Current Issue

20 July 2016, Volume 32 Issue 7

Previous Issue    Next Issue

Viewpoint aggregation

Analysis and suggestion of future 5G directions

Shanzhi CHEN

2016, 32(7):  1-10.  doi:10.11959/j.issn.1000-0801.2016185

Asbtract ( 776 )   HTML ( 83)   PDF (1821KB) ( 1499 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Firstly,the global research progress of 5G was briefly introduced,and the requirements and challenges of 5G were analyzed.The understanding and views on 5G were shared,and 5G was pointed out as an internet of things generation,a telecom IT generation,software definition and cloud generation,a cellular structure transition generation,and serving as a link between the past and the future generation.Then,the key technologies of 5G wireless transmission and network were also analyzed,including PDMA,UUDN and virtual RAT technologies,which were proposed by the author's team.Particularly,the advantages of TDD in 5G was pointed,and the new air interface of 5G adopting TDD mode was predicted.At last,combined with China's innovative experience in TD-SCDMA and TD-LTE,suggestions on how to develop 5G in China were provided.

A function composition method of software defined networking based on topology transformation

Xiaoqiang XI,Julong LAN,Tong DUAN,Yiming JIANG

2016, 32(7):  11-20.  doi:10.11959/j.issn.1000-0801.2016175175

Asbtract ( 275 )   HTML ( 3)   PDF (1575KB) ( 371 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The existing function composition methods of software defined networking (SDN) are mostly carried out in the single node without considering the function bearing capacity of the single switch.To solve this problem,firstly a function composition method based on topology transformation was proposed to carry out function composition in multiple nodes by transforming abstract topology.Secondly,the topology transformation was modeled as the 0-1 linear programming problem and a comprehensive search algorithm was proposed to solve this problem.Finally,the function composition module and implemented the prototype system based on NetFPGA-10G and Ryu controller were devised to do the function composition.The experimental results show that the method can reduce processing delay and storage cost as well as improve the composition efficiency compared with the existing method.

PCA clustering algorithm for indoor positioning in WLAN

Mingji YANG,Kaiyi LIU,Dan SHAO

2016, 32(7):  21-26.  doi:10.11959/j.issn.1000-0801.2016186

Asbtract ( 359 )   HTML ( 6)   PDF (868KB) ( 489 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In WLAN indoor location system,aiming at the problem of time-varying characteristic of received signal strength (RSS) which reduces indoor positioning accuracy,a clustering algorithm based on principal component analysis (PCA) albino RSS was put forward.The algorithm firstly treated the RSS with PCA whitening treatment to remove the correlation and improve reliability and rationality of the cluster centers.Then,K-means clustering method was used to cluster the RSS and the clustering accuracy was improved effectively,so as to improve positioning accuracy.Experimental results show that compared with the traditional clustering algorithm without PCA,probability of positioning error within 2 meters has improved 44.8% in positioning accuracy,and the performance of positioning system has been more excellent.

A novel channel access algorithm based on clusters and MAB model in cognitive vehicular network

Fei PENG,Guoan ZHANG,Yuqi YANG

2016, 32(7):  27-33.  doi:10.11959/j.issn.1000-0801.2016184

Asbtract ( 237 )   HTML ( 2)   PDF (1194KB) ( 488 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Considering the cognitive channel access problem of vehicle nodes in cognitive vehicular networks with heavy traffic environment,a channel access algorithm called clusters-UCB which based on clusters and MAB model was proposed.The cooperation of cluster members could improve perception accuracy and enhance the learning speed.And using improved multi-user UCB algorithm,cluster heads could quickly search out the optimal channel in a distributed way,which could make the network asymptotically achieve the optimal slot throughput.Simulation results show that with respect to UCB algorithm and ε-greedy algorithm,the regret of the proposed algorithm is lower and the speed of approaching logarithmic form is faster.What's more,clusters-UCB can effectively reduce the number of collisions when clusters access the cognitive channels,ensuring the fairness of the channel access and achieving better slot throughput.

