CN114051000A - Service flow switching method and device based on time series model - Google Patents
Service flow switching method and device based on time series model Download PDFInfo
- Publication number
- CN114051000A CN114051000A CN202111359801.3A CN202111359801A CN114051000A CN 114051000 A CN114051000 A CN 114051000A CN 202111359801 A CN202111359801 A CN 202111359801A CN 114051000 A CN114051000 A CN 114051000A
- Authority
- CN
- China
- Prior art keywords
- flow
- index
- server cluster
- switching
- service
- 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
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3051—Monitoring arrangements for monitoring the configuration of the computing system or of the computing system component, e.g. monitoring the presence of processing resources, peripherals, I/O links, software programs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- 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
- H04L47/20—Traffic policing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention provides a service flow switching method and a device based on a time series model, which can be used in the technical field of artificial intelligence, and the method comprises the following steps: receiving a flow switching request transmitted by an operation and maintenance personnel terminal; acquiring server cluster information for processing a service, acquiring index data corresponding to a cut flow index in a server cluster through the server cluster information according to a preset cut flow index, and predicting the index data through a preset time sequence model to obtain a change trend of the cut flow index; the method and the device have the advantages that the traffic flow is subjected to the switching control according to the switching index variation trend, the switching index variation of the server cluster for processing the traffic is predicted through the preset time sequence model to obtain the switching index variation trend, the cost of performance test is reduced, and the accuracy of predicting the switching index variation trend of the system and the stability of processing the traffic of the server cluster are improved.
Description
Technical Field
The invention relates to the technical field of operation and maintenance of information systems, in particular to the technical field of finance, and particularly relates to a service flow switching method and device based on a time series model.
Background
The size of the service flow is closely related to the operation state of the server cluster for service processing, and if the service flow is too large, the size exceeds the load which can be borne by the service operation environment of the server cluster, service failure is easy to occur, and service failure is caused. In the current production, the service flow is limited mainly by setting a service flow threshold, the threshold can obtain the maximum transaction amount which can be carried by a transaction environment through transaction pressure measurement, then a 90% proportion is set on the basis of the maximum transaction amount as a current flow switching triggering condition, or the current flow switching threshold is dynamically set according to historical monitoring data through a general big data and artificial intelligence algorithm. The method for estimating the cut-off value through the production pressure measurement needs to be operated manually, and frequent pressure measurement is often needed to prevent the change of the transaction environment or the change of the cut-off value caused by the optimization of the requirement of the transaction, so that the method is time-consuming and labor-consuming, and the efficiency is relatively low. However, the common big data and artificial intelligence algorithm cannot automatically adjust the cut-flow value along with the change of the transaction environment (server aging, performance reduction and transaction optimization), and cannot predict the non-periodic burst transaction concurrent change, and the cut-flow adjustment mode and strategy are relatively single.
Disclosure of Invention
The invention aims to provide a service flow switching method based on a time series model, which predicts the switching index change of a service processing server cluster through a preset time series model to obtain the switching index change trend, reduces the cost of performance test, and improves the accuracy of system switching index change trend prediction and the stability of server cluster service processing. The invention also aims to provide a service flow cut-off device based on the time series model. It is a further object of this invention to provide such a computer apparatus. It is a further object of this invention to provide such a readable medium.
In order to achieve the above object, in one aspect, the present invention discloses a method for traffic flow switching based on a time series model, including:
receiving a flow switching request transmitted by an operation and maintenance personnel terminal;
acquiring server cluster information for processing a service, acquiring index data corresponding to a cut flow index in a server cluster through the server cluster information according to a preset cut flow index, and predicting the index data through a preset time sequence model to obtain a change trend of the cut flow index;
and performing flow switching control on the service flow according to the flow switching index variation trend.
Preferably, before obtaining the server cluster information for processing the service, the method further includes:
determining whether a corresponding change trend of the flow switching index exists according to the flow switching request, and if so, performing flow switching control on the service flow according to the change trend of the flow switching index;
and if not, executing to obtain the server cluster information of the processing service.
Preferably, the flow cutting request comprises a designated server cluster;
the acquiring server cluster information of a processing service, and acquiring index data corresponding to a cut flow index in a server cluster according to a preset cut flow index through the server cluster information specifically includes:
determining the designated server cluster according to the flow switching request;
acquiring server cluster information of the designated server cluster, wherein the server cluster information comprises cluster nodes and transaction information;
and acquiring index data corresponding to the tangent flow index according to the server cluster information.
Preferably, the flow cutting request comprises a designated server cluster;
the method further comprises the following steps of obtaining index data corresponding to the flow cutting indexes in the server cluster through the server cluster information according to preset flow cutting indexes, wherein before:
determining the designated server cluster according to the flow switching request;
acquiring a corresponding index configuration file according to the designated server cluster;
and analyzing the index configuration file to obtain the tangent flow index.
Preferably, the predicting the index data through a preset time series model to obtain the tangential flow index variation trend specifically includes:
preprocessing the index data;
and predicting the preprocessed index data through a preset time sequence model to obtain the change trend of the tangential flow index.
Preferably, the performing flow switching control on the service flow according to the flow switching index variation trend specifically includes:
obtaining a service flow change trend according to the cut flow index change trend and a fitting curve of service flow and the cut flow index;
and if the current service flow is larger than the corresponding service flow in the service flow variation trend, switching at least part of the service flow to other server clusters.
Preferably, the method further comprises the step of predetermining the fitted curve:
and fitting the preprocessed historical index data according to a polynomial fitting algorithm to obtain a fitting curve corresponding to the service flow and each tangential flow index.
Preferably, obtaining the traffic flow variation trend according to the traffic flow variation trend and the fitting curve of the traffic flow and the traffic flow index specifically includes:
determining the sampling tangential flow index at each sampling moment according to the tangential flow index change trend;
determining sampling service flow corresponding to the sampling tangential flow index according to the sampling tangential flow index and the fitting curve;
and fitting the sampled service flow at all sampling moments to obtain the service flow change trend.
Preferably, the method further comprises the step of establishing the time series model in advance:
acquiring historical index data of the tangential flow index within a historical preset time period;
and training a preset machine learning model through the historical index data to obtain the time sequence model.
