Low-orbit constellation network SDN controller multi-stage migration method and device

Abstract

The invention provides a low-orbit constellation network SDN controller multi-stage migration method and device, and relates to the field of low-orbit satellite network data transmission. The method comprises the following steps: judging whether to start a pre-synchronization process for an original SDN controller deployment node according to overload predicted values of intra-domain average transmission delay variation trend data and resource utilization rate variation trend data of the original SDN controller deployment node in a target control area in a low-orbit constellation network, wherein the overload predicted values are acquired in real time; and after the pre-synchronization process is started, synchronizing the static data and the original quasi-static data to a pre-synchronization node, carrying out migration triggering judgment by adopting a dynamic threshold value determined on the basis of the average value of the resource utilization rates of all satellite nodes in the target control area, and realizing dynamic data sharing on the basis of the satellite nodes in the domain after the migration is triggered. According to the method and the device, the condition of resource overload during migration of the SDN controller can be effectively prevented, and migration oscillation caused by repeated migration of the SDN controller in limited candidate nodes can be avoided.

Description

Technical Field

[0001] The present application relates to the field of low-orbit satellite network data transmission, and in particular to a multi-stage migration method and device for a low-orbit constellation network SDN controller. Background Art

[0002] With the development of satellite communication technology, low-orbit constellation networks are increasingly being used in global communications, the Internet of Things and other fields. Low-orbit constellation networks are composed of a large number of low-orbit satellites. These low-orbit satellites move quickly and the network topology changes frequently, which brings huge challenges to network management and control. In low-orbit constellation networks, the introduction of software-defined networking (SDN) technology provides a new idea for network management. The SDN controller separates the control plane from the data plane to achieve centralized control and flexible management of the network. However, due to the particularity of low-orbit constellation networks, a single controller is difficult to meet the needs of network management, so multiple SDN controllers need to be deployed to work together. In low-orbit constellation networks where multiple SDN controllers are dynamically deployed, controller migration is a key issue. When the network topology changes and the SDN controller resources are insufficient, the SDN controller needs to be migrated in time to ensure the stable operation and service quality of the network.

[0003] At present, the existing multi-stage migration method of the SDN controller in the low-orbit constellation network determines whether the SDN controller migration for the original SDN controller deployment node in the target control area of the low-orbit constellation network is triggered according to the real-time monitored average transmission delay and multi-dimensional resource load in the domain corresponding to the original SDN controller deployment node in the target control area of the low-orbit constellation network. If so, a satellite node is selected in the target control area as the target SDN controller deployment node; and the SDN controller management data corresponding to the original SDN controller deployment node is synchronized to the target SDN controller deployment node.

[0004] However, in the existing multi-stage migration method of SDN controllers in low-orbit constellation networks, when the SDN controller migration is triggered, the resource consumption of the migration process itself can easily lead to resource overload, which in turn affects the reliability and stability of the SDN controller migration; at the same time, since the static control area division will not be dynamically adjusted with the satellite resource load, when all satellites in the control area are collectively highly loaded due to high population density or concentrated business traffic, the SDN controller will be repeatedly migrated among the limited candidate satellite nodes to form migration oscillations.

[0005] Therefore, there is an urgent need to design a method that can solve the problems of resource overload and migration oscillation that easily occur during the migration process of the existing multi-stage migration method of the low-orbit constellation network SDN controller. Summary of the Invention

[0006] In view of this, embodiments of the present application provide a multi-stage migration method and apparatus for an SDN controller in a low-Earth orbit constellation network to eliminate or improve one or more defects existing in the prior art.

[0007] One aspect of the present application provides a multi-stage migration method for an SDN controller in a low-Earth orbit constellation network, including:

[0008] According to the overload prediction value corresponding to the current intra-domain average transmission delay change trend data and resource utilization rate change trend data of the original SDN controller deployment nodes in the target control area of the low-Earth orbit constellation network obtained in real time, determine whether to start a pre-synchronization process for the original SDN controller deployment nodes. If so, select a satellite node in the target control area as the pre-synchronization node, and synchronize the static data and original quasi-static data in the SDN controller management data corresponding to the original SDN controller deployment nodes to the pre-synchronization node;

[0009] Based on a preset dynamic threshold and average transmission delay threshold, determine in real time whether to trigger the migration of the SDN controller for the original SDN controller deployment nodes. If so, select a satellite node in the target control area as the target SDN controller deployment node, where the dynamic threshold is determined based on the average resource utilization rate of all current satellite nodes in the target control area;

[0010] If the target SDN controller deployment node and the pre-synchronization node are the same satellite node, based on each satellite node in the target control area, share the dynamic data in the SDN controller management data with the original SDN controller deployment node and the target SDN controller deployment node in real time.

[0011] In some embodiments of the present application, the multi-stage migration method for the SDN controller in the low-Earth orbit constellation network further includes:

[0012] If the target SDN controller deployment node and the pre-synchronization node are different satellite nodes respectively, control the pre-synchronization node to transmit the static data and original quasi-static data to the target SDN controller deployment node;

[0013] Based on each satellite node in the target control area, share the dynamic data in the SDN controller management data with the original SDN controller deployment node and the target SDN controller deployment node in real time.

[0014] In some embodiments of the present application, before determining in real time whether to trigger the SDN controller migration for the original SDN controller deployment node based on a preset dynamic threshold and an average transmission delay threshold, it further includes:

[0015] During the process of synchronizing the static data and the original quasi-static data to the pre-synchronization node, record the version number of the original quasi-static data in the original SDN controller;

[0016] Correspondingly, before sharing the dynamic data in the SDN controller management data from each satellite node in the target control area to the original SDN controller deployment node and the target SDN controller deployment node in real time, it further includes:

[0017] Judge whether the original quasi-static data currently transmitted to the target SDN controller deployment node is the latest version according to the version number of the original quasi-static data. If not, transmit the incremental data of the latest version of the quasi-static data relative to the original quasi-static data to the target SDN controller deployment node.