Modeling of the 2.4 GHz wireless channel path loss in substation

Qiang LI,Hongxin ZHANG,Jiaqi LUO,Yang LU,Jianqi LI,Yinghua LV

2016, 32(7):  34-39.  doi:10.11959/j.issn.1000-0801.2016195195

Asbtract ( 354 )   HTML ( 0)   PDF (892KB) ( 735 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In order to assess the influence of electromagnetic interference in the substation of the electric power communication system,frequency measurement method was adopted to obtain the data of 2.4 GHz electromagnetic wave path loss of the substation of 110 kV and 220 kV in a certain city.By using the method of minimum mean square error (MMSE) and cumulative sum (CUSUM) to estimate the parameters of path loss model such as path loss index and the standard deviation,the path loss model was set up according to measured data,respectively.The simulation results show that the gap between estimation results and the measured values is not big.In addition,a ZigBee simulation system was constructed to simulate the relationship of bit error rate (BER) varies with distance in two cases of the signal to noise ratio (SNR) at 5 dB and 10 dB respectively.A research basis for short distance wireless communication devices decorated in the substation environment was provided.

A novel chaotic interleaving algorithm for mobile wireless channels

Xianping WANG,Hui CAO

2016, 32(7):  40-44.  doi:10.11959/j.issn.1000-0801.2016156156

Asbtract ( 232 )   HTML ( 0)   PDF (774KB) ( 596 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Interleaving technique is an efficient technique to resist serious burst errors over mobile wireless fading channels.To resist 2 dimensionality burst errors effectively,a novel chaotic interleaving algorithm based on Baker map was proposed.In the proposed scheme,the binary source sequence was converted to the data matrix,and then the data matrix was dispersed randomly by using the chaotic Baker map approach,in order to realize the function of transforming 2 dimensionality long bust error into the short 1 dimensionality short bust error after de-interleaving.In additional,the proposed algorithm was combined with the convolution code based on Viterbi decoding,and was applied into the scenario of convolutional codes (2,1,3) and the scenario of (2,1,7) separately for a performance comparison.The simulation results show that the performance of the proposed algorithm outperforms better than the traditional algorithms under image transmission over mobile wireless channel.Moreover,the anti-fading capability of the proposed algorithm grows as the packet length increases,while reducing the complexity significantly.Finally,the chaotic interleaver can also enhance every transmitted packet's security with different secret keys.

Spectrum sensing algorithm based on average value of middle part of power spectral density

Zhijin ZHAO,Xi LV,Shilian ZHENG

2016, 32(7):  53-60.  doi:10.11959/j.issn.1000-0801.2016196

Asbtract ( 279 )   HTML ( 4)   PDF (1251KB) ( 593 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The difference between maximum and minimum value of the received signal power spectrum is distinct when the primary user signal is present or absent.Using this characteristic,the spectrum sensing algorithm based on the average of the middle part of power spectral density was proposed.Since the minimum of the signal power spectral density fluctuated,the minimum couldn't be accurately estimated from a frequency point.The minimum value of the power spectrum was estimated by using the average value of the middle part of the received signal power spectrum to reduce the effect of the randomness of minimum value on spectrum sensing performance.The expressions of detection threshold and detection probability were derived.Simulation results show that performance of the algorithm is better than those of the present spectrum sensing algorithms based on power spectrum density under the AWGN channel and the Rayleigh fading channel.The algorithm didn't need the primary user information and complicated eigenvalue decomposition.

LAA system dynamic sub-frame configuration strategy in unlicensed bands

Wei JIANG,Shixiao LIU,Heng HU,Chenlu ZHANG

2016, 32(7):  61-67.  doi:10.11959/j.issn.1000-0801.2016193

Asbtract ( 306 )   HTML ( 2)   PDF (1100KB) ( 525 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The use of dynamic TDD technology in heterogeneous network can effectively increase the system throughput and improve the performance of the system.Due to the limitation of signaling control and other issues,there is usually a dynamic switching between the traditional seven fixed sub-frame ratios in the licensed bands.But as a complement to the LTE system worked in the licensed bands,the unlicensed bands can achieve a more flexible and complete dynamic sub-frame configuration without considering signaling control and other issues.Two new dynamic sub-frame configuration algorithms in unlicensed bands were proposed and compared with traditional static sub-frame configuration,then the impact of dynamic sub-frame allocation algorithms on system performance was verified by LAA system level simulation platform.The results show that the proposed dynamic sub-frame configuration strategies can effectively improve the resource utilization and the overall system throughput.

