CN108989129A - A kind of device and method based on the storage of network big data, acquisition and analysis - Google Patents
A kind of device and method based on the storage of network big data, acquisition and analysis Download PDFInfo
- Publication number
- CN108989129A CN108989129A CN201810964091.9A CN201810964091A CN108989129A CN 108989129 A CN108989129 A CN 108989129A CN 201810964091 A CN201810964091 A CN 201810964091A CN 108989129 A CN108989129 A CN 108989129A
- Authority
- CN
- China
- Prior art keywords
- network
- wireless
- wireless aps
- wireless network
- data
- 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.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0677—Localisation of faults
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a kind of based on the storage of network big data, acquisition and the device analyzed, comprising: installation operating system, wireless network AP big data acquisition management software, wireless network AP failure predication diagnostic software, wireless network AP resource reclaim release software, wireless network AP user location services software and the wireless network secure management software of device host and installation inside it；Also disclose acquisition and storage method, wireless network intelligent O&M method, wireless network AP resource reclaim method for releasing and wireless network secure judgment method based on the present apparatus.The present invention has the advantages that having autonomous performance strong, the high advantage of stability has high adaptability safety and scalability.Be able to satisfy school, government bodies, market, tourist attractions demand, improve the utilization rate of source material, improve the construction of smart city level.
Description
Technical field
The present invention relates to network big data technical fields, in particular to a kind of to be stored, acquired and divided based on network big data
The device and method of analysis.
Background technique
As user is higher and higher using the frequency of wireless WiFi, so that as school, government bodies, quotient in subrange
Field, tourist attractions etc. dispose AP quantity it is more and more, the data volume got using AP is increasing, especially flow of the people compared with
Big school, market, tourist attractions.Single AP available to several hundred reported datas per minute, under normal circumstances,
School, government bodies, market, tourist attractions installation AP quantity can reach several hundred or even thousands of.These AP are per minute, every
Hour, the data volume that can get daily be it is very huge, consequent is the exacerbation of maintenance task and mentioning for protection level
Height is unable to satisfy O&M demand by pure artificial mode completely.The centralization of wireless device, intelligent operation management research
It is extremely urgent.The information obtained using big data platform combination artificial intelligence means analysis wireless aps then can be very good to solve fortune
Dimension with service two fold problem, can intelligent management O&M wireless network and be each wireless network user
More preferable more efficient service is provided.Wireless aps big data technology is combined with artificial intelligence and is not only able to satisfy various wireless services
Requirement, more realize the fusion of new and old technology, be able to satisfy school, government bodies, market, tourist attractions demand, improve
The utilization rate of source material improves the construction of smart city level.Therefore the present invention will with the intellectual analysis of failure, position positioning,
Wireless aps resource management provides more aid decisions and support hand as breach, for the daily O&M of cordless communication network
Section, also provides positioning analysis decision, energy-saving and emission-reduction, wireless network secure, optimization in combination with big data for wireless network user
The service such as environmental resource.
Single AP available to several hundred reported datas per minute, under normal circumstances, school, government bodies, a quotient
The quantity that AP is installed in field, tourist attractions can reach several hundred or even thousands of.These AP can be obtained per minute, per hour, daily
The data volume got be it is very huge, consequent is the exacerbation of maintenance task and the raising of protection level, government of school machine
Pass, market, tourist attractions and building for enterprise-level wireless network generally use " AC+AP " this mode, to guarantee enterprise wireless
The normal operation of network, it is necessary to ensure that the round-the-clock stabilization of AC and AP is efficiently run, if only manually going to be monitored, work
It is inconceivable as amount.Wireless network maintenance personnel is usually busy with the monitoring and processing of wide variety of conventional alarm, and limited technical ability
Level can not often analyze wireless various hidden danger in time, can not also eliminate problem in budding state.Due to wireless network
Excessively huge wireless network secure hidden danger can not find that wireless network is caused to be paralysed in time, a large amount of human factor and manpower bottleneck
The fault time for resulting in wireless network is longer, and business recovery is slower, and overall quality of service is relatively low.The shortcomings that above-mentioned prior art
It is: (1) since wireless aps enormous amount staff can not be managed collectively (i.e. wireless network to wireless network AP resource
The recycling and release of AP resource).(2) since wireless aps enormous amount investment manpower and material resources maintenance cost is high.(3) wireless aps failure
It can not be prejudged in advance.(4) since wireless aps enormous amount searches the comparatively laborious a large amount of manpower and material resources of waste of malfunctioning node.
