CN112202619A - Intelligent cloud computing network flow adjusting and optimizing system and method - Google Patents
Intelligent cloud computing network flow adjusting and optimizing system and method Download PDFInfo
- Publication number
- CN112202619A CN112202619A CN202011083918.9A CN202011083918A CN112202619A CN 112202619 A CN112202619 A CN 112202619A CN 202011083918 A CN202011083918 A CN 202011083918A CN 112202619 A CN112202619 A CN 112202619A
- Authority
- CN
- China
- Prior art keywords
- data
- flow
- strategy
- model
- cloud computing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 27
- 238000005457 optimization Methods 0.000 claims abstract description 19
- 238000010801 machine learning Methods 0.000 claims abstract description 18
- 238000007405 data analysis Methods 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims description 17
- 238000001595 flow curve Methods 0.000 claims description 12
- 238000013500 data storage Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000007726 management method Methods 0.000 claims description 7
- 238000007635 classification algorithm Methods 0.000 claims description 6
- 238000003064 k means clustering Methods 0.000 claims description 6
- 230000015654 memory Effects 0.000 claims description 6
- 239000000523 sample Substances 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 230000014759 maintenance of location Effects 0.000 claims description 3
- 238000011897 real-time detection Methods 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims description 3
- 241001123248 Arma Species 0.000 claims 1
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000007123 defense Effects 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 230000003068 static effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 6
- 238000012706 support-vector machine Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 230000006403 short-term memory Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
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
- H04L41/08—Configuration management of networks or network elements
- H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/80—Actions related to the user profile or the type of traffic
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention particularly relates to an intelligent cloud computing network flow adjusting and optimizing system and method. The intelligent cloud computing network flow optimizing system is composed of a data acquisition layer, a data analysis and modeling layer and a strategy service layer. According to the intelligent cloud computing network flow optimizing system and method, artificial intelligence is used for providing high-quality service, passive defense is used for active optimization, static configuration is used for dynamic adjustment, flow monitoring can be better carried out, resource bottlenecks of a network can be excavated by using a machine learning algorithm, an optimal bandwidth configuration scheme is obtained, the utilization rate of bandwidth is improved, user experience is improved, and operation cost and investment are reduced; by strategy configuration, early warning and automatic capacity expansion of bandwidth resources are realized, and thus automatic adjustment of bandwidth is realized.
Description
Technical Field
The invention relates to the technical field of cloud computing and machine learning, in particular to an intelligent cloud computing network flow adjusting and optimizing system and method.
Background
With the rapid increase of network flow and the development of new technologies such as NFV/SDN/5G and the like, the network scale is rapidly expanded, the network topology structure and the service type are abnormal and complex, and higher requirements are provided for the planning and maintenance of network bandwidth. Especially, in a cloud center multi-tenant scenario, internet traffic changes are complex, and professional knowledge and experience are needed to manually optimize bandwidth. The currently commonly used network bandwidth adjusting method has the following defects:
firstly, the operation and maintenance workload is large, the manual configuration is complicated and is easy to make mistakes, and the flexible bandwidth requirement is difficult to meet by adopting the fixed configuration;
in order to guarantee important services, network managers need to perform flow scheduling manually, and real-time flow optimization is difficult to achieve. The manual mode operation and maintenance cost is high, the requirement on the experience of an administrator is high, and the risk of network flow blockage caused by improper operation exists.
II, secondly: the manual configuration has poor flexibility, and real-time adjustment according to the time characteristics, the space characteristics and the service characteristics of the flow cannot be realized due to the absence of a real-time prediction mechanism. In order to guarantee the service quality, operators are often configured according to experience peaks and redundancy, so that bandwidth resources are wasted in the low-grade service, and network congestion may be caused by insufficient resources in hot spot events such as sunclubs and other emergencies.
And thirdly, the change trend of the flow cannot be sensed in advance, and the change and the fault of the flow cannot be estimated in real time for early warning, which is a time mechanism, namely emergency response is carried out after the fault occurs, and passive capacity expansion is carried out.
The invention provides an intelligent cloud computing network flow adjusting and optimizing system and method.