Preferably, the method further comprises the following steps:
receiving a monitoring message of the server cluster;
analyzing the monitoring message to obtain the index data of each preset flow switching index.
The invention also discloses a service flow switching device based on the time series model, which comprises a switching evaluation module, a big data platform, a monitoring platform and a flow distribution platform;
the system comprises a tangent flow evaluation module, a big data platform and a monitoring platform, wherein the tangent flow evaluation module is used for receiving a tangent flow request transmitted by an operation and maintenance personnel terminal, acquiring server cluster information for processing a service, acquiring index data corresponding to the tangent flow index in a server cluster from the big data platform and the monitoring platform through the server cluster information according to a preset tangent flow index, and predicting the index data through a preset time sequence model to obtain the change trend of the tangent flow index;
and the flow distribution platform is used for carrying out flow switching control on the service flow according to the flow switching index variation trend.
The invention also discloses a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor,
the processor, when executing the program, implements the method as described above.
The invention also discloses a computer-readable medium, having stored thereon a computer program,
which when executed by a processor implements the method as described above.
The service flow switching method based on the time series model receives a switching request transmitted by an operation and maintenance personnel terminal, obtains server cluster information for processing services, obtains index data corresponding to the switching indexes in a server cluster through the server cluster information according to preset switching indexes, predicts the index data through the preset time series model to obtain the switching index variation trend, and controls the switching of service flow according to the switching index variation trend. Therefore, the method and the device predict the change trend of the tangent flow index through the time series model and the index data of the tangent flow index in the server cluster, determine the change trend of the tangent flow index, and perform tangent flow control on the server cluster according to the change trend of the tangent flow index. Therefore, the method and the device do not need to carry out pressure measurement on the server cluster, can predict the change trend of the flow switching index of the server cluster according to the index data of the flow switching index, further realize the flow switching control of the service flow, save a large amount of performance test workload, reduce the performance test cost determined by the change trend of the service flow switching index of the server cluster, improve the accuracy of prediction of the change trend of the flow switching index of the server cluster, further ensure the operation stability of service processing of the server cluster through the service flow switching, and improve the convenience of operation and maintenance.
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 described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a structural diagram illustrating a specific embodiment of a traffic flow switching system based on a time series model according to the present invention;
FIG. 2 is a flow chart of a specific embodiment of a method for traffic flow switching based on a time series model according to the present invention;
fig. 3 is a structural diagram illustrating a specific embodiment of a traffic flow switching apparatus for performing a traffic flow switching method based on a time series model according to the present invention;
fig. 4 is a block diagram illustrating a traffic switching evaluation module in the traffic switching apparatus of fig. 3;
fig. 5 is a block diagram illustrating a large data platform in the traffic flow switching apparatus of fig. 3;
fig. 6 is a block diagram illustrating a monitoring platform in the traffic flow switching apparatus of fig. 3;
fig. 7 is a block diagram illustrating a traffic distribution platform in the traffic shedding apparatus of fig. 3;
FIG. 8 is a flowchart illustrating a specific example of a traffic flow switching method based on a time series model according to the present invention;
FIG. 9 shows a schematic block diagram of a computer device suitable for use in implementing embodiments of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.
It should be noted that the service traffic flow splitting method and device based on the time series model disclosed in the present application can be used in the field of artificial intelligence technology, and can also be used in any field except the field of artificial intelligence technology.
It should be noted that, in one or more embodiments of the present invention, the polynomial fitting refers to fitting the observation points of each index with a polynomial expansion to obtain a nonlinear relationship of the observation data, and the expansion coefficient is determined by a least square fitting.
It should be noted that, in one or more embodiments of the present invention, the Prophet algorithm is a time series prediction model of facebook open source, and any parameter value affecting the prediction process can be set.
The current method for the switching of the service processing server cluster mainly depends on manual pressure measurement to obtain a switching value, and switching control is performed according to the switching value, so that time and labor are wasted, efficiency is low, automatic switching value adjustment cannot be performed along with change of a transaction environment, and the switching value may not be accurately calculated. In order to solve the problems that the efficiency of acquiring the tangential flow of the transaction service by artificial pressure measurement is low and the calculation of the tangential flow value is inaccurate, the invention predicts index data of the tangential flow index in the server cluster through a time series model to obtain the variation trend of the tangential flow index, and performs tangential flow control on the server cluster according to the variation trend of the tangential flow index. Therefore, the method and the device do not need to carry out pressure measurement on the server cluster, predict the change trend of the flow switching indexes of the server cluster according to the index data of the flow switching indexes, further realize the flow switching control of the service flow, save a large amount of performance test workload, reduce the performance test cost determined by the change trend of the service flow switching indexes of the server cluster, improve the accuracy of prediction of the change trend of the flow switching indexes of the server cluster, further ensure the operation stability of service processing of the server cluster through the service flow switching, and improve the convenience of operation and maintenance.
Fig. 1 is a schematic structural diagram of a service traffic flow cut-off system based on a time series model according to an embodiment of the present invention, and as shown in fig. 1, the service traffic flow cut-off system based on a time series model according to an embodiment of the present invention includes an operation and maintenance personnel terminal 100, at least one server cluster 200, and a service traffic flow cut-off device 300 based on a time series model.
And the operation and maintenance personnel terminal sends a flow switching request to the service flow switching device.
The service flow switching device receives a switching request transmitted by an operation and maintenance personnel terminal; acquiring server cluster information for processing a service, acquiring index data corresponding to a cut flow index in a server cluster through the server cluster information according to a preset cut flow index, and predicting the index data through a preset time sequence model to obtain a change trend of the cut flow index; and performing flow switching control on the service flow according to the flow switching index variation trend.
It should be noted that, the operation and maintenance personnel terminal in the service traffic flow switching system based on the time series model of the present invention may be integrated with the service traffic flow switching device, that is, the operation and maintenance personnel directly operate on the interactive device provided by the service traffic flow switching device to form a flow switching request.
The following describes an implementation process of the service traffic flow switching method based on the time series model, which is provided by the embodiment of the present invention, by taking the service traffic flow switching device based on the time series model as an example. It can be understood that the execution subject of the service traffic flow switching method based on the time series model provided by the embodiment of the invention includes, but is not limited to, the service traffic flow switching device based on the time series model.
