Adaptive routing method, device, equipment and readable storage medium for cloud dedicated line
Patent Information
- Application Number
- CN202111613722.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-27
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2041-12-27
AI Technical Summary
针对云专线选路这一需求,目前主要是采用静态配置主备、负载模式实现,对于主备模式而言,其只能固定选择一条链路而不能动态调整;对于负载模式而言,其只能平均选路而不能考虑实际物理链路质量选路,即目前的选路模式只能固定的选择专线物理链路,难以实现链路的自适应调整
[0010] The adaptive routing method of the cloud private line provided by the embodiment of the present invention uses the machine learning model of the support vector machine to establish a multi-dimensional feature vector of the traffic data sample value and the link configuration sample value, and uses the multi-dimensional feature vector as the cloud private line Type, the resulting routing model can perform intelligent routing based on the type of cloud private line.
Smart Images

Figure CN114465954B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of cloud computing technology, and in particular to an adaptive routing method, device, equipment and readable storage medium for a cloud dedicated line. Background Art
[0002] With the development of cloud computing technology, cloud dedicated lines are becoming increasingly important for enterprises to enter the cloud. Cloud dedicated lines include optical transport network (OTN), IP radio access network (IPRAN) and passive optical network (PON). Since the link data of cloud dedicated lines such as OTN, IPRAN and PON are very different, the access methods of sub-cloud dedicated lines are also very different.
[0003] As an important node for enterprises to enter the cloud, cloud dedicated lines often choose two or more types of dedicated lines considering the high availability of cloud dedicated lines, which requires cloud dedicated line routing. In response to the demand for cloud dedicated line routing, static configuration of active and standby and load modes are currently used. For active and standby modes, it can only select a fixed link and cannot be adjusted dynamically; for load modes, it can only select routes on an average basis and cannot consider the actual physical link quality. That is, the current routing mode can only select dedicated line physical links, making it difficult to achieve adaptive adjustment of links. Summary of the invention
[0004] In view of this, an embodiment of the present invention provides an adaptive routing method, device, equipment and readable storage medium for a cloud dedicated line to solve the problem that the current routing mode can only fixedly select the dedicated line physical link and it is difficult to achieve adaptive adjustment of the link.
[0005] According to the first aspect, an embodiment of the present invention provides an adaptive routing method for a cloud dedicated line, which is used to control a device. The method includes: obtaining link configuration data and link traffic data corresponding to a cloud dedicated line switch; inputting the link configuration data and the link traffic data into a preset routing model to obtain a routing strategy; and sending the routing strategy to the cloud dedicated line switch so that the cloud dedicated line switch dynamically adjusts the communication link according to the routing strategy.
[0006] The adaptive routing method for cloud dedicated lines provided in an embodiment of the present invention controls a device to obtain link configuration data and link flow data corresponding to a cloud dedicated line switch, input the link configuration data and link flow data into a preset routing model, obtain a routing strategy, and send the routing strategy to the cloud dedicated line switch so that the cloud dedicated line switch dynamically adjusts the communication link according to the routing strategy. This enables adaptive dynamic adjustment of the communication link according to the link configuration data and the link flow data collected in real time, thereby meeting more cloud dedicated line access scenarios and improving the quality of network services.
[0007] In combination with the first aspect, in a first implementation of the first aspect, the method for generating the routing model includes: collecting the flow data sample values and link configuration sample values corresponding to the cloud dedicated switch, and determining the routing results corresponding to the flow data sample values and the link configuration sample values; training a preset training model based on the flow data sample values, the link configuration sample values and the routing results to obtain the routing model.
[0008] In combination with the first implementation of the first aspect, in the second implementation of the first aspect, the preset training model is trained based on the traffic data sample values, the link configuration sample values and the routing results to obtain the routing model, including: generating a multidimensional feature vector based on the traffic data sample values and the link configuration sample values; inputting the multidimensional feature vector and the routing results into the preset training model, training the preset training model, and obtaining the routing model.
[0009] In combination with the second implementation manner after the first implementation manner of the first aspect, in a third implementation manner of the first aspect, the preset training model is a support vector machine model.