Disclosure of Invention
In order to make up for the defects of the prior art, the invention provides a simple and efficient intelligent cloud computing network flow adjusting and optimizing system and method.
The invention is realized by the following technical scheme:
the utility model provides an intelligence cloud computing network flow tuning system which characterized in that: the system consists of a data acquisition layer, a data analysis and modeling layer and a strategy service layer;
the data acquisition layer is responsible for acquiring the flow and quality KPI of the managed network element through the probe and the network manager, and simultaneously supports receiving the data of a third party;
the data analysis and modeling layer is responsible for elastically storing and analyzing the data collected by the data collection layer, building a model through training a machine learning model based on historical observation data and real-time flow data stored on a big data platform, and producing an optimization strategy;
the policy service layer is responsible for providing a service interface to the outside and pushing a produced optimization policy to an external management node for executing the policy; and simultaneously, an external query interface is provided for the query of the demand side.
The data analysis and modeling layer comprises a big data storage analysis platform, an AI platform algorithm library and a modeling data and flow modeling application module;
the big data storage and analysis platform is used for elastically storing and analyzing data acquired by a data source, adopting different storages for different data and using a Spark distributed computing framework as a bottom platform;
the AI platform algorithm library is used for providing algorithm support for upper-layer machine learning application;
the modeling data is used for modeling analysis of machine learning, including historical observation data and real-time flow data stored on a big data platform.
According to the intelligent cloud computing network flow optimizing method, under the cloud technology network flow optimizing scene, a prediction model forming strategy is established through a machine learning method on the basis of historical data, so that the bandwidth is automatically adjusted in real time;
the method specifically comprises the following steps:
first, data acquisition
Collecting the flow and the quality KPI of the managed network element by using a collecting probe and a network manager, and supporting the collection of the data of a third party;
second, data cleansing and storage
Cleaning the acquired data, and storing the cleaned data in a big data storage system according to rows or columns;
third, model building and training
Performing statistical analysis on the performance data by using a machine learning algorithm to obtain a flow characteristic model and a flow prediction model, establishing a dynamic flow threshold, and training the flow characteristic model and the flow prediction model;
step four, strategy issuing and application
Actively or passively distributing the strategy to a management side through a uniform strategy service interface; judging whether the flow exceeds a threshold value according to the real-time detection performance data, and triggering strategy execution; making a bandwidth adjustment strategy by utilizing the traffic characteristics acquired by the trained traffic characteristic model and the traffic rules analyzed by the trained traffic prediction model;
fifthly, strategy tuning
And adjusting parameters according to the bandwidth adjustment strategy, continuously acquiring data, judging whether the target is reached, and further finely adjusting.
And in the third step, training the flow prediction model by adopting a regression and supervised learning method and training the flow characteristic model by adopting an unsupervised learning mode based on the algorithm library.
The regression classification supervised learning method is the combination of an autoregressive moving average model ARMA, a long-short term memory network model LSTM or an absolute median difference MAD and a Mean value algorithm.
The unsupervised learning mode is a k-means clustering algorithm; when the flow characteristic model is trained, similar flow curves are gathered into one class through a k-means clustering algorithm, the rules of the similar flow curves are excavated, and then the similar flow curves are classified according to flow characteristics through a classification algorithm, so that the flow curve at a certain time is predicted.
The classification algorithm adopts an SVM (Support Vector Machine) method.
In the fourth step, performance data is detected, and after a strategy is triggered, adjustment is carried out according to a rule so as to ensure the service quality; and performing bandwidth real-time overrun adjustment on the real-time performance data, and performing bandwidth threshold pre-adjustment on the detection of the hot spot event.
The invention has the beneficial effects that: according to the intelligent cloud computing network flow optimizing system and method, artificial intelligence is used for providing high-quality service, passive defense is used for active optimization, static configuration is used for dynamic adjustment, flow monitoring can be better carried out, resource bottlenecks of a network can be excavated by using a machine learning algorithm, an optimal bandwidth configuration scheme is obtained, the utilization rate of bandwidth is improved, user experience is improved, and operation cost and investment are reduced; by strategy configuration, early warning and automatic capacity expansion of bandwidth resources are realized, and thus automatic adjustment of bandwidth is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic diagram of an intelligent cloud computing network traffic optimization system according to the present invention.
Fig. 2 is a schematic diagram of the intelligent cloud computing network traffic tuning system method of the present invention.
FIG. 3 is a flow trend diagram of a sampling period of time in accordance with the present invention.
FIG. 4 is a schematic diagram of the LSTM model of the long-short term memory network according to the present invention.
FIG. 5 is a schematic diagram of the ARMA prediction curve of the autoregressive moving average model of the present invention.
FIG. 6 is a diagram of the predicted curve trend of the long-term and short-term memory network model LSTM according to the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the embodiment of the present invention. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The intelligent cloud computing network flow optimizing system consists of a data acquisition layer, a data analysis and modeling layer and a strategy service layer;
the data acquisition layer is responsible for acquiring the flow and quality KPI (Key Performance Indicators) of the managed network element through the probe and the network manager, and supports receiving the data of a third party;
the data analysis and modeling layer is responsible for elastically storing and analyzing the data collected by the data collection layer, building a model through training a machine learning model based on historical observation data and real-time flow data stored on a big data platform, and producing an optimization strategy;
the policy service layer is responsible for providing a service interface to the outside and pushing a produced optimization policy to an external management node for executing the policy; and simultaneously, an external query interface is provided for the query of the demand side.
The data analysis and modeling layer comprises a big data storage analysis platform, an AI platform algorithm library and a modeling data and flow modeling application module;
the big data storage and analysis platform is used for elastically storing and analyzing data acquired by a data source, adopting different storages for different data and using a Spark distributed computing framework as a bottom platform;
the AI platform algorithm library is used for providing algorithm support for upper-layer machine learning application;
the AI algorithms support a variety of components, scimit-spare, XGboost, spark-mlib, Tensorflow for deep neural networks, Pythrch, etc., as well as other visual modeling tools.
The modeling data is used for modeling analysis of machine learning, including historical observation data and real-time flow data stored on a big data platform.
According to the intelligent cloud computing network flow optimizing method, under the scene of cloud technology network flow optimizing, a prediction model forming strategy is established through a machine learning method on the basis of historical data, so that the bandwidth is automatically adjusted in real time;
the method specifically comprises the following steps:
first, data acquisition
Collecting the flow and the quality KPI of the managed network element by using a collecting probe and a network manager, and supporting the collection of the data of a third party;
second, data cleansing and storage
Cleaning the collected data, and storing the cleaned data in different compression formats such as partial, snap, orc and the like in a big data storage system according to rows or columns;
third, model building and training
Performing statistical analysis on the performance data by using a machine learning algorithm to obtain a flow characteristic model and a flow prediction model, establishing a dynamic flow threshold, and training the flow characteristic model and the flow prediction model;
step four, strategy issuing and application
Actively or passively distributing the strategy to a management side through a uniform strategy service interface; judging whether the flow exceeds a threshold value according to the real-time detection performance data, and triggering strategy execution; making a bandwidth adjustment strategy by utilizing the traffic characteristics acquired by the trained traffic characteristic model and the traffic rules analyzed by the trained traffic prediction model;
fifthly, strategy tuning
And adjusting parameters according to the bandwidth adjustment strategy, continuously acquiring data, judging whether the target is reached, and further finely adjusting.
And in the third step, training the flow prediction model by adopting a regression and supervised learning method and training the flow characteristic model by adopting an unsupervised learning mode based on the algorithm library.
The research essence of the system flow is modeling based on a time sequence, and the regression and classification supervised learning method is that an autoregressive moving average model ARMA, a long-short term memory network model LSTM or an absolute median difference MAD are used for modeling and analyzing the time sequence and combined with a Mean algorithm.
The unsupervised learning mode is a k-means clustering algorithm; when the flow characteristic model is trained, similar flow curves are gathered into one class through a k-means clustering algorithm, the rules of the similar flow curves are excavated, and then the similar flow curves are classified according to flow characteristics through a classification algorithm, so that the flow curve at a certain time is predicted.
