CN110944354B - Base station interference monitoring method and system based on waveform analysis and deep learning - Google Patents

Base station interference monitoring method and system based on waveform analysis and deep learning Download PDF

Info

Publication number
CN110944354B
CN110944354B CN201911102563.0A CN201911102563A CN110944354B CN 110944354 B CN110944354 B CN 110944354B CN 201911102563 A CN201911102563 A CN 201911102563A CN 110944354 B CN110944354 B CN 110944354B
Authority
CN
China
Prior art keywords
interference
base station
grid
prediction model
waveform
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
Application number
CN201911102563.0A
Other languages
Chinese (zh)
Other versions
CN110944354A (en
Inventor
陈曦
蓝志坚
李海燕
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Richstone Technology Co ltd
Original Assignee
Guangzhou Richstone Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Richstone Technology Co ltd filed Critical Guangzhou Richstone Technology Co ltd
Priority to CN201911102563.0A priority Critical patent/CN110944354B/en
Publication of CN110944354A publication Critical patent/CN110944354A/en
Application granted granted Critical
Publication of CN110944354B publication Critical patent/CN110944354B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/08—Testing, supervising or monitoring using real traffic
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/309—Measuring or estimating channel quality parameters
    • H04B17/345—Interference values
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/04—Processing captured monitoring data, e.g. for logfile generation
    • H04L43/045—Processing captured monitoring data, e.g. for logfile generation for graphical visualisation of monitoring data
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/06—Testing, supervising or monitoring using simulated traffic

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Biomedical Technology (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Quality & Reliability (AREA)
  • Electromagnetism (AREA)
  • Monitoring And Testing Of Transmission In General (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

The invention discloses a base station interference monitoring method based on waveform analysis and deep learning, which is characterized in that data required by interference monitoring of an LTE system is acquired; screening out a high uplink interference cell according to the acquired network management data; carrying out primary matching on the interference wave types of the high uplink interference cells by utilizing the similarity, and marking the base station faults; feeding back the interference wave type obtained by primary matching to the grid in a thermal mode according to the GPS position of the base station to obtain a grid thermodynamic diagram; establishing an interference prediction model based on a deep neural network; and updating the grid thermodynamic diagram and the interference experience base according to the predicted interference type and the results of field investigation and processing, and optimizing the interference prediction model. The method and the device perform interference wave matching based on the similarity, and provide directional guidance for technical personnel to inquire fault sources by combining graphical deep network prediction, thereby improving the accuracy and efficiency of base station interference monitoring.

