CN110290071A - Method and system, cloud server and the monitoring device of network flow equilibrium adjustment - Google Patents
Method and system, cloud server and the monitoring device of network flow equilibrium adjustment Download PDFInfo
- Publication number
- CN110290071A CN110290071A CN201910673540.9A CN201910673540A CN110290071A CN 110290071 A CN110290071 A CN 110290071A CN 201910673540 A CN201910673540 A CN 201910673540A CN 110290071 A CN110290071 A CN 110290071A
- Authority
- CN
- China
- Prior art keywords
- flow
- equipment
- network
- optimal
- monitoring device
- 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
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0876—Network utilisation, e.g. volume of load or congestion level
- H04L43/0882—Utilisation of link capacity
-
- 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
- H04L43/16—Threshold monitoring
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/12—Avoiding congestion; Recovering from congestion
- H04L47/125—Avoiding congestion; Recovering from congestion by balancing the load, e.g. traffic engineering
-
- 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
Abstract
The application provides method and system, cloud server and the monitoring device of a kind of network flow equilibrium adjustment, which comprises receives the business datum that cloud business platform in edge is sent；According to the business datum and network depth model, the optimal flow assignment strategy of each equipment is determined；The optimal flow assignment strategy of each equipment is sent to monitoring device, so that the monitoring device is adjusted the flow of each equipment according to the optimal flow assignment strategy of each equipment.In the application, each equipment is not necessarily to server resets and manual intervention, is all automatically performed by system, in the premise for guaranteeing data complete and accurate, substantially increases the safety of the utilization rate and data of network flow, realizes the optimization collocation of network link.
Description
Technical field
The application belongs to data processing field, and in particular to method and system, the cloud service of network flow equilibrium adjustment
Device and monitoring device.
Background technique
Recently as the development of industry internet, 5G network, operator is to be advanced by leaps and bounds by demographic dividend decrease, the end 2C hurricane
Epoch terminate substantially, 2C development is slowed down, and the internet second half belongs to industry internet, and internet power-assisted industrial circle produces
It is worth huge.Operator will become emphasis in industrial plant edge cloud 5G network, and edge cloud in workshop distributes different according to different business
Network link flow, business carries out data transmission according to different network flows, but in transmitting, is bound to cause some networks
Load too high, some network links leave unused situation, and it is very unbalanced to often result in network link flow use.
Existing network link flow is relatively fixed, if multiple network links connect, certainly will will cause network flow
It measures used uneven, causes the waste of network flow.The problem of based on the waste of network link flow, although can manually more
Change each network flow, still, each service network link traffic volume is that dynamic adjusts, can not be thorough if fixed adjustment
Solve the problems, such as the waste of basic flow.And although existing flow is also adjustable, after adjustment, the service of each equipment
It must restart, modified flow could be allowed to come into force, the service of restarting certainly will will cause the loss of a certain amount of data, for life
Industry business has very big risk.
Summary of the invention
The application based on network link flow waste aiming at the problem that, although each network flow can be changed manually, be
Fixed adjustment can not thoroughly solve the problems, such as basic flow waste, and after adjustment, the service of each equipment must open again
It is dynamic, modified flow could be allowed to come into force, the problem of service of restarting will cause the loss of a certain amount of data, provide a kind of network flow
Method and system, cloud server and the monitoring device of the balanced adjustment of amount.
The application provides a kind of method of network flow equilibrium adjustment, comprising:
Receive the business datum that cloud business platform in edge is sent；
According to the business datum and network depth model, the optimal flow assignment strategy of each equipment is determined；
The optimal flow assignment strategy of each equipment is sent to monitoring device, so that the monitoring device is according to
The optimal flow assignment strategy of each equipment is adjusted the flow of each equipment.
Optionally, the method also includes:
Receive the flow adjustment result that the monitoring device is sent；
Adjust result and network depth model according to the flow, to the optimal flow assignment strategy of every kind of equipment into
Row updates；
The optimal flow assignment strategy of updated each equipment is sent to monitoring device so that the monitoring device according to
The optimal flow assignment strategy of updated each equipment is adjusted the flow of each equipment.
The application also provides a kind of method of network flow equilibrium adjustment characterized by comprising
The real-time traffic of each equipment is obtained using data, and institute is calculated using data according to the real-time traffic of each equipment
There is the average flow rate remaining proportion of equipment；
The optimal flow assignment strategy for each equipment that cloud server is sent is received, the optimal flow assignment strategy is institute
It states business datum that cloud server is sent according to edge cloud business platform and network depth model determines；
Judge whether the average flow rate remaining proportion of all devices is greater than first threshold；
If more than, then according to the network real-time traffic use data and each equipment optimal flow assignment strategy pair
The flow of each equipment is adjusted in network.
Optionally, the method also includes:
The flow of each equipment adjustment result is sent to the cloud server, so that the cloud server is according to respectively setting
Standby flow adjustment result updates the optimal flow assignment strategy of each equipment.
Optionally, the optimal flow assignment strategy of each equipment is each optimal machine allocation flow, described according to institute
Network real-time traffic is stated to carry out using flow of the optimal flow assignment strategy of data and each equipment to equipment each in network
Set-up procedure, comprising:
The flow utilization rate of each equipment is calculated using data according to the network real-time traffic, and according to the flow of each equipment
Utilization rate determines that flow utilization rate is greater than the equipment of second threshold less than the equipment and flow utilization rate of second threshold；
The flow that flow utilization rate is less than the equipment of second threshold is moved into flow utilization rate setting greater than second threshold
In standby, flow adjustment is obtained as a result, the flow that flow adjustment result is equipment adjusted is less than or equal to the equipment
Optimum allocation flow.
The application also provides a kind of cloud server, comprising:
First receiving module, for receiving the business datum of edge cloud business platform transmission；
Determining module, for determining the optimal flow assignment of each equipment according to the business datum and network depth model
Strategy；
First sending module, for the optimal flow assignment strategy of each equipment to be sent to monitoring device, so that institute
Monitoring device is stated to be adjusted the flow of each equipment according to the optimal flow assignment strategy of each equipment.
Optionally, the cloud server further include:
Second receiving module adjusts result for receiving the flow that the monitoring device is sent；
Update module, for adjusting result and network depth model according to the flow, to the optimal of every kind of equipment
Traffic distribution strategy is updated；
Second sending module, for the optimal flow assignment strategy of updated each equipment to be sent to monitoring device, with
It is adjusted the monitoring device to the flow of each equipment according to the optimal flow assignment strategy of updated each equipment.
The application also provides a kind of monitoring device, comprising:
Computing module, the real-time traffic for obtaining each equipment use data, and according to the real-time traffic of each equipment
The average flow rate remaining proportion of all devices is calculated using data；
Receiving module, the optimal flow assignment strategy of each equipment for receiving cloud server transmission, the optimal stream
Amount allocation strategy is that the business datum that the cloud server is sent according to edge cloud business platform and network depth model determine
Out；
Judgment module, for judging whether the average flow rate remaining proportion of all devices is greater than first threshold；
Flow adjustment module, for if more than then using data and each equipment according to the network real-time traffic
Optimal flow assignment strategy is adjusted the flow of equipment each in network.
Optionally, the monitoring device further include:
Sending module, for the flow adjustment result of each equipment to be sent to the cloud server, so that the cloud
Server adjusts the optimal flow assignment strategy that result updates each equipment according to the flow of each equipment.
Optionally, the flow adjustment module, comprising:
Determine submodule, for the flow utilization rate of each equipment to be calculated using data according to the network real-time traffic, and
Determine that flow utilization rate is less than the equipment of second threshold and flow utilization rate is greater than the second threshold according to the flow utilization rate of each equipment
The equipment of value；
Flow migrates submodule, moves to flow utilization for flow utilization rate to be less than to the flow of equipment of second threshold
Rate is greater than in the equipment of second threshold, obtains flow adjustment as a result, flow adjustment result is the flow of equipment adjusted
Less than or equal to the optimal machine allocation flow.
The application also provides a kind of system of network flow equilibrium adjustment, the system comprises: provided herein is upper
State cloud server and above-mentioned monitoring device provided herein.