[0018] In some embodiments of the present application, before determining whether to start the pre-synchronization process for the original SDN controller deployment node according to the overload prediction values corresponding to the current intra-domain average transmission delay change trend data and resource utilization rate change trend data in the target control area of the low-earth orbit constellation network obtained in real time, it further includes:

[0019] Obtain the current intra-domain average transmission delay of the original SDN controller deployment node and the change rate of the intra-domain average transmission delay per unit time to form corresponding intra-domain average transmission delay change trend data;

[0020] And obtain the current resource utilization rate of the original SDN controller deployment node and the change rate of the resource utilization rate per unit time to form corresponding resource utilization rate change trend data;

[0021] Determine a delay prediction value according to the intra-domain average transmission delay change trend data, a preset average transmission delay threshold, and a first weighting coefficient, and determine a resource prediction value according to the resource utilization rate change trend data, a preset dynamic threshold, and a second weighting coefficient; wherein the sum of the first weighting coefficient and the second weighting coefficient is equal to 1;

[0022] Add the delay prediction value and the resource prediction value to obtain a corresponding overload prediction value;

[0023] Correspondingly, determining whether to initiate a pre-synchronization process for the original SDN controller deployment node based on the resource overload prediction value corresponding to the current in-domain average transmission delay change trend data and resource utilization rate change trend data of the original SDN controller deployment node in the target control area of the low-earth orbit constellation network obtained in real time includes:

[0024] Determine whether the overload prediction value is equal to or greater than 1. If so, determine whether to initiate a pre-synchronization process for the original SDN controller deployment node.

[0025] In some embodiments of the present application, selecting a satellite node in the target control area as a pre-synchronization node includes:

[0026] Obtain the current respective resource utilization rates of each satellite node in the target control area;

[0027] And obtain the current respective longitudes and latitudes of each satellite node in the target control area to obtain the included angles between the respective satellite nodes with the earth's center as the vertex and the center of the target control area in the target control area;

[0028] According to the respective resource utilization rates, the included angles, the longitude and latitude of the area center of each satellite node in the target control area, respectively determine the comprehensive scores of each satellite node in the target control area at the current moment;

[0029] Based on the comprehensive scores of each satellite node in the target control area at the current moment and the change rates of the comprehensive scores corresponding to each satellite node in the target control area, determine the predicted comprehensive scores of each satellite node in the target control area after the predicted time period;

[0030] Select a satellite node in the target control area as a pre-synchronization node according to the predicted comprehensive scores corresponding to each satellite node in the target control area.

[0031] In some embodiments of the present application, obtaining the current resource utilization rate of the original SDN controller deployment node includes:

[0032] Determine the current resource utilization rate of the original SDN controller deployment node according to the current battery energy utilization rate and multi-dimensional resource load of the original SDN controller deployment node, where the multi-dimensional resource load includes: bandwidth utilization rate, CPU utilization rate, and memory utilization rate;

[0033] Correspondingly, obtaining the current respective resource utilization rates of each satellite node in the target control area includes:

[0034] Based on the current respective battery energy utilization rates and the multi-dimensional resource loads of each satellite node in the target control area, respectively determine the current respective resource utilization rates of each satellite node in the target control area.

[0035] In some embodiments of the present application, the method of determining in real time whether to trigger an SDN controller migration for the original SDN controller deployment node based on a preset dynamic threshold and an average transmission delay threshold. If so, select a satellite node in the target control area as the target SDN controller deployment node, including:

[0036] Determine the current dynamic threshold according to the average value of the resource utilization rates of all satellite nodes in the target control area and a preset multiple coefficient of the resource load threshold;

[0037] Real-time determine whether the current intra-domain average transmission delay of the original SDN controller deployment node exceeds the preset average transmission delay threshold, and real-time determine whether the current resource utilization rate of the original SDN controller deployment node exceeds the dynamic threshold;

[0038] If it is determined that the current intra-domain average transmission delay of the original SDN controller deployment node exceeds the preset average transmission delay threshold, and / or, the current resource utilization rate of the original SDN controller deployment node exceeds the dynamic threshold, then it is determined that the SDN controller migration for the original SDN controller deployment node is triggered, and a satellite node is selected in the target control area as the target SDN controller deployment node.

[0039] In some embodiments of the present application, the method of selecting a satellite node in the target control area as the target SDN controller deployment node includes:

[0040] Based on the current respective resource utilization rates, included angles, longitude and latitude of the center of the target control area of each satellite node in the target control area, respectively determine the comprehensive scores of each satellite node in the target control area at the current moment;

[0041] Based on the comprehensive scores and corresponding weight coefficients of each satellite node in the target control area at the current moment, and the change rates and corresponding weight coefficients of the comprehensive scores of each satellite node in the target control area, determine the final comprehensive scores of each satellite node in the target control area;

[0042] Select a satellite node in the target control area as the target SDN controller deployment node according to the final comprehensive scores corresponding to each satellite node in the target control area.

[0043] Another aspect of the present application provides a multi-stage migration device for an SDN controller in a low-earth orbit constellation network, including:

[0044] A pre-synchronization module, configured to determine whether to start a pre-synchronization process for the current original SDN controller deployment node in the target control area of the low-earth orbit constellation network according to the overload prediction values corresponding to the current intra-domain average transmission delay change trend data and resource utilization rate change trend data of the original SDN controller deployment node obtained in real time. If so, select a satellite node in the target control area as the pre-synchronization node, and synchronize the static data and original quasi-static data in the SDN controller management data corresponding to the original SDN controller deployment node to the pre-synchronization node;

[0045] A trigger migration module, configured to determine in real time whether to trigger the migration of the SDN controller for the original SDN controller deployment node based on a preset dynamic threshold and average transmission delay threshold. If so, select a satellite node in the target control area as the target SDN controller deployment node, where the dynamic threshold is determined based on the average resource utilization rate of all current satellite nodes in the target control area;

[0046] A migration execution module, configured to, if the target SDN controller deployment node and the pre-synchronization node are the same satellite node, share the dynamic data in the SDN controller management data from each satellite node in the target control area to the original SDN controller deployment node and the target SDN controller deployment node in real time.

[0047] A third aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the multi-stage migration method of the SDN controller in the low-earth orbit constellation network is implemented.

[0048] A fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the multi-stage migration method of the SDN controller in the low-earth orbit constellation network is implemented.

[0049] A fifth aspect of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the multi-stage migration method of the SDN controller in the low-earth orbit constellation network is implemented.