[0010] The adaptive routing method for cloud dedicated lines provided in an embodiment of the present invention establishes a multi-dimensional feature vector of traffic data sample values and link configuration sample values through a machine learning model of a support vector machine, and uses the multi-dimensional feature vector as the cloud dedicated line type. The routing model obtained thereby can perform intelligent routing according to the cloud dedicated line type.
[0011] In combination with the first aspect, in a fourth implementation of the first aspect, obtaining link configuration data corresponding to a cloud dedicated switch includes: obtaining a link type corresponding to the cloud dedicated switch; and determining the link configuration data corresponding to the cloud dedicated switch based on the link type.
[0012] The adaptive routing method for a cloud dedicated line provided in an embodiment of the present invention enables a control device to obtain the link type corresponding to a cloud dedicated line switch, and determine the link configuration data corresponding to the cloud dedicated line switch based on the link type, thereby enabling the cloud dedicated line type to be determined according to the link configuration data, so that the accuracy of the adaptive routing of the cloud dedicated line can be further ensured based on the link configuration data corresponding to the current cloud dedicated line type.
[0013] According to the second aspect, an embodiment of the present invention provides an adaptive routing method for a cloud dedicated line, which is used for a cloud dedicated line switch. The method includes: collecting link traffic data corresponding to the cloud dedicated line switch, and reporting the link traffic data to a control device so that the control device determines a routing strategy based on the link configuration data and the link traffic data; receiving the routing strategy issued by the control device; and dynamically adjusting the communication link of the cloud dedicated line switch according to the routing strategy.
[0014] The adaptive routing method for cloud dedicated lines provided in an embodiment of the present invention, the cloud dedicated line switch collects link traffic data corresponding to the cloud dedicated line switch, and reports the link traffic data to the control device, so that the control device determines the routing strategy according to the link configuration data and the link traffic data, and can dynamically adjust the communication link of the cloud dedicated line switch according to the routing strategy issued by the control device, thereby solving the problem of only being able to select a fixed communication link, realizing adaptive dynamic adjustment of the communication link, and improving the network service quality.
[0015] According to the third aspect, an embodiment of the present invention provides an adaptive routing device for a cloud dedicated line, which is used to control equipment. The device includes: an acquisition module, which is used to obtain link configuration data and link traffic data corresponding to a cloud dedicated line switch; a determination module, which is used to input the link configuration data and the link traffic data into a preset routing model to obtain a routing strategy; and a sending module, which is used to send the routing strategy to the cloud dedicated line switch so that the cloud dedicated line switch dynamically adjusts the communication link according to the routing strategy.
[0016] According to the fourth aspect, an embodiment of the present invention provides an adaptive routing device for a cloud dedicated line, which is used for a cloud dedicated line switch. The device includes: a collection module, which is used to collect link traffic data corresponding to the cloud dedicated line switch, and report the link traffic data to a control device, so that the control device determines a routing strategy based on the link configuration data and the link traffic data; a receiving module, which is used to receive the routing strategy issued by the control device; and an adjustment module, which is used to dynamically adjust the communication link of the cloud dedicated line switch according to the routing strategy.
[0017] According to the fifth aspect, an embodiment of the present invention provides an electronic device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the adaptive routing method for cloud dedicated lines described in the first aspect or any embodiment of the first aspect, or the adaptive routing method for cloud dedicated lines described in the second aspect, by executing the computer instructions.
[0018] According to the sixth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the adaptive routing method for a cloud dedicated line described in the first aspect or any implementation scheme of the first aspect, or the adaptive routing method for a cloud dedicated line described in the second aspect.