Multi-group target tracking method based on adaptive predictive clustering in WSN

Shumu LIU,Jian YANG,Yuansong LI

2016, 32(7):  68-75.  doi:10.11959/j.issn.1000-0801.2016128

Asbtract ( 275 )   HTML ( 0)   PDF (1371KB) ( 333 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Aiming at the imbalance between energy using and tracking accuracy in multi-sensor target tracking,a method of trade-off network lifetime and accuracy was proposed.It was a multi-group target tracking method based on adaptive predictive clustering (APCMT),realizing the simultaneous tracking of multiple groups.Firstly,cluster was realized,which was to capture the changes of group behavior attributes,such as forming,mergering and spliting.Then,sensors were selected,which were expected to contribute to the group area sensor activation,and the sensors were used for group tracking.Scene simulation was in a square area of 1 000 m ×1 000 m with 500 randomly deployed sensors.The effectiveness of the proposed method was verified by the simulation results.Compared with Kalman,energy-effective node selection (EENS) method and the improved dynamic cluster (IDC) method,the tracking precision of proposed method was higher.And because of the number of activate sensors was less,the computational time was less,the network lifetime had been improved significantly.

Performance analysis for pseudo-random asynchronous FH-CDMA system based on average-hit method

GTao ZHEN,Qi ZENG

2016, 32(7):  76-81.  doi:10.11959/j.issn.1000-0801.2016126

Asbtract ( 316 )   HTML ( 1)   PDF (820KB) ( 565 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The pseudo-random M-ary sequence (such as RS code,polynomial code and low-hit zone FH code and so forth) is widely adopted as FH code in FH-CDMA system.However,the performance of FH-CDMA system employing FH sequence is usually evaluated by simulation,and lack of substantial theoretical analysis.A systematic method for modeling the frequency-hit according to the pre-assigned FH code was proposed; then with the proposed model,the analysis for multi-access interference(MAI)was simplified.The numerical relation between the properties of pseudo-random FH code and the error-rate performance of FH-CDMA system was established.Theoretical and simulation results show that the proposed average-hit model is an efficient method to evaluate the frequency hit and the error-rate of pseudo-randomly FH-CDMA system.Meanwhile,the optimal error-rate low-bound of FH-CDMA system which can achieved by pseudo-random FH code is shown in the conclusion.

Design and implementation of semi-physical simulation platform in space delay tolerant network

Siyao ZHANG,Jing WU,Hao JIANG,Yufan XIANG

2016, 32(7):  82-89.  doi:10.11959/j.issn.1000-0801.2016187

Asbtract ( 279 )   HTML ( 3)   PDF (1287KB) ( 649 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The architecture of space delay tolerant networking can effectively support a deep space communication network with long delay,high error rate and on-off frequently link characteristics through“store-carry-forwards”and other features.Due to the experiment of application of deep space communication is not easy to carry,so building an accurate and reliable semi-physical simulation platform for simulating and making an argumentation of the design of deep space communication tasks was very necessary.A space DTN semi-physical simulation platform was proposed which supported a variety of specific deep space communication tasks simulation.The simulation platform provided new theory and technology for ground simulation and verification,and provided analysis tools and test instruments for carrying out deep space communication application study.

Hybrid k-anonymity approach based on TDS and BUG under the environment of big data cloud

Xiaofeng FAN,Feng YAN,Yang LIU

2016, 32(7):  90-96.  doi:10.11959/j.issn.1000-0801.2016135

Asbtract ( 265 )   HTML ( 3)   PDF (1111KB) ( 351 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

As the issue of low efficiency and poor scalability in general sub-tree anonymous method of treating big data,a bottom-up generalization(BUG) method with scalability was proposed,and on this basis,combined with the existing top-down specialization(TDS),a hybrid approach was formed.In the proposed method,k-anonymity was being as a privacy model,the compositions of TDS and BUG were developed with mapping simplification,and higher scalability through powerful cloud computing capabilities were achieved.The proposed mapping simplification BUG could insert a new candidate after several cycles of generalization,and would not affect information loss of another generalization.Given the complexity of the relationship between workload balancing point K and anonymous parameter k,mapping simplifications of BUG and TDS were combined to form a hybrid approach.Experimental results demonstrate the effectiveness of the proposed method and compared with TDS and BUG,the efficiency and scalability of hybrid method are greatly improved.