Description

Base station interference monitoring method and system based on waveform analysis and deep learning
Technical Field
The invention relates to the technical field of mobile communication, in particular to a base station interference monitoring method and system based on waveform analysis and deep learning.
Background
In the daily optimization process of a mobile communication network, the positioning analysis and optimization of interference is one of the key tasks. The currently adopted high uplink interference positioning technology needs to consider multi-dimensional interference characteristics such as frequency domain, time domain, space and the like to correlate and position interference factors. Due to the complex and various factors of high uplink interference, the position of the interference source and the interference information are difficult to judge quickly and accurately, and certain experienced technicians are needed; meanwhile, as the acquisition and operation of the features are complex, a large amount of manpower and material resources are consumed in the process, so that the positioning time of the interference information is slow, and the positioning accuracy is low.
In addition, most of the existing high uplink interference positioning technologies aim at regional position information, recognize limited interference factors and perform manual matching. In a larger area, the maintenance cost is directly increased, and the interference diversity is more complicated, so that the interference is difficult to position in the larger area, and the high-accuracy fault prediction and prediction are not facilitated.
Disclosure of Invention
The invention provides a base station interference monitoring method and system based on waveform analysis and deep learning, and aims to solve the problems that the existing high uplink interference positioning technology is slow in positioning time, low in positioning accuracy and small in positioning area range.
In order to achieve the above purpose, the technical means adopted is as follows:
the base station interference monitoring method based on waveform analysis and deep learning comprises the following steps:
s1, collecting data required by interference monitoring of an LTE system;
s2, screening out a high uplink interference cell according to the acquired network management data;
s3, carrying out primary matching on the interference wave types of the high uplink interference cells by utilizing similarity, and marking base station faults;
s4, feeding back the interference wave type obtained by primary matching to the grid in a thermal form according to the GPS position of the base station to obtain a grid thermodynamic diagram;
s5, establishing an interference prediction model based on a deep neural network, wherein the input of the interference prediction model is a grid thermodynamic diagram, and the output of the interference prediction model is a predicted interference type of the high uplink interference cell;
and S6, updating the grid thermodynamic diagram and an interference experience library according to the predicted interference type and the results of field investigation and processing, and optimizing the interference prediction model.
In the scheme, interference wave matching is carried out based on the similarity, and graphical deep network prediction is combined, compared with a single-point base station interference wave matching method based on the similarity, the method can be used for correlating the influence of other base stations in the grid thermodynamic diagram on a base station to be monitored, forming area monitoring, clearly and intuitively seeing the influence range of the fault and general fault information on the grid thermodynamic diagram, and providing directional guidance for technical personnel to inquire the fault source, so that the accuracy and the efficiency of base station interference monitoring are improved. In addition, the accuracy of the interference prediction model may be continually improved based on the accumulated experience of troubleshooting each time.
Preferably, the data in step S1 includes XDR information, network management information, and 4G LTE engineering parameter information.
Preferably, the step S3 specifically includes the following steps:
s31, calculating the shortest algorithm distance between a given waveform in the high uplink interference cell and a matched waveform in a preset interference experience base;
and S32, ascending sorting is carried out on the shortest algorithm distances obtained through calculation, the matchable waveform types corresponding to the first N shortest algorithm distances are selected as the initial matching interference wave types of the high uplink interference cell, and the base station fault is marked.
Preferably, the method for calculating the shortest algorithm distance in step S31 is as follows:
let a be any real number, calculate the minimum value of the solution formula, i.e.
Figure GDA0003733960800000021
Minimum value of (d);
wherein j =1,2, 3.., 100, which is the PRB value; x denotes a given waveform, x j For the jth data in a given waveform; y is i The identification of a waveform that can be matched,
Figure GDA0003733960800000022
is the jth data in the ith matchable waveform; wherein a is used for eliminating the difference caused by control translation;
and expanding the solving formula:
Figure GDA0003733960800000023
the minimum value of the formula solved by the matching method is:
Figure GDA0003733960800000024
preferably, the step S4 specifically includes: expressing different interference wave types on the grid in different colors in the initially matched interference wave types obtained in the step S3, and setting color depth according to the interference wave influence range to obtain a grid thermodynamic diagram; wherein the latitude and longitude values of the base station form the vertices of the grid. In the preferred scheme, the color depth is set according to the influence range of the interference wave, namely, for example, the GPS desynchronization can cause the square circle to be several kilometers, and the thermal value of the interference wave fault is very large; for example, a single point of influence failure, the thermal value is small.