The classification algorithm adopts an SVM (Support Vector Machine) method.
In the fourth step, performance data is detected, and after a strategy is triggered, adjustment is carried out according to a rule so as to ensure the service quality; and performing bandwidth real-time overrun adjustment on the real-time performance data, and performing bandwidth threshold pre-adjustment on the detection of the hot spot event.
And in the fourth step, the query of the strategy is provided through APIs such as protobuf and restful, and the dynamic adjustment strategy is pushed to the management side.
And training the flow total time series data counted by minutes in a sampling period of a certain day, wherein the flow trend is shown in a graph 3, and cutting a training set, a testing set and a flow sequence trend.
The Autoregressive moving average model ARMA (Autoregressive moving average model) is a combined model of an Autoregressive model (AR model for short) and a moving average model (MA model for short), and has the following formula:
wherein p and q are the autoregressive order and the moving average order of the model;
and θ is a pending coefficient other than zero; an ε t independent error term; xt is a smooth, normal, zero mean time series.
The Long Short-Term Memory network model LSTM (Long Short-Term Memory) is a time-cycle neural network. The method is an optimization model of the RNN, can solve the problems of gradient disappearance and non-memorability long-time dependence of the RNN model, and is the most common mode for solving the sequence problem at present, as shown in FIG. 5.
The method uses the accuracy as an evaluation function 1- | Yt-Ypt |/Yt (wherein Yt is a true value, Ypt is a predicted value, a prediction effect curve of a set is verified through a model, such as an ARMA prediction function curve shown in figure 5 and an LSTM model function curve shown in figure 6. analysis on the result of the prediction curve shows that the results of an autoregressive sliding average model ARMA and a long-short term memory network model LSTM are closer to the current time, the higher the accuracy is, the longer the current time is, the worse the accuracy is, but the autoregressive sliding average model ARMA can be used for predicting multi-step time interval data, the long-short term memory network model LSTM does not have a multi-step prediction interface, new prediction data is required to be used as new time sequence data, and an iterative method can be used for predicting and completing the prediction
The above-described embodiment is only one specific embodiment of the present invention, and general changes and substitutions by those skilled in the art within the technical scope of the present invention are included in the protection scope of the present invention.
Claims (8)
1. The utility model provides an intelligence cloud computing network flow tuning system which characterized in that: the system consists of a data acquisition layer, a data analysis and modeling layer and a strategy service layer;
the data acquisition layer is responsible for acquiring the flow and quality KPI of the managed network element through the probe and the network manager, and simultaneously supports receiving the data of a third party;
the data analysis and modeling layer is responsible for elastically storing and analyzing the data collected by the data collection layer, building a model through training a machine learning model based on historical observation data and real-time flow data stored on a big data platform, and producing an optimization strategy;
the policy service layer is responsible for providing a service interface to the outside and pushing a produced optimization policy to an external management node for executing the policy; and simultaneously, an external query interface is provided for the query of the demand side.
2. The intelligent cloud computing network traffic optimization system of claim 1, wherein: the data analysis and modeling layer comprises a big data storage analysis platform, an AI platform algorithm library and a modeling data and flow modeling application module;
the big data storage and analysis platform is used for elastically storing and analyzing data acquired by a data source, adopting different storages for different data and using a Spark distributed computing framework as a bottom platform;
the AI platform algorithm library is used for providing algorithm support for upper-layer machine learning application;
the modeling data is used for modeling analysis of machine learning, including historical observation data and real-time flow data stored on a big data platform.