According to an aspect of the present invention, the present embodiment discloses a method for traffic flow switching based on a time series model. As shown in fig. 2, in this embodiment, the method includes:
s100: and receiving a flow switching request of the operation and maintenance personnel terminal.
S200: the method comprises the steps of obtaining server cluster information for processing services, obtaining index data corresponding to a cut flow index in a server cluster through the server cluster information according to a preset cut flow index, and predicting the index data through a preset time sequence model to obtain a change trend of the cut flow index.
S300: and performing flow switching control on the service flow according to the flow switching index variation trend.
The service flow switching method based on the time series model receives a switching request transmitted by an operation and maintenance personnel terminal, obtains server cluster information for processing services, obtains index data corresponding to the switching indexes in a server cluster through the server cluster information according to preset switching indexes, predicts the index data through the preset time series model to obtain the switching index variation trend, and controls the switching of service flow according to the switching index variation trend. Therefore, the method and the device predict the change trend of the tangent flow index through the time series model and the index data of the tangent flow index in the server cluster, determine the change trend of the tangent flow index, and perform tangent flow control on the server cluster according to the change trend of the tangent flow index. Therefore, the method and the device do not need to carry out pressure measurement on the server cluster, can predict the change trend of the flow switching index of the server cluster according to the index data of the flow switching index, further realize the flow switching control of the service flow, save a large amount of performance test workload, reduce the performance test cost determined by the change trend of the service flow switching index of the server cluster, improve the accuracy of prediction of the change trend of the flow switching index of the server cluster, further ensure the operation stability of service processing of the server cluster through the service flow switching, and improve the convenience of operation and maintenance.
Specifically, as shown in fig. 3, in a preferred embodiment, a traffic flow switching apparatus for performing a traffic flow switching method based on a time series model may include a switching evaluation module 1, a big data platform 2, a monitoring platform 3, and a traffic distribution platform 4.
The tangential flow evaluation module 1 is connected with the big data platform 2, the flow distribution platform 4 and the flow control platform 5 through a network; the big data platform 2 is connected with the monitoring platform 3 and the tangential flow evaluation module 1; the monitoring platform 3 is connected with the big data platform 2 and the actual production service system; the flow distribution platform 4 is deployed in each server cluster and connected with the tangential flow evaluation module 1.
The flow switching evaluation module 1 is used for triggering flow switching index evaluation of the whole server cluster, initiating a flow switching configuration pushing flow and realizing flow switching control. And performing flow switching evaluation by assembling related message instructions.
The big data platform 2 is used for inquiring index data in monitoring data of the server cluster, processing the index data, evaluating the future performance expression trend of the server cluster according to a preset time sequence model, forming a tangential flow index change trend, and returning the tangential flow index change trend to the tangential flow evaluation module 1 according to requirements.
The monitoring platform 3 is used for analyzing the monitoring messages reported by the server cluster, collecting various tangent flow index data, storing indexes and providing other modules, platforms and servers for access.
The flow distribution platform 4 is used for receiving the flow cutting instruction, analyzing the flow cutting instruction to obtain the change trend of the flow cutting index, and starting a flow cutting mechanism according to the change trend of the flow cutting index to realize the flow cutting function.
It should be noted that the big data platform 2, the monitoring platform 3, and the traffic distribution platform 4 of the present invention may be a server or a server cluster, and those skilled in the art may set the architecture of the big data platform 2, the monitoring platform 3, and the traffic distribution platform 4 according to actual requirements, which is not described herein again.
More preferably, as shown in fig. 4, the cut-flow evaluating module 1 may include a cut-flow evaluating unit 11, a message transmitting/receiving unit 12, a cut-flow control unit 13, and a cut-flow configuring unit 14.
The switching flow evaluation unit 11 triggers a switching flow evaluation instruction based on a switching flow request transmitted by an operation and maintenance personnel terminal, assembles a switching flow evaluation instruction message after acquiring the name of the corresponding server cluster, and calls the message sending/receiving unit 12 to send the instruction to the big data platform 2.
The message sending/receiving unit 12 is responsible for sending the messages assembled by the modules to the big data platform, the tangential flow evaluation module 1 and the like.
The switching control unit 13 is responsible for assembling the switching index variation trend of the corresponding server cluster into a switching instruction, and calls the message sending/receiving unit 12 to send the switching instruction to the flow distribution platform 4.
The flow switching configuration unit 14 is responsible for storing relevant configuration information of flow switching, server cluster information, message templates, and the like.
As shown in fig. 5, the big data platform 2 may include an instruction receiving unit 21, a data querying unit 22, a data preprocessing unit 23, an index prediction unit 24, and an index sending unit 25.
The instruction receiving unit 21 is responsible for receiving the evaluation instruction sent by the cut-flow evaluation module 1 and analyzing the execution instruction.
The data query unit 22 is responsible for querying and loading the tangential flow index data of the monitoring platform 3 according to the requirement of the evaluation instruction.
The data preprocessing unit 23 is responsible for preprocessing the queried tangential flow index data according to the requirement of inputting data by a preset time series model, and forming a data set which can be processed by a correlation algorithm.
The index prediction unit 24 is responsible for predicting the switching index change trend of the preprocessed switching index data by using a preset time sequence model, and determining the performance of the service cluster at a certain time point. Preferably, the time series model can be obtained by training a machine learning model formed based on the prophet algorithm principle.
The index sending unit 25 is responsible for sending the tangential flow index change trend obtained by the index prediction unit 24 to the tangential flow evaluation module 1.
As shown in fig. 6, the monitoring platform 3 includes a monitoring message receiving unit 31, a monitoring message parsing unit 32, a cut flow index storage unit 33, and a cut flow index access unit 34.
The monitoring message receiving unit 31 is responsible for receiving a monitoring message sent by the server cluster.
The monitoring message parsing unit 32 is responsible for parsing the message received by the monitoring message receiving unit 31, and storing the flow cut indicators of the relevant cluster, such as CPU usage, memory usage, disk usage, network timeout, I/O throughput, etc., in the flow cut indicator storage unit 33.