Preferably, the interference prediction model based on the deep neural network in step S5 includes a conv convolution unit, M residual error units, and a conv output layer, which are connected in sequence; wherein the conv input layer is used for extracting the image features of the grid thermodynamic diagram, and the convolution of the image features is X c (1) ＝f(W c (1) *X c (0) +b c (1) )；
Wherein W c (1) Representing the weight of the convolution kernel, b c (1) The convolution bias is represented, the convolution operation is represented, and f is a special convolution and is used for ensuring that the output and the input are the same in size;
the mathematical model of the residual error unit is X c (l+1) ＝X c (l) +F(X c (l) ；θ c (l) ),l＝1,2,...,L
Where F is the residual equation, θ c (l) All parameters needing to be learned in the first layer are contained;
obtaining a predicted interference type X c (L+1) And outputting by a conv output layer.
In the preferred embodiment, since the obtained image information of the grid thermodynamic diagrams is not much, and the size of each grid thermodynamic diagram is 32 × 32, a multi-level deep neural network is not required to be used.
Preferably, a hyperbolic tangent function tanh and an optimization function MinimizLoss are connected behind a conv output layer of the interference prediction model; the hyperbolic tangent function tanh is used for standardizing a predicted value output by the conv output layer, and the optimization function MinimizLoss is used for calculating a metric value between the predicted value and a true value output by the interference prediction model, namely:
Figure GDA0003733960800000031
wherein X t In order to be a matrix of predicted values,
Figure GDA0003733960800000032
is a true value matrix.
Preferably, the predicted value is normalized by the hyperbolic tangent function tanh and then is located in the range of [ -1,1 ].
The invention also provides a base station interference monitoring system based on waveform analysis and deep learning, which comprises the following steps:
the data acquisition module is used for acquiring data required by interference monitoring of the LTE system;
the high uplink interference cell screening module is used for screening out the high uplink interference cell according to the acquired network management data;
the interference wave type primary matching module is used for carrying out primary matching on the interference wave types of the high uplink interference cells by utilizing similarity and marking base station faults;
the grid thermodynamic diagram building module is used for feeding back the interference wave type obtained by primary matching to a grid in a thermodynamic mode according to the GPS position of the base station to obtain a grid thermodynamic diagram;
the interference prediction model building module is used for building an interference prediction model based on a deep neural network, the input of the interference prediction model is a grid thermodynamic diagram, and the output of the interference prediction model is the predicted interference type of the high uplink interference cell;
and the interference optimization module is used for updating the grid thermodynamic diagram and the interference experience base according to the predicted interference type and the result of on-site investigation and processing, and optimizing the interference prediction model.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that:
compared with a single-point base station interference wave matching method based on the similarity, the base station interference monitoring method and the base station interference monitoring system based on the similarity can correlate the influence of other base stations in the grid thermodynamic diagram on the base station to be monitored, form area monitoring, clearly and intuitively see the influence range of the fault and approximate fault information on the grid thermodynamic diagram, provide directional guidance for technical personnel to inquire the fault source, improve the accuracy and efficiency of base station interference monitoring, and can be positioned in a region with a larger range. In addition, based on experience accumulation of troubleshooting each time, the accuracy of the interference prediction model can be continuously improved, and benign and high-precision prejudgment closed-loop operation is formed.
The method solves the problems of slow positioning time, low positioning accuracy and smaller positioning area range of the high uplink interference positioning technology due to the need of considering multi-dimensional interference characteristics of frequency domain, time domain, space and the like.
Drawings
FIG. 1 is a process flow diagram of example 1.
Fig. 2 is a schematic diagram of a given waveform a in example 1.
Fig. 3 is a diagram of a matchable waveform B similar to the given waveform a in example 1.
Fig. 4 is a schematic diagram of a residual error unit in embodiment 1.
FIG. 5 is a block diagram of a system according to example 2.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent;
for the purpose of better illustrating the embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product;
it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
Example 1
As shown in fig. 1, the method for monitoring interference of a base station based on waveform analysis and deep learning includes the following steps:
s1, collecting data required by interference monitoring of an LTE system; the method comprises XDR information, network management information and 4G LTE working parameter information;
s2, screening out a high uplink interference cell according to the acquired network management data;
s3, carrying out primary matching on the interference wave types of the high uplink interference cells by utilizing similarity, and marking base station faults; the method specifically comprises the following steps:
s31, calculating the shortest algorithm distance between the given waveform in the high uplink interference cell and the matched waveform in the preset interference experience library, wherein the calculation method comprises the following steps:
let a be any real number, calculate the minimum of the solution formula, i.e.
Figure GDA0003733960800000051
Minimum value of (d);
wherein j =1,2, 3.., 100, which is the PRB value; x denotes a given waveform, x j For the jth data in a given waveform; y is i The identification of a waveform that can be matched,
Figure GDA0003733960800000052
the j data in the i-th matchable waveform; wherein a is used for eliminating the difference caused by control translation; the preset interference experience library comprises a plurality of PRB values of known interference types;
the above solving formula is to find out the waveform with the minimum sum of squared differences with the given waveform except the translation factor from all other matchable waveforms;
and expanding the solving formula:
Figure GDA0003733960800000053
the minimum value of the formula solved by the matching method is:
Figure GDA0003733960800000054
s32, performing ascending sequencing on the calculated shortest algorithm distances, selecting the matchable waveform types corresponding to the first N shortest algorithm distances as the initial matched interference wave types of the high uplink interference cell, and marking the base station fault; FIG. 2 shows one of the given waveforms A, FIG. 3 shows one of the similar matchable waveforms B for the given waveform, with the shortest algorithmic distance of 1.9;
s4, feeding back the interference wave types obtained by primary matching to a grid in a thermal form according to the GPS position of the base station to obtain a grid thermodynamic diagram, namely, expressing different interference wave types on the grid in different colors in the primary matching interference wave types obtained in the step S3, and setting color depth according to the interference wave influence range to obtain the grid thermodynamic diagram; for example, if the GPS is out of step and several kilometers of squares are caused, the thermal value of the interference wave fault is large; for example, a single point of influence fault, the thermal value is small; wherein the latitude and longitude values of the base station form the vertices of the grid;
s5, establishing an interference prediction model based on a deep neural network, wherein the input of the interference prediction model is a grid thermodynamic diagram, and the output of the interference prediction model is a predicted interference type of the high uplink interference cell;
the interference prediction model based on the deep neural network comprises a conv convolution unit, M residual error units, a conv output layer, a hyperbolic tangent function tanh and an optimization function Minimiz Loss which are sequentially connected; wherein the conv input layer is used for extracting the image characteristics of the grid thermodynamic diagram, and the convolution of the image characteristics is X c (1) ＝f(W c (1) *X c (0) +b c (1) )；
Wherein W c (1) Representing the weight of the convolution kernel, b c (1) Representing convolution offset, representing convolution operationF is a special convolution for ensuring that the output and input are the same size;
the mathematical model of the residual error unit is X c (l+1) ＝X c (l) +F(X c (l) ；θ c (l) ),l＝1,2,...,L
As shown in fig. 4, where F is the residual equation, combined by two relus and convolution; theta c (l) All parameters needing to be learned of the first layer are contained;
obtaining a predicted interference type X c (L+1) Output by the conv output layer;
the output predicted value is normalized by the hyperbolic tangent function tanh and then is positioned in an interval of [ -1,1], and then the metric value of the predicted value and the true value is calculated by an optimization function MinimizLoss, namely:
Figure GDA0003733960800000061
wherein X t In order to be a matrix of predicted values,
Figure GDA0003733960800000062
is a true value matrix;
and S6, updating the grid thermodynamic diagram and an interference experience library according to the predicted interference type and the result of on-site investigation and processing, and optimizing the interference prediction model.
Example 2
As shown in fig. 5, the system for monitoring interference of a base station based on waveform analysis and deep learning includes:
the data acquisition module 1 is used for acquiring data required by interference monitoring of the LTE system;
the high uplink interference cell screening module 2 is used for screening out the high uplink interference cell according to the acquired network management data;
an interference wave type primary matching module 3, configured to perform primary matching on the interference wave type of the high uplink interference cell by using similarity, and mark a base station fault;
the grid thermodynamic diagram building module 4 is used for feeding back the interference wave type obtained by primary matching to the grid in a thermodynamic mode according to the GPS position of the base station to obtain a grid thermodynamic diagram;
the interference prediction model building module 5 is used for building an interference prediction model based on a deep neural network, the input of the interference prediction model is a grid thermodynamic diagram, and the output of the interference prediction model is the predicted interference type of the high uplink interference cell;
and the interference optimization module 6 is used for updating the grid thermodynamic diagram and an interference experience base according to the predicted interference type and the results of field investigation and processing, and optimizing the interference prediction model.
The terms describing positional relationships in the drawings are for illustrative purposes only and are not to be construed as limiting the patent;
it should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.