(5) can not issue early warning net safety problem to security risk, security breaches existing for wireless network and in time leads to wireless network
Network paralysis.(6) continuous collecting storage and analysis can not be carried out to wireless network data causes wireless network data to be lost.
Summary of the invention
The present invention in view of the drawbacks of the prior art, provides a kind of dress based on the storage of network big data, acquisition and analysis
It sets and method, can effectively solve the above-mentioned problems of the prior art.
In order to realize the above goal of the invention, the technical solution adopted by the present invention is as follows:
A kind of device based on the storage of network big data, acquisition and analysis, comprising: crust of the device；
Liquid crystal display, network interface A, network interface B, equipment debugging interface, a upper note is arranged in described device case nose
Record button and next record button.
Liquid crystal display is for showing equipment state and information
Network interface A facilitates administrator to use for connecting client computer；
Network interface B is for spare, when network interface A breaks down with network interface B connection；
Equipment debugging interface is used to carry out information configuration to device；
A upper record button is used to show the state of a recording equipment；
Next record button is used to show the state of next recording equipment.
Power interface, UPS interface, network module A and network module B is arranged in described device outer casing back；
Power interface is for connecting alternating current as present apparatus power supply；
UPS interface is for connecting ups power；
Network module A connects backstage big data storage platform for this network module, is responsible for storage wireless network big data；
Network module B is responsible for the acquisition of wireless network big data for connecting wireless network AC and switch device.
CPU processor, RAM memory, ROM memory, flash storage, network interface mould are equipped with inside crust of the device
Block, neural network framework and to install operating system, wireless network AP big data acquisition management software, wireless network AP failure pre-
Survey diagnostic software, wireless network AP resource reclaim release software, wireless network AP user location services software and wireless network peace
Full management software；
CPU processor: central processing unit；
RAM memory: mainly running gear is interim, is equivalent to calculator memory；
ROM memory: for the starting and maintenance of system, it is equivalent to computer BIOS；
Flash storage: some temporary files are stored and are equivalent to hard disc of computer；
Network Interface Module: 10,000,000,000 network interface of gigabit (RJ45) either optical fiber interface is provided；
Liquid crystal display: for showing equipment state and information；
Operating system: the hardware for management equipment；
Neural network framework: integrated Tensorflow and Keras neural network algorithm and model；
Wireless network AP big data acquisition management software: it is responsible for the acquisition of wireless network big data and manages the data of acquisition
It stores in Hadoop platform；
Wireless network AP failure predication diagnostic software: diagnosis and failure are carried out to wireless network AP equipment by neural network
Prediction；
Wireless network AP resource reclaim release software: recycling and release by neural network to wireless network AP resource；
Wireless network AP user location services software: responsible to the customer quantity statistics of wireless network AP connection and position
Service；
Wireless network secure management software: it is carried out by network security of the big data combination neural network to wireless network AP
Prediction and analysis.
Apparatus of the present invention are examined by network connecting radio network wireless controller (AC), access-layer switch, internet behavior
Meter carries out the acquisition of wireless network big data and storage, and Hadoop big data platform is arrived in storage.
Acquisition and storage method based on apparatus of the present invention, include the following steps:
Step 1: passing through Network Interface Module B connection radio network controller AC；
Step 2: successful connection, successful connection to step are judged whether by wireless network AP big data acquisition management software
3, otherwise return step 1；
Step 3: wireless network AP data being acquired by Telnet agreement, wireless aps user is acquired by behavior auditing equipment
Flow acquires access switch wireless aps port flow；
Step 4: by wireless network AP big data acquisition management software by collected data, acquire data format A and
Acquire data format B；Specifically:
Acquisition data format A includes: acquisition time, wireless aps number, wireless aps SN coding, wireless aps name, wireless aps
Position, wireless aps model, wireless aps MAC Address, connection wireless aps number of users, wireless aps SSID, wireless aps data traffic,
Wireless aps cpu frequency；
Acquisition data format B includes: acquisition time, wireless aps number, wireless aps SN is encoded, wireless aps are named, wireless
The address APMAC, connection wireless aps user's MAC address, connection wireless aps ID users, wireless aps SSID, wireless aps number of users
According to flow.