[0050] The multi-stage migration method of the LEO constellation network SDN controller provided by this application determines whether to start the pre-synchronization process for the current original SDN controller deployment node in the target control area of the LEO constellation network according to the overload prediction values corresponding to the current in-domain average transmission delay change trend data and resource utilization rate change trend data of the original SDN controller deployment nodes in the target control area. If so, a satellite node is selected in the target control area as the pre-synchronization node, and the static data and original quasi-static data in the SDN controller management data corresponding to the original SDN controller deployment node are synchronized to the pre-synchronization node; based on a preset dynamic threshold and average transmission delay threshold, it is determined in real time whether to trigger the SDN controller migration for the original SDN controller deployment node. If so, a satellite node is selected in the target control area as the target SDN controller deployment node, where the dynamic threshold is determined based on the average resource utilization rate of all current satellite nodes in the target control area; if the target SDN controller deployment node and the pre-synchronization node are the same satellite node, the dynamic data in the SDN controller management data is shared by each satellite node in the target control area with the original SDN controller deployment node and the target SDN controller deployment node in real time; that is, by first pre-synchronizing and transmitting static data and original quasi-static data, and then sharing dynamic data when the SDN controller migration is triggered, it can effectively reduce the resource consumption during the SDN controller migration process, and thus can effectively avoid resource overload during the SDN controller migration, and can effectively improve the reliability and efficiency of the SDN controller migration process; and, by obtaining the overload prediction value based on the in-domain average transmission delay change trend data and resource utilization rate change trend data, it can effectively improve the accuracy and timeliness of the pre-synchronization start, and can balance network performance and satellite node stability; by using the dynamic threshold pre-determined based on the average resource utilization rate of all current satellite nodes in the target control area as one of the conditions for triggering the SDN controller migration, establishing a connection between the dynamic threshold and the resource conditions of all satellite nodes in the area, it can effectively prevent the situation where the SDN controller migrates repeatedly among limited candidate nodes to form frequent migration oscillations due to the collective high load of all satellites in the area caused by high population density or concentrated traffic, etc., and thus can effectively improve the application stability and reliability after the SDN controller migration.

[0051] The additional advantages, objectives, and features of this application will be partially described below, and will become partially apparent to those of ordinary skill in the art after studying the following text, or can be learned from the practice of this application. The objectives and other advantages of this application can be achieved and obtained through the structures specifically pointed out in the description and the drawings.

[0052] Those skilled in the art will understand that the objectives and advantages achievable with the present application are not limited to those specifically described above, and the above and other objectives achievable with the present application will be more clearly understood from the following detailed description. Description of the Drawings

[0053] The drawings described herein are used to provide a further understanding of the present application and form a part of the present application, but do not limit the present application. The components in the drawings are not drawn to scale, but are only for showing the principles of the present application. For the convenience of showing and describing some parts of the present application, the corresponding parts in the drawings may be enlarged, that is, they may become larger relative to other components in the exemplary device actually manufactured according to the present application. In the drawings:

[0054] Figure 1 FIG. 1 is a first schematic flowchart of a multi-stage migration method for a low-earth orbit constellation network SDN controller in an embodiment of the present application.

[0055] Figure 2 FIG. 2 is an example schematic diagram for control area division and SDN controller deployment.

[0056] Figure 3 FIG. 3 is a second schematic flowchart of a migration method for a low-earth orbit constellation network SDN controller in an embodiment of the present application.

[0057] Figure 4 FIG. 4 is a third schematic flowchart of a migration method for a low-earth orbit constellation network SDN controller in an embodiment of the present application.

[0058] Figure 5 FIG. 5 is a fourth schematic flowchart of a migration method for a low-earth orbit constellation network SDN controller in an embodiment of the present application.

[0059] Figure 6 FIG. 6 is a fifth schematic flowchart of a migration method for a low-earth orbit constellation network SDN controller in an embodiment of the present application.

[0060] Figure 7 FIG. 7 is a schematic diagram of the included angle between a satellite node and the center of a target control area in an example of the present application.

[0061] Figure 8 FIG. 8 is a sixth schematic flowchart of a migration method for a low-earth orbit constellation network SDN controller in an embodiment of the present application.

[0062] Figure 9 FIG. 9 is a seventh schematic flowchart of a migration method for a low-earth orbit constellation network SDN controller in an embodiment of the present application.

[0063] Figure 10 FIG. 10 is a schematic flowchart of the processing flow in the pre-synchronization stage in an application example of the present application.

[0064] Figure 11 It is a schematic diagram of the processing flow in the trigger migration and selection node stage and the status synchronization stage in an application example of this application.

[0065] Figure 12 It is a schematic diagram of the processing flow when the pre-synchronization node is inconsistent with the optimal node in an application example of this application.

[0066] Figure 13 It is a schematic diagram of the processing flow when the pre-synchronization node is consistent with the optimal node in an application example of this application.

[0067] Figure 14 It is a schematic diagram of the structure of the multi-stage migration device of the LEO constellation network SDN controller in an embodiment of this application. Detailed implementation manners

[0068] To make the objectives, technical solutions and advantages of this application clearer and more understandable, the following further elaborates on this application in combination with the implementation manners and the drawings. Herein, the illustrative implementation manners of this application and their descriptions are used to explain this application, but are not intended to limit this application.

[0069] Herein, it also needs to be noted that in order to avoid obscuring this application due to unnecessary details, only the structures and / or processing steps closely related to the solution of this application are shown in the drawings, while other details less related to this application are omitted.

[0070] It should be emphasized that the term "including / containing" when used herein refers to the presence of features, elements, steps or components, but does not exclude the presence or addition of one or more other features, elements, steps or components.

[0071] Herein, it also needs to be noted that if not otherwise specified, the term "connection" in this text can not only refer to a direct connection, but also represent an indirect connection with an intermediate object.

[0072] In the following, the embodiments of this application will be described with reference to the drawings. In the drawings, the same reference numerals represent the same or similar components, or the same or similar steps.

[0073] In order to solve the problems of resource overload and migration oscillation that are prone to occur during the migration process of the existing multi-stage migration method of the low-orbit constellation network SDN controller, the embodiments of the present application respectively provide a multi-stage migration method of a low-orbit constellation network SDN controller, a multi-stage migration device of a low-orbit constellation network SDN controller for executing the multi-stage migration method of the low-orbit constellation network SDN controller, a physical device, a computer-readable storage medium and a computer program product, which can effectively prevent resource overload from occurring during the migration of the SDN controller, and can minimize the repeated migration of the SDN controller among limited candidate nodes to form migration oscillations.