Claims (8)

1. The base station interference monitoring method based on waveform analysis and deep learning is characterized by comprising the following steps of:
s1, collecting data required by interference monitoring of an LTE system;
s2, screening out a high uplink interference cell according to the acquired network management data;
s3, carrying out primary matching on the interference wave types of the high uplink interference cells by utilizing the similarity, and marking the base station faults; the step S3 specifically includes the following steps:
s31, calculating the shortest algorithm distance between the given waveform in the high uplink interference cell and the matched waveform in a preset interference experience library;
s32, performing ascending sequencing on the calculated shortest algorithm distances, selecting the matchable waveform types corresponding to the first N shortest algorithm distances as the primary matched interference wave types of the high uplink interference cell, and marking the base station faults;
s4, feeding back the interference wave type obtained by primary matching to the grid in a thermal form according to the GPS position of the base station to obtain a grid thermodynamic diagram;
s5, establishing an interference prediction model based on a deep neural network, wherein the input of the interference prediction model is a grid thermodynamic diagram, and the output of the interference prediction model is a predicted interference type of the high uplink interference cell;
and S6, updating the grid thermodynamic diagram and an interference experience library according to the predicted interference type and the result of on-site investigation and processing, and optimizing the interference prediction model.
2. The base station interference monitoring method based on waveform analysis and deep learning of claim 1, wherein the data in step S1 includes XDR information, network management information, and 4G LTE engineering parameter information.
3. The method for monitoring interference of base station based on waveform analysis and deep learning according to claim 1, wherein the method for calculating the shortest algorithm distance in step S31 is as follows:
let a be any real number, calculate the minimum value of the solution formula, i.e.
Figure FDA0003733960790000011
The minimum value of (d);
wherein j =1,2, 3.., 100, which is the PRB value; x denotes a given waveform, x j For the jth data in a given waveform; y is i The identification of a waveform that can be matched,
Figure FDA0003733960790000012
is the jth data in the ith matchable waveform; wherein a is for eliminating control translation zoneThe difference from the previous;
and expanding the solving formula:
Figure FDA0003733960790000021
the minimum value of the formula solved by the matching method is:
Figure FDA0003733960790000022
4. the method for monitoring interference of a base station based on waveform analysis and deep learning according to claim 1, wherein the step S4 specifically comprises: expressing different interference wave types on the grid in different colors in the initially matched interference wave types obtained in the step S3, and setting color depth according to the interference wave influence range to obtain a grid thermodynamic diagram; wherein the latitude and longitude values of the base station form the vertices of the grid.
5. The base station interference monitoring method based on waveform analysis and deep learning of claim 1, wherein the interference prediction model based on the deep neural network of step S5 comprises a conv convolution unit, M residual error units, and a conv output layer which are connected in sequence; wherein the conv input layer is used for extracting the image features of the grid thermodynamic diagram, and the convolution of the image features is X c (1) ＝f(W c (1) *X c (0) +b c (1) )；
Wherein W c (1) Representing the weight of the convolution kernel, b c (1) Representing convolution bias, representing convolution operation, and f is special convolution and is used for ensuring that output and input have the same size;
the mathematical model of the residual error unit is X c (l+1) ＝X c (l) +F(X c (l) ；θ c (l) ),l＝1,2,...,L
Wherein F isResidual equation, θ c (l) All parameters needing to be learned in the first layer are contained;
obtaining a predicted interference type X c (L+1) And outputting by a conv output layer.
6. The base station interference monitoring method based on waveform analysis and deep learning of claim 5, wherein a hyperbola tangent function tanh and an optimization function MinimizLoss are further connected behind a conv output layer of the interference prediction model; the hyperbolic tangent function tanh is used for standardizing the predicted value output by the conv output layer, and the optimization function MinimizLoss is used for calculating the metric value of the predicted value and the true value output by the interference prediction model, namely:
Figure FDA0003733960790000023
wherein X t In order to be a matrix of predicted values,
Figure FDA0003733960790000024
is a true value matrix.
7. The method of claim 6, wherein the predicted value is located in an interval of [ -1,1] after being normalized by the hyperbolic tangent function tanh.
8. The system for monitoring the base station interference based on the waveform analysis and the deep learning according to any one of claims 1 to 7, characterized by comprising:
the data acquisition module is used for acquiring data required by interference monitoring of the LTE system;
the high uplink interference cell screening module is used for screening out the high uplink interference cell according to the acquired network management data;
the interference wave type primary matching module is used for carrying out primary matching on the interference wave types of the high uplink interference cells by utilizing similarity and marking base station faults;
the grid thermodynamic diagram building module is used for feeding back the interference wave type obtained by primary matching to a grid in a thermodynamic mode according to the GPS position of the base station to obtain a grid thermodynamic diagram;
the interference prediction model building module is used for building an interference prediction model based on a deep neural network, the input of the interference prediction model is a grid thermodynamic diagram, and the output of the interference prediction model is the predicted interference type of the high uplink interference cell;
and the interference optimization module is used for updating the grid thermodynamic diagram and the interference experience base according to the predicted interference type and the result of on-site investigation and processing, and optimizing the interference prediction model.
CN201911102563.0A 2019-11-12 2019-11-12 Base station interference monitoring method and system based on waveform analysis and deep learning Active CN110944354B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911102563.0A CN110944354B (en) 2019-11-12 2019-11-12 Base station interference monitoring method and system based on waveform analysis and deep learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911102563.0A CN110944354B (en) 2019-11-12 2019-11-12 Base station interference monitoring method and system based on waveform analysis and deep learning