[0019] It should be noted that the corresponding beneficial effects of the adaptive routing device, electronic device and computer-readable storage medium of the cloud dedicated line provided by the embodiments of the present invention can be found in the description of the corresponding contents in the adaptive routing method of the cloud dedicated line, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0021] Figure 1 is a flow chart of the adaptive routing method of the cloud dedicated line controlling the device end in this embodiment;
[0022] Figure 2 is another flow chart of the adaptive routing method for controlling the cloud dedicated line on the device side in this embodiment;
[0023] Figure 3 is another flow chart of the adaptive routing method for controlling the cloud dedicated line on the device side in this embodiment;
[0024] Figure 4 is a flow chart of the adaptive routing method of the cloud dedicated line at the cloud dedicated line switch end in this embodiment;
[0025] Figure 5 This is an overall flow chart of the adaptive routing method for cloud dedicated lines in this embodiment;
[0026] Figure 6 The overall deployment architecture diagram of the intelligent routing system in this embodiment is shown;
[0027] Figure 7This is a structural block diagram of the adaptive routing device of the cloud dedicated line at the control device end of this embodiment;
[0028] Figure 8 1 is a structural block diagram of an adaptive routing device for a cloud dedicated line at a cloud dedicated line switch end of the present embodiment;
[0029] Fig. 9 It is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0030] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0031] The technical solution of the present invention sets a routing model to adaptively and dynamically adjust the communication link according to the link configuration data and link traffic data corresponding to the cloud dedicated line switch without manual intervention, thereby effectively improving the cloud access experience and network service quality of the cloud dedicated line.
[0032] According to an embodiment of the present invention, an embodiment of an adaptive routing method for a cloud dedicated line is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0033] In this embodiment, an adaptive routing method for a cloud dedicated line is provided, which can be used to control devices such as mobile phones, tablet computers, and computers. Figure 1 is a flow chart of an adaptive routing method for a cloud dedicated line according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:
[0034] S11, obtaining the link configuration data and link flow data corresponding to the cloud dedicated line switch.
[0035] The link configuration data is the link information corresponding to the physical port of the cloud dedicated line switch and the cloud access interface of the private network (Virtual Private Cloud, VPC) gateway. Specifically, the link configuration data includes information such as link quality value, link price value and user weight value. Among them, the link quality value is used to characterize the link network quality of the cloud dedicated line, the link price value is used to characterize the link setting price of the cloud dedicated line, and the user weight value is used to characterize the link demand for the cloud dedicated line. Of course, the link configuration data can also include other link configuration information for characterizing the link corresponding to the cloud dedicated line switch, which is not specifically limited here and can be determined by technicians in this field according to actual needs.
[0036] The link configuration data is determined by the user according to actual needs and stored in the database. The control device can obtain the link configuration data corresponding to the current cloud dedicated line switch by accessing the database.
[0037] Link traffic data is the traffic information collected by the cloud dedicated line switch in real time to characterize the link corresponding to the cloud dedicated line switch. Specifically, the link traffic data may include information such as data packet transmission rate and packet loss rate. The cloud dedicated line switch can report the link traffic data collected in real time to the control device. Accordingly, the control device can obtain the link traffic data uploaded by the cloud dedicated line switch in real time.
[0038] S12, inputting the link configuration data and the link flow data into a preset routing model to obtain a routing strategy.
[0039] The preset routing model is used to generate the optimal routing strategy based on the link configuration data and link traffic data corresponding to the current cloud dedicated line switch. The routing strategy is used to instruct the cloud dedicated line switch to perform routing selection to obtain a communication link that meets the current link configuration data and the current link traffic data.
[0040] S13: Send the routing strategy to the cloud dedicated line switch, so that the cloud dedicated line switch dynamically adjusts the communication link according to the routing strategy.
[0041] After the routing model in the control device outputs the routing strategy, the communication interface can be called to send the routing strategy to the cloud dedicated line switch, so that the cloud dedicated line switch can adjust the route according to the routing strategy, thereby realizing dynamic adjustment of the communication link to determine the optimal communication link.
[0042] The adaptive routing method for cloud dedicated lines provided in this embodiment controls the device to obtain the link configuration data and link flow data corresponding to the cloud dedicated line switch, input the link configuration data and link flow data into a preset routing model, obtain a routing strategy, and send the routing strategy to the cloud dedicated line switch so that the cloud dedicated line switch dynamically adjusts the communication link according to the routing strategy. This enables adaptive dynamic adjustment of the communication link according to the link configuration data and the link flow data collected in real time, thereby meeting more cloud dedicated line access scenarios and improving the quality of network services.
[0043] In this embodiment, an adaptive routing method for a cloud dedicated line is provided, which can be used to control devices such as mobile phones, tablet computers, and computers. Figure 2 is a flow chart of an adaptive routing method for a cloud dedicated line according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:
[0044] S20, collecting the flow data sample values and link configuration sample values corresponding to the cloud dedicated line switch, and determining the routing results corresponding to the flow data sample values and link configuration sample values.