[0074] The details are described in detail through the following examples.

[0075] Based on this, the embodiment of the present application provides a multi-stage migration method of a low-orbit constellation network SDN controller that can be implemented by a multi-stage migration device of a low-orbit constellation network SDN controller, see Figure 1 The multi-stage migration method of the low-orbit constellation network SDN controller specifically includes the following contents:

[0076] Step 100: Based on the overload prediction value corresponding to the current intra-domain average transmission delay change trend data and resource utilization rate change trend data of the original SDN controller deployment node in the target control area of the low-orbit constellation network obtained in real time, determine whether to start the pre-synchronization process for the original SDN controller deployment node. If so, select a satellite node in the target control area as a pre-synchronization node, and synchronize the static data and original quasi-static data in the SDN controller management data corresponding to the original SDN controller deployment node to the pre-synchronization node.

[0077] See also Figure 2 The earth's surface can be divided into multiple areas (also called control areas) by static division. Each control area corresponds to a regional center, and a satellite node is deployed in each control area to serve as the SDN controller in the control area. The satellite node can be called the original SDN controller deployment node at this time, and the control area where the original SDN controller deployment node is located can be called the target control area.

[0078] As the constellation moves, the original SDN controller deployment node will gradually deviate from the center position of the target control area, which will lead to an increase in the average transmission delay between the SDN controller and other satellite nodes within the target control area. At the same time, since the population in the satellite coverage area changes with the movement, it may cause the resource load in the target control area to fail to meet the actual demand, thereby affecting the normal operation of network management. To address the above problems, it is necessary to timely migrate the SDN controller to other satellite nodes within the target control area, and the satellite node selected as the new SDN controller can be referred to as the target SDN controller deployment node at this time.

[0079] However, the static area division does not dynamically adjust with the satellite resource load. When all satellites in the area experience a collective high load due to high population density or concentrated traffic, etc., the SDN controller repeatedly migrates among the limited candidate nodes due to the fixed migration trigger condition value, forming a migration oscillation. Therefore, to solve this problem, step 100 of this application first determines whether to start the pre-synchronization process, and when it is determined to start the pre-synchronization process for the original SDN controller deployment node, or after that, a satellite node is selected in the target control area as the pre-synchronization node.

[0080] In one or more embodiments of this application, the satellite node refers to a low-earth orbit satellite. The original SDN controller deployment node refers to the satellite node currently deployed with SDN controller data, and this satellite node is called the original SDN controller deployment node for the purpose of distinguishing different roles; the original SDN controller deployment node can be abbreviated as the original SDN controller or the old SDN controller. The pre-synchronization node refers to the satellite node that is the pre-synchronization object of the original SDN controller deployment node. The target SDN controller deployment node refers to the satellite node that is the migration object of the original SDN controller deployment node, and the target SDN controller deployment node can be abbreviated as the new SDN controller or the optimal node.

[0081] It can be understood that in the existing multi-stage migration method of the LEO constellation network SDN controller, the trigger of SDN controller migration is determined only based on the current intra-domain average transmission delay and resource utilization rate of the original SDN controller deployment node and their respective fixed thresholds. However, this method only considers real-time data and cannot be applied to the pre-synchronization startup judgment process of this application. Based on this, in step 100 of this application, the overload prediction values corresponding to the current intra-domain average transmission delay change trend data and resource utilization rate change trend data are used as the prediction data for future delay and resource overload, which can effectively realize the pre-synchronization startup judgment for the SDN controller and transmit static data and quasi-static data, so as to avoid the occurrence of sudden overload situations in the subsequent SDN controller migration process; at the same time, by considering the change trends of both delay and resource load, the network performance and node stability can also be balanced.

[0082] It should be noted that the current intra-domain average transmission delay change trend data of the original SDN controller deployment node refers to the change trend of the intra-domain average transmission delay of the original SDN controller deployment node during a certain historical time point to the current time point t. The length from the certain historical time point to the current time point t can be denoted as the prediction time period T, which is also a prediction time window, that is, it is necessary to predict the load situation after how long in the future. The larger T is, the longer the prediction is, and it is applicable to scenarios that require advance planning.

[0083] Among them, the current intra-domain average transmission delay change trend data of the original SDN controller deployment node can be obtained according to the current intra-domain average transmission delay D(t) of the original SDN controller deployment node and the change rate r of the intra-domain average transmission delay per unit time. D Obtained.

[0084] It should be noted that the current resource utilization rate change trend data of the original SDN controller deployment node refers to the change trend of the resource utilization rate of the original SDN controller deployment node within the prediction time period T.

[0085] Among them, the current resource utilization rate change trend data of the original SDN controller deployment node can be obtained according to the current resource utilization rate R(t) of the original SDN controller deployment node and the change rate r of the resource utilization rate per unit time. R Obtained. In one or more embodiments of this application, the resource utilization rate can also be referred to as the resource usage situation.

[0086] In addition, the SDN controller management data can be divided into three categories, namely static data, quasi-static data, and dynamic data.

[0087] Specifically, static data is used to represent the hardware and identity information, network infrastructure information, initial system configuration, etc. corresponding to each satellite node within the target control area, which belongs to the basic information that will not change.

[0088] Quasi-static data is used to represent information such as user-defined policy rules, network management policies, and management configurations corresponding to the SDN controller, which belongs to data with a low change frequency and will not change in real time.

[0089] Dynamic data includes real-time changing operation data such as the current satellite network topology structure, link status, and running status of each satellite node within the target control area.

[0090] Step 200: Based on a preset dynamic threshold and average transmission delay threshold, it is determined in real time whether to trigger the migration of the SDN controller for the original SDN controller deployment node. If so, a satellite node is selected in the target control area as the target SDN controller deployment node, where the dynamic threshold is determined based on the average resource utilization rate of all current satellite nodes within the target control area.

[0091] In step 200, since the dynamic threshold is determined based on the average resource utilization rate of all current satellite nodes within the target control area, by establishing a connection between the dynamic threshold and the resource conditions of all satellite nodes within the target control area (which can be abbreviated as the area), the problem of frequent migration caused by a fixed threshold can be prevented.