Publications (2)

Publication Number Publication Date
CN110944354A CN110944354A (en) 2020-03-31
CN110944354B true CN110944354B (en) 2022-10-04

Family

ID=69906827

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911102563.0A Active CN110944354B (en) 2019-11-12 2019-11-12 Base station interference monitoring method and system based on waveform analysis and deep learning

Country Status (1)

Country Link
CN (1) CN110944354B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111934810B (en) * 2020-06-28 2022-08-16 广州市贝讯通信技术有限公司 Method and device for determining cell interference type and interference cell
CN111835454B (en) * 2020-07-09 2021-03-19 北京中超伟业信息安全技术股份有限公司 Environment identification method and system for cellular network electromagnetic interference system

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105744551B (en) * 2016-03-01 2019-07-02 浪潮天元通信信息系统有限公司 A kind of automatic investigation method of wireless network interference based on pattern-recognition
US10321344B2 (en) * 2017-02-17 2019-06-11 Cisco Technology, Inc. System and method to facilitate troubleshooting and predicting application performance in wireless networks
CN109302262B (en) * 2018-09-27 2020-07-10 电子科技大学 Communication anti-interference method based on depth determination gradient reinforcement learning
CN109376969A (en) * 2018-12-14 2019-02-22 中南大学 City fining population distribution dynamic prediction method and device based on deep learning
CN109756911B (en) * 2019-01-31 2020-11-27 腾讯科技（深圳）有限公司 Network quality prediction method, service adjustment method, related device and storage medium

Also Published As

Publication number Publication date
CN110944354A (en) 2020-03-31

Similar Documents

Publication Publication Date Title
US11740274B2 (en) Phase identification in power distribution systems
CN106643765B (en) Method for calculating acquisition abnormal maintenance time length
Ficco et al. Calibrating indoor positioning systems with low efforts
CN110418354A (en) It is a kind of that propagation model wireless network planning method is exempted from based on machine learning
CN110944354B (en) Base station interference monitoring method and system based on waveform analysis and deep learning
CN104618045B (en) Collected data-based wireless channel transmission model establishing method and system
CN104834017A (en) Positioning method for hazardous gas leakage diffusion accident source
CN105049141A (en) Analysis method for interference relation among signals based on multidimensional interference space model
CN107194565B (en) Power grid scheduling optimization method and system based on cloud decision
Wu et al. 3D spectrum mapping based on ROI-driven UAV deployment
CN112612000B (en) Intelligent configuration platform suitable for rapidly laying UWB positioning system
CN104038901A (en) Indoor positioning method for reducing fingerprint data acquisition workload
KR20130076406A (en) Apparatus and method for estimating location using log data
CN104540221A (en) WLAN indoor positioning method based on semi-supervised SDE algorithm
CN111866912B (en) Time-space based traffic volume region classification and analysis method
CN108834041B (en) Indoor position fingerprint positioning Radio Map establishing method based on tensor reconstruction
CN113239764A (en) Unmanned aerial vehicle inspection image preprocessing method for power transmission line
Liang et al. Mobile traffic prediction based on densely connected CNN for cellular networks in highway scenarios
KR101655086B1 (en) method for selecting optimal position of DCU
CN110231665B (en) Strapdown aviation gravity measurement precision evaluation method based on repetition line
KR101586568B1 (en) Planning method of stereo CCTV for 3D map construcing and apparatus thereof
US9473948B2 (en) Method and apparatus for analyzing pilot pollution
CN113673809A (en) Shared energy storage system-oriented five-stage coordinated optimization scheduling control method and system
CN117498551B (en) Intelligent inspection management and control system for transformer substation
Almeida et al. Collaborative wind power forecast

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant