Current Issue

20 March 2020, Volume 36 Issue 3

Previous Issue    Next Issue

Topic:Industrial Internet Platform and Security

Development of industrial internet platform and its security challenges

Rongrong JIANG,Zhengqiu WENG,Tieming CHEN

2020, 36(3):  6-10.  doi:10.11959/j.issn.1000-0801.2020067

Asbtract ( 428 )   HTML ( 90)   PDF (1028KB) ( 444 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The deep integration of the internet and traditional industries promotes the rapid development of the industrial internet.Key factors such as digitization,networking,and intelligence have made the industrial internet platform a new infrastructure project,and new technologies like identification systems,edge computing,and digital twin have emerged.Industrial internet platforms also bring new security challenges (e.g.,terminal security,control security,and business security).Starting from the current situation of industrial internet,the technological development of the industrial internet platform was sorted out,the security challenges were analyzed,the new trends of the industrial internet security were elaborated,and a framework of “ubiquitous security” for industrial internet was proposed.

Wireless sensor node localization based on IPSO-MC

Yongyan LI,Jianping WU

2020, 36(3):  11-18.  doi:10.11959/j.issn.1000-0801.2020063

Asbtract ( 165 )   HTML ( 6)   PDF (760KB) ( 322 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

To solve the problem of insufficient node positioning accuracy in wireless sensor networks,an algorithm based on improved particle swarm optimization by membrane computing (IPSO-MC) was proposed.Kent mapping was used to initialize the population and domain particles were introduced to improve the global optimization of the particle swarm.The weight factor and nonlinear extreme value perturbation were used to improve the local optimization ability of the particle swarm,and the Levy flight mechanism was used to optimize the individual position.Finally,the optimal solution of the particle swarm algorithm was obtained by the evolutionary rules of the membrane computing.Simulation experiments show that compared with the chicken flock algorithm,the improved particle swarm algorithm and the membrane computing,the proposed algorithm improves 3.24%,5.12% and 8.15% in the comparison of reference node ratio indicators,and the increase in the number of nodes indicators by 2.26%,7.82% and 9.81%,and the comparison of communication radius indicators increased by 2.15%,5.5% and 7.5%,respectively.This indicates that the algorithm has a good effect in node localization.

IBEXSec:a universal security framework for industrial internet terminal access

Yuan CHEN,Tieming CHEN,Qijie SONG,Dongjie MA

2020, 36(3):  19-26.  doi:10.11959/j.issn.1000-0801.2020069

Asbtract ( 236 )   HTML ( 15)   PDF (764KB) ( 389 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

s:With the development and application of the industrial internet platform,the security risks of massive heterogeneous terminals need to be solved urgently.Aiming at the current industrial internet terminal access and data transmission security problems,a universal terminal security service framework called IBEXSec based on the identity public key cryptographic service (IBE-XKMS) was proposed to support security functions such as secure access,authentication agents,cross-domain communications and privacy protection of heterogeneous terminal devices on the industrial internet.

Improved fish swarm algorithm based on chaos and its application in abnormal detection of industrial control network

Yaping WU,Hongzhao DONG,Yingying LIN,Jing LIU

2020, 36(3):  27-33.  doi:10.11959/j.issn.1000-0801.2020068

Asbtract ( 192 )   HTML ( 12)   PDF (772KB) ( 175 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Artificial fish swarm algorithm as a new type of bionic swarm intelligence optimization algorithm has been successfully used in a variety of optimization problems and practical engineering field,but when faced with the complex optimization problems,especially the multiple extreme value of peak and multimodal function optimization problems,due to the objective function has many local minima,inevitably there are defects such as premature and slow convergence speed.The random and ergodic theory was introduced into the basic artificial fish swarm algorithm,and an improved algorithm was constructed to make artificial fish swarm search avoid possible local extremum.The effectiveness of the algorithm was validated in the simulation application in industrial control network anomaly detection.Compared with the basic artificial fish school algorithm,the chaos improved artificial fish swarm algorithm can effectively avoid the long-term search of the algorithm near the local extreme value.The algorithm has better performance in terms of global convergence and the search efficiency is more prominent.