[0092] Step 300: If the target SDN controller deployment node and the pre-synchronization node are the same satellite node, the dynamic data in the SDN controller management data is shared in real time with the original SDN controller deployment node and the target SDN controller deployment node based on each satellite node within the target control area.

[0093] In step 300, if the target SDN controller deployment node and the pre-synchronization node are the same satellite node, the target SDN controller deployment node already stores the static data and the quasi-static data at this time. At this time, it is only necessary for the original SDN controller deployment node to broadcast a controller migration preparation instruction containing real-time notification indication information of network status changes to each satellite node in the target control area (the satellite nodes here can refer to satellite nodes other than the original SDN controller deployment node and the target SDN controller deployment node), and receive the migration confirmation messages returned by each satellite node, so that each satellite node can transmit dynamic data such as network status change data detected by itself in the target control area to both the original SDN controller deployment node and the target SDN controller deployment node according to the real-time notification indication information of network status changes.

[0094] As can be seen from the above description, the multi-stage migration method of the LEO constellation network SDN controller provided by the embodiments of the present application can effectively reduce the resource consumption during the SDN controller migration process by first pre-synchronously transmitting static data and original quasi-static data and then sharing dynamic data when triggering the SDN controller migration. Furthermore, it can effectively avoid resource overload during the SDN controller migration, and can effectively improve the reliability and efficiency of the SDN controller migration process; in addition, by obtaining the overload prediction value based on the data of the change trend of the average transmission delay within the domain and the data of the change trend of the resource utilization rate, it can effectively improve the accuracy and timeliness of the pre-synchronization start, and can balance the network performance and the stability of satellite nodes; by using the dynamic threshold determined in advance based on the average value of the resource utilization rates of all current satellite nodes in the target control area as one of the conditions for triggering the SDN controller migration, establishing a connection between the dynamic threshold and the resource conditions of all satellite nodes in the area can effectively prevent the situation where the SDN controller migrates repeatedly among limited candidate nodes to form frequent migration oscillations due to the collective high load of all satellites in the area caused by reasons such as high population density or concentrated traffic volume, and can effectively improve the application stability and reliability after the SDN controller migration.

[0095] In order to further improve the reliability and stability of the multi-stage migration of the LEO constellation network SDN controller, in a multi-stage migration method of the LEO constellation network SDN controller provided by the embodiments of the present application, refer to Figure 3 , after step 200 in the multi-stage migration method of the LEO constellation network SDN controller, the following specific content is further included:

[0096] Step 400: If the target SDN controller deployment node and the pre-synchronization node are different satellite nodes respectively, control the pre-synchronization node to transmit the static data and the original quasi-static data to the target SDN controller deployment node.

[0097] Specifically, after determining the target SDN controller deployment node, if the target SDN controller deployment node and the pre-synchronization node are not the same satellite node, the target SDN controller deployment node notifies the pre-synchronization node to synchronize the static data and the quasi-static data to the optimal node. And after the pre-synchronization node confirms that the target SDN controller deployment node has received the static data and the quasi-static data, the pre-synchronization node deletes the local static data and the quasi-static data to release local resources, and then switches itself from the pre-synchronization node to an ordinary satellite node acting as a switch.

[0098] Step 500: Based on each satellite node in the target control area, share the dynamic data in the SDN controller management data with the original SDN controller deployment node and the target SDN controller deployment node in real time.

[0099] In order to further improve the reliability of SDN controller migration on the basis of minimizing the data transmission volume, in a multi-stage SDN controller migration method for a low-earth orbit constellation network provided in an embodiment of the present application, refer to Figure 4 There is also the following specific content between step 100 and step 200 in the multi-stage SDN controller migration method for the low-earth orbit constellation network:

[0100] Step 010: During the process of synchronizing the static data and the original quasi-static data to the pre-synchronization node, record the version number of the original quasi-static data in the original SDN controller.

[0101] Correspondingly, step 300 in the multi-stage SDN controller migration method for the low-earth orbit constellation network specifically includes:

[0102] Step 310: If the target SDN controller deployment node and the pre-synchronization node are the same satellite node, judge whether the original quasi-static data currently transmitted to the target SDN controller deployment node is the latest version according to the version number of the original quasi-static data. If not, transmit the incremental data of the latest version of the quasi-static data relative to the original quasi-static data to the target SDN controller deployment node.

[0103] And step 500 in the multi-stage SDN controller migration method for the low-earth orbit constellation network specifically includes:

[0104] Step 510: Determine whether the original quasi-static data currently transmitted to the target SDN controller deployment node is the latest version according to the version number of the original quasi-static data. If not, transmit the incremental data of the latest version of the quasi-static data relative to the original quasi-static data to the target SDN controller deployment node.

[0105] Specifically, the pre-synchronization node synchronizes the full amount of static data and quasi-static data to the target SDN controller deployment node. Mainly considering the low-frequency change characteristic of the quasi-static data, that is, the quasi-static data basically does not change, avoiding repeated verification; only when the quasi-static data actually changes (such as adding a routing policy), the original SDN controller transmits lightweight incremental data (instead of full retransmission) to the target SDN controller deployment node through the recorded change log to ensure that the latest policy takes effect.

[0106] In order to further improve the effectiveness and reliability of the pre-synchronization trigger judgment, in a multi-stage migration method for an SDN controller in a low-earth orbit constellation network provided in an embodiment of the present application, refer to Figure 5 , before step 100 in the multi-stage migration method for the SDN controller in the low-earth orbit constellation network, the following specific content is further included:

[0107] Step 020: Obtain the current intra-domain average transmission delay of the original SDN controller deployment node and the change rate of the intra-domain average transmission delay per unit time to form corresponding intra-domain average transmission delay change trend data.

[0108] And, step 030: Obtain the current resource utilization rate of the original SDN controller deployment node and the change rate of the resource utilization rate per unit time to form corresponding resource utilization rate change trend data;

[0109] Specifically, obtain the current intra-domain average transmission delay D(t) of the original SDN controller deployment node (that is, at the current time point t) and the change rate r D of the intra-domain average transmission delay per unit time; and, the current resource utilization rate R(t) of the original SDN controller deployment node (that is, at the current time point t) and the change rate r R of the resource utilization rate per unit time.