[0045] The traffic data sample values and link configuration sample values are collected offline to characterize the link status of each communication link corresponding to the cloud dedicated line switch. The routing results are used to characterize the optimal communication link determined based on the current traffic data sample values and link configuration sample values.
[0046] S21, training a preset training model based on the flow data sample value, the link configuration sample value and the routing result to obtain a routing model.
[0047] The preset training model is a support vector machine (SVM) model, which uses the flow data sample value and the link configuration sample value as input, and the routing result as output to train in the SVM model, obtain a trained routing model, and load the routing model to the control device. For example, if the link configuration sample value includes a link quality value, a link price value, and a user weighted value, the flow data sample value, the link quality value, the link price value, and the user weighted value are used as the input of the model, and the routing result is used as the output of the model, the input and output are placed in the SVM model for training, and a trained SVM model, i.e., a routing model, is obtained.
[0048] Specifically, the above step S21 may include:
[0049] (1) Generate a multi-dimensional feature vector based on the traffic data sample values and link configuration sample values.
[0050] The flow data sample value and the link configuration sample value are used as the link features corresponding to the cloud dedicated line switch, and the flow data sample value and the link configuration sample value are combined to generate a multi-dimensional feature vector. For example, the flow data sample value, the link quality value, the link price value and the user weight value are combined into a multi-dimensional feature vector.
[0051] (2) The multi-dimensional feature vector and the routing result are input into a preset training model, and the preset training model is trained to obtain a routing model.
[0052] The routing result is used as the output vector, the multidimensional feature vector is used as the input vector, and the input vector and the output vector are input as training vectors into a preset training model for model training to obtain a trained model, that is, a routing model for determining the optimal communication link.
[0053] S22, obtaining the link configuration data and link flow data corresponding to the cloud dedicated line switch. For detailed description, please refer to the relevant description of the above embodiment, which will not be repeated here.
[0054] S23, input the link configuration data and the link flow data into a preset routing model to obtain a routing strategy. For detailed description, please refer to the relevant description of the above embodiment, which will not be repeated here.
[0055] S24, sending the routing strategy to the cloud dedicated line switch, so that the cloud dedicated line switch dynamically adjusts the communication link according to the routing strategy. For detailed description, please refer to the relevant description of the above embodiment, which will not be repeated here.
[0056] The adaptive routing method for cloud dedicated lines provided in this embodiment establishes a multi-dimensional feature vector of traffic data sample values and link configuration sample values through a machine learning model of a support vector machine, and uses the multi-dimensional feature vector as the cloud dedicated line type. The resulting routing model can perform intelligent routing according to the cloud dedicated line type.
[0057] In this embodiment, an adaptive routing method for a cloud dedicated line is provided, which can be used to control devices such as mobile phones, tablet computers, and computers. Figure 3 is a flow chart of an adaptive routing method for a cloud dedicated line according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:
[0058] S31, obtaining link configuration data and link flow data corresponding to the cloud dedicated line switch.
[0059] Specifically, the above step S31 may include:
[0060] S311, obtaining the link flow data corresponding to the cloud dedicated line switch.
[0061] The cloud dedicated line switch can collect the corresponding link traffic data in real time and report it to the control device in real time. Correspondingly, the control device can obtain the link traffic data reported by the cloud dedicated line switch in real time.
[0062] S312: Obtain the link type corresponding to the cloud dedicated line switch.
[0063] The link type is used to characterize the cloud dedicated line type, which includes OTN, IPRAN, PON, etc. Different cloud dedicated line types have different identification information in their link traffic data. The control device can determine the link type corresponding to the cloud dedicated line switch by analyzing the identification information carried in the link traffic data reported by the cloud dedicated line switch.
[0064] S313: Determine the link configuration data corresponding to the cloud dedicated line switch based on the link type.
[0065] Different link types have corresponding link configuration data. The database stores link configuration data corresponding to each link type. The control device can retrieve corresponding link configuration data from the database according to the determined link type.
[0066] S32, input the link configuration data and the link flow data into a preset routing model to obtain a routing strategy. For detailed description, please refer to the relevant description of the above embodiment, which will not be repeated here.