The method of network flow equilibrium adjustment provided by the present application, each equipment are not necessarily to server resets and manual intervention, all
It is automatically performed by system, in the premise for guaranteeing data complete and accurate, substantially increases the utilization rate and data of network flow
Safety, realize the optimization collocation of network link.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the method for network flow equilibrium adjustment that the application first embodiment provides；
Fig. 2 is a kind of flow chart of the method for network flow equilibrium adjustment that the application second embodiment provides；
A kind of preferred embodiment of step S204 in Fig. 2 that Fig. 3 provides for the application second embodiment；
Fig. 4 is a kind of structural schematic diagram for cloud server that the application 3rd embodiment provides；
Fig. 5 is a kind of structural schematic diagram for monitoring device that the application fourth embodiment provides.
Specific embodiment
Technical solution in order to enable those skilled in the art to better understand the present invention, with reference to the accompanying drawing and specific embodiment party
Present invention is further described in detail for formula.
The application provides method and system, cloud server and the monitoring device of a kind of network flow equilibrium adjustment.Below
It is described in detail one by one respectively in connection with the attached drawing of embodiment provided by the present application.
The application is that the system based on network flow equilibrium adjustment is completed, and the system of network flow equilibrium adjustment includes cloud
Server and monitoring device are held, following is a brief introduction of the concrete operating principle of the system of the network flow equilibrium adjustment.In order to
Equilibrium adjustment network flow, the optimal flow assignment strategy of each equipment is determined by cloud server, by the optimal flux of each equipment
Allocation strategy shifts monitoring device onto, and monitoring device carries out data real time monitoring, and records the real-time service condition of network flow, monitors
Equipment can carry out network flow equilibrium allocation according to the real-time service condition of network flow and optimal flow assignment strategy.
Monitoring device: it is the equipment for carrying out the well-balanced adjustment for network link flow, and uses newest optimal flux
Allocation strategy adjusts traffic conditions all in all-network link in equipment room, edge cloud platform and cloud server monitoring equal
Weighing apparatus, including flow has been used, not used flow etc..
Cloud server: using the model algorithm of deep learning, according to different user types, user class, Yi Jixiang
The period answered carries out largely obtaining optimal flow assignment strategy, and transmitted in monitoring device with being originally trained
Carry out deployment operation.
In a preferred embodiment, the system of the network flow equilibrium adjustment further include:
Edge cloud equipment: main acquisition stores, the terminal of the network data of processing equipment.
Edge cloud business platform: referring to the equipment platform of each plant area, carries out for the data that edge cloud equipment is sent real-time
Acquisition and reception, and corresponding business processing is carried out, cloud server, which is sent, by certain data carries out model training.
A kind of method for network flow equilibrium adjustment that the application first embodiment provides is as follows:
The executing subject of the embodiment of the present application is cloud server, as shown in Figure 1, it illustrates the embodiment of the present application offers
A kind of network flow equilibrium adjustment method, include the following steps.
Step S101 receives the business datum that cloud business platform in edge is sent.
In this step, cloud server receives the business datum that cloud business platform in edge is sent.The business data packet
It includes user type, user class, the corresponding period, used flow, residual flow.
It is understood that before this step, edge cloud equipment (for example, camera) record is gone through using with part in real time
The network data (for example, having used flow, residual flow) that history uses, and it is assembled into device data to be sent, it is pushed to side
Edge cloud business platform.Edge cloud business platform carries out preliminary treatment to device data, will a large amount of newest industry according to business rule
Data-pushing be engaged in cloud server.That is, data of the edge cloud business platform real-time reception from edge cloud equipment, fast
Time series database in speed deposit platform, and by low delay communication network, construct machine learning/deep learning training data
Collection, the training dataset include user type, user class, the corresponding period, have used the data such as flow, residual flow.
Step S102 determines the optimal flow assignment strategy of each equipment according to the business datum and network depth model.
In this step, cloud server carries out learning training using network depth model, according to different user types, uses
Family rank, corresponding period have used flow and residual flow, carry out largely lasting model training and result feedback, really
The optimal flow assignment strategy of fixed each equipment.Specifically, can be directed to each equipment, according to user type, user class, it is corresponding when
Section has used flow, residual flow and user type, user class, the corresponding period, has used flow, residual flow respective
Each optimal machine allocation flow of weight calculation.
The optimal flow assignment strategy of each equipment is sent to monitoring device by step S103, so that the monitoring is set
It is standby that the flow of each equipment is adjusted according to the optimal flow assignment strategy of each equipment.