Step 5 is stored data format A and data format B to Hadoop big data platform by Network Interface Module A；
Step 6: return step 3 executes downwards continuous circle collection.
Wireless network intelligent O&M method based on apparatus of the present invention, includes the following steps:
Step 1: acquisition wireless aps data, data format C are as follows: the time, wireless aps cpu frequency, connects wireless aps data traffic
Connect wireless aps number of users；Data are sent into step 2.
Step 2: logistic regression network mould is used by machine learning algorithm in wireless network AP failure predication diagnostic software
Type judges wireless aps with the presence or absence of potential faults, and fault-free hidden danger return step 1, there are potential faults to step 3.
Step 3: the wireless network big data in Hadoop big data platform being analyzed using Apache Spark.Knot
Fruit is sent into step 4.
Step 4: logistic regression is used by machine learning algorithm in present apparatus wireless network AP failure predication diagnostic software
Network model judges that wireless aps are hardware fault or software fault, hardware fault to step 5, software fault to step 6
Step 5: administrator solves failure.Failure is solved to step 7.
Step 6: restarting wireless aps, failure solution to step 7, failure do not solve step 5.
Step 7: failure solves return step 1.
Wireless network AP resource reclaim method for releasing based on apparatus of the present invention, includes the following steps:
Step 1: acquisition data, data format D includes: time, wireless aps number, wireless aps position, adjacent wireless aps 1
It sets, 2 position of adjacent wireless aps, 1 data traffic of adjacent wireless aps, 2 data traffic of adjacent wireless aps, wireless aps data traffic；
Step 2: data feeding BP neural network model is judged whether that recycling wireless aps resource still discharges wireless aps money
Source.It is recovered to step 3 and is discharged into step 4；
Step 3: wireless aps power supply recycling wireless network AP resource: being closed by radio network controller (AC).Return to step
Rapid 1；
Step 4: wireless aps power supply release wireless aps resource: being opened by radio network controller (AC).Return step 1.
Wireless network secure judgment method based on apparatus of the present invention, includes the following steps:
Step 1: acquisition data, data format N { time, wireless aps position, wireless aps data traffic, wireless aps CPU frequency
Rate, connection wireless aps number of users wherein N be wireless aps number (all wireless aps data), by data be sent into step 2.
Step 2: collected institute's wireless network AP data feeding CNN (convolutional neural networks model) being identified, is known
Other result is without security risk return step 1, and there are security risks to step 3 for recognition result.
Step 3: carrying out analysis to the wireless network big data in Hadoop big data platform using Apache Spark will
Wireless aps number, wireless aps data traffic, wireless aps cpu frequency, the data knot for connecting results abnormity in wireless aps number of users
Fruit is sent into step 4.
Step 4: wireless network administrator solves wireless network secure hidden danger return step 1 by analysis result, does not solve
Certainly security risk return step 3 continues to analyze wireless network secure big data.