[0067] S33, sending the routing strategy to the cloud dedicated line switch, so that the cloud dedicated line switch dynamically adjusts the communication link according to the routing strategy. For detailed description, please refer to the relevant description of the above embodiment, which will not be repeated here.
[0068] The adaptive routing method for the cloud dedicated line provided in this embodiment controls the device to obtain the link type corresponding to the cloud dedicated line switch, and determines the link configuration data corresponding to the cloud dedicated line switch based on the link type, thereby determining the cloud dedicated line type according to the link configuration data, so that the link configuration data corresponding to the current cloud dedicated line type can be used to further ensure the accuracy of the adaptive routing of the cloud dedicated line.
[0069] In this embodiment, an adaptive routing method for a cloud dedicated line is provided, which can be used for a cloud dedicated line switch. Figure 4 is a flow chart of an adaptive routing method for a cloud dedicated line according to an embodiment of the present invention. Figure 4 As shown, the process includes the following steps:
[0070] S41, collecting link flow data corresponding to the cloud dedicated line switch, and reporting the link flow data to the control device, so that the control device determines a routing strategy according to the link configuration data and the link flow data.
[0071] The cloud dedicated line switch can monitor the link traffic data corresponding to each link in its operating state in real time, such as the transmission rate of traffic data packets, the packet loss rate, etc. The cloud dedicated line switch is connected to the control device and can report the link traffic data collected in real time to the control device. When the control device receives the link traffic data, it can determine the current routing strategy in combination with the link configuration data corresponding to the cloud dedicated line switch, and send the routing strategy to the cloud dedicated line switch.
[0072] S42: Receive a routing policy sent by a control device.
[0073] The cloud dedicated line switch can monitor the communication interface between it and the control device in real time to determine whether the control device sends down a routing policy. When it detects that the control device sends down a routing policy to it, it can receive the routing policy through the communication interface.
[0074] S43: Dynamically adjust the communication link of the cloud dedicated line switch according to the routing strategy.
[0075] After receiving the routing strategy, the cloud dedicated line switch can analyze the routing information carried by the routing strategy and dynamically adjust the current communication link according to the routing information to obtain the best communication link.
[0076] The adaptive routing method for cloud dedicated lines provided in this embodiment is that the cloud dedicated line switch collects link traffic data corresponding to the cloud dedicated line switch and reports the link traffic data to the control device, so that the control device determines the routing strategy according to the link configuration data and the link traffic data, and can dynamically adjust the communication link of the cloud dedicated line switch according to the routing strategy issued by the control device, thereby solving the problem of only being able to select a fixed communication link, realizing adaptive dynamic adjustment of the communication link, and improving the network service quality.
[0077] In this embodiment, a method for adaptive routing of a cloud dedicated line is provided. Figure 6 The cloud dedicated line intelligent routing system shown in the figure, Figure 5 is a flow chart of an adaptive routing method for a cloud dedicated line according to an embodiment of the present invention. Figure 5 As shown, the process includes the following steps:
[0078] S51, the cloud dedicated line switch collects the corresponding link traffic data. For detailed description, please refer to the relevant description of the above embodiment, which will not be repeated here.
[0079] S52: reporting the link flow data to the control device. For detailed description, please refer to the relevant description of the above embodiment, which will not be repeated here.
[0080] S53, the control device receives the link flow data reported by the cloud dedicated line switch. For detailed description, please refer to the relevant description of the above embodiment, which will not be repeated here.
[0081] S54, the control device obtains the link configuration data of the cloud dedicated line switch. For detailed description, please refer to the relevant description of the above embodiment, which will not be repeated here.
[0082] S55, the control device inputs the link configuration data and the link flow data into a preset routing model to obtain a routing strategy. For detailed description, please refer to the relevant description of the above embodiment, which will not be repeated here.
[0083] S56, the control device sends the routing strategy to the cloud dedicated line switch. For detailed description, please refer to the relevant description of the above embodiment, which will not be repeated here.
[0084] S57, the cloud dedicated line switch receives the routing policy sent by the control device. For detailed description, please refer to the relevant description of the above embodiment, which will not be repeated here.
[0085] S58, the cloud dedicated line switch dynamically adjusts the communication link of the cloud dedicated line switch according to the routing strategy. For detailed description, please refer to the relevant description of the above embodiment, which will not be repeated here.