[0110] Step 040: Determine a delay prediction value according to the intra-domain average transmission delay change trend data, a preset average transmission delay threshold, and a first weighting coefficient, and determine a resource prediction value according to the resource utilization rate change trend data, a preset dynamic threshold, and a second weighting coefficient; where the sum of the first weighting coefficient and the second weighting coefficient is equal to 1;

[0111] Specifically, according to the current average intra-domain transmission delay D(t) of the original SDN controller deployment node, the change rate r of the average intra-domain transmission delay per unit time D , a preset average transmission delay threshold D th and a first weighting coefficient w1, determine the delay prediction value: where Δt represents the time interval for the monitoring system to collect the average intra-domain transmission delay or resource utilization rate once, and is used to calculate the change rate;

[0112] And, according to the current resource utilization rate R(t) of the original SDN controller deployment node, the change rate r of the resource utilization rate per unit time R , a preset dynamic threshold and a second weighting coefficient w2, determine the resource prediction value: where a represents the resource load threshold multiple coefficient, and is used to define how many times the resource utilization rate of the SDN controller exceeds the regional average value to trigger migration; is the average value of the resource utilization rates of all current satellite nodes in the target control area.

[0113] Among them, w1 + w2 = 1, which is used to balance the importance of the delay change trend and the resource load change trend. By adjusting w1 and w1, different network requirements can be flexibly adapted, and the universality of the solution can be enhanced.

[0114] Step 050: Add the delay prediction value and the resource prediction value to obtain the corresponding overload prediction value.

[0115] Correspondingly, step 100 in the multi-stage migration method of the LEO constellation network SDN controller specifically includes the following content:

[0116] Step 110: Determine whether the overload prediction value is equal to or greater than 1. If so, determine whether to start the pre-synchronization process for the original SDN controller deployment node and execute step 120; if not, return to execute step 020 at the next time point.

[0117] Step 120: Select a satellite node in the target control area as the pre-synchronization node;

[0118] Step 130: Synchronize the static data and the original quasi-static data in the SDN controller management data corresponding to the original SDN controller deployment node to the pre-synchronization node.

[0119] Specifically, the solution formula for determining whether the overload prediction value is equal to or greater than 1 is shown in formula (1):

[0120]

[0121] The average resource utilization rate of all current satellite nodes within the target control area The solution formula is as shown in Formula (2):

[0122]

[0123] Among them, R i (t) represents the resource utilization rate of the i-th satellite node at the current time point t, and n represents the total number of satellite nodes within the target control area.

[0124] The change rate r D of the average in-domain transmission delay in the above step 020 per unit time is calculated by the formula as shown in Formula (3):

[0125]

[0126] Among them, D(t + Δt) represents the average in-domain transmission delay at the time point that is one time interval Δt away from the current time point t for the original SDN controller deployment node.

[0127] The change rate r R of the resource utilization rate in the above step 030 per unit time is calculated by the formula as shown in Formula (4):

[0128]

[0129] Among them, R(t + Δt) represents the resource utilization rate at the time point that is one time interval Δt away from the current time point t for the original SDN controller deployment node.

[0130] To further improve the effectiveness and reliability of pre-synchronized node selection, in a multi-stage migration method for an SDN controller in a low-earth orbit constellation network provided in an embodiment of the present application, refer to Figure 6 , step 120 in the multi-stage migration method for the SDN controller in the low-earth orbit constellation network specifically includes the following content:

[0131] Step 121: Obtain the current respective resource utilization rates of each satellite node within the target control area.

[0132] And, step 122: Obtain the current respective longitudes and latitudes of each satellite node within the target control area to obtain the angles between each satellite node with the earth's center as the vertex and the center of the target control area within the target control area.

[0133] Specifically, the solution formula for the angle between the satellite node with the earth's center as the vertex and the center of the target control area is as shown in Formula (5):

[0134]

[0135] Among them, θ i (t) represents the included angle between the i-th satellite node with the earth's center as the vertex and the center of the target control area. As Figure 7 shown, θ1 and θ2 respectively represent the included angle values between two different satellite nodes with the earth's center as the vertex and the center of the target control area. represents the latitude of the i-th satellite node; λ i (t) represents the longitude of the i-th satellite node; represents the latitude of the area center; λ represents the longitude of the area center.

[0136] That is to say, for the problem in the prior art that using spatial distance calculation to determine whether a satellite node is close to the area center will be affected by the height setting of the area center mass point in the calculation of whether the satellite node is close to the area center, resulting in error determination, in the embodiments of the present application, only the geocentric included angle between the satellite node based on longitude and latitude and the area center mass point is used as the determination basis for whether the satellite node is close to the area center, which can effectively improve the determination accuracy and reliability of whether the satellite node is close to the area center.

[0137] Step 123: According to the respective resource utilization rates, the included angles, the longitude and latitude of the area center corresponding to each satellite node in the target control area, respectively determine the comprehensive scores of each satellite node in the target control area at the current moment.

[0138] Specifically, the solution formula for the comprehensive scores of each satellite node in the target control area at the current moment is as shown in formula (6):

[0139]

[0140] Among them, f i (t) represents the comprehensive score of the i-th satellite node corresponding to the current time point t, which is used to evaluate its advantages and disadvantages as a pre-synchronization node or a target SDN controller deployment node; α (alpha) represents the weight coefficient of the position factor (geocentric included angle) in formula (6), which is used to adjust the importance of the position advantage in the comprehensive score; ∈ represents an extremely small positive number, which is used to avoid mathematical errors with a denominator of zero; β represents the weight coefficient of the resource utilization rate in formula (6), which is used to adjust the importance of the resource load in the comprehensive score; R i (t) represents the resource utilization rate of the i-th satellite node at the current time point t.

[0141] Step 124: Based on the comprehensive scores of each satellite node in the target control area at the current moment and the change rates of the comprehensive scores corresponding to each satellite node in the target control area, determine the predicted comprehensive scores of each satellite node in the target control area after the prediction time period.

[0142] The solution formula for the predicted comprehensive score corresponding to each satellite node after the prediction time period is shown in Formula (7):

[0143]

[0144] where, f i (T) represents the predicted comprehensive score of the i-th satellite node after the prediction time period T; r f represents the change rate of the comprehensive score f i (t) of the i-th satellite node, that is, the growth or decay rate of the comprehensive score f i (t) with time. By r f , predict the predicted comprehensive score f i (T) after the prediction time period in the future, which is used for forward-looking screening of long-term stable pre-synchronization nodes.