In this step, the optimal flow assignment strategy of each equipment is transmitted and is disposed in monitoring device
Operation, so that monitoring device is adjusted the flow of each equipment according to the optimal flow assignment strategy of each equipment.
Preferably, the method also includes:
Step a receives the flow adjustment result that the monitoring device is sent.
In this step, the optimal flow assignment strategy of each equipment sent in monitoring device according to cloud server is to each
After the flow of equipment is adjusted, flow adjustment result is sent to cloud server.
Step b adjusts result and network depth model according to the flow, to the optimal flow assignment of every kind of equipment
Strategy is updated.
In this step, cloud server adjusts result and network depth model according to the flow that monitoring device is sent, into
Largely lasting model training, iteration are updated, are updated to the optimal flow assignment strategy of every kind of equipment row.Flow adjustment knot
Used flow and unused flow including each equipment in fruit, cloud server according to pre-save user type, user
Rank, corresponding period and each equipment of newest collection using flow, flow is not used and network depth model recalculates
The optimal flow assignment strategy of updated each equipment.
The optimal flow assignment strategy of updated each equipment is sent to monitoring device by step c, so that the monitoring is set
It is standby that the flow of each equipment is adjusted according to the optimal flow assignment strategy of updated each equipment.
In this step, the optimal flow assignment strategy of the updated each equipment calculated is sent to by cloud server
Monitoring device, monitoring device are adjusted the flow of each equipment according to the optimal flow assignment strategy of updated each equipment.
Circulation executes above-mentioned steps a-c, and timing updates the network flow configuration of all devices between network, until all devices in network
Average flow rate remaining proportion be less than or equal to first threshold, that is, determine network in all devices network flow maximization make
With.First threshold can be not construed as limiting herein with sets itself, generally a lesser numerical value, such as 10%.
The method of network flow equilibrium adjustment provided by the present application, each equipment are not necessarily to server resets and manual intervention, all
It is automatically performed by system, in the premise for guaranteeing data complete and accurate, substantially increases the utilization rate and data of network flow
Safety, realize the optimization collocation of network link.
A kind of method for network flow equilibrium adjustment that the application second embodiment provides is as follows:
The executing subject of the embodiment of the present application is cloud server, as shown in Fig. 2, it illustrates the embodiment of the present application offers
A kind of network flow equilibrium adjustment method, include the following steps.
Step S201 is obtained the real-time traffic of each equipment and is used using data, and according to the real-time traffic of each equipment
The average flow rate remaining proportion of data calculating all devices.
In this step, the real-time traffic that monitoring device monitors each equipment in real time obtains each equipment using data
Used flow and unused flow, according to the stream for having used flow and each equipment of unused flow rate calculation of each equipment
Remaining proportion is measured, flow remaining proportion, which is equal to, is not used flow/(use flow+flow is not used), for example, No. 1 equipment,
Using flow 200, residue 800, then flow remaining proportion is equal to 800/ (200+800)=80%.Then according to each equipment
Flow remaining proportion calculates the average value of the flow remaining proportion of each equipment, is the average flow rate residue ratio of all devices
Example.
Step S202 receives the optimal flow assignment strategy for each equipment that cloud server is sent.
In this step, monitoring device receives the optimal flow assignment strategy for each equipment that cloud server is sent, described
The business datum and network depth model that optimal flow assignment strategy, which is cloud server, to be sent according to edge cloud business platform are true
It makes.Cloud server carries out learning training using network depth model, according to different user types, user class, corresponding
Period, used flow and residual flow, carry out largely lasting model training and result feedback, determine each equipment most
Excellent traffic distribution strategy.Specifically, each equipment can be directed to, according to user type, user class, the corresponding period, stream has been used
Amount, user class, the corresponding period, has respectively been set using flow, the respective weight calculation of residual flow residual flow and user type
Standby optimum allocation flow.
Step S203, judges whether the average flow rate remaining proportion of all devices is greater than first threshold, if so, holding
Row step S204；If it is not, process terminates.
In this step, monitoring device judges whether the average flow rate remaining proportion of all devices is greater than first threshold, if
It is greater than, illustrates that the network flow of all devices in network does not maximize use, needs to continue to adjust each equipment in network
Network flow is adjusted, and executes step S204；If being less than or equal to, the network flow of all devices in network is illustrated
It is used through maximizing, does not then need again to be adjusted the network flow of equipment each in network, process terminates.