The cut-flow index storage unit 33 is responsible for storing cut-flow indexes such as CPU usage, memory usage, disk usage, network timeout, I/O throughput, and the like.
The cut flow index access unit 34 is responsible for providing a cut flow index access interface, and providing cut flow indexes such as CPU usage, memory usage, disk usage, network timeout, I/O throughput, and the like of each IP in a certain server cluster.
As shown in fig. 7, the flow distribution platform 4 includes a tangential flow instruction receiving unit 41, a tangential flow configuration unit 42, and a tangential flow unit 43.
The flow cutting instruction receiving unit 41 is responsible for receiving the flow cutting instruction sent by the flow cutting evaluation module 1 and analyzing the change trend of the flow cutting index.
The cut-flow configuration unit 42 is responsible for storing the cut-flow index variation trend analyzed by the instruction receiving unit 41.
The flow switching unit 43 is responsible for performing traffic flow switching control on the corresponding server cluster according to the flow switching index variation trend in the flow switching configuration unit 42 and according to the flow switching index variation trend.
In a preferred embodiment, when performing flow switching control on a service traffic according to the flow switching index variation trend, the flow switching unit 43 obtains the service traffic variation trend according to the flow switching index variation trend and a fitted curve of the service traffic and the flow switching index, and switches at least part of the service traffic to another server cluster if the current service traffic is greater than the corresponding service traffic in the service traffic variation trend.
More preferably, when obtaining the traffic flow variation trend according to the traffic flow index variation trend and the fitting curve between the traffic flow and the traffic flow index, the flow switching unit 43 determines the sampling traffic flow index at each sampling time according to the traffic flow index variation trend; determining sampling service flow corresponding to the sampling tangential flow index according to the sampling tangential flow index and the fitting curve; and fitting the sampled service flow at all sampling moments to obtain the service flow change trend.
Wherein the tangential flow unit 43 may predetermine the fitting curve. Specifically, the preprocessed historical index data can be fitted according to a polynomial fitting algorithm to obtain a fitting curve corresponding to the service flow and each tangential flow index. Specifically, the preprocessed tangential flow index data may be fitted according to a polynomial fitting algorithm to form, for example, y ═ aX1 n1+bX2 n2+cX3 n3+dX4 n4+eX5 n5+fX6 n6+gX7 n7+ h fitting curve, where y denotes traffic flow and X1、X2、X3、X4、X5、X6And X7For the index of cut flow, a, b, c, d, e, f, g, h, n1, n2, n3, n4, n5, n6 and n7 areAnd (4) carrying out polynomial fitting to obtain parameters of the tangential flow index. And according to the obtained fitting curve, estimating the highest upper limit of the performance to obtain a cut-flow evaluation index, wherein the related indexes comprise CPU (Central processing Unit) usage, memory usage, CPU usage rate, memory usage rate, disk usage rate, network timeout and I/O (input/output) throughput.
The flow cutting unit 43 further may pre-build the time series model. Specifically, the flow cutting unit 43 may obtain historical index data of the flow cutting index within a historical preset time period; and training a preset machine learning model through the historical index data to obtain the time sequence model.
In order to improve the execution efficiency of the traffic switching, in a preferred embodiment, the method further includes, before acquiring server cluster information for processing the traffic at S200:
s110: and determining whether a corresponding change trend of the flow switching index exists according to the flow switching request, and if so, performing flow switching control on the service flow according to the change trend of the flow switching index.
S120: and if not, executing to obtain the server cluster information of the processing service.
Specifically, the flow switching evaluation module inquires whether a designated server cluster flow switching index change trend exists after receiving a flow switching request transmitted by an operation and maintenance worker. And if the change trend of the flow switching index exists, directly triggering the flow switching configuration pushing flow, and switching the flow of the service according to the change trend of the flow switching index. And if the change trend of the tangent flow index does not exist, continuously executing to acquire server cluster information for processing the service, and performing tangent flow on the traffic after determining the change trend of the tangent flow index in real time.
In a preferred embodiment, the request to cut flow includes a designated server cluster.
The step S200 of acquiring server cluster information for processing a service, and acquiring index data corresponding to a cut flow index in a server cluster according to a preset cut flow index through the server cluster information specifically includes:
s211: and determining the designated server cluster according to the flow switching request.
S212: and acquiring server cluster information of the designated server cluster, wherein the server cluster information comprises cluster nodes and transaction information.
S213: and acquiring index data corresponding to the tangent flow index according to the server cluster information.
It can be understood that the index data of the server cluster can be obtained by using a large data platform and a monitoring platform which are conventionally configured in the system, and the difficulty and the cost of generating the change trend of the tangential flow index are reduced. Specifically, a message of the tangential flow evaluation instruction can be assembled and sent to the big data platform. And the big data platform judges whether the instruction type is a cut flow evaluation instruction. If the instruction is a cut flow evaluation instruction, the next step is executed continuously. The big data platform analyzes the switching evaluation instruction and inquires the switching index data of the monitoring platform (a plurality of switching indexes of the server cluster are appointed, such as CPU utilization rate and the like). The monitoring platform can return the tangent flow index data within a certain time range to the big data platform.
In a preferred embodiment, the request to cut flow includes a designated server cluster.
The method further includes, in S200, obtaining index data corresponding to the cut flow index in the server cluster through the server cluster information according to a preset cut flow index, before:
s130: and determining the designated server cluster according to the flow switching request.
S140: and acquiring a corresponding index configuration file according to the designated server cluster.
S150: and analyzing the index configuration file to obtain the tangent flow index.
Specifically, the configuration file may include configuration files of different configuration types, and the configuration types include cluster configuration, flow switching configuration, and packet configuration. The cluster configuration file comprises a cluster ID, a cluster name, a corresponding cluster IP address set and a corresponding cluster transaction name, namely the name of a specific server cluster and the IP address of each node in the corresponding cluster.
The cut flow configuration file comprises a cut flow configuration ID, a cluster name and a cut flow index, namely the cut flow index of the corresponding server cluster. The cut flow index storage may include cut flow index ID, cluster name, IP, index name, and index value, where the index name refers to CPU usage, memory usage, disk usage, network timeout, I/O throughput, and the index value refers to specific CPU usage.