Compared with prior art the present invention has the advantages that having autonomous performance strong, control stability is high under adverse circumstances
The advantages of, especially in colleges and universities, the actual measurement of the lower development of the higher environment of market crowd density shows have in wireless network day
Beneficial complicated, network equipment AP type is increasingly various, high adaptability safety in the case that the portfolio of carrying is also increasing
Property and scalability.The present invention provides to the acquisition of wireless network big data, storage device and method.Utilize deep learning algorithm pair
Wireless network AP equipment fault carries out risk assessment and studies and judges with trend, realizes that wireless network AP equipment fault identification, trend are studied and judged
And wireless network AP equipment fault hidden danger is, it is envisioned that ensure the safe operation of wireless network fault-free.Pass through Hadoop big data platform
Wireless network big data is precisely matched, provides auxiliary reference for defect existing for wireless network, reduces Wireless Communication Equipment event
Barrier rate improves wireless device safety.Optimize wireless network by Hadoop big data platform, optimize Internet resources, predicts user
Security risk improves wireless network use environment.It improves user and uses wireless network satisfaction.Wireless network under big data driving
It is environmentally protective rationally to discharge recycling optimization wireless network energy-saving and emission-reduction to wireless network resource for network resource analysis decision model.It is logical
It crosses and security risk, security breaches existing for wireless network is found to wireless network big data analysis and issue early warning in time, reduce
The loss of wireless network secure bring provides big data support for wireless network secure.By wireless aps big data with Hadoop technology
The requirement for being not only able to satisfy various wireless services is combined, the fusion of new and old technology is more realized, is able to satisfy school, government's machine
The demand of pass, market, tourist attractions improves the utilization rate of source material, improves the construction of smart city level.
Detailed description of the invention
Fig. 1 is the device of that embodiment of the invention front-end architecture schematic diagram；
Fig. 2 is the device of that embodiment of the invention rear end structure schematic diagram；
Fig. 3 is the device of that embodiment of the invention schematic diagram of internal structure；
Fig. 4 is hardware connection diagram of the embodiment of the present invention；
Fig. 5 is that wireless network of embodiment of the present invention big data acquires Stored Procedure figure；
Fig. 6 is wireless network intelligent of embodiment of the present invention O&M method flow diagram；
Fig. 7 is wireless network of embodiment of the present invention AP resource reclaim method for releasing flow chart；
Fig. 8 is wireless network secure of embodiment of the present invention judgment method flow chart.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention more comprehensible, below in conjunction with attached drawing and embodiment is enumerated,
The present invention is described in further details.
A kind of device based on the storage of network big data, acquisition and analysis, comprising: crust of the device；
As shown in Figure 1, described device case nose setting liquid crystal display, network interface A, network interface B, equipment debugging connect
Mouth, a upper record button and next record button.
Liquid crystal display is for showing equipment state and information；
Network interface A facilitates administrator to use for connecting client computer；
Network interface B is for spare, when network interface A breaks down with network interface B connection；
Equipment debugging interface is used for: for carrying out information configuration such as to this equipment: software in IP address and equipment into
Row configuration initializes this equipment.Debugging initialization is carried out to equipment by this interface when this equipment delay machine；
A upper record button is used for: showing the state of the such as preceding 1 minute equipment of a upper record of liquid crystal display；
Next record button is used for: showing the state of the such as rear 1 minute equipment of next record of liquid crystal display.
As shown in Fig. 2, described device outer casing back setting power interface, UPS interface, network module A and network module B；
Power interface is for connecting alternating current as present apparatus power supply；
UPS interface is for connecting ups power；
Network module A connects backstage big data storage platform for this network module, is responsible for storage wireless network big data；
Network module B is responsible for the acquisition of wireless network big data for connecting wireless network AC and switch device.
As shown in figure 3, crust of the device inside be equipped with CPU processor, RAM memory, ROM memory, flash storage,
Network Interface Module, neural network framework simultaneously install operating system, wireless network AP big data acquisition management software, wireless network
Network AP failure predication diagnostic software, wireless network AP resource reclaim release software, wireless network AP user location services software and
Wireless network secure management software；
CPU processor: central processing unit；
RAM memory: mainly running gear is interim, is equivalent to calculator memory；
ROM memory: for the starting and maintenance of system, it is equivalent to computer BIOS；
Flash storage: some temporary files are stored and are equivalent to hard disc of computer；
Network Interface Module: 10,000,000,000 network interface of gigabit (RJ45) either optical fiber interface is provided；
Liquid crystal display: for showing equipment state and information；
Operating system: the hardware for management equipment；
Neural network framework: integrated Tensorflow and Keras neural network algorithm and model；
Wireless network AP big data acquisition management software: it is responsible for the acquisition of wireless network big data and manages the data of acquisition
It stores in Hadoop platform；
Wireless network AP failure predication diagnostic software: diagnosis and failure are carried out to wireless network AP equipment by neural network
Prediction；
Wireless network AP resource reclaim release software: recycling and release by neural network to wireless network AP resource；
Wireless network AP user location services software: responsible to the customer quantity statistics of wireless network AP connection and position
Service；
Wireless network secure management software: it is carried out by network security of the big data combination neural network to wireless network AP
Prediction and analysis.