Step S204 uses the optimal flow assignment strategy pair of data and each equipment according to the network real-time traffic
The flow of each equipment is adjusted in network.
Preferably, as shown in figure 3, the optimal flow assignment strategy of each equipment is each optimal machine allocation flow,
The step S204, according to the network real-time traffic using the optimal flow assignment strategy of data and each equipment to network
In the flow of each equipment be adjusted step, comprising:
Step S204-1, calculates the flow utilization rate of each equipment according to the network real-time traffic using data, and according to
The flow utilization rate of each equipment determines that flow utilization rate is less than the equipment of second threshold and flow utilization rate is greater than second threshold
Equipment.
In this step, when the average flow rate remaining proportion for judging all devices is greater than first threshold, then according to net
Network real-time traffic calculates the flow utilization rate of each equipment using data, i.e., has used flow and unused flow according to each equipment
Calculate the flow utilization rate of each equipment.Second threshold is an intermediate quantity, can be set to 50%, can be with sets itself, herein
It is not construed as limiting.Flow utilization rate is less than equipment, that is, lesser equipment of flow utilization rate of second threshold, and flow utilization rate is greater than the
The equipment of the two threshold values, that is, biggish equipment of flow utilization rate.Flow utilization rate, which is equal to, has used flow/(flow is used+do not make
With flow), for example, No. 1 equipment, used flow 200, residue 800, then flow utilization rate be equal to 200/ (200+800)=
20%.
The flow that flow utilization rate is less than the equipment of second threshold is moved to flow utilization rate and is greater than the by step S204-2
In the equipment of two threshold values, obtains flow and adjust result.
In this step, the flow for the equipment that flow utilization rate is less than second threshold is moved to flow and utilized by monitoring device
Greater than in the equipment of second threshold, i.e., moving to the flow of the lesser equipment of flow utilization rate, flow utilization rate is biggish to be set rate
In standby.It, need to be according to each equipment that cloud server is sent most and during monitoring device adjusts the flow of each equipment
Excellent traffic distribution strategy is adjusted, that is, is met the flow that flow adjustment result is equipment adjusted and be less than or equal to the equipment
Optimum allocation flow condition.
Preferably, the method also includes:
The flow adjustment result of each equipment is sent to the cloud server, so that the cloud server root by step d
The optimal flow assignment strategy of each equipment is updated according to the flow adjustment result of each equipment.
In this step, the optimal flow assignment strategy of each equipment sent in monitoring device according to cloud server is to each
After the flow of equipment is adjusted, flow adjustment result is sent to cloud server and carries out following model optimization, meanwhile, it will
The optimal flow assignment strategy for receiving updated each equipment that cloud server is sent, according to the optimal of updated each equipment
Each equipment of traffic distribution strategy real-time perfoming is optimized and revised, in order to which the maximization of network flow uses.Repeat step
Rapid S201- step S204, until judging that the average flow rate remaining proportion of all devices is less than or equal to first in step S203
When threshold value, process terminates, and illustrates that the network flow of each equipment in network has maximized use.Also, since monitoring device can
Data are used to monitor the real-time traffic of each equipment in real time, and recycles and balanced adjustment is carried out to the flow of each equipment, therefore is each
Equipment avoids the generation of event of data loss from service disruption/restart.
The method of network flow equilibrium adjustment provided by the present application, each equipment are not necessarily to server resets and manual intervention, all
It is automatically performed by system, in the premise for guaranteeing data complete and accurate, substantially increases the utilization rate and data of network flow
Safety, realize the optimization collocation of network link.
A kind of cloud server that the application 3rd embodiment provides is as follows:
As shown in figure 4, it illustrates a kind of structural schematic diagrams of cloud server provided by the embodiments of the present application, including with
Lower module.
First receiving module 11, for receiving the business datum of edge cloud business platform transmission；
Determining module 12, for determining the optimal flux point of each equipment according to the business datum and network depth model
With strategy；
First sending module 13, for the optimal flow assignment strategy of each equipment to be sent to monitoring device, so that
The monitoring device is adjusted the flow of each equipment according to the optimal flow assignment strategy of each equipment.