[0086] The adaptive routing method of the cloud dedicated line provided in this embodiment is that the cloud dedicated line switch collects the link flow data corresponding to the cloud dedicated line switch and reports the link flow data to the control device; the control device obtains the link configuration data and link flow data corresponding to the cloud dedicated line switch, inputs the link configuration data and link flow data into the preset routing model, obtains the routing strategy, and sends the routing strategy to the cloud dedicated line switch; the cloud dedicated line switch receives the routing strategy sent by the control device, and dynamically adjusts the communication link of the cloud dedicated line switch according to the routing strategy. This method can adaptively and dynamically adjust the communication link according to the link configuration data and the link flow data collected in real time, so as to meet more cloud dedicated line access scenarios, solve the problem of only being able to select a fixed communication link, realize the adaptive dynamic adjustment of the communication link, and improve the network service quality.
[0087] In this embodiment, an adaptive routing device for a cloud dedicated line is also provided, which is used to implement the above embodiments and preferred implementation modes, and will not be repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.
[0088] This embodiment provides an adaptive routing device for a cloud dedicated line, which is used to control a device, such as Figure 7 As shown, the device comprises:
[0089] The acquisition module 61 is used to acquire the link configuration data and link flow data corresponding to the cloud dedicated line switch. For detailed description, please refer to the relevant description corresponding to the above method embodiment, which will not be repeated here.
[0090] The determination module 62 is used to input the link configuration data and the link flow data into a preset routing model to obtain a routing strategy. For detailed description, please refer to the relevant description corresponding to the above method embodiment, which will not be repeated here.
[0091] The sending module 63 is used to send the routing strategy to the cloud dedicated line switch, so that the cloud dedicated line switch dynamically adjusts the communication link according to the routing strategy. For detailed description, please refer to the relevant description corresponding to the above method embodiment, which will not be repeated here.
[0092] The adaptive routing device for the cloud dedicated line provided in this embodiment controls the device to obtain the link configuration data and link flow data corresponding to the cloud dedicated line switch, input the link configuration data and link flow data into a preset routing model, obtain the routing strategy, and send the routing strategy to the cloud dedicated line switch so that the cloud dedicated line switch can dynamically adjust the communication link according to the routing strategy. In this way, adaptive dynamic adjustment of the communication link can be achieved according to the link configuration data and the link flow data collected in real time, thereby meeting more cloud dedicated line access scenarios and improving the network service quality.
[0093] The adaptive routing device of the cloud dedicated line in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.
[0094] The further functional description of each of the above modules is the same as that of the above corresponding embodiments and will not be repeated here.
[0095] This embodiment provides an adaptive routing device for a cloud dedicated line, which is used for a cloud dedicated line switch, such as Figure 8 As shown, the device comprises:
[0096] The collection module 71 is used to collect the link flow data corresponding to the cloud dedicated line switch and report the link flow data to the control device so that the control device determines the routing strategy according to the link configuration data and the link flow data. For detailed description, please refer to the relevant description corresponding to the above method embodiment, which will not be repeated here.
[0097] The receiving module 72 is used to receive the routing strategy sent by the control device. For detailed description, please refer to the relevant description of the above method embodiment, which will not be repeated here.
[0098] The adjustment module 73 is used to dynamically adjust the communication link of the cloud dedicated switch according to the routing strategy. For detailed description, please refer to the relevant description corresponding to the above method embodiment, which will not be repeated here.
[0099] The adaptive routing device for the cloud dedicated line provided in this embodiment, the cloud dedicated line switch collects the link flow data corresponding to the cloud dedicated line switch, and reports the link flow data to the control device, so that the control device determines the routing strategy according to the link configuration data and the link flow data, and can dynamically adjust the communication link of the cloud dedicated line switch according to the routing strategy issued by the control device, thereby solving the problem of only being able to select a fixed communication link, realizing adaptive dynamic adjustment of the communication link, and improving the network service quality.
[0100] The embodiment of the present invention also provides an electronic device having the above Figure 7 The adaptive routing device of the cloud dedicated line shown, or Figure 8 The adaptive routing device of the cloud dedicated line is shown.