As shown in figure 4, apparatus of the present invention by network connecting radio network wireless controller (AC), access-layer switch,
Internet behavior audit carries out the acquisition of wireless network big data and storage, and Hadoop big data platform is arrived in storage.
Acquisition and storage method based on apparatus of the present invention, process are as shown in Figure 5；
Step 1: passing through the Network Interface Module B connection radio network controller AC of the present apparatus；
Step 2: successful connection, successful connection are judged whether by present apparatus wireless network AP big data acquisition management software
To step 3, otherwise return step 1；
Step 3: wireless network AP data being acquired by Telnet agreement, wireless aps user is acquired by behavior auditing equipment
Flow acquires access switch wireless aps port flow；
Step 4: by present apparatus wireless network AP big data acquisition management software by collected data preparation at as follows
Data format:
Acquisition data format A includes: acquisition time, wireless aps number, wireless aps SN coding, wireless aps name, wireless aps
Position, wireless aps model, wireless aps MAC Address, connection wireless aps number of users, wireless aps SSID, wireless aps data traffic,
Wireless aps cpu frequency；
Acquisition data format B includes: acquisition time, wireless aps number, wireless aps SN is encoded, wireless aps are named, wireless
The address APMAC, connection wireless aps user's MAC address, connection wireless aps ID users, wireless aps SSID, wireless aps number of users
According to flow.
Step 5 is stored data format A and data format B to the big number of Hadoop by the Network Interface Module A of the present apparatus
According to platform；
Step 6: return step 3 executes downwards continuous circle collection.
Wireless network intelligent O&M method based on apparatus of the present invention, process are as shown in Figure 6；
Step 1: acquisition wireless aps data, data format C are as follows: the time, wireless aps cpu frequency, connects wireless aps data traffic
Connect wireless aps number of users；Data are sent into step 2.
Step 2: logistic regression is used by machine learning algorithm in present apparatus wireless network AP failure predication diagnostic software
Network model judges wireless aps with the presence or absence of potential faults, and fault-free hidden danger return step 1, there are potential faults to step 3.
Step 3: the wireless network big data in Hadoop big data platform being analyzed using Apache Spark.Knot
Fruit is sent into step 4.
Step 4: logistic regression is used by machine learning algorithm in present apparatus wireless network AP failure predication diagnostic software
Network model judges that wireless aps are hardware fault or software fault, hardware fault to step 5, software fault to step 6
Step 5: administrator solves failure.Failure is solved to step 7.
Step 6: restarting wireless aps, failure solution to step 7, failure do not solve step 5.
Step 7: failure solves return step 1.
Wireless network AP resource reclaim method for releasing based on apparatus of the present invention, process are as shown in Figure 7；
Step 1: acquisition data, data format D includes: time, wireless aps number, wireless aps position, adjacent wireless aps 1
It sets, 2 position of adjacent wireless aps, 1 data traffic of adjacent wireless aps, 2 data traffic of adjacent wireless aps, wireless aps data traffic；
Step 2: data feeding BP neural network model is judged whether that recycling wireless aps resource still discharges wireless aps money
Source.It is recovered to step 3 and is discharged into step 4；
Step 3: wireless aps power supply recycling wireless network AP resource: being closed by radio network controller (AC).Return to step
Rapid 1；
Step 4: wireless aps power supply release wireless aps resource: being opened by radio network controller (AC).Return step 1.
Wireless network secure judgment method based on apparatus of the present invention, process are as shown in Figure 8；
Step 1: acquisition data, data format N { time, wireless aps position, wireless aps data traffic, wireless aps CPU frequency
Rate, connection wireless aps number of users wherein N be wireless aps number (all wireless aps data), by data be sent into step 2.
Step 2: collected institute's wireless network AP data feeding CNN (convolutional neural networks model) being identified, is known
Other result is without security risk return step 1, and there are security risks to step 3 for recognition result.