3. An intelligent cloud computing network flow optimization method is characterized by comprising the following steps: under the scene of cloud technology network flow optimization, a prediction model forming strategy is established through a machine learning method on the basis of historical data, so that the bandwidth is automatically adjusted in real time;
the method specifically comprises the following steps:
first, data acquisition
Collecting the flow and the quality KPI of the managed network element by using a collecting probe and a network manager, and supporting the collection of the data of a third party;
second, data cleansing and storage
Cleaning the acquired data, and storing the cleaned data in a big data storage system according to rows or columns;
third, model building and training
Performing statistical analysis on the performance data by using a machine learning algorithm to obtain a flow characteristic model and a flow prediction model, establishing a dynamic flow threshold, and training the flow characteristic model and the flow prediction model;
step four, strategy issuing and application
Actively or passively distributing the strategy to a management side through a uniform strategy service interface; judging whether the flow exceeds a threshold value according to the real-time detection performance data, and triggering strategy execution; making a bandwidth adjustment strategy by utilizing the traffic characteristics acquired by the trained traffic characteristic model and the traffic rules analyzed by the trained traffic prediction model;
fifthly, strategy tuning
And adjusting parameters according to the bandwidth adjustment strategy, continuously acquiring data, judging whether the target is reached, and further finely adjusting.
4. The intelligent cloud computing network traffic optimization method according to claim 3, wherein: and in the third step, training the flow prediction model by adopting a regression and supervised learning method and training the flow characteristic model by adopting an unsupervised learning mode based on the algorithm library.
5. The intelligent cloud computing network traffic optimization method according to claim 4, wherein: the regression classification supervised learning method is the combination of an autoregressive moving average model ARMA, a long-short term memory network model LSTM or an absolute median difference MAD and a Mean value algorithm.
6. The intelligent cloud computing network traffic optimization method according to claim 4, wherein: the unsupervised learning mode is a k-means clustering algorithm; when the flow characteristic model is trained, similar flow curves are gathered into one class through a k-means clustering algorithm, the rules of the similar flow curves are excavated, and then the similar flow curves are classified according to flow characteristics through a classification algorithm, so that the flow curve at a certain time is predicted.
7. The intelligent cloud computing network traffic optimization method according to claim 6, wherein: the classification algorithm adopts an SVM method.
8. The intelligent cloud computing network traffic optimization method according to claim 3, wherein: in the fourth step, performance data is detected, and after a strategy is triggered, adjustment is carried out according to a rule so as to ensure the service quality; and performing bandwidth real-time overrun adjustment on the real-time performance data, and performing bandwidth threshold pre-adjustment on the detection of the hot spot event.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011083918.9A CN112202619A (en) | 2020-10-12 | 2020-10-12 | Intelligent cloud computing network flow adjusting and optimizing system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011083918.9A CN112202619A (en) | 2020-10-12 | 2020-10-12 | Intelligent cloud computing network flow adjusting and optimizing system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112202619A true CN112202619A (en) | 2021-01-08 |
Family
ID=74014015
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011083918.9A Pending CN112202619A (en) | 2020-10-12 | 2020-10-12 | Intelligent cloud computing network flow adjusting and optimizing system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112202619A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112838957A (en) * | 2021-02-23 | 2021-05-25 | 成都卓源网络科技有限公司 | Flow prediction system with intelligent scheduling function |
| WO2023138014A1 (en) * | 2022-01-19 | 2023-07-27 | 浪潮通信信息系统有限公司 | Intelligent operation and maintenance system oriented to computing-network integration scenario and use method thereof |
| CN117729164A (en) * | 2024-02-08 | 2024-03-19 | 深圳中科云信息技术有限公司 | Dynamic bandwidth allocation system for four-port gigabit network card |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102413063A (en) * | 2012-01-12 | 2012-04-11 | 盛科网络（苏州）有限公司 | Method and system for dynamically adjusting allocation threshold value of output port resources |