[0101] See also Fig. 9 , Fig. 9 is a schematic diagram of the structure of an electronic device provided by an optional embodiment of the present invention, such as Fig. 9 As shown, the electronic device may include: at least one processor 801, such as a CPU (Central Processing Unit), at least one communication interface 803, a memory 804, and at least one communication bus 802. The communication bus 802 is used to realize the connection and communication between these components. The communication interface 803 may include a display screen (Display), a keyboard (Keyboard), and the optional communication interface 803 may also include a standard wired interface and a wireless interface. The memory 804 may be a high-speed RAM memory (Random Access Memory) or a non-volatile memory (non-volatile memory), such as at least one disk storage. The memory 804 may optionally be at least one storage device located away from the aforementioned processor 801. The processor 801 may be combined with Figure 7 or Figure 8 In the described adaptive routing device for cloud dedicated lines, the memory 804 stores an application program, and the processor 801 calls the program code stored in the memory 804 to execute any of the above method steps.
[0102] The communication bus 802 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The communication bus 802 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig. 9 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0103] Among them, the memory 804 may include a volatile memory (English: volatile memory), such as a random access memory (English: random-access memory, abbreviated: RAM); the memory may also include a non-volatile memory (English: non-volatile memory), such as a flash memory (English: flash memory), a hard disk drive (English: hard disk drive, abbreviated: HDD) or a solid-state drive (English: solid-state drive, abbreviated: SSD); the memory 804 may also include a combination of the above types of memory.
[0104] The processor 801 may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and a NP.
[0105] The processor 801 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.
[0106] Optionally, the memory 804 is also used to store program instructions. The processor 801 can call the program instructions to implement the present application Figures 1 to 5The adaptive routing method for cloud dedicated lines shown in the embodiment.
[0107] The embodiment of the present invention also provides a non-transitory computer storage medium, which stores computer executable instructions, and the computer executable instructions can execute the processing method of the adaptive routing method of the cloud dedicated line in any of the above method embodiments. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memory.
[0108] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.
Claims
1. An adaptive routing method for cloud dedicated lines, characterized in that: For controlling a device, the method comprises: Obtain link configuration data and link flow data corresponding to the cloud dedicated switch; the link configuration data is determined by the user according to actual needs and stored in a database, and the link configuration data corresponding to the cloud dedicated switch is obtained by accessing the database; the link flow data is the flow information collected in real time by the cloud dedicated switch to characterize the link corresponding to the cloud dedicated switch; Inputting the link configuration data and the link flow data into a preset routing model to obtain a routing strategy; wherein the preset routing model is used to generate an optimal routing strategy according to the link configuration data and the link flow data, and the routing strategy is used to instruct the cloud dedicated line switch to perform routing selection to obtain a communication link that satisfies the link configuration data and the link flow data; Sending the routing strategy to the cloud dedicated line switch so that the cloud dedicated line switch dynamically adjusts the communication link according to the routing strategy; The method for generating the routing model includes: Collecting the flow data sample value and the link configuration sample value corresponding to the cloud dedicated line switch, and determining the routing result corresponding to the flow data sample value and the link configuration sample value; The preset training model is trained based on the flow data sample value, the link configuration sample value and the routing result to obtain the routing model, including: Generate a multidimensional feature vector based on the traffic data sample value and the link configuration sample value; The multi-dimensional feature vector and the routing result are input into a preset training model, and the preset training model is trained to obtain a routing model; the preset training model is a support vector machine model.
2. The method according to claim 1, characterized in that Get the link configuration data corresponding to the cloud dedicated line switch, including: Obtain the link type corresponding to the cloud dedicated line switch; Determine link configuration data corresponding to the cloud dedicated switch based on the link type.