Step 3: carrying out analysis to the wireless network big data in Hadoop big data platform using Apache Spark will
Wireless aps number, wireless aps data traffic, wireless aps cpu frequency, the data knot for connecting results abnormity in wireless aps number of users
Fruit is sent into step 4.
Step 4: wireless network administrator solves wireless network secure hidden danger return step 1 by analysis result, does not solve
Certainly security risk return step 3 continues to analyze wireless network secure big data.
Those of ordinary skill in the art will understand that the embodiments described herein, which is to help reader, understands this hair
Bright implementation method, it should be understood that protection scope of the present invention is not limited to such specific embodiments and embodiments.Ability
The those of ordinary skill in domain disclosed the technical disclosures can make its various for not departing from essence of the invention according to the present invention
Its various specific variations and combinations, these variations and combinations are still within the scope of the present invention.
Claims (5)
1. a kind of device based on the storage of network big data, acquisition and analysis characterized by comprising crust of the device；
Described device case nose setting liquid crystal display, network interface A, network interface B, equipment debugging interface, a upper record are pressed
Button and next record button；
Liquid crystal display is for showing equipment state and information；
Network interface A facilitates administrator to use for connecting client computer；
Network interface B is for spare, when network interface A breaks down with network interface B connection；
Equipment debugging interface is used to carry out information configuration to device；
A upper record button is used to show the state of a recording equipment；
Next record button is used to show the state of next recording equipment；
Power interface, UPS interface, network module A and network module B is arranged in described device outer casing back；
Power interface is for connecting alternating current as present apparatus power supply；
UPS interface is for connecting ups power；
Network module A connects backstage big data storage platform for this network module, is responsible for storage wireless network big data；
Network module B is responsible for the acquisition of wireless network big data for connecting wireless network AC and switch device；
CPU processor, RAM memory, ROM memory, flash storage, Network Interface Module, mind are equipped with inside crust of the device
Through network frame and operating system, wireless network AP big data acquisition management software, the diagnosis of wireless network AP failure predication are installed
Software, wireless network AP resource reclaim release software, wireless network AP user location services software and wireless network secure management
Software；
CPU processor: central processing unit；
RAM memory: mainly running gear is interim, is equivalent to calculator memory；
ROM memory: for the starting and maintenance of system, it is equivalent to computer BIOS；
Flash storage: some temporary files are stored and are equivalent to hard disc of computer；
Network Interface Module: 10,000,000,000 network interface of gigabit (RJ45) either optical fiber interface is provided；
Liquid crystal display: for showing equipment state and information；
Operating system: the hardware for management equipment；
Neural network framework: integrated Tensorflow and Keras neural network algorithm and model；
Wireless network AP big data acquisition management software: it is responsible for the acquisition of wireless network big data and manages to store the data of acquisition
To in Hadoop platform；
Wireless network AP failure predication diagnostic software: diagnosis is carried out to wireless network AP equipment by neural network and failure is pre-
It surveys；
Wireless network AP resource reclaim release software: recycling and release by neural network to wireless network AP resource；
Wireless network AP user location services software: responsible that the customer quantity statistics of wireless network AP connection and position are taken
Business；
Wireless network secure management software: it is predicted by network security of the big data combination neural network to wireless network AP
And analysis；
Apparatus of the present invention by network connecting radio network wireless controller (AC), access-layer switch, internet behavior audit into
Hadoop big data platform is arrived in the acquisition of row wireless network big data and storage, storage.
2. the acquisition and storage method of device according to claim 1, which comprises the steps of:
Step 1: passing through Network Interface Module B connection radio network controller AC；
Step 2: judging whether that successful connection, successful connection to step 3 are no by wireless network AP big data acquisition management software
Then return step 1；
Step 3: wireless network AP data being acquired by Telnet agreement, wireless aps user stream is acquired by behavior auditing equipment
Amount acquires access switch wireless aps port flow；
Step 4: by wireless network AP big data acquisition management software by collected data, acquiring data format A and acquisition
Data format B；Specifically:
Acquisition data format A include: acquisition time, wireless aps number, wireless aps SN coding, wireless aps name, wireless aps position,
It is wireless aps model, wireless aps MAC Address, connection wireless aps number of users, wireless aps SSID, wireless aps data traffic, wireless
APCPU frequency；
Acquisition data format B includes: acquisition time, wireless aps number, wireless aps SN coding, wireless aps name, wireless aps MAC
Location, connection wireless aps user's MAC address, connection wireless aps ID users, wireless aps SSID, wireless aps user data traffic；
Step 5 is stored data format A and data format B to Hadoop big data platform by Network Interface Module A；
Step 6: return step 3 executes downwards continuous circle collection.