Application of fuzzy comprehensive evaluation method in network information security assessment of electric power enterprises

Daoyuan LIU,Keda SUN,Junliang ZHOU,Haidong FAN

2020, 36(3):  34-41.  doi:10.11959/j.issn.1000-0801.2020065

Asbtract ( 166 )   HTML ( 4)   PDF (880KB) ( 204 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Nowadays,electric power enterprises have realized the operation and production of information technology,and the importance of network information security evaluation is more and more obvious.Two-level fuzzy comprehensive evaluation method was used to evaluate the security level of network information security system of power enterprises based on PRDD model,and Delphi method was used to determine the weight coefficients of various factors of network security of power enterprises in the evaluation process.Through objective analysis of the evaluation results,the network credit of power enterprises was found out.The prominent problems existing in the informa tion security system should be solved and the corresponding security reinforcement scheme should be formulated.The validation results show that the optimized network information security model is more robust,practicability and operability are significantly improved,which effectively improve the network information security level of power enterprises,and can be used as a favorable reference for the construction of network information security of other power enterprises.

Research and Development

Joint optimization algorithm for task offloading resource allocation based on edge-end collaboration

Liuqing WU,Xiaorong ZHU

2020, 36(3):  42-52.  doi:10.11959/j.issn.1000-0801.2020044

Asbtract ( 333 )   HTML ( 52)   PDF (843KB) ( 813 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In order to solve the problem of limited mobile terminal resources and improve task processing efficiency,a task offloading resource allocation algorithm based on edge-end collaboration was proposed.With the goal of maximizing the total benefit of tasks,the optimal task offloading resource allocation problem based on Lyapunov theory was formed by the constraint of service QoS guarantee and resource limitation.Since the problem is NP-hard,it was decoupled into a channel resource allocation problem solved by KKT condition and a 0-1 integer programming problem about task assignment.Compared with the traditional algorithm,the complexity of the proposed algorithm was O(mn),the efficiency was improved by about 20%,and the delay was reduced more than 15%.

One-bit maximum likelihood algorithm for sensor networks in non-ideal channels

Nana WANG,Zhaoting LIU,Yingbiao YAO

2020, 36(3):  53-60.  doi:10.11959/j.issn.1000-0801.2020041

Asbtract ( 136 )   HTML ( 8)   PDF (737KB) ( 95 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Wireless sensor networks typically consist of wireless sensor nodes that are distributed in a certain spatial range.In general,the energy storage,computing and communication capabilities of nodes are extremely limited.Direct transmission of the sampled signals of the various nodes to the fusion center will result in more energy consumption and greater network communication load.If the sampled signal value of each sensor node is compressed into a one-bit measurement value and then transmitted,the energy consumption and the communication load can be greatly reduced.The parameter estimation problem based on one-bit measurement of sensor networks in multiplicative noise environment was studied.Considering the non-ideal binary channel with interference between the node and the fusion center,a parameter estimation algorithm based on maximum likelihood was proposed,Cramér-Rao lower bound of the parameter estimation was analyzed,and the effectiveness of the algorithm was verified through a series of simulation experiments.

Overview of research on fiber nonlinear equalization algorithm based on artificial intelligence

Yajie LI,Yongli ZHAO,Shoudong LIU,Jie ZHANG

2020, 36(3):  61-70.  doi:10.11959/j.issn.1000-0801.2020054

Asbtract ( 312 )   HTML ( 19)   PDF (811KB) ( 822 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The necessity and importance of nonlinear equalization algorithm in optical transmission systems were outlined.The principle of classical nonlinear equalization algorithm was described,and the shortcomings and limitations of classical algorithms were presented.Combined with the status in recent years,four kinds of nonlinear equalization algorithms based on artificial intelligence were introduced in detail.These algorithms include artificial neural networks,support vector machine,unsupervised clustering and deep neural network.All the nonlinear equalization algorithms mentioned were compared in terms of performance,complexity,instantaneity and application flexibility.Finally,the future development trend of nonlinear equalization algorithm based on artificial intelligence was analyzed.