3. An adaptive routing method for cloud dedicated lines, characterized in that: For a cloud dedicated line switch, the method includes: Collect link flow data corresponding to the cloud dedicated switch, and report the link flow data to the control device, so that the control device determines the routing strategy according to the preset routing model, link configuration data and link flow data; the link configuration data is determined by the user according to actual needs and stored in the database, and the link configuration data corresponding to the cloud dedicated switch is obtained by accessing the database; the link flow data is the flow information collected by the cloud dedicated switch in real time for characterizing the link corresponding to the cloud dedicated switch; wherein the preset routing model is used to generate the optimal routing strategy according to the link configuration data and the link flow data, and the routing strategy is used to instruct the cloud dedicated switch to perform routing selection to obtain the satisfied The communication link of the link configuration data and the link flow data; wherein, the method for generating the routing model comprises: collecting the flow data sample value and the link configuration sample value corresponding to the cloud dedicated line switch, and determining the routing result corresponding to the flow data sample value and the link configuration sample value; training a preset training model based on the flow data sample value, the link configuration sample value and the routing result to obtain the routing model, comprising: generating a multidimensional feature vector based on the flow data sample value and the link configuration sample value; inputting the multidimensional feature vector and the routing result into a preset training model, and training the preset training model to obtain the routing model; the preset training model is a support vector machine model; Receiving a routing strategy sent by the control device; The communication link of the cloud dedicated switch is dynamically adjusted according to the routing strategy.
4. An adaptive routing device for a cloud dedicated line, characterized in that: For controlling a device, the apparatus comprises: The acquisition module is used to obtain the link configuration data and link flow data corresponding to the cloud dedicated line switch; A determination module is used to input the link configuration data and the link flow data into a preset routing model to obtain a routing strategy; the link configuration data is determined by the user according to actual needs and stored in a database, and the link configuration data corresponding to the cloud dedicated line switch is obtained by accessing the database; the link flow data is the flow information collected by the cloud dedicated line switch in real time to characterize the link corresponding to the cloud dedicated line switch; wherein the preset routing model is used to generate an optimal routing strategy according to the link configuration data and the link flow data, and the routing strategy is used to instruct the cloud dedicated line switch to perform routing selection to obtain a route that satisfies the link configuration data and the link flow data. Communication link of traffic data; wherein, the method for generating the routing model comprises: collecting the traffic data sample value and the link configuration sample value corresponding to the cloud dedicated line switch, and determining the routing result corresponding to the traffic data sample value and the link configuration sample value; training a preset training model based on the traffic data sample value, the link configuration sample value and the routing result to obtain the routing model, comprising: generating a multidimensional feature vector based on the traffic data sample value and the link configuration sample value; inputting the multidimensional feature vector and the routing result into a preset training model, and training the preset training model to obtain the routing model; the preset training model is a support vector machine model; The sending module is used to send the routing strategy to the cloud dedicated line switch, so that the cloud dedicated line switch dynamically adjusts the communication link according to the routing strategy.
5. An adaptive routing device for a cloud dedicated line, characterized in that: For a cloud dedicated line switch, the device comprises: A collection module is used to collect link flow data corresponding to the cloud dedicated line switch, and report the link flow data to the control device, so that the control device determines the routing strategy according to the preset routing model, link configuration data and link flow data; the link configuration data is determined by the user according to actual needs and stored in the database, and the link configuration data corresponding to the cloud dedicated line switch is obtained by accessing the database; the link flow data is the flow information collected by the cloud dedicated line switch in real time for characterizing the link corresponding to the cloud dedicated line switch; wherein the preset routing model is used to generate the optimal routing strategy according to the link configuration data and the link flow data, and the routing strategy is used to instruct the cloud dedicated line switch to perform routing selection to obtain to a communication link that satisfies the link configuration data and the link traffic data; wherein the method for generating the routing model comprises: collecting the traffic data sample value and the link configuration sample value corresponding to the cloud dedicated line switch, and determining the routing result corresponding to the traffic data sample value and the link configuration sample value; training a preset training model based on the traffic data sample value, the link configuration sample value and the routing result to obtain the routing model, comprising: generating a multidimensional feature vector based on the traffic data sample value and the link configuration sample value; inputting the multidimensional feature vector and the routing result into a preset training model, training the preset training model, and obtaining the routing model; the preset training model is a support vector machine model; A receiving module, used to receive the routing strategy sent by the control device; An adjustment module is used to dynamically adjust the communication link of the cloud dedicated line switch according to the routing strategy.
6. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the adaptive routing method for a cloud dedicated line according to any one of claims 1 to 2, or the adaptive routing method for a cloud dedicated line according to claim 3, by executing the computer instructions.
7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the adaptive routing method for a cloud dedicated line according to any one of claims 1 to 2, or the adaptive routing method for a cloud dedicated line according to claim 3.