Discovery and segmentation method in micro-blog topics based on public emotional engagement analysis

Chunhua JU,Fuguang BAO,Junyan DAI

2016, 32(7):  97-105.  doi:10.11959/j.issn.1000-0801.2016158

Asbtract ( 275 )   HTML ( 1)   PDF (1561KB) ( 655 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

To improve the discovery efficiency and quality of micro-blog topic,a method of rapid discovery and segmentation in micro-blog topics based on public emotional engagement analysis was proposed,it would prompt evolution of the topics,then generate new topics and gain emotional change trend.Firstly,common emotional words were mined from corpus to build emotional thesaurus based on emotional word dictionary and TFDF.Then,emotional text was extracted quickly and sigmoid function was utilized to detect the intensive period of emotional engagement,ensuring the validity of topic mining.Besides,an improved adaptive FCM was used to cluster and discover topics.The experimental results show that this method can enhance the efficiency and quality of topic discovery in mobile environment.

Hierarchical micro-blog sentiment classification based on feature fusion

Xianying ZHU,Zhen LIU,Wei JIN,Tingting LIU,Cuijuan LIU,Yanjie CHAI

2016, 32(7):  106-114.  doi:10.11959/j.issn.1000-0801.2016182

Asbtract ( 409 )   HTML ( 4)   PDF (1214KB) ( 589 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Sentiment classification is an important issue of opinion mining.It has a high application value to classify sentiment in micro-blogs.As traditional feature selection method has semantic gap,a neural network language model was used to propose a deep feature representation method based on probability model to distribute weight to the word vector.Using this method,text semantic vector could be built.In order to avoid the semantic gap,the deep features and shallow features of text were integrated and feature vector that contained semantic information was constructed.With SVM hierarchical classification model,a variety of sentiments could be classified.Experimental results show that the hierarchical sentiment classification method based on feature fusion can improve the accuracy of sentiment classification in micro-blogs.

Hadoop bottleneck detection algorithm based on information gain

Zaole TAN,Zhifeng HAO,Ruichu CAI,Xiaojun XIAO,Yu LU

2016, 32(7):  115-120.  doi:10.11959/j.issn.1000-0801.2016203

Asbtract ( 256 )   HTML ( 2)   PDF (1007KB) ( 587 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Hadoop has become a major platform for big data storage and large data mining nowadays.Although Hadoop platform achieves high performance parallel computing through a distributed cluster of machines,the bottlenecks will inevitably appear on a machine when cluster load increases,because the cluster is composed of inexpensive host.Aiming at this problem,a bottleneck detection algorithms based on information gain was proposed.The algorithm detected cluster's bottlenecks resource by computing the information gain of each resource.The experiments show that the bottleneck detection algorithm is feasible.

Routing selection algorithm based on ant colony optimization in mobile P2P network

Lifang MA,Weifeng CHEN,Shizhan LAN,Song LU,Yulan ZHANG,Xiaobin MO,Changzhi HE

2016, 32(7):  121-125.  doi:10.11959/j.issn.1000-0801.2016207

Asbtract ( 197 )   HTML ( 3)   PDF (807KB) ( 648 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

For the dynamic of P2P network and the limited energy of the mobile node,enhancing the mobile P2P data transmission efficiency is essential.By using ant colony optimization algorithm the ant pheromones were combined with the node energy and communication bandwidth.When ACO selected the path,the concentration of the pheromone on its optimization path was reduced.The routing selection strategy was adaptively adjusted by the pheromone density of routing probability table in order to avoid network congestion and excessive energy consumption of individual nodes.A multipath routing selection algorithm in mobile P2P network was proposed.Experiment results show that the proposed algorithm can reduce packet loss rate and the average delay compared with EDSR routing protocol,prolonging the lifecycle of the whole network.

Iris recognition based on generalized Gaussian distribution FDCT_Wrap and FSVM

Zhenhong HE

2016, 32(7):  126-131.  doi:10.11959/j.issn.1000-0801.2016200

Asbtract ( 284 )   HTML ( 2)   PDF (1038KB) ( 461 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In order to improve the accuracy rate of iris recognition,an improved curvelet transform algorithm for iris recognition was proposed.Firstly,the iris image was decomposed with fast discrete curvelet transform by wrapping algorithm.Mean variance and energy of curvelet sub-band coefficients in different scales and different orientations were extracted.The weights of sub-bands were estimated by generalized Gaussian distribution.The feature vectors with stronger classification ability had large weight,which were calculated to constitute feature vectors of iris image.Finally,feature vectors were matched and recognized by classifier combined with fuzzy support vector machine and binary decision tree.The algorithm performances were tested with UBIRIS and CASIA iris database.Simulation results show that the proposed algorithm has higher recognition accuracy rate and efficiency.It is feasibility.

Operating technology wide-angle

Mobile edge computing and application in traffic offloading

Jianmin ZHANG,Weiliang XIE,Fengyi YANG,Zhouyun WU,Liang XIE

2016, 32(7):  132-143.  doi:10.11959/j.issn.1000-0801.2016165

Asbtract ( 1487 )   HTML ( 91)   PDF (1258KB) ( 3634 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Mobile edge computing（MEC）makes it possible to deploy and provide service locally,which is close to the users,by enabling the IT and cloud computation capacity at the radio access network (RAN).Thus,MEC can improve the quality of experience (QoE) by reducing the latency,and decrease the network operation cost through reducing backhaul capacity requirement.Meanwhile,based on the network context information (location,network traffic load,radio information,etc) exposure to applications and services,MEC can further improve the QoE of user and provide the platform to third-party partners for application and service innovation.Besides the introduction of MEC,the detailed MEC platform was presented.Furthermore,the traffic offloading solution based on MEC was proposed and compared with the solution of local IP access and selected IP traffic offload (LIPA/SIPTO).In addition,the problems and challenges of the MEC were also discussed in detail.

Error vector magnitude measurement and analysis in optical communication system

Junsen LAI,Xiaohua TANG,Rui TANG,Xin ZHAO,Wenyu ZHAO,Haiyi ZHANG

2016, 32(7):  140-145.  doi:10.11959/j.issn.1000-0801.2016159

Asbtract ( 365 )   HTML ( 4)   PDF (3266KB) ( 939 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Vector modulation format of high speed optical communication system calls for new measurement and analysis scheme.Error vector magnitude (EVM) is one of the most important parameters in vector modulation evaluation.The definition of EVM parameters,its test methods and instruments were analyzed,and application of EVM related parameter in transmitter measurement and its standardization progress were also discussed.

A novel low cost bidirectional transmission coherent passive optical network system

Shunli QIU,Yi YANG,Rong HU

2016, 32(7):  146-151.  doi:10.11959/j.issn.1000-0801.2016202

Asbtract ( 257 )   HTML ( 2)   PDF (978KB) ( 465 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Based on the coherent optical reception technology,a cost-effective structure for the optical network unit (ONU) transceivers in ultra-dense wavelength division multiplexing passive optical network using a single directly modulated laser (DML)was proposed.To reduce the number of required light sources,only one DML was used in both upstream and downstream links.By experimental investigations,the impacts of driving amplitude and bias current on DML's performance were analyzed.Meanwhile,the impact of frequency spacing between upstream and downstream signal and the Rayleigh backscattering interference on system performance were investigated.The method has better performance of system receiving and can effectively reduce the cost and complexity of coherent passive optical network system.