3. the wireless network intelligent O&M method of device according to claim 1, which comprises the steps of:
Step 1: acquisition wireless aps data, data format C are as follows: time, wireless aps data traffic, wireless aps cpu frequency, connection nothing
Line AP number of users；Data are sent into step 2；
Step 2: being sentenced by machine learning algorithm in wireless network AP failure predication diagnostic software using logistic regression network model
Disconnected wireless aps whether there is potential faults, and fault-free hidden danger return step 1, there are potential faults to step 3；
Step 3: the wireless network big data in Hadoop big data platform being analyzed using Apache Spark, is as a result sent
Enter step 4；
Step 4: logistic regression network is used by machine learning algorithm in present apparatus wireless network AP failure predication diagnostic software
Model judges that wireless aps are hardware fault or software fault, hardware fault to step 5, software fault to step 6；
Step 5: administrator solves failure, and failure is solved to step 7；
Step 6: restarting wireless aps, failure solution to step 7, failure do not solve step 5；
Step 7: failure solves return step 1.
4. the wireless network AP resource reclaim method for releasing of device according to claim 1, which is characterized in that including walking as follows
It is rapid:
Step 1: acquisition data, data format D include: the time, wireless aps number, wireless aps position, 1 position of adjacent wireless aps,
Adjacent 2 position of wireless aps, 1 data traffic of adjacent wireless aps, 2 data traffic of adjacent wireless aps, wireless aps data traffic；
Step 2: data feeding BP neural network model is judged whether that recycling wireless aps resource still discharges wireless aps resource, returns
It receives step 3 and is discharged into step 4；
Step 3: wireless aps power supply, return step 1 recycling wireless network AP resource: being closed by radio network controller (AC)；
Step 4: wireless aps power supply release wireless aps resource: being opened by radio network controller (AC)；Return step 1.
5. the wireless network secure judgment method of device according to claim 1, which comprises the steps of:
Step 1: acquisition data, { time, wireless aps data traffic, wireless aps cpu frequency, connects wireless aps position data format N
Connect wireless aps number of users } wherein N be wireless aps number (all wireless aps data), by data be sent into step 2；
Step 2: collected institute's wireless network AP data feeding CNN (convolutional neural networks model) being identified, identification knot
Fruit is without security risk return step 1, and there are security risks to step 3 for recognition result；
Step 3: being analyzed using Apache Spark the wireless network big data in Hadoop big data platform will be wireless
AP number, wireless aps data traffic, wireless aps cpu frequency, the data result of results abnormity is sent in connection wireless aps number of users
Enter step 4；
Step 4: wireless network administrator solves wireless network secure hidden danger return step 1 by analysis result, does not solve to pacify
Full hidden danger return step 3 continues to analyze wireless network secure big data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810964091.9A CN108989129A (en) | 2018-08-23 | 2018-08-23 | A kind of device and method based on the storage of network big data, acquisition and analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810964091.9A CN108989129A (en) | 2018-08-23 | 2018-08-23 | A kind of device and method based on the storage of network big data, acquisition and analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108989129A true CN108989129A (en) | 2018-12-11 |
Family
ID=64547733
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810964091.9A Pending CN108989129A (en) | 2018-08-23 | 2018-08-23 | A kind of device and method based on the storage of network big data, acquisition and analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108989129A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109819352A (en) * | 2019-01-28 | 2019-05-28 | 中国联合网络通信集团有限公司 | A kind of fiber data processing system framework and processing method |
| CN110188017A (en) * | 2019-05-28 | 2019-08-30 | 承德石油高等专科学校 | Network computer room server and network equipment big data acquisition device and method |