[0145] Step 125: Select a satellite node in the target control area as the pre-synchronization node according to the predicted comprehensive scores corresponding to each satellite node in the target control area.

[0146] That is, a satellite node with the highest predicted comprehensive score can be selected as the pre-synchronization node.

[0147] In order to further improve the effectiveness and reliability of obtaining the resource utilization rate of satellite nodes and prevent the risk of network interruption caused by sudden exhaustion of energy, in a multi-stage migration method for a low-earth orbit constellation network SDN controller provided in an embodiment of the present application, see Figure 8 , step 030 in the multi-stage migration method for the low-earth orbit constellation network SDN controller specifically includes the following content:

[0148] Step 031: Determine the current resource utilization rate of the original SDN controller deployment node according to the current battery energy utilization rate and multi-dimensional resource load of the original SDN controller deployment node, where the multi-dimensional resource load includes: bandwidth utilization rate, CPU utilization rate, and memory utilization rate.

[0149] Specifically, the solution formula for determining the current resource utilization rate R(t) of the original SDN controller deployment node is shown in Formula (8):

[0150] R(t) = w b ·B(t) + wc ·C(t) + w m ·M(t) + w e ·E(t) Formula (8)

[0151] Among them, B(t), C(t), M(t), and E(t) represent the current bandwidth, CPU, memory, and battery energy utilization rates of the original SDN controller deployment node in sequence, and w b , w c , w m and w e represent the weight coefficients corresponding to the bandwidth, CPU, memory, and battery energy utilization rates respectively.

[0152] Step 032: Obtain the change rate of the resource utilization rate per unit time, so as to form corresponding resource utilization rate change trend data according to the current resource utilization rate of the original SDN controller deployment node and the change rate of the resource utilization rate per unit time.

[0153] Correspondingly, step 121 in the multi-stage migration method of the LEO constellation network SDN controller specifically includes the following contents:

[0154] Step 1211: According to the current battery energy utilization rates and the multi-dimensional resource loads of the respective satellite nodes in the target control area, determine the current resource utilization rates of the respective satellite nodes in the target control area respectively.

[0155] Specifically, the solution formula for determining the current resource utilization rate R i (t) is as shown in Formula (9):

[0156] R i (t)) = w b ·B i (t) + w c ·C i (t) + w m ·M i (t) + w e ·E i (t) Formula (9)

[0157] Among them, B i (t), C i (t), M i (t), and E i (t) represent the current bandwidth, CPU, memory, and battery energy utilization rates of the i-th satellite node in sequence.

[0158] Based on this, in the embodiments of the present application, the battery energy utilization rate is incorporated into the assessment of the resource usage of satellite nodes. Considering the characteristics of low-earth orbit satellites with limited energy, relying on solar power supply, and periodically entering the shadow area, it effectively avoids selecting nodes with nearly exhausted batteries as SDN controllers, preventing the risk of network interruption caused by sudden energy depletion. By comprehensively evaluating the battery energy utilization rate and resource dimensions such as CPU, bandwidth, and memory, and combining weight adjustment to achieve dynamic balance between energy consumption and load, satellites with sufficient energy are preferentially selected to undertake control tasks. This not only avoids excessive consumption of nodes with "strong performance but weak energy", but also balances the energy distribution of the entire constellation, extending the operating life of satellite nodes and the entire constellation.

[0159] In order to further improve the effectiveness and reliability of trigger migration judgment, and prevent the situation where the SDN controller migrates repeatedly among limited candidate nodes to form frequent migration oscillations due to the collective high load of all satellites in the region caused by high population density or concentrated traffic flow, etc., in a multi-stage migration method for the SDN controller of a low-earth orbit constellation network provided in the embodiments of the present application, refer to Figure 8 In step 200 of the multi-stage migration method for the SDN controller of the low-earth orbit constellation network, it specifically includes the following content:

[0160] Step 210: Determine the current dynamic threshold according to the average resource utilization rate of all current satellite nodes in the target control area and a preset multiple coefficient of the resource load threshold.

[0161] Specifically, the embodiments of the present application adopt as the dynamic threshold. By establishing a connection between the dynamic threshold and the resource situation of all satellite nodes in the region, the problem of frequent migration caused by a fixed threshold can be prevented.

[0162] Step 220: Real-time determine whether the current intra-domain average transmission delay of the original SDN controller deployment node exceeds a preset average transmission delay threshold and whether the current resource utilization rate of the original SDN controller deployment node exceeds the dynamic threshold; if it is determined that the current intra-domain average transmission delay of the original SDN controller deployment node exceeds the preset average transmission delay threshold, and / or, the current resource utilization rate of the original SDN controller deployment node exceeds the dynamic threshold, then it is determined that the SDN controller migration for the original SDN controller deployment node is triggered currently, and step 230 is executed.

[0163] Specifically, the judgment conditions for real-time determining whether the current intra-domain average transmission delay of the original SDN controller deployment node exceeds a preset average transmission delay threshold and whether the current resource utilization rate of the original SDN controller deployment node exceeds the dynamic threshold are shown in formula (10):

[0164]

[0165] Step 230: Select a satellite node in the target control area as a target SDN controller deployment node.

[0166] In order to further improve the effectiveness and reliability of selecting the target SDN controller deployment node, in a multi-stage migration method of a low-orbit constellation network SDN controller provided in an embodiment of the present application, see Figure 9 , step 230 in the multi-stage migration method of the low-orbit constellation network SDN controller specifically includes the following contents:

[0167] Step 231: Determine the comprehensive score of each satellite node in the target control area at the current moment according to the current resource utilization rate, angle, longitude and latitude of the regional center of the target control area of each satellite node in the target control area.

[0168] Specifically, the comprehensive score of each satellite node in the target control area at the current moment is determined respectively according to the aforementioned formula (6).

[0169] Step 232: Determine the final comprehensive score of each satellite node in the target control area based on the comprehensive score and the corresponding weight coefficient of each satellite node in the target control area at the current moment, as well as the change rate of the comprehensive score and the corresponding weight coefficient of each satellite node in the target control area.