Preferably, the cloud server further include:
Second receiving module adjusts result for receiving the flow that the monitoring device is sent；
Update module, for adjusting result and network depth model according to the flow, to the optimal of every kind of equipment
Traffic distribution strategy is updated；
Second sending module, for the optimal flow assignment strategy of updated each equipment to be sent to monitoring device, with
It is adjusted the monitoring device to the flow of each equipment according to the optimal flow assignment strategy of updated each equipment.
A kind of cloud server that the application fourth embodiment provides is as follows:
As shown in figure 5, it illustrates a kind of structural schematic diagram of monitoring device provided by the embodiments of the present application, including it is following
Module.
Computing module 21, the real-time traffic for obtaining each equipment use data, and according to the real-time streams of each equipment
Amount calculates the average flow rate remaining proportion of all devices using data；
Receiving module 22, the optimal flow assignment strategy of each equipment for receiving cloud server transmission are described optimal
The business datum and network depth model that traffic distribution strategy, which is the cloud server, to be sent according to edge cloud business platform are true
It makes；
Judgment module 23, for judging whether the average flow rate remaining proportion of all devices is greater than first threshold；
Flow adjustment module 24 is used for if more than then data and each equipment is used according to the network real-time traffic
Optimal flow assignment strategy the flow of equipment each in network is adjusted.
Preferably, the monitoring device further include:
Sending module, for the flow adjustment result of each equipment to be sent to the cloud server, so that the cloud
Server adjusts the optimal flow assignment strategy that result updates each equipment according to the flow of each equipment.
Preferably, the flow adjustment module 24, comprising:
Determine submodule, for the flow utilization rate of each equipment to be calculated using data according to the network real-time traffic, and
Determine that flow utilization rate is less than the equipment of second threshold and flow utilization rate is greater than the second threshold according to the flow utilization rate of each equipment
The equipment of value；
Flow migrates submodule, moves to flow utilization for flow utilization rate to be less than to the flow of equipment of second threshold
Rate is greater than in the equipment of second threshold, obtains flow adjustment as a result, flow adjustment result is the flow of equipment adjusted
Less than or equal to the optimal machine allocation flow.
A kind of system for network flow equilibrium adjustment that the 5th embodiment of the application provides is as follows:
The embodiment of the present application provides a kind of system of network flow equilibrium adjustment, the system comprises: the application third is real
Apply above-mentioned monitoring device provided by cloud server provided by example and the application fourth embodiment.
It is understood that the principle that embodiment of above is intended to be merely illustrative of the present and the exemplary implementation that uses
Mode, however the present invention is not limited thereto.For those skilled in the art, essence of the invention is not being departed from
In the case where mind and essence, various changes and modifications can be made therein, these variations and modifications are also considered as protection scope of the present invention.
Claims (11)
1. a kind of method of network flow equilibrium adjustment characterized by comprising
Receive the business datum that cloud business platform in edge is sent；
According to the business datum and network depth model, the optimal flow assignment strategy of each equipment is determined；
The optimal flow assignment strategy of each equipment is sent to monitoring device, so that the monitoring device is respectively set according to described
Standby optimal flow assignment strategy is adjusted the flow of each equipment.
2. the method for network flow equilibrium adjustment according to claim 1, which is characterized in that the method also includes:
Receive the flow adjustment result that the monitoring device is sent；
Result and network depth model are adjusted according to the flow, the optimal flow assignment strategy of every kind of equipment is carried out more
Newly；
The optimal flow assignment strategy of updated each equipment is sent to monitoring device, so that the monitoring device is according to
The optimal flow assignment strategy of updated each equipment is adjusted the flow of each equipment.
3. a kind of method of network flow equilibrium adjustment characterized by comprising
The real-time traffic of each equipment is obtained using data, and all set is calculated using data according to the real-time traffic of each equipment
Standby average flow rate remaining proportion；
The optimal flow assignment strategy for each equipment that cloud server is sent is received, the optimal flow assignment strategy is the cloud
What the business datum and network depth model that end server is sent according to edge cloud business platform were determined；
Judge whether the average flow rate remaining proportion of all devices is greater than first threshold；
If more than, then according to the network real-time traffic using the optimal flow assignment strategy of data and each equipment to network
In the flow of each equipment be adjusted.
4. the method for network flow equilibrium adjustment according to claim 3, which is characterized in that the method also includes:
The flow adjustment result of each equipment is sent to the cloud server, so that the cloud server is according to each equipment
Flow adjustment result updates the optimal flow assignment strategy of each equipment.