EFH:an online unsupervised hash learning algorithm

Zhenyu SHOU,Jiangbo QIAN,Yihong DONG,Huahui CHEN

2020, 36(3):  71-82.  doi:10.11959/j.issn.1000-0801.2020055

Asbtract ( 145 )   HTML ( 12)   PDF (999KB) ( 209 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Many unsupervised learning to hash algorithm needs to load all data to memory in the training phase,which will occupy a large memory space and cannot be applied to streaming data.An unsupervised online learning to hash algorithm called evolutionary forest hash (EFH) was proposed.In a large-scale data retrieval scenario,the improved evolution tree can be used to learn the spatial topology of the data.A path coding strategy was proposed to map leaf nodes to similarity-preserved binary code.To further improve the querying performance,ensemble learning was combined,and an online evolving forest hashing method was proposed based on the evolving trees.Finally,the feasibility of this method was proved by experiments on two widely used data sets.

Method of short text strategy mining based on sub-semantic space

Yang SUN,Li SU,Xing ZHANG,Fengsheng WANG,Haitao DU

2020, 36(3):  83-94.  doi:10.11959/j.issn.1000-0801.2020061

Asbtract ( 150 )   HTML ( 13)   PDF (749KB) ( 163 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

To solve the problem of identifying short text data accurately,a method of short text strategy mining based on sub-semantic space was proposed.Firstly,semantic space technology was used to solve the problem of “vocabularygap” and “data sparseness” in short text analysis.Then,based on clustering algorithm,the semantic space was divided into several sub-semantic spaces,and association rules were mined in the sub-semantic space,which improved the efficiency and quality of strategy generation.Finally,binary tree was used to merge strategies and generate the simplest strategy set.Experiments show that compared with the traditional classification model,the accuracy rate of the strategy set generated by the proposed scheme can achieve 85% when the false positive rate is 6.5%.In the processing of illegal short messages,using this technology to mine potential policy sets has strong coverage ability,high accuracy and strong practicability.

Comprehensive Review

Overview and prospect for the development of C-V2X internet of vehicles industry

Bo JIN,Yanming HU

2020, 36(3):  93-99.  doi:10.11959/j.issn.1000-0801.2020064

Asbtract ( 480 )   HTML ( 82)   PDF (727KB) ( 1345 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Review on heterogeneous transfer learning

Yingzhao ZHU

2020, 36(3):  100-110.  doi:10.11959/j.issn.1000-0801.2020060

Asbtract ( 1127 )   HTML ( 127)   PDF (716KB) ( 1699 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Heterogeneous transfer learning breaks through the boundary that the feature space of source domain and target domain must be the same.It realizes analysis mining and knowledge migration of heterogeneous data.It further promotes data reuse and opens up a wider range of applications for the field of machine learning.Firstly,the definition and classification of transfer learning was introduced.Then,the research status of heterogeneous transfer learning was elaborated and its application scenarios were analyzed.At last,the existing problems and the possible research direction in the future were pointed out.

Operation Technology

SRE transformation for operator core network maintenance

Yun XU,Bingbai HUANG,Zuohui LI,Jie HUANG

2020, 36(3):  111-116.  doi:10.11959/j.issn.1000-0801.2020023

Asbtract ( 379 )   HTML ( 25)   PDF (743KB) ( 295 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

With the rapid development of core network technology,network structures have become increasingly complicated.Nowadays,it is urgent to transform from the traditional CT core network to IT core network.Widely used in the IT field,SRE model provided core network maintenance personnel with an applicable transformation way.The feasibility of SRE model through the CT maintenance point of view was analyzed,emphasizing on the comparison of IT maintenance with CT maintenance in reality with principles mentioned in SRE.Moreover,cases were expounded in the thesis to demonstrate an effective transformation strategy with the help of SRE model.