| CN112118331A (en) * | 2020-09-22 | 2020-12-22 | 贵州电网有限责任公司 | Network resource release acquisition method, device and system and electronic equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106817353A (en) * | 2015-11-30 | 2017-06-09 | 任子行网络技术股份有限公司 | For MAC collections and the wireless aps and method of network security audit |
| CN108199922A (en) * | 2018-01-11 | 2018-06-22 | 承德石油高等专科学校 | A kind of system and method for diagnosing and repairing for the network equipment and server failure |
-
2018
- 2018-08-23 CN CN201810964091.9A patent/CN108989129A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106817353A (en) * | 2015-11-30 | 2017-06-09 | 任子行网络技术股份有限公司 | For MAC collections and the wireless aps and method of network security audit |
| CN108199922A (en) * | 2018-01-11 | 2018-06-22 | 承德石油高等专科学校 | A kind of system and method for diagnosing and repairing for the network equipment and server failure |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109819352A (en) * | 2019-01-28 | 2019-05-28 | 中国联合网络通信集团有限公司 | A kind of fiber data processing system framework and processing method |
| CN109819352B (en) * | 2019-01-28 | 2021-12-07 | 中国联合网络通信集团有限公司 | Optical fiber data processing system architecture and processing method |
| CN110188017A (en) * | 2019-05-28 | 2019-08-30 | 承德石油高等专科学校 | Network computer room server and network equipment big data acquisition device and method |
| CN112118331A (en) * | 2020-09-22 | 2020-12-22 | 贵州电网有限责任公司 | Network resource release acquisition method, device and system and electronic equipment |
| CN112118331B (en) * | 2020-09-22 | 2023-01-10 | 贵州电网有限责任公司 | Network resource release acquisition method, device and system and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108591104B (en) | A kind of Research on Fan Fault Forecasting based on cloud platform and health management system arranged, method | |
| CN108989129A (en) | A kind of device and method based on the storage of network big data, acquisition and analysis | |
| CN107528832A (en) | Baseline structure and the unknown anomaly detection method of a kind of system-oriented daily record | |
| CN106780115A (en) | Abnormal electricity consumption monitoring and alignment system and method | |
| CN110175451A (en) | A kind of method for safety monitoring and system based on electric power cloud | |
| CN109299642A (en) | Logic based on Identification of Images is deployed to ensure effective monitoring and control of illegal activities early warning system and method | |
| CN108737182A (en) | The processing method and system of system exception | |
| CN103596208A (en) | Method and system for judging fault of network element | |
| CN104574557A (en) | Alarm-based site polling method, alarm-based site polling manipulation device and alarm-based site polling system | |
| CN110460454B (en) | Intelligent network equipment port fault prediction method based on deep learning | |
| CN107070680A (en) | A kind of intelligent operational system of IT information machine rooms and method | |
| CN109362235A (en) | Classify to the affairs at network accessible storage device | |
| CN101789899A (en) | Network service quality analysis method and system | |
| CN110162445A (en) | The host health assessment method and device of Intrusion Detection based on host log and performance indicator | |
| CN104574219A (en) | System and method for monitoring and early warning of operation conditions of power grid service information system | |
| CN115809183A (en) | Method for discovering and disposing information-creating terminal fault based on knowledge graph | |
| CN106375295B (en) | Data store monitoring method | |
| CN101710863B (en) | Method and system for restoring single board alarm | |
| CN106355490A (en) | Financial information sharing platform system | |
| CN112001443A (en) | Network behavior data monitoring method and device, storage medium and electronic equipment | |
| CN113505048A (en) | Unified monitoring platform based on application system portrait and implementation method | |
| CN107317708B (en) | Monitoring method and device for court business application system | |
| CN115424340A (en) | Method for identifying protective clothing based on YOLOV5 neural network technology | |
| CN115348080A (en) | Network equipment vulnerability comprehensive analysis system and method based on big data | |
| CN106372171B (en) | Monitor supervision platform real-time data processing method |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181211 |
|
| RJ01 | Rejection of invention patent application after publication |