5. the method for network flow equilibrium adjustment according to claim 3, which is characterized in that the optimal stream of each equipment
Amount allocation strategy is each optimal machine allocation flow, described to use data and each equipment according to the network real-time traffic
Optimal flow assignment strategy step is adjusted to the flow of equipment each in network, comprising:
The flow utilization rate of each equipment is calculated using data according to the network real-time traffic, and is utilized according to the flow of each equipment
Rate determines that flow utilization rate is greater than the equipment of second threshold less than the equipment and flow utilization rate of second threshold；
The flow that flow utilization rate is less than the equipment of second threshold is moved to flow utilization rate to be greater than in the equipment of second threshold,
Flow adjustment is obtained as a result, flow adjustment result is that the flow of equipment adjusted is less than or equal to the most optimal sorting of the equipment
With flow.
6. a kind of cloud server characterized by comprising
First receiving module, for receiving the business datum of edge cloud business platform transmission；
Determining module, for determining the optimal flow assignment strategy of each equipment according to the business datum and network depth model；
First sending module, for the optimal flow assignment strategy of each equipment to be sent to monitoring device, so that the prison
Control equipment is adjusted the flow of each equipment according to the optimal flow assignment strategy of each equipment.
7. cloud server according to claim 6, which is characterized in that the cloud server further include:
Second receiving module adjusts result for receiving the flow that the monitoring device is sent；
Update module, for adjusting result and network depth model according to the flow, to the optimal flux of every kind of equipment
Allocation strategy is updated；
Second sending module, for the optimal flow assignment strategy of updated each equipment to be sent to monitoring device, so that institute
Monitoring device is stated to be adjusted the flow of each equipment according to the optimal flow assignment strategy of updated each equipment.
8. a kind of monitoring device characterized by comprising
Computing module, the real-time traffic for obtaining each equipment are used using data, and according to the real-time traffic of each equipment
The average flow rate remaining proportion of data calculating all devices；
Receiving module, the optimal flow assignment strategy of each equipment for receiving cloud server transmission, the optimal flux point
It is that business datum and network depth model that the cloud server is sent according to edge cloud business platform are determined with strategy；
Judgment module, for judging whether the average flow rate remaining proportion of all devices is greater than first threshold；
Flow adjustment module, for if more than then using the optimal of data and each equipment according to the network real-time traffic
Traffic distribution strategy is adjusted the flow of equipment each in network.
9. monitoring device according to claim 8, which is characterized in that the monitoring device further include:
Sending module, for the flow adjustment result of each equipment to be sent to the cloud server, so that the cloud service
Device adjusts the optimal flow assignment strategy that result updates each equipment according to the flow of each equipment.
10. monitoring device according to claim 8, which is characterized in that the flow adjustment module, comprising:
Determine submodule, for calculating the flow utilization rate of each equipment using data according to the network real-time traffic, and according to
The flow utilization rate of each equipment determines that flow utilization rate is less than the equipment of second threshold and flow utilization rate is greater than second threshold
Equipment；
Flow migrates submodule, big for flow utilization rate to be moved to flow utilization rate less than the flow of the equipment of second threshold
In the equipment of second threshold, flow adjustment is obtained as a result, the flow that flow adjustment result is equipment adjusted is less than
Or it is equal to the optimal machine allocation flow.
