CN105188080B - Cell outage detection method in mobile communications network based on direct-push confidence machine and hypothesis testing - Google Patents
Cell outage detection method in mobile communications network based on direct-push confidence machine and hypothesis testing Download PDFInfo
- Publication number
- CN105188080B CN105188080B CN201510474466.XA CN201510474466A CN105188080B CN 105188080 B CN105188080 B CN 105188080B CN 201510474466 A CN201510474466 A CN 201510474466A CN 105188080 B CN105188080 B CN 105188080B
- Authority
- CN
- China
- Prior art keywords
- class
- data
- value
- data point
- tested
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/04—Arrangements for maintaining operational condition
Abstract
The invention discloses the cell outage detection methods in a kind of mobile communications network based on direct-push confidence machine and hypothesis testing.The present invention passes through the matching degree that direct-push confidence machine provides data to be tested point and normal cell or abnormal cell first, then carries out hypothesis testing according to matching degree information.The discriminative information amount that a kind of judgement of data point is normal cell and abnormal cell is defined according to matching degree in hypothesis testing, decision rule is then defined according to discriminative information amount, sequential detection is utilized to carry out conclusive judgement.This method adjudicates accuracy height, and false alarm rate is low.Using the method in the present invention, can be coordinated between the accuracy and complexity of judgement by adjusting threshold value.
Description
Technical field
The present invention relates to the cell outage test problems in wireless communication, belong to the network technique field in wireless communication.
Background technique
It, can due to network configuration of software fault, hardware fault or some mistakes etc. in mobile radio telecommunications
Cell communication disruption can be will lead to.In the case that network self-healing conjunction technology is intended to prosthetic operation, system can in time, automatically
It was found that failure and restoring from failure.Cell self-healing function includes two stages, cell outage detection and cell outage compensation.
Cell outage detection mainly carries out analyzing and diagnosing according to the parameter that network node (base station, mobile terminal, access gateway) reports, if
It notes abnormalities, then triggering cell is reported to interrupt compensation.Cell outage be detected as efficiently detecting network failure open one it is new
Approach.
Summary of the invention
The object of the present invention is to provide in a kind of radio communication network cell based on direct-push confidence machine and hypothesis testing
Disconnected detection method.Using the method in the present invention, can be obtained between the accuracy and complexity of judgement by adjusting threshold value
Coordinate.
The present invention passes through that direct-push confidence machine provides data to be tested point and normal cell or abnormal cell first
With degree, hypothesis testing is then carried out according to matching degree information, defining a kind of judgement of data point according to matching degree is normal cell
With the discriminative information amount of abnormal cell, sequential detection is then carried out according to discriminative information amount, carries out conclusive judgement.
1 direct-push confidence machine
Direct-push confidence machine is wide using a kind of use scope of the algorithmic theory of randomness theory foundation of Kolmogorov
Machine learning confidence level mechanism.It is used to measure the credibility that a sample is belonging respectively to existing several classifications.It is logical
Confidence level is estimated frequently with a kind of random detection function for meeting Kolmogorov randomness theory, it is this with machine examination
The value for surveying function is referred to as P value, and sample generally defined as to be sorted belongs to the probability of already present sample space, relative to
The value of certain class sample space is bigger, then shows that a possibility that it belongs to the sample space is bigger.
Direct-push confidence machine is substantially a kind of sorting algorithm, and in processing classification problem, it attempts for sample to be classified as
There is certain one kind in classification.It passes through the method that distance calculates, and is classified according to classified data set to observation sampling point.For
Calculating P value, first defines singular value:
Di yIndicate certain data point x to sort from small to largeiWith classification data concentrate all data points of a certain class y away from
From.Similar, Di -yIndicate the data point x to sort from small to largeiWith in classified data set all data points of-y class away from
From.- y indicates all classes that y class is removed in classified data set.K indicates the number for the neighbour's data point taken, and the value of k can
It is voluntarily determined by operator according to network condition.αi yAs certain data point xiThe singular value of y class is concentrated with classification data.
After given singular value, a kind of definition method of P value is as follows:
# indicates the data point number for meeting condition in the gesture of set, that is, set.αtest yIndicate data point to be tested with
The singular value of y class, α in classified data setj y(j=1,2 ..., n) indicate y class all data points singular value, n is y
The number of class data point.Py(αtest y) be data point in y class singular value be greater than data point to be tested relative to this class singular value
Ratio.It is not difficult to find out Py(αtest y) value interval of value is [0,1], and its value is bigger, shows sample data point to be tested
A possibility that belonging to class y is bigger.Sample to be sorted is divided into maximum P by direct-push confidence machiney(αtest y) class corresponding to value.
In calculating process, concentrates the singular value of the sample of a certain class to be less than when data to be tested and training data and be used for
It when calculating k minimum range of this sample singular value, needs to recalculate singular value for such all sample, to be to be sorted
Sample recalculates P value.For every one kind in training data, data to be tested have a corresponding P value to calculate.
2 cell outage detection methods
Cell outage detection process is divided into two parts, i.e., monitoring and test are established and interrupted to interruption detection model.In model
Establish the following steps are included:
1) different states, i.e. normal condition or interrupt status are in by manually setting cell, to acquire inhomogeneity
The training data vector of type (modeling class) is used for model foundation.Training data vector can select signal reception power (RSRP),
Signal to Interference plus Noise Ratio (SINR), cutting off rate etc., specific vector can voluntarily be determined by operator according to network operation situation.
2) trained number is calculated with the method for direct-push confidence machine to the training data vector of the different modeling types of acquisition
According to the singular value relative to each modeling class and preservation.
It interrupts in monitoring and detection process, by monitoring network state, acquires data vector to be tested, carry out interruption inspection
It surveys.Detection process is as follows:
1) P value of the data point to be tested relative to each modeling class is calculated according to direct-push confidence machine first, saved.
2) hypothesis testing is carried out according to P value.
(1) assume to establish: assuming that data to be tested vector is Xn={ x1,x2,...,xi,...,xn}.Modeling class number is
M.It interrupts detection process and follows following hypothesis:
H0:Xn~P0
H1:Xn~P1
(3)
…
HM:Xn~PM
P0~PMFor the P state of value space of different modeling classes.H0~HMRespectively assume that data point to be tested belongs to accordingly
Modeling class.
(2) determine that a decision criteria differentiates which modeling class is data point to be tested belong to.
Direct-push confidence machine gives P value of each test data point relative to training class, that is, a kind of test data
The measurement of point and the matching degree of training class.
The discriminative information amount for the y class that single test data point provides is defined as:
D is the number of class in-y.PyIt is worth bigger, indicates that attribution data to be tested is bigger in the y class a possibility that, so y class
Discriminative information amount Iy(xi) bigger.P-yIt is bigger, indicate that a possibility that attribution data is with other classes are bigger, so the judgement of y class
Information content Iy(xi) accordingly reduce.
Decision rule are as follows: Λ* y={ Xn:Iy(Xn) > Tn(λ) }, i.e., if certain a kind of accumulative sentence information content exceeds certain
One thresholding, judgement test data vector belong to the modeling class.Thresholding TnThe value of (λ) can by operator according to network condition voluntarily
It determines.
(3) adjudicate: the method for taking sequential detection carries out conclusive judgement.The discriminative information amount for initializing each class first is
Zero.For each test data, the discriminative information amount for all classes that data point provides is calculated according to formula (4), then to each
The information content of illegally occupying of class adds up, until the discriminative information amount of some class reaches a decision threshold Tn(λ), judgement test number
According to such is belonged to, stop detection.Thresholding Tn(λ) is bigger, detects that accurate provisioning request is higher, and corresponding detection complexity is higher.
The invention has the following advantages: the matching of data point and cell that the present invention is provided according to direct-push confidence machine
It spends information and carries out hypothesis testing.The discriminative information amount that a kind of judgement of data point is normal cell and abnormal cell is defined, then
Sequential detection judgement is carried out according to discriminative information amount.This method adjudicates accuracy height, and false alarm rate is low.
It is had the following advantages based on cell outage judgement of the invention:
1. training vector is selected by operator's self assemble, there is high flexibility.
2. if then the definition of information content only needs operator's selection is modeled by the parameter of user or base station measurement
Local information can be realized by distributed algorithm.
3. operator can voluntarily be adjusted between detection complexity and accuracy in detection by adjusting decision threshold
Section.
4. using Sequential Detection, there is high detection efficiency.
Specific embodiment
The embodiment of the present invention in the mobile communication network is described further below:
(1) model foundation: acquisition training data vector calculates training data vector according to formula (1) and builds relative to each
The singular value of mould class and preservation.
(2) data vector to be tested is acquired, calculates vector to be tested relative to each modeling class according to formula (1), (2)
P value.
(3) it makes the assumption that, the discriminative information amount for initializing each modeling class is zero.
(4) the discriminative information amount that each class that data point provides is calculated according to formula (4), adds up.
(5) it if the accumulative sentence information content of certain class is more than thresholding, adjudicates, stops.Otherwise, continue to collect data, add up
Discriminative information amount.
Claims (1)
1. the cell outage detection method in a kind of mobile communications network based on direct-push confidence machine and hypothesis testing, passes through first
Direct-push confidence machine provides the matching degree of data to be tested point and normal cell or abnormal cell, then according to matching degree information
Hypothesis testing is carried out, the discriminative information amount that a kind of judgement of data point is normal cell and abnormal cell is defined according to matching degree,
Then sequential detection is carried out according to discriminative information amount, carries out conclusive judgement；
Wherein direct-push confidence machine is wide using a kind of use scope of the algorithmic theory of randomness theory foundation of Kolmogorov
Machine learning confidence level mechanism；It is used to measure the credibility that a sample is belonging respectively to existing several classifications, adopts
Confidence level is estimated with a kind of random detection function for meeting Kolmogorov randomness theory, this random detection letter
Several values is referred to as P value, is defined as the probability that sample to be sorted belongs to already present sample space, opposite Mr. Yu's class sample
The value in space is bigger, then shows that a possibility that it belongs to the sample space is bigger；
In order to calculate P value, singular value is first defined:
Di yIndicate certain data point x to sort from small to largeiAt a distance from all data points that classification data concentrates a certain class y；
Similar, Di -yIndicate the data point x to sort from small to largeiWith in classified data set all data points of-y class away from
From-y indicates all classes for removing y class in classified data set, and k indicates the number for the neighbour's data point taken, and the value of k can
It is voluntarily determined by operator according to network condition, αi yAs certain data point xiThe singular value of y class is concentrated with classification data；
After given singular value, a kind of definition method of P value is as follows:
# indicates the data point number for meeting condition in the gesture of set, that is, set；αtest yIt indicates data point to be tested and has divided
The singular value of y class, α in the data set of classj y(j=1,2 ..., n) indicate y class all data points singular value, n is y class number
The number at strong point, Py(αtest y) it is the singular value of data point in y class greater than ratio of the data point to be tested relative to this class singular value
Sample to be sorted is divided into maximum P by example, direct-push confidence machiney(αtest y) class corresponding to value；
In calculating process, when data to be tested and training data concentrate the singular value of the sample of a certain class to be less than for calculating
It when k minimum range of this sample singular value, needs to recalculate singular value for such all sample, to be sample to be sorted
Recalculate P value；For every one kind in training data, data to be tested have a corresponding P value to calculate；
Cell outage detection method specifically includes:
Cell outage detection process is divided into two parts, i.e., monitoring and test are established and interrupted to interruption detection model；
The interruption detection model establish the following steps are included:
101) different states, i.e. normal condition or interrupt status are in by manually setting cell, to acquire different type
Training data vector be used for model foundation, training data vector select include signal reception power RSRP, signal and interference plus
Noise ratio SINR and cutting off rate, specific vector are voluntarily determined by operator according to network operation situation；
102) training data is calculated with the method for direct-push confidence machine to the training data vector of the different modeling types of acquisition
Singular value and preservation relative to each modeling class；
The interruption monitoring and detection process: by monitoring network state, acquiring data vector to be tested, carry out interruption detection,
Detection process is as follows:
201) P value of the data point to be tested relative to each modeling class is calculated according to direct-push confidence machine first, saved；
202) hypothesis testing is carried out according to P value, having includes following 3 steps:
(1) assume to establish: assuming that data to be tested vector is Xn={ x1,x2,...,xi,...,xn, modeling class number is M, in
Disconnected detection process follows following hypothesis:
P0~PMFor the P state of value space of different modeling classes, H0~HMRespectively assume that data point to be tested belongs to build accordingly
Mould class；
(2) determine that a decision criteria differentiates which modeling class is data point to be tested belong to；
Direct-push confidence machine give each test data point relative to training class P value, that is, a kind of test data point with
The measurement of the matching degree of training class；
The discriminative information amount for the y class that single test data point provides is defined as:
D is the number of class in-y, PyIt is worth bigger, indicates that attribution data to be tested is bigger in the y class a possibility that, so the judgement of y class
Information content Iy(xi) bigger, P-yIt is bigger, indicate that a possibility that attribution data is with other classes are bigger, so the discriminative information amount I of y classy
(xi) accordingly reduce；
Decision rule are as follows: Λ* y={ Xn:Iy(Xn) > Tn(λ) }, i.e., if certain a kind of accumulative sentence information content exceeds a certain door
Limit, judgement test data vector belong to the modeling class, thresholding TnThe value of (λ) can be voluntarily true according to network condition by operator
It is fixed；
(3) adjudicate: the method for taking sequential detection carries out conclusive judgement；The discriminative information amount for initializing each class first is zero,
For each test data, the discriminative information amount for all classes that data point provides is calculated according to formula (4), then to each class
It illegally occupies information content to add up, until the discriminative information amount of some class reaches a decision threshold Tn(λ) adjudicates test data category
In such, stop detection, thresholding Tn(λ) is bigger, detects that accurate provisioning request is higher, and corresponding detection complexity is higher.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510474466.XA CN105188080B (en) | 2015-08-05 | 2015-08-05 | Cell outage detection method in mobile communications network based on direct-push confidence machine and hypothesis testing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510474466.XA CN105188080B (en) | 2015-08-05 | 2015-08-05 | Cell outage detection method in mobile communications network based on direct-push confidence machine and hypothesis testing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105188080A CN105188080A (en) | 2015-12-23 |
| CN105188080B true CN105188080B (en) | 2019-04-23 |
Family
ID=54909868
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510474466.XA Active CN105188080B (en) | 2015-08-05 | 2015-08-05 | Cell outage detection method in mobile communications network based on direct-push confidence machine and hypothesis testing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105188080B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107105432A (en) * | 2017-06-12 | 2017-08-29 | 北京奇虎科技有限公司 | The detection method and device of WLAN |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102325342A (en) * | 2011-10-31 | 2012-01-18 | 北京邮电大学 | Cell interrupt detection and judgment method and device for self-recovery function of self-organization of network (SON) system |
| CN102932826A (en) * | 2012-11-30 | 2013-02-13 | 北京邮电大学 | Cell interruption detection positioning method in self-organizing network of cell mobile communication system |
| CN103561419A (en) * | 2013-11-07 | 2014-02-05 | 东南大学 | Distributed event detection method based on correlation |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2271142B1 (en) * | 2009-06-26 | 2012-08-29 | Alcatel Lucent | Method, computer program product and base station apparatus for detecting PCI collisions |
-
2015
- 2015-08-05 CN CN201510474466.XA patent/CN105188080B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102325342A (en) * | 2011-10-31 | 2012-01-18 | 北京邮电大学 | Cell interrupt detection and judgment method and device for self-recovery function of self-organization of network (SON) system |
| CN102932826A (en) * | 2012-11-30 | 2013-02-13 | 北京邮电大学 | Cell interruption detection positioning method in self-organizing network of cell mobile communication system |
| CN103561419A (en) * | 2013-11-07 | 2014-02-05 | 东南大学 | Distributed event detection method based on correlation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105188080A (en) | 2015-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108322347B (en) | Data detection method, device, detection server and storage medium | |
| Liu et al. | Fault-tolerant event region detection on trajectory pattern extraction for industrial wireless sensor networks | |
| CN113344134B (en) | Low-voltage distribution monitoring terminal data acquisition abnormality detection method and system | |
| CN103812577A (en) | Method for automatically identifying and learning abnormal radio signal type | |
| CN103176164A (en) | Multi-target passive tracking method based on wireless sensor network | |
| CN107205244A (en) | A kind of design method of the sensor network anomaly data detection based on temporal correlation | |
| CN110086767A (en) | A kind of hybrid intrusion detection system and method | |
| CN110062410A (en) | A kind of cell outage detection localization method based on adaptive resonance theory | |
| CN113591393A (en) | Fault diagnosis method, device, equipment and storage medium of intelligent substation | |
| CN105188080B (en) | Cell outage detection method in mobile communications network based on direct-push confidence machine and hypothesis testing | |
| Lin et al. | A static state estimation approach including bad data detection and identification in power systems | |
| CN111738348B (en) | Power data anomaly detection method and device | |
| CN113810792A (en) | Edge data acquisition and analysis system based on cloud computing | |
| EP4173339A1 (en) | False cell detection in a wireless communication network | |
| CN109521451A (en) | Judgment method, equipment, system and the storage medium of smart machine local environment | |
| US9609533B2 (en) | Method and device for optimizing a handover parameter | |
| CN109963292A (en) | Complain method, apparatus, electronic equipment and the storage medium of prediction | |
| CN114936614B (en) | Operation risk identification method and system based on neural network | |
| Rizvi et al. | Real-time zip load parameter tracking using sensitivity-based adaptive window and variable elimination with realistic synchrophasor data | |
| Matsuda et al. | Traffic anomaly detection based on robust principal component analysis using periodic traffic behavior | |
| Kuntz et al. | Detecting, locating, & quantifying false data injections utilizing grid topology through optimized D-FACTS device placement | |
| De Sousa et al. | Event detection framework for wireless sensor networks considering data anomaly | |
| CN110472188A (en) | A kind of abnormal patterns detection method of facing sensing data | |
| CN114597886A (en) | Power distribution network operation state evaluation method based on interval type two fuzzy clustering analysis | |
| CN114912372A (en) | High-precision filling pipeline fault early warning method based on artificial intelligence algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210331 Address after: 201306 building C, No. 888, Huanhu West 2nd Road, Lingang New Area, Pudong New Area, Shanghai Patentee after: Shanghai Hanxin Industrial Development Partnership (L.P.) Address before: 210096 No. four archway, 2, Jiangsu, Nanjing Patentee before: SOUTHEAST University |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230914 Address after: 201615 room 301-6, building 6, no.1158, Jiuting Central Road, Jiuting Town, Songjiang District, Shanghai Patentee after: White box (Shanghai) Microelectronics Technology Co.,Ltd. Address before: 201306 building C, No. 888, Huanhu West 2nd Road, Lingang New Area, Pudong New Area, Shanghai Patentee before: Shanghai Hanxin Industrial Development Partnership (L.P.) |