing schemes are either traffic oblivious such as OSPF, which can’t adapt to real-time traffic changes, or centralized control such as linear programming, which can’t efficiently react to traffic bursts due to slow computation. To address this problem in a practical and efficient approach, a novel intelligent routing algorithm based on machine learning (ML) was proposed. On the one hand, the proposed algorithm can leverage the promising modelling ability of machine learning to learn the implicit clue of routing decision. On the other hand, the proposed algorithm enjoys the ultralow processing latency benefited from the fast inference of ML, thus speeding up the reaction to traffic bursts. Experiments on two open-source datasets demonstrate that the proposed scheme can reduce utilization of bottleneck link by 13%～70%, compared with the baselines.

Internet source address verification method based on synchronization and dynamic filtering in address domain

Dan LI,Lancheng QIN,Jianping WU,Yingying SU,Mingwei XU,Xingang SHI,Yunan GU,Tao LIN

2020, 36(10):  21-28.  doi:10.11959/j.issn.1000-0801.2020289

Asbtract ( 417 )   HTML ( 32)   PDF (864KB) ( 309 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

At the beginning of the design of the Internet architecture,it assumed that all network members were trusted,and did not fully consider the security threat brought by the untrusted network members.For a long time,routers only forward packets based on the destination IP address of the packet,and do not carry out any verification on the source IP address of the packet.The lack of packet level authenticity on the Internet results in the header being maliciously altered.A real source address verification mechanism with routing synchronization and dynamic filtering were proposed.This mechanism constructs the filter table based on the prefix-topology mapping synchronization,the problem of inconsistent state between the filter table and the route caused by routing asymmetry were solved,false positives and false negatives was avoided,and a low-overhead and low-latency source address verification of the IP address prefix level granularity in the address domain were realized.

Design of federated routing mechanism in cross-domain scenario

Peizhuang CONG, Yuchao ZHANG, Ye TIAN, Wendong WANG, Dan LI

2020, 36(10):  29-36.  doi:10.11959/j.issn.1000-0801.2020286

Asbtract ( 459 )   HTML ( 40)   PDF (1061KB) ( 506 )   PDF（mobile） (1719KB) ( 15 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

With the development of multi-network integration,how to ensure efficient interconnections among multiple independent network domains is becoming a key problem.Traditional interdomain routing protocol fails due to the limitation of domain information privacy,where each autonomous domain doesn’t share any specific intra-domain information.A machine learning-based federated routing mechanism was proposed to overcome the existing shortcomings.Each autonomous domain shares intra-domain information implicitly via neural network models and parameters.It not only breaks data islands problems but also greatly reduces the amount of transmitted data shared between domains,then decreases convergence delay of entire network information.Based on the federated routing mechanism,border routers can formulate global optimal routing strategies according to the status of entire network.

Endogenous detection framework of malicious behavior in information network

Zhe TU,Huachun ZHOU,Kun LI,Weilin WANG

2020, 36(10):  37-45.  doi:10.11959/j.issn.1000-0801.2020282

Asbtract ( 208 )   HTML ( 24)   PDF (931KB) ( 254 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

“Endogenous security” gives the information network the ability of self-learning and self-growth,and it’s the important part of building a trusted intelligent communication network.“Endogenous security” was combined with malicious behavior detection,and an endogenous detection framework of malicious behavior with endogenous security capabilities was proposed.Passive defense was turned into active interception.In addition,the five key components in the endogenous detection framework were also modeled and analyzed,and explained the self-learning and self-growth malicious behavior detection mechanism.Finally,the deployment method of the prototype system was introduced.Preliminary test results show the proposed framework is feasible and effective.

An overview of artificial intelligence assisted channel estimation

Kun LI,Jing ZHANG,Xiao LI,Shi JIN

2020, 36(10):  46-55.  doi:10.11959/j.issn.1000-0801.2020288

Asbtract ( 620 )   HTML ( 54)   PDF (706KB) ( 1263 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

As the mainstream of the sixth generation mobile communication development,intelligent communication assisted by artificial intelligence technology is vigorously developing,and has initially demonstrated its advantages over traditional communication methods.As an important component of intelligent communication,artificial intelligence assisted channel estimation shows its superiority over traditional channel estimation algorithms in the existing research results,especially those researches based on compressive sensing technology,super resolution technology,residual learning,etc.Aiming at the channel estimation technology assisted by artificial intelligence,combined with the latest research results in the academic field,the whole picture of the channel estimation technology assisted by artificial intelligence from the four dimensions of deep convolution neural network,deep recurrent neural network,super-resolution technology and compression sensing technology were showed.Finally,the advantages and disadvantages of four kinds of channel estimation methods and their future research directions,and the broad prospect of the combination of channel estimation and deep learning were looked forward.

A survey on deep learning based joint source-channel coding

Tianjie MU,Xiaohui CHEN,Yiyun WANG,Lupeng MA,Dong LIU,Jing ZHOU,Wenyi ZHANG

2020, 36(10):  56-66.  doi:10.11959/j.issn.1000-0801.2020290

Asbtract ( 1712 )   HTML ( 232)   PDF (762KB) ( 1893 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Classical information theory shows that separate source-channel coding is asymptotically optimal over a point-to-point channel.As modern communication systems are becoming more sensitive to delays and bandwidth,it becomes difficult to adopt the assumption that such separate designs have unlimited computing power for encoding and decoding.Compared to joint source-channel coding,separate coding has proven to be sub-optimal when the bandwidth is limited.However,conventional joint source-channel coding schemes require complicated design.In contrast,data-driven deep learning brings new designing ideas into the paradigm.A summary of relevant research results was provided,which will help to clarify the way in which deep learning methods solve the joint source-channel coding problem and to provide an overviewof new research directions.Source compression schemes and end-to-end communication system models were firstly introduced,both based on deep learning,then two kinds of joint coding designs under different types of source,and potential problems of joint source-channel coding based on deep learning and possible future research directions were introduced.

Multi-stage hashing network storage structure for intelligent routing

Feng ZHU,Qun HUANG

2020, 36(10):  67-78.  doi:10.11959/j.issn.1000-0801.2020287

Asbtract ( 231 )   HTML ( 13)   PDF (909KB) ( 487 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Network data collection and storage are fundamental for intelligent routing control,providing massive flow data for model training and decision-making.However,as the key device in network storage system,switches have very limited memory size and design flexibility,which can’t satisfy the needs of intelligent routing control for comprehensive high-precision data and lightweight storage system,thus reducing the effectiveness of intelligent routing control.A multi-stage hashing network storage structure (MHNSS) was proposed for intelligent routing control,which fully utilized the limited memory resource of switch and completed network data storage with low collision rate.The number of candidate buckets of the flow key was augmented by multi-stage hash table,thus reducing collision rate and improving memory load ratio.Hash collision was resolved via coarse-grained timestamp LRU algorithm,which always stored most recently used data and cleared least recently used data to avoid subsequent collisions as far as possible.Trace-driven experiments showed that compared with widely used single hash table,MHNSS had significant performance advantage in collision rate and load ratio.

Intelligent security relay selection for full duplex wireless communications

Fang LIU,Yajuan WANG,Zhengrong LAI,Yuan’an LIU

2020, 36(10):  79-86.  doi:10.11959/j.issn.1000-0801.2020291

Asbtract ( 130 )   HTML ( 8)   PDF (762KB) ( 360 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Full-duplex can double the spectrum efficiency theoretically.Thus it can further improve the spectrum efficiency when it is used in the relay systems.Considering the residual self-interference and signal-to-noise ratio,a problem was set to maximize the security capacity by selecting the optimal relay.This optimization problem was transformed into multi-classification problem.Thus a convolutional neural network (CNN)-based intelligent relay selection scheme was proposed.In the design of the classification model,the CNN was used to extract the spatial correlation of the channel,and the dimension of the convolution kernel was related to the number of relays.The pooling layer was not used to preserve the matrix characteristics of the input features.The simulation results show that the proposed CNN-based intelligent selection classification model has high classification accuracy,and can obtain the same security performance as the traditional exhaustive search scheme,and the real-time performance is significantly improved.

Comprehensive Review

Key technologies and research progresses in cognitive SWIPT

Xiaorong XU,Minghang SUN,Linhui SHEN,Yingbiao YAO,Wei FENG

2020, 36(10):  87-101.  doi:10.11959/j.issn.1000-0801.2020138

Asbtract ( 259 )   HTML ( 31)   PDF (1348KB) ( 392 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The combination of cognitive radio (CR) and simultaneous wireless information and power transfer (SWIPT) has become one of the research hotspots in modern high-efficient cognitive radio communications.Firstly,the introduction of SWIPT and cognitive SWIPT were illustrated.Secondly,two types of receiver structures commonly used in SWIPT networks were introduced and the corresponding energy harvesting formulas were given.Thirdly,system model of cognitive SWIPT network and the research progresses of cognitive SWIPT combined with cooperative relaying and MIMO were presented respectively.Future research prospects of the key technologies in cognitive SWIPT network were investigated.Finally,some recent research achievements of the key technologies in cognitive SWIPT were given.Certain referencing values in the theoretical research and future practical applications of high energy-efficient secure cognitive SWIPT communication network were provided.

Topic: 5G Architecture and Deployment

Novel open-WDM technical architecture for 5G fronthaul network

Dong WANG,Han LI,Dechao ZHANG,Qian CAI,Jiang SUN,Yang ZHAO,Yunbo LI,Liuyan HAN

2020, 36(10):  102-108.  doi:10.11959/j.issn.1000-0801.2020243

Asbtract ( 320 )   HTML ( 20)   PDF (1446KB) ( 535 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

C-RAN may be a promising way for 5G fronthaul network associated with significant changes in 5G fronthaul architecture.Based on the analysis of existing schemes such as optical fiber direct connection,passive WDM and active WDM/OTN,open wavelength division multiplexing (open-WDM) system was proposed to satisfy the new requirements of 5G fronthaul network.In the open-WDM system,WDM technology is used to save optical fiber resource and the semi-active architecture can achieve flexible deployment.The low-cost management and control technology was further applied to perform efficiently network operation.

Intelligent planning and simulation of 5G wireless network

Jun LI

2020, 36(10):  109-119.  doi:10.11959/j.issn.1000-0801.2020182

Asbtract ( 390 )   HTML ( 41)   PDF (2151KB) ( 664 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Traditional planning methods based on human experience have been limited for 5G networks.It is urgent to introduce intelligent planning methods for 5G wireless networks based on large data analysis.Athree-step closed-loop planning scheme of 5G intelligent station location planning,parameter planning and post-evaluation was proposed.A 5G wireless network intelligent planning system was built and applied to the actual 5G wireless network planning and simulation,which effectively supports the future 5G wireless networking deployment,ensures the precise investment of resources,and lays the foundation for the construction of 5G high-quality target network.

A solution for 5G indoor coverage

Hao XU,Chen LIU

2020, 36(10):  120-125.  doi:10.11959/j.issn.1000-0801.2020166

Asbtract ( 360 )   HTML ( 28)   PDF (2223KB) ( 561 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Indoor coverage is a very important and difficult problem for 5G network deployment.By analyzing the technical characteristics of 5G massive MIMO systems and solutions to improve the performance of indoor coverage.The most important way which the outdoor macro cells were still for basic coverage was proposed,proved by theoretical analysis based on the field test results.By the meantime using digital indoor distribution system and small cells according to scenarios requirement can provide an all-round solution for indoor coverage.

5G highway tunnel deployment scheme and performance verification

Yan YANG,Tao ZHANG,Xirui GUO,Xiang PAN

2020, 36(10):  126-133.  doi:10.11959/j.issn.1000-0801.2020244

Asbtract ( 320 )   HTML ( 24)   PDF (1419KB) ( 849 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The scheme of deploying highway tunnel in 3.5 GHz typical frequency band of 5G was systematically analyzed.And the performance of the new antenna and the new leaky cable deployed for highway tunnel were comprehensively evaluated by RSRP,SINR,and rate distribution.The coverage performance,safety requirements,cost and other aspects of each scheme were proposed.It made up for the current research gap in this area,provided the first-hand materials for the 5G highway tunnel deployment,and effectively promoted the equipment evolution.

5G wireless private network scheme and its technical implementation for industrial users

Fuqiang LI,Hua ZHOU,Xiaowei SONG

2020, 36(10):  134-139.  doi:10.11959/j.issn.1000-0801.2020259

Asbtract ( 338 )   HTML ( 28)   PDF (922KB) ( 612 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

5G can provide public network mode and private network mode for public users and vertical industries.Based on the requirements of service continuity and industry users,three deployment modes of 5G wireless private network for different scenarios and needs of industry users were studied,the standardization status,industrialization ability and supporting degree of 5G wireless private network was discussed,and the scenarios and applications that 5G wireless private network can achieve at present were analyzed.In the end,the future implementation of 5G wireless private network technology with ultra-low delay demand was prospected.