Research on differentiation of influential factors of key account satisfaction in fixed communication industry

Botao XIA

2016, 32(7):  152-165.  doi:10.11959/j.issn.1000-0801.2016191

Asbtract ( 307 )   HTML ( 9)   PDF (2191KB) ( 615 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Based on the existing findings of previous customer satisfaction studies and a telecom operator's key account satisfaction assessment results of 5 consecutive years,CNCCSI model was established to study influential factors of key accounts in fixed communication industry.Methods were discussed to segment key accounts in fixed communication industry through multiple indicator cluster analysis of influential factors of satisfaction and industry characteristic indicators.Clustering technology was used to divide 11 industries into 4 customer segments and demand character,concerned factors and satisfaction of each segment were analyzed.Aiming at a telecom operator's problems of present marketing service analysis of key accounts,improvement suggestions of market system were put forward.

Application of 5.8 GHz optical fiber converged communication in transmission line monitoring system

Jie TONG,Yanli LIU,Delong YANG,Hongli LUO,Huan WANG

2016, 32(7):  166-174.  doi:10.11959/j.issn.1000-0801.2016201

Asbtract ( 284 )   HTML ( 2)   PDF (1493KB) ( 863 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

When in the depths of the mountains,2G/3G signal is weak or don't exist,or when the high definition video is needed,2G/3G couldn't meet requirements of such high bandwidth,so that communication is intermittent or interrupt,resulting in the condition monitoring data is difficult to transmit reliably to the master station.To solve this problem,2G/3G+5.8 GHz or 5.8 GHz +OPGW converged communication mode was proposed,the signal could be switched automatically to the 5.8 GHz communication mode,and transmits back to the master station after converging the main line and OPGW.Based on the optical fiber converged communication,the transmission line monitoring system and work flow were designed and the application example and the future development prospect were given finally.

Development trend and typical applications of industrial big data

Mingfeng HUANG

2016, 32(7):  175-178.  doi:10.11959/j.issn.1000-0801.2016183

Asbtract ( 327 )   HTML ( 8)   PDF (718KB) ( 1665 )   Knowledge map   

References | Related Articles | Metrics

The concept and characteristics of industrial big data were introduced,and its development trend was discussed.It meant that industrial big data cluld be widely used in the whole production process in manufacturing enterprises.According to application scenes of research and design,supply,manufacturing,marketing and service,the applications of industrial big data were analyzed and summed up.

Optimization strategy and solution of 4G high-speed rail network

Zongzhang LI,Zhitong SHI,Yuling WANG,Kun YUAN,Zhiguo WANG,Xinchao ZHANG

2016, 32(7):  179-187.  doi:10.11959/j.issn.1000-0801.2016189

Asbtract ( 567 )   HTML ( 16)   PDF (1607KB) ( 1446 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

With the development of LTE data and VoLTE services,subscribers pay more and more attention to network experience.LTE optimization faces many challenges.Therefore,China Mobile Shandong Corporation made a complete and feasibility solution,which met the requirement of high-speed scene optimization.There were four dimensions in this solution: double layers network deployment,VoLTE optimization of high-speed rail,coordinating optimization in the boundary of high-speed network and normal LTE network,and the exploration and deployment of new functions.After the implementation of the solution,VoLTE coverage rate increases from 87.95% to 91.66%,MOS value upgrades from 3.6 to 4,the ratio of MOS value greater than 3.0 rised from 89.61% to 96.70%.

Fault early warning model of 4G base station out of service based on centralized monitoring data resources

Yang WANG,Yi MAN,Zhipeng CHEN

2016, 32(7):  188-196.  doi:10.11959/j.issn.1000-0801.2016147

Asbtract ( 331 )   HTML ( 10)   PDF (1363KB) ( 626 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

4G wireless base station equipment is an important link which has direct impact on information communication network customer service quality,and 4G wireless base stations out of service fault will directly block users' normal communication.Aiming at these problems,based on the centralized monitoring warning message data resources through association rule mining and time trace deduction analysis,4G base stations out of service fault short-term warning was achieved.Based on centralized monitoring equipment performance data resources,by the classification of network elements (data cleaning,feature selection,network elements clustering),index dimension reduction (grouped by cluster,principal component analysis),principal component expression and out of service fault correlation analysis,performance indicators selection and threshold analysis,4G base stations out of service fault long-term warning was achieved.The test can accurately predict the 27.8% of 4G base station equipment out of service fault next month.