11. a kind of system of network flow equilibrium adjustment, which is characterized in that the system comprises: described in claim 6 or 7
Cloud server, the described in any item monitoring devices of claim 8-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910673540.9A CN110290071A (en) | 2019-07-24 | 2019-07-24 | Method and system, cloud server and the monitoring device of network flow equilibrium adjustment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910673540.9A CN110290071A (en) | 2019-07-24 | 2019-07-24 | Method and system, cloud server and the monitoring device of network flow equilibrium adjustment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110290071A true CN110290071A (en) | 2019-09-27 |
Family
ID=68022378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910673540.9A Pending CN110290071A (en) | 2019-07-24 | 2019-07-24 | Method and system, cloud server and the monitoring device of network flow equilibrium adjustment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110290071A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112202619A (en) * | 2020-10-12 | 2021-01-08 | 浪潮云信息技术股份公司 | Intelligent cloud computing network flow adjusting and optimizing system and method |
| CN113824733A (en) * | 2021-10-16 | 2021-12-21 | 西安明德理工学院 | Computer network management system |
| CN114051005A (en) * | 2022-01-14 | 2022-02-15 | 国能日新科技股份有限公司 | Network flow control method, electronic device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170019806A1 (en) * | 2015-07-13 | 2017-01-19 | Le Holdings (Beijing) Co., Ltd. | Method and device for adjusting network quality of service strategies |
| CN107835131A (en) * | 2017-12-15 | 2018-03-23 | 北京星河星云信息技术有限公司 | Network traffics dispatching method, device and storage medium |
| CN107846445A (en) * | 2017-09-20 | 2018-03-27 | 南京邮电大学 | A kind of server load balancing method based on SDN |
| CN108282419A (en) * | 2018-02-24 | 2018-07-13 | 葛晗 | A kind of network flow dispatching method and device |
-
2019
- 2019-07-24 CN CN201910673540.9A patent/CN110290071A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170019806A1 (en) * | 2015-07-13 | 2017-01-19 | Le Holdings (Beijing) Co., Ltd. | Method and device for adjusting network quality of service strategies |
| CN107846445A (en) * | 2017-09-20 | 2018-03-27 | 南京邮电大学 | A kind of server load balancing method based on SDN |
| CN107835131A (en) * | 2017-12-15 | 2018-03-23 | 北京星河星云信息技术有限公司 | Network traffics dispatching method, device and storage medium |
| CN108282419A (en) * | 2018-02-24 | 2018-07-13 | 葛晗 | A kind of network flow dispatching method and device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112202619A (en) * | 2020-10-12 | 2021-01-08 | 浪潮云信息技术股份公司 | Intelligent cloud computing network flow adjusting and optimizing system and method |
| CN113824733A (en) * | 2021-10-16 | 2021-12-21 | 西安明德理工学院 | Computer network management system |
| CN113824733B (en) * | 2021-10-16 | 2023-08-18 | 西安明德理工学院 | Computer network management system |
| CN114051005A (en) * | 2022-01-14 | 2022-02-15 | 国能日新科技股份有限公司 | Network flow control method, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110290071A (en) | Method and system, cloud server and the monitoring device of network flow equilibrium adjustment | |
| CN111708640A (en) | Edge calculation-oriented federal learning method and system | |
| CN106900011A (en) | Task discharging method between a kind of cellular basestation based on MEC | |
| CN107204894A (en) | The monitoring method and device of network servicequality | |
| CN106411774A (en) | Method and device for controlling transaction data volume | |
| CN105050125A (en) | Method and device for evaluating mobile data service quality oriented to user experience | |
| US9565102B2 (en) | Method and apparatus for determining energy efficient route | |
| CN110519849B (en) | Communication and computing resource joint allocation method for mobile edge computing | |
| CN109361762A (en) | A kind of document transmission method, apparatus and system | |
| CN105933329A (en) | Video streaming business code rate self-adaption method based on online study | |
| CN107454630B (en) | Load balancing method and load balancing router | |
| CN113361113B (en) | Energy-consumption-adjustable twin data distribution method for high-speed rail bogie | |
| CN105792252A (en) | Wireless communication network performance optimization method based on SDN and SDN controller | |
| CN106101010A (en) | VBRAS flow load balance method and device based on end office's cloud | |
| CN107196863A (en) | A kind of code rate adjustment method and electronic equipment | |
| EP3148130B1 (en) | Traffic flow switching method and device | |
| CN106656840A (en) | Dynamic flow control method for web crawler | |
| CN107995199A (en) | The port speed constraint method and device of the network equipment | |
| CN105656709A (en) | Method and apparatus for predicting capacity of packet domain network | |
| JP2015228568A (en) | Apparatus, method, and program for video quality estimation | |
| WO2022148299A1 (en) | File transmission method and apparatus, device, and storage medium | |
| CN112600827B (en) | Virtual service migration method and system based on incremental minimum cost maximum flow | |
| WO2018082518A1 (en) | Tunnel adjustment method and device, and computer storage medium | |
| CN105376178B (en) | A kind of method and apparatus of data transmission | |
| CN112732960B (en) | Image classification method based on online federal learning |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190927 |