[0170] The calculation formula corresponding to the final comprehensive score f of each satellite node in the target control area is shown in formula (11):

[0171] f=w r r f +w f f i (t) Formula (11)

[0172] Among them, w r represents the comprehensive score f of the i-th satellite node i (t) rate of change r f The weight coefficient is used to indicate the degree of attention paid to the “future trend” of satellite nodes; w f represents the comprehensive score f of the i-th satellite node i The weight coefficient of (t) is used to indicate the consideration of the current spatial position and resource usage of the candidate satellite node.

[0173] Step 233: Select a satellite node in the target control area as the target SDN controller deployment node according to the final comprehensive scores corresponding to the respective satellite nodes in the target control area.

[0174] That is, a satellite node with the highest final comprehensive score can be selected as the target SDN controller deployment node.

[0175] To further illustrate the above embodiments, the present application also provides a specific application example of the multi-stage migration method of the LEO constellation network SDN controller. In this application example, a complete process of the multi-stage migration of the LEO constellation network SDN controller is provided in combination with the above embodiments. The multi-stage migration includes: a pre-synchronization stage and an SDN controller migration stage. The SDN controller migration stage is further divided into: a trigger migration and node selection stage, a status synchronization stage, and a new connection and original SDN controller exit stage. The specific description is as follows:

[0176] (1) Pre-synchronization stage

[0177] See Figure 10 , the processing flow of the pre-synchronization stage is as follows:

[0178] S11: Monitor the network transmission delay and the satellite resources to which the controller belongs, specifically as follows:

[0179] That is: Obtain the current intra-domain average transmission delay of the original SDN controller deployment node and the change rate of the intra-domain average transmission delay per unit time to form corresponding intra-domain average transmission delay change trend data; and, obtain the current resource utilization rate of the original SDN controller deployment node and the change rate of the resource utilization rate per unit time to form corresponding resource utilization rate change trend data.

[0180] S12: Whether the pre-synchronization limit is reached, specifically as follows:

[0181] When the intra-domain average transmission delay D(t) monitored by the SDN controller and the resource usage situation R(t) of the satellite node to which the SDN controller belongs satisfy formula (1) within the specified time T, pre-synchronization will be triggered, that is, S13 will be executed.

[0182] That is, during the operation of the SDN controller, the intra-domain average transmission delay and the resource usage situation of the satellite node to which it belongs will be monitored, and pre-synchronization will be triggered when a certain limit is reached.

[0183] S13: Select candidate nodes (that is, satellite nodes in the target control area that have not been used as the original SDN controller deployment node) as pre-synchronization target nodes (that is, pre-synchronization nodes), specifically as follows:

[0184] Obtain the respective predicted comprehensive scores corresponding to each satellite node within the target control area according to formula (7), and select a satellite node with the highest predicted comprehensive score in the target control area as the pre-synchronization node.

[0185] S14: The controller synchronizes static data and quasi-static data to the target node (i.e., the pre-synchronization node), specifically as follows:

[0186] After the pre-synchronization node is selected, the SDN controller transmits static data and quasi-static data to the pre-synchronization node. During the transmission of the quasi-static data, the SDN controller records the version number of this part of the data transmitted to the pre-synchronization node.

[0187] (II) Trigger the migration and selection of nodes phase

[0188] See Figure 11 , the processing flow of the trigger migration and selection of nodes phase is as follows:

[0189] S21: Monitor the network transmission delay and the satellite resources to which the controller belongs, specifically as follows:

[0190] Obtain the current intra-domain average transmission delay and the current resource utilization rate of the original SDN controller deployment node in real time.

[0191] S22: Determine whether it exceeds the limit, specifically as follows:

[0192] According to formula (10), determine whether the current intra-domain average transmission delay of the original SDN controller deployment node exceeds the preset average transmission delay threshold and whether the current resource utilization rate of the original SDN controller deployment node exceeds the judgment condition corresponding to the dynamic threshold. If it is determined that the current intra-domain average transmission delay of the original SDN controller deployment node exceeds the preset average transmission delay threshold, and / or, the current resource utilization rate of the original SDN controller deployment node exceeds the dynamic threshold, then it is determined that the SDN controller migration for the original SDN controller deployment node is triggered currently, and S23 is executed.

[0193] That is to say, during the operation of the SDN controller, the relevant resource usage situation is monitored. When the intra-domain average transmission delay and the resource usage situation of the SDN controller reach the limit of formula (10), the SDN controller migration operation will be triggered.

[0194] S23: Select the optimal node as the new controller deployment node (i.e., the target SDN controller deployment node), specifically as follows:

[0195] Calculate the respective final comprehensive scores of each satellite node within the target control area according to formula (11), and use the satellite node with the highest final comprehensive score as the optimal node, and then select it as the target SDN controller deployment node.

[0196] That is to say, when the SDN controller migration is triggered, the SDN controller will select the optimal node according to formula (11). By introducing the change amount, formula (11) can take into account the current operation trend of the satellite nodes.

[0197] (III) State Synchronization Phase

[0198] See Figure 11 , the processing flow in the state synchronization phase is as follows:

[0199] S31: Whether the optimal node and the pre-synchronization node are the same node, specifically as follows:

[0200] Judge whether the target SDN controller deployment node and the pre-synchronization node are the same satellite node. If not, execute S32; if so, execute S33.

[0201] S32: The pre-synchronization node synchronizes static data and quasi-static data to the optimal node, specifically as follows:

[0202] Control the pre-synchronization node to transmit the static data and the original quasi-static data to the target SDN controller deployment node.

[0203] S33: Whether the quasi-static data version numbers are the same, specifically as follows:

[0204] Judge whether the version number of the original quasi-static data in the target SDN controller deployment node is the same as the version number of the latest quasi-static data in the original SDN controller deployment node. If not, execute S34; if so, execute S35.

[0205] S34: The controller incrementally synchronizes the quasi-static data to the optimal node, specifically as follows:

[0206] The original SDN controller deployment node transmits the incremental data of the latest version of the quasi-static data relative to the original quasi-static data to the target SDN controller deployment node.

[0207] S35: The dynamic data is updated simultaneously by each satellite node in the area to the controller and the optimal node, specifically as follows:

[0208] Based on each satellite node in the target control area, the dynamic data in the SDN controller management data is shared in real time to the original SDN controller deployment node and the target SDN controller deployment node.

[0209] Specifically, refer to Figure 12 When the pre-synchronization node is inconsistent with the optimal node (i.e