| CN103728974A (en) * | 2014-01-20 | 2014-04-16 | 北京航空航天大学 | Quality of Service (QoS) evaluation based dynamic network scheduling and control method, system and device |
| CN108924057A (en) * | 2018-08-02 | 2018-11-30 | 浙江口碑网络技术有限公司 | The port flow intelligence control system of system on a kind of cloud |
| CN110290071A (en) * | 2019-07-24 | 2019-09-27 | 中国联合网络通信集团有限公司 | Method and system, cloud server and the monitoring device of network flow equilibrium adjustment |
| CN111371644A (en) * | 2020-02-28 | 2020-07-03 | 山东工商学院 | Multi-domain SDN network traffic situation prediction method and system based on GRU |
-
2020
- 2020-10-12 CN CN202011083918.9A patent/CN112202619A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102413063A (en) * | 2012-01-12 | 2012-04-11 | 盛科网络（苏州）有限公司 | Method and system for dynamically adjusting allocation threshold value of output port resources |
| CN103728974A (en) * | 2014-01-20 | 2014-04-16 | 北京航空航天大学 | Quality of Service (QoS) evaluation based dynamic network scheduling and control method, system and device |
| CN108924057A (en) * | 2018-08-02 | 2018-11-30 | 浙江口碑网络技术有限公司 | The port flow intelligence control system of system on a kind of cloud |
| CN110290071A (en) * | 2019-07-24 | 2019-09-27 | 中国联合网络通信集团有限公司 | Method and system, cloud server and the monitoring device of network flow equilibrium adjustment |
| CN111371644A (en) * | 2020-02-28 | 2020-07-03 | 山东工商学院 | Multi-domain SDN network traffic situation prediction method and system based on GRU |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112838957A (en) * | 2021-02-23 | 2021-05-25 | 成都卓源网络科技有限公司 | Flow prediction system with intelligent scheduling function |
| WO2023138014A1 (en) * | 2022-01-19 | 2023-07-27 | 浪潮通信信息系统有限公司 | Intelligent operation and maintenance system oriented to computing-network integration scenario and use method thereof |
| CN117729164A (en) * | 2024-02-08 | 2024-03-19 | 深圳中科云信息技术有限公司 | Dynamic bandwidth allocation system for four-port gigabit network card |
| CN117729164B (en) * | 2024-02-08 | 2024-04-12 | 深圳中科云信息技术有限公司 | Dynamic bandwidth allocation system for four-port gigabit network card |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108415789B (en) | Node fault prediction system and method for large-scale hybrid heterogeneous storage system | |
| CN112202619A (en) | Intelligent cloud computing network flow adjusting and optimizing system and method | |
| CN111885012B (en) | Network situation perception method and system based on information acquisition of various network devices | |
| US11616682B2 (en) | Threshold selection for KPI candidacy in root cause analysis of network issues | |
| US20190372827A1 (en) | Anomaly severity scoring in a network assurance service | |
| Zacheilas et al. | Elastic complex event processing exploiting prediction | |
| US20210281492A1 (en) | Determining context and actions for machine learning-detected network issues | |
| CN109753385A (en) | A kind of restoration methods and system towards the monitoring of stream calculation system exception | |
| CN110891283A (en) | Small base station monitoring device and method based on edge calculation model | |
| WO2021057382A1 (en) | Abnormality detection method and apparatus, terminal, and storage medium | |
| CN106250306A (en) | A kind of performance prediction method being applicable to enterprise-level O&M automatization platform | |
| Ali-Tolppa et al. | Self-healing and resilience in future 5G cognitive autonomous networks | |
| US10680919B2 (en) | Eliminating bad rankers and dynamically recruiting rankers in a network assurance system | |
| US10542517B1 (en) | Characterizing movement behaviors of wireless nodes in a network | |
| CN113542039A (en) | Method for positioning 5G network virtualization cross-layer problem through AI algorithm | |
| CN113259355B (en) | Industrial Internet identification slice management system based on SDN | |
| Yahia et al. | CogNitive 5G networks: Comprehensive operator use cases with machine learning for management operations | |
| US11197175B2 (en) | Forcasting time series data | |
| CN114338351B (en) | Network anomaly root cause determination method and device, computer equipment and storage medium | |
| CN105022823B (en) | A kind of cloud service performance early warning event generation method based on data mining | |
| CN101651567A (en) | Available risk spread evaluating method | |
| Lujic et al. | Resilient edge data management framework | |
| CN110647086B (en) | Intelligent operation and maintenance monitoring system based on operation big data analysis | |
| CN115495231A (en) | Dynamic resource scheduling method and system under complex scene of high concurrent tasks | |
| CN111327494B (en) | Multi-domain SDN network flow situation assessment method and system |
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: 20210108 |
|
| RJ01 | Rejection of invention patent application after publication |