Regional communication base station planning scheme based on high traffic demand of Winter Olympic Games

Suxia JIANG,Xi ZHOU,Xinghui HUANG

2020, 36(10):  140-146.  doi:10.11959/j.issn.1000-0801.2020280

Asbtract ( 119 )   HTML ( 4)   PDF (2060KB) ( 275 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Mountain area base station planning and construction,especially in high traffic demand scenarios,always has been a challenge in communication engineering.Taking the public mobile communication network planning of Beijing 2022 Winter Olympic Games and Winter Paralympics Chongli Zhangjiakou Competition area as an example,where the terrain is mostly mountainous and the scenario is characterized of high density crowds and instantly increasing demand of telephone traffic,an effective method of 2G/4G/5G bast-station planning was proposed,aiming at a high-speed,safe and widespread mobile communication service network for the Winter Olympics.A references was provided for the implementation of the 5G high telephone traffic mobile communication network planning in the mountain area .

Operation Technology

Analysis of operator’s flow middle platform in 5G⁺native system

Yingqi WEI,Weiping LIN,Ying LI,Hua TAN

2020, 36(10):  147-152.  doi:10.11959/j.issn.1000-0801.2020246

Asbtract ( 196 )   HTML ( 9)   PDF (639KB) ( 365 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Based on the 5G mobile network,the traffic middle station was proposed,and the structure of the traffic middle station was introduced in detail.Flow middle platform highly abstracts the 5G connection management and flow delicacy control functions,simplify the operator’s traditional complicated IT interfaces,combines with data intelligent analysis.It helps massive industrial endpoints to access the 5G networks,build data connections to applications.It supports radio connection functions out of the box,frees the 5G industry internet application developers from intricacy radio connection development.

Bandwidth prediction of power communication network based on DBN-Softmax

Jia LI,Li CONG,Hua JIANG,Yang HU,Meng XU

2020, 36(10):  153-158.  doi:10.11959/j.issn.1000-0801.2020155

Asbtract ( 141 )   HTML ( 5)   PDF (794KB) ( 134 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

With the change of the power communication network,the data of the bearer service of the power communication network has increased exponentially,which puts higher requirements on the processing capability of the power communication network.In order to guarantee the service quality of communication network,aiming at the current unreasonable distribution of network bandwidth,a bandwidth prediction algorithm based on deep confidence for power communication network was proposed.The deep confidence network formed by the Boltzmann machine was used to obtain the characteristics that could perfectly express the network bandwidth,and the reasonable prediction of the bandwidth of the power communication network planning stage was realized.The implementation results show that the proposed algorithm is more accurate and robust than neural network.It has the advantage of improving the carrying capacity of the power communication network and providing a powerful guarantee for the safe and stable operation of the power system.

Alarm information association scheme of cloud resource pool based on big data analysis

Qing LI

2020, 36(10):  159-171.  doi:10.11959/j.issn.1000-0801.2020141

Asbtract ( 212 )   HTML ( 22)   PDF (955KB) ( 275 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

An end-to-end intelligent operation and maintenance management system of cloud resource pool was studied,and a technical framework of intelligent obstacle detection module was proposed.The basic method of realizing end-to-end alarm association of cloud resource pool was analyzed.The realization of anomaly detection analysis method of single KPI and fault propagation chain analysis method of multi-KPI in cloud resource pool were expounded.The relationship between physical host alarm and virtual host alarm,IP SAN storage alarm and virtual object storage alarm,host device alarm and network alarm were introduced emphatically,which provide a reference for improving the end-to-end intelligent operation and maintenance capability of cloud resource pool.

Knowledge communication model of social network with user cooperation and leadership encouragement

Qiuyang GU,Chunhua JU,Gongxing WU

2020, 36(10):  172-182.  doi:10.11959/j.issn.1000-0801.2020284

Asbtract ( 180 )   HTML ( 6)   PDF (4023KB) ( 353 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In recent years,social networks have become a common medium for users to share knowledge.The knowledge communication in the social network environment was modeled and researched,with a hope to provide reference for relevant departments to effectively implement supervision and improve users’ knowledge exchange efficiency.Based on the classic SIS and SIR models,factors such as user cooperation and leadership encouragement for optimization were integrated,and the replication of dynamic equations was combined to construct and analyze two social network user knowledge communication models (SISL /SIRL).Finally,the data and model examples were given.The results show that the speed of knowledge communication is faster in social networks with leaders.In the process of social network knowledge communication,the number of vulnerable users decreases while that of the immune users increases,and the number of infected users fluctuates within a small range.Compared with the classic model and the real social network,the knowledge communication model constructed has a stronger fit.