Development trend and application analysis of blockchain with 5G

Dandan XU,Yunyong ZHANG,Daolin ZHANG,Di ZHANG,Xiao WANG,Yixin CAI

2020, 36(3):  117-124.  doi:10.11959/j.issn.1000-0801.2020033

Asbtract ( 641 )   HTML ( 72)   PDF (779KB) ( 845 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Through the evolution from the information internet era of large connections and large collaborations to the era of strong trust and strong security,the blockchain has triggered a multi-wave technology wave with its characteristics of openness,transparency and decentralization,becoming the new generation of information technology development trends.Starting from the dimensions of technology,people's livelihood and industry,the infrastructure and evolution trends reveal that the blockchain was the essence of the reorganization and re-innovation of the existing technology.The applications were re-divided into the currency circle and chain ring from a technical perspective.By comparing the blockchain technology with 5G technology,the innovative application scenarios of the decoupling and cross-integration were explored that may be involved in the future of the blockchain.

Evolution and key technologies of 5G-oriented IP RAN

Xiaoming HE,Ping YUE,Quan LU,Yuanyang YIN

2020, 36(3):  125-135.  doi:10.11959/j.issn.1000-0801.2020001

Asbtract ( 433 )   HTML ( 18)   PDF (1048KB) ( 527 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

IP RAN need to adapt to the changes of 5G network architecture to meet the differentiated bearing requirements of eMBB,uRLLC and mMTC services defined by 5G.The network capabilities of “large bandwidth,low latency,flexible connection” are the basic requirements of IP RAN for 5G bearer.Firstly,the characteristics of 5G services and network architecture were analyzed,and the 5G-oriented IP RAN evolution scheme was proposed.Then,the key technologies of 5G-beared IP RAN were investigated and tested to provide support and suggestions for large-scale commercial deployment of 5G.

SG-CIM model application method in data middle platform

Qiming WAN,Sining WANG,Xin HE

2020, 36(3):  136-143.  doi:10.11959/j.issn.1000-0801.2020066

Asbtract ( 754 )   HTML ( 96)   PDF (821KB) ( 1053 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The overall framework of State Grid ubiquitous power IoT and the layered architecture of data middle platform were analyzed.The positioning and application mode of SG-CIM in data middle platform,and the support of model for data analysis application were studied.The physical model design of data middle platform was put forward,on the premise of adopting the baseline version control,parallel expansion tables and joint views was created for personalized model expansion design.As to the integrated implementation of model data for data middle platform,combining database selection and adopt bulk data loading was proposed,so as to improve efficiency of data integration.As for the upgrading and updating of data middle platform model,creating a middle table to minimize the impact on the data analysis application was recommended,and a good support was achieved for the data analysis application based on data middle platform.

End-to-end network collaboration in 5G networks

Yiliang LIU,Xin LI,Kaitao BO

2020, 36(3):  144-155.  doi:10.11959/j.issn.1000-0801.2020040

Asbtract ( 416 )   HTML ( 41)   PDF (1440KB) ( 901 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The advent of 5G network era puts forward higher requirements for telecom operators’ networks.The current situation,overall coordination framework and key capabilities of wireless access network,bearer network and core network in network slice were mainly described from the perspective of 5G end-to-end network coordination key technology,the actual case scenario of end-to-end slice was introduced,helping operators to successfully transform the network,one network multi-purpose was completed,network construction cost was reduced and differentiated service capacity was improved.

Research and application of VoLTE video call quality based on machine learning

Qizhu ZHONG

2020, 36(3):  156-165.  doi:10.11959/j.issn.1000-0801.2020021

Asbtract ( 242 )   HTML ( 24)   PDF (814KB) ( 410 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

To overcome the shortcomings of current methods for evaluating VoLTE video call quality,a method for evaluating VoLTE video call quality without reference based on machine learning and network index parameters was proposed.Firstly,the network parameters of the decoding core network were collected and preprocessed; then,the key features for VoLTE video call quality assessment were selected,and a reference-free evaluation model for VoLTE video quality assessment was constructed by comparing and selecting appropriate machine learning algorithms,so as to achieve real-time VoLTE video call quality assessment independent of the test environment and the original video.By researching the preprocessing of feature index data extracted from XDR data,the standardization of feature index was solved,and the evaluation model of feature input was convenient; the key features of VoLTE video call were selected and evaluated by feature engineering,which reduced the feature dimension and the complexity of the algorithm; at the same time,advanced machine learning technology was adopted to ensure and enhance the algorithm assessment accuracy.