The message configuration details include a message configuration ID, a message type, a cluster list, an index or a policy, that is, an evaluation type message, a set of names of designated clusters, and a predicted index. The command type message specifies the name set of the cluster, the cluster list, the flow switching time and the flow distribution strategy.
In a preferred embodiment, the step S200 of predicting the index data through a preset time series model to obtain a tangential flow index variation trend specifically includes:
s221: and preprocessing the index data.
S222: and predicting the preprocessed index data through a preset time sequence model to obtain the change trend of the tangential flow index.
It can be understood that, in order to improve the fitting accuracy of the fitting curve, the queried tangential flow index data may be preprocessed in advance according to the polynomial fitting requirement, so as to form a data set that can be processed by a correlation algorithm. Specifically, the preprocessing can include processing steps such as data cleaning and data standardization, so that the preprocessed index data can better meet the requirement of polynomial fitting, and the accuracy of a fitting curve obtained by fitting is improved. The preprocessing may adopt an existing data processing method, and is not described herein again.
In a preferred embodiment, the step S300 of performing flow switching control on the service traffic according to the flow switching indicator variation trend specifically includes:
s310: and obtaining the service flow change trend according to the cut flow index change trend and a fitting curve of the service flow and the cut flow index.
S320: and if the current service flow is larger than the corresponding service flow in the service flow variation trend, switching at least part of the service flow to other server clusters.
It can be understood that the tangential flow index change trend represents a change trend of the index data of the tangential flow index in a future time period, and a relationship between the index data of the tangential flow index and the traffic flow may be determined according to a fitting curve obtained by fitting in advance. Therefore, the change trend of the bearable service flow in the future time period can be obtained according to the change trend of the tangent flow index and the fitting curve, namely, the change trend of the index data of the tangent flow index representing the processing performance of the server cluster is predicted, and the change trend of the maximum service flow bearable by the server cluster corresponding to the change trend of the tangent flow index, namely, the change trend of the service flow is determined according to the corresponding relation between the index data and the fitting curve of the service flow.
And then, when the current service flow of the server cluster is larger than the corresponding service flow in the service flow change trend, switching at least part of the service flow to other server clusters. For example, the system may be provided with at least one master server cluster and at least one slave server cluster for processing the service traffic, and when the service traffic is greater than the corresponding service traffic in the service traffic variation trend, at least a part of the service traffic on the master server cluster may be transferred to the slave server cluster to perform the service traffic distribution.
In a preferred embodiment, the method further comprises the step of predetermining the fitted curve:
s301: and fitting the preprocessed historical index data according to a polynomial fitting algorithm to obtain a fitting curve corresponding to the service flow and each tangential flow index.
Specifically, the preprocessed tangential flow index is fitted according to a polynomial fitting algorithm to form a fitted curve, for example, y ═ aX may be formed1 n1+bX2 n2+cX3 n3+dX4 n4+eX5 n5+fX6 n6+gX7 n7+ h fitting curve, where y denotes traffic flow and X1、X2、X3、X4、X5、X6And X7For the index of tangential flow, a, b, c, d, e, f, g, h, n1, n2, n3, n4, n5, n6 and n7 are parameters of the index of tangential flow obtained by polynomial fitting. According to the obtained fitting curve, the variation trend of the tangent flow index can be obtained by estimating the highest upper limit of the performance, and relevant indexes comprise CPU (Central processing Unit) usage, memory usage, CPU usage rate, memory usage rate, disk usage rate, network timeout and I/O (input/output) throughput.
In a preferred embodiment, the step S310 of obtaining the traffic flow variation trend according to the tangential flow index variation trend and the fitted curve of the traffic flow and the tangential flow index specifically includes:
s311: determining the sampling tangential flow index at each sampling moment according to the tangential flow index change trend;
s312: determining sampling service flow corresponding to the sampling tangential flow index according to the sampling tangential flow index and the fitting curve;
s313: and fitting the sampled service flow at all sampling moments to obtain the service flow change trend.
Specifically, for the tangential flow index change trend, the sampling precision can be determined according to actual requirements, a plurality of sampling moments are further determined, the sampling tangential flow index of each sampling moment is determined from the tangential flow index change trend, and index data of the tangential flow indexes of a plurality of sampling moments in the future are obtained. And for each sampling cut-flow index, determining index data of the sampling cut-flow index, and further determining the service flow corresponding to the cut-flow index data as the maximum service flow bearable by the server cluster, namely the sampling service flow, according to the fitted curve. And finally, fitting the sampled service flow at all sampling moments to obtain the service flow variation trend.
In a preferred embodiment, the method further comprises the step of pre-establishing the time series model:
s302: acquiring historical index data of the tangential flow index within a historical preset time period;
s303: and training a preset machine learning model through the historical index data to obtain the time sequence model.
Specifically, a machine learning principle can be adopted to learn the index data of the traffic index history, the index data is used as a training sample, and a machine learning model is trained to obtain a time series model. Therefore, the change trend of the index data of the tangential flow index in the future can be predicted on the basis of the current index data according to the time series model, and the change trend of the tangential flow index is obtained.
In a preferred embodiment, the method further includes, before S200 obtaining, according to a preset cut flow index, index data corresponding to the cut flow index in the server cluster through the server cluster information, that:
s160: and receiving the monitoring message of the server cluster.
S170: analyzing the monitoring message to obtain the index data of each preset flow switching index.
It can be understood that a monitoring platform is usually provided in the existing system to monitor various operation data of the server cluster, so that the monitoring platform can receive the monitoring message of the server cluster and analyze the monitoring message to obtain the index data of each tangent flow index.
In one embodiment, the traffic flow switching method based on the time series model comprises a performance capacity fitting evaluation process. Firstly, an operation and maintenance worker sends a flow switching request to trigger a flow switching evaluation unit 11, checks whether a designated server cluster has a flow switching index change trend, if so, directly performs a flow switching configuration pushing process, if not, inquires the flow switching configuration unit 14 to obtain cluster information, assembles a flow switching evaluation message, sends the message to a big data platform 2 through a message sending/receiving unit, the big data platform 2 inquires flow switching index data from a monitoring platform 3 according to the instruction type, the monitoring platform 3 returns the index data to the big data platform 2 after acquiring related index data from a flow switching index storage unit 33 through a flow switching index access unit 34, and after preprocessing is performed by a data preprocessing unit 23, generates a flow switching index change trend through an index prediction unit 24, returns the flow switching index change trend to a flow switching evaluation module 1, and stores the flow switching index change trend in the flow switching configuration unit 14.
Specifically, as shown in fig. 8, the performance capacity fitting evaluation process may include the following steps:
step S101: the operation and maintenance personnel designate the server cluster to trigger the flow switching evaluation unit 11, and initiate flow switching evaluation.
Step S102: and inquiring whether the cut flow configuration unit 14 has a change trend of the cut flow index of the specified server cluster. And if the index exists, directly starting to switch the flow and configuring a pushing flow. And if no index exists, continuing to execute the next step.
Step S103: the cut-flow evaluation unit 11 obtains the corresponding server cluster information including cluster nodes, transaction information, and the like from the cut-flow configuration unit 14.
Step S104: the flow switching evaluation unit 11 assembles a flow switching evaluation message according to the selected server cluster and the relevant configuration information in the flow switching configuration unit.
Step S105: the message sending/receiving unit 12 sends the message assembled by the tangential flow evaluation unit to the big data platform 2.
Step S106: and the instruction receiving unit 21 of the big data platform 2 judges whether the instruction type is a cut flow evaluation instruction or not. If the instruction is a cut flow evaluation instruction, the next step is executed continuously.
Step S107: the instruction receiving unit 21 of the big data platform 2 analyzes according to the cut-stream evaluation instruction, and sends a data request to the data query unit 22.
Step S108: the data query unit 22 queries the data of the tangent flow index (specifying several tangent flow indexes of the server cluster, such as CPU utilization rate, etc.) of the monitoring platform 3 according to the data query request
Step S109: and a flow cutting index access unit 34 of the monitoring platform 3 forms an access request according to the server cluster range and the flow cutting index.
Step S110: the cut-flow index storage unit 33 of the monitoring platform 3 returns cut-flow index data within a certain time range according to the access request.
Step S111: the tangential flow index access unit 34 of the monitoring platform 3 returns tangential flow index data to the big data platform 2.
Step S112: the tangential flow index data provided by the monitoring platform 3 enters the data preprocessing unit 23 of the big data platform 2, and the data is preprocessed according to the preprocessing requirement of the preset time series model according to the requirement of the evaluation instruction.
Step S113: the data read by the index prediction unit 24 and processed by the data preprocessing unit 23 is predicted by a time series model to generate a tangential flow index change trend.
Step S114: the index sending unit 25 sends the tangential flow index change tendency generated by the index prediction unit 24 to the tangential flow evaluation module.
Step S115: and storing the change trend of the corresponding server cluster cut flow index generated by the big data platform 2 to a cut flow configuration unit.
Further, the service traffic flow switching method based on the time series model further comprises a switching configuration pushing process: firstly, an operation and maintenance person triggers the switching configuration pushing, a server cluster is appointed to set a switching index through a switching control unit 13, whether the switching index change trend exists in a switching configuration unit 14 or not is checked, and if the switching index change trend exists, a switching instruction message template in the switching configuration unit 14 is continuously read, and a switching instruction is organized. The flow switching instruction is pushed to the flow distribution platform 4 through the message sending/receiving unit 12, and after the flow distribution platform 4 analyzes the flow switching index of the flow switching instruction, the flow switching is performed through the flow switching unit 43.
Specifically, the flow switching unit 43 may obtain the traffic flow variation trend based on the flow switching index variation trend and a preset fitting curve of the flow switching index and the traffic flow, so as to obtain a flow switching prediction index of the traffic flow, and compare the traffic flow with the predicted flow switching prediction index, if the traffic flow is smaller than the flow switching prediction index, the flow switching is not required to be controlled, and the process is directly ended. And if the service flow is greater than the cut flow prediction index, switching at least part of the service flow to other server clusters according to a flow distribution strategy for processing.
As shown in fig. 8, the cut flow configuration push flow:
step S201: the operation and maintenance personnel trigger the flow switching configuration pushing, and the flow switching control unit 13 designates the server cluster to set the flow switching index.
Step S202: and inquiring whether the cut flow configuration unit 14 has a change trend of the cut flow index of the specified server cluster.
Step S203: the flow switching control unit 13 reads the flow switching message template configuration information and the server cluster information in the flow switching configuration unit 14.
Step S204: the switching control unit 13 sets a switching index variation trend and a switching message template according to the designated server cluster, and assembles the switching message.
Step S205: the message sending/receiving unit 12 sends the assembled message to the designated server cluster.
Step S206: the flow switching instruction receiving unit 41 of the flow switching evaluation module 14 of each node of the server cluster receives and analyzes the flow switching message instruction.
Step S207: the cut-flow command receiving unit 41 stores the analyzed cut-flow configuration in the cut-flow configuration unit 42.
Step S208: the flow switching unit 43 performs flow switching in accordance with a flow switching configuration in the form of a token bucket or the like.
The invention evaluates the transaction processing upper limit of the whole server cluster through a preset time sequence model based on the monitoring data accumulated by the monitoring platform, and realizes the general flow switching control flow and strategy. Specifically, the index data change trend is predicted according to actual production cut-flow index data, the production cluster transaction processing upper limit is reasonably evaluated, cut-flow control is performed based on the index data change trend and the cluster transaction processing upper limit, the cut-flow control is more reasonable, a large amount of performance test workload is saved, and operation and maintenance efficiency and stable production operation are facilitated. The performance test cost is reduced, the accuracy of the prediction of the change trend of the system tangential flow index and the stability of a service system are improved, the existing capabilities of the existing monitoring platform and the existing big data platform can be fully utilized, and the operation and maintenance convenience is improved.
Based on the same principle, the embodiment also discloses a service flow cut-off device based on the time series model. The device comprises a tangential flow evaluation module, a big data platform, a monitoring platform and a flow distribution platform.
The system comprises a tangent flow evaluation module, a big data platform and a monitoring platform, wherein the tangent flow evaluation module is used for receiving a tangent flow request of an operation and maintenance personnel terminal, acquiring server cluster information for processing a service, acquiring index data corresponding to the tangent flow index in a server cluster from the big data platform and the monitoring platform through the server cluster information according to a preset tangent flow index, and predicting the index data through a preset time sequence model to obtain the change trend of the tangent flow index;
and the flow distribution platform is used for carrying out flow switching control on the service flow according to the flow switching index variation trend.
Since the principle of the device for solving the problems is similar to the method, the implementation of the device can refer to the implementation of the method, and the detailed description is omitted here.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. A typical implementation device is a computer device, which may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
In a typical example, the computer device specifically comprises a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method performed by the client as described above when executing the program, or the processor implementing the method performed by the server as described above when executing the program.
Referring now to FIG. 9, shown is a schematic diagram of a computer device 600 suitable for use in implementing embodiments of the present application.
As shown in fig. 9, the computer apparatus 600 includes a Central Processing Unit (CPU)601 which can perform various appropriate works and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM)) 603. In the RAM603, various programs and data necessary for the operation of the system 600 are also stored. The CPU601, ROM602, and RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output section 607 including a Cathode Ray Tube (CRT), a liquid crystal feedback (LCD), and the like, and a speaker and the like; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 606 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted as necessary on the storage section 608.
In particular, according to an embodiment of the present invention, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the invention include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (13)
1. A service flow switching method based on a time series model is characterized by comprising the following steps:
receiving a flow switching request transmitted by an operation and maintenance personnel terminal;
acquiring server cluster information for processing a service, acquiring index data corresponding to a cut flow index in a server cluster through the server cluster information according to a preset cut flow index, and predicting the index data through a preset time sequence model to obtain a change trend of the cut flow index;
and performing flow switching control on the service flow according to the flow switching index variation trend.
2. The method of claim 1, further comprising, before obtaining the server cluster information for processing the service:
determining whether a corresponding change trend of the flow switching index exists according to the flow switching request, and if so, performing flow switching control on the service flow according to the change trend of the flow switching index;
and if not, executing to obtain the server cluster information of the processing service.
3. The traffic flow switching method based on the time series model according to claim 1, wherein the switching request includes a designated server cluster;
the acquiring server cluster information of a processing service, and acquiring index data corresponding to a cut flow index in a server cluster according to a preset cut flow index through the server cluster information specifically includes:
determining the designated server cluster according to the flow switching request;
acquiring server cluster information of the designated server cluster, wherein the server cluster information comprises cluster nodes and transaction information;
and acquiring index data corresponding to the tangent flow index according to the server cluster information.
4. The traffic flow switching method based on the time series model according to claim 3, wherein the switching request includes a designated server cluster;
the method further comprises the following steps of obtaining index data corresponding to the flow cutting indexes in the server cluster through the server cluster information according to preset flow cutting indexes, wherein before:
determining the designated server cluster according to the flow switching request;
acquiring a corresponding index configuration file according to the designated server cluster;
and analyzing the index configuration file to obtain the tangent flow index.
5. The method for traffic flow switching based on the time series model according to claim 1, wherein the predicting the index data by the preset time series model to obtain the switching index variation trend specifically includes:
preprocessing the index data;
and predicting the preprocessed index data through a preset time sequence model to obtain the change trend of the tangential flow index.
6. The method according to claim 1, wherein the performing traffic flow switching control on the traffic flow according to the traffic flow index variation trend specifically comprises:
obtaining a service flow change trend according to the cut flow index change trend and a fitting curve of service flow and the cut flow index;
and if the current service flow is larger than the corresponding service flow in the service flow variation trend, switching at least part of the service flow to other server clusters.
7. The traffic flow switching method based on the time series model according to claim 6, further comprising the step of predetermining the fitting curve:
and fitting the preprocessed historical index data according to a polynomial fitting algorithm to obtain a fitting curve corresponding to the service flow and each tangential flow index.
8. The traffic flow switching method based on the time series model according to claim 6, wherein obtaining the traffic flow change trend according to the traffic flow change trend and a fitted curve of the traffic flow and the traffic flow index specifically comprises:
determining the sampling tangential flow index at each sampling moment according to the tangential flow index change trend;
determining sampling service flow corresponding to the sampling tangential flow index according to the sampling tangential flow index and the fitting curve;
and fitting the sampled service flow at all sampling moments to obtain the service flow change trend.
9. The method for traffic flow switching based on time series model according to claim 1, further comprising the step of pre-establishing the time series model:
acquiring historical index data of the tangential flow index within a historical preset time period;
and training a preset machine learning model through the historical index data to obtain the time sequence model.
10. The method for traffic flow switching based on time series model according to claim 1, further comprising:
receiving a monitoring message of the server cluster;
analyzing the monitoring message to obtain the index data of each preset flow switching index.
11. A service flow switching device based on a time series model is characterized by comprising a switching evaluation module, a big data platform, a monitoring platform and a flow distribution platform;
the system comprises a tangent flow evaluation module, a big data platform and a monitoring platform, wherein the tangent flow evaluation module is used for receiving a tangent flow request transmitted by an operation and maintenance personnel terminal, acquiring server cluster information for processing a service, acquiring index data corresponding to the tangent flow index in a server cluster from the big data platform and the monitoring platform through the server cluster information according to a preset tangent flow index, and predicting the index data through a preset time sequence model to obtain the change trend of the tangent flow index;
and the flow distribution platform is used for carrying out flow switching control on the service flow according to the flow switching index variation trend.
12. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor,
the processor, when executing the program, implements the method of any of claims 1-10.
13. A computer-readable medium, having stored thereon a computer program,
the program when executed by a processor implementing the method according to any one of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111359801.3A CN114051000A (en) | 2021-11-17 | 2021-11-17 | Service flow switching method and device based on time series model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111359801.3A CN114051000A (en) | 2021-11-17 | 2021-11-17 | Service flow switching method and device based on time series model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114051000A true CN114051000A (en) | 2022-02-15 |
Family
ID=80209597
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111359801.3A Pending CN114051000A (en) | 2021-11-17 | 2021-11-17 | Service flow switching method and device based on time series model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114051000A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160140262A1 (en) * | 2014-11-16 | 2016-05-19 | International Business Machines Corporation | Predicting Performance Regression of a Computer System with a Complex Queuing Network Model |
| CN107659595A (en) * | 2016-07-25 | 2018-02-02 | 阿里巴巴集团控股有限公司 | A kind of method and apparatus for the ability for assessing distributed type assemblies processing specified services |
| CN108259376A (en) * | 2018-04-24 | 2018-07-06 | 北京奇艺世纪科技有限公司 | The control method and relevant device of server cluster service traffics |
| CN108667938A (en) * | 2018-05-18 | 2018-10-16 | 阿里巴巴集团控股有限公司 | Switch the method, apparatus and server of flow |
| CN110083512A (en) * | 2019-04-16 | 2019-08-02 | 上海易点时空网络有限公司 | The method and device of cluster monitoring |
| CN110471671A (en) * | 2019-08-12 | 2019-11-19 | 深圳前海微众银行股份有限公司 | Using dispositions method, device, system, equipment and computer readable storage medium |
| CN111459761A (en) * | 2020-04-01 | 2020-07-28 | 广州虎牙科技有限公司 | Redis configuration method, device, storage medium and equipment |
| CN111966289A (en) * | 2020-08-13 | 2020-11-20 | 上海哔哩哔哩科技有限公司 | Partition optimization method and system based on Kafka cluster |
| CN112162821A (en) * | 2020-09-25 | 2021-01-01 | 中国电力科学研究院有限公司 | Container cluster resource monitoring method, device and system |
| CN112613995A (en) * | 2020-12-30 | 2021-04-06 | 中国工商银行股份有限公司 | Abnormality diagnosis method and apparatus |
| CN112633542A (en) * | 2019-09-24 | 2021-04-09 | 顺丰科技有限公司 | System performance index prediction method, device, server and storage medium |
| CN113094198A (en) * | 2021-04-13 | 2021-07-09 | 中国工商银行股份有限公司 | Service fault positioning method and device based on machine learning and text classification |
-
2021
- 2021-11-17 CN CN202111359801.3A patent/CN114051000A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160140262A1 (en) * | 2014-11-16 | 2016-05-19 | International Business Machines Corporation | Predicting Performance Regression of a Computer System with a Complex Queuing Network Model |
| CN107659595A (en) * | 2016-07-25 | 2018-02-02 | 阿里巴巴集团控股有限公司 | A kind of method and apparatus for the ability for assessing distributed type assemblies processing specified services |
| CN108259376A (en) * | 2018-04-24 | 2018-07-06 | 北京奇艺世纪科技有限公司 | The control method and relevant device of server cluster service traffics |
| CN108667938A (en) * | 2018-05-18 | 2018-10-16 | 阿里巴巴集团控股有限公司 | Switch the method, apparatus and server of flow |
| CN110083512A (en) * | 2019-04-16 | 2019-08-02 | 上海易点时空网络有限公司 | The method and device of cluster monitoring |
| CN110471671A (en) * | 2019-08-12 | 2019-11-19 | 深圳前海微众银行股份有限公司 | Using dispositions method, device, system, equipment and computer readable storage medium |
| CN112633542A (en) * | 2019-09-24 | 2021-04-09 | 顺丰科技有限公司 | System performance index prediction method, device, server and storage medium |
| CN111459761A (en) * | 2020-04-01 | 2020-07-28 | 广州虎牙科技有限公司 | Redis configuration method, device, storage medium and equipment |
| CN111966289A (en) * | 2020-08-13 | 2020-11-20 | 上海哔哩哔哩科技有限公司 | Partition optimization method and system based on Kafka cluster |
| CN112162821A (en) * | 2020-09-25 | 2021-01-01 | 中国电力科学研究院有限公司 | Container cluster resource monitoring method, device and system |
| CN112613995A (en) * | 2020-12-30 | 2021-04-06 | 中国工商银行股份有限公司 | Abnormality diagnosis method and apparatus |
| CN113094198A (en) * | 2021-04-13 | 2021-07-09 | 中国工商银行股份有限公司 | Service fault positioning method and device based on machine learning and text classification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108632365B (en) | Service resource adjusting method, related device and equipment | |
| CN111026553B (en) | Resource scheduling method and server system for offline mixed part operation | |
| CN109981744B (en) | Data distribution method and device, storage medium and electronic equipment | |
| CN107645483B (en) | Risk identification method, risk identification device, cloud risk identification device and system | |
| CN111198808A (en) | Method, device, storage medium and electronic equipment for predicting performance index | |
| CN112187512B (en) | Port automatic expansion method, device and equipment based on flow monitoring | |
| CN113704063B (en) | Performance monitoring method, device, equipment and storage medium of cloud mobile phone | |
| CN113312244A (en) | Fault monitoring method, equipment, program product and storage medium | |
| CN113031976B (en) | Cluster capacity management method, device and medium based on Ambari | |
| CN111885618A (en) | Network performance optimization method and device | |
| CN113360353A (en) | Test server and cloud platform | |
| CN114051000A (en) | Service flow switching method and device based on time series model | |
| CN116992982A (en) | Model deployment method, device, system, electronic equipment and storage medium | |
| CN108770014B (en) | Calculation evaluation method, system and device of network server and readable storage medium | |
| CN112214303A (en) | Kubernetes cluster automatic scaling system | |
| CN115048186A (en) | Method and device for processing expansion and contraction of service container, storage medium and electronic equipment | |
| CN114079635A (en) | Service flow current limiting method and device based on polynomial fitting | |
| CN110989518B (en) | Control method and control system for integrated manufacturing field | |
| CN114625570A (en) | Database backup scheduling method and device | |
| CN113204411A (en) | Data processing method, intermediate processing equipment and storage medium | |
| CN112418509A (en) | Task data prediction method and device, storage medium and electronic device | |
| CN110955728A (en) | Power consumption data transmission method, server and storage medium | |
| CN113656299B (en) | Method and device for determining limit QPS, electronic equipment and readable storage medium | |
| CN111258866A (en) | Computer performance prediction method, device, equipment and readable storage medium | |
| WO2023119623A1 (en) | Management device, communication system, control method, and non-transitory computer-readable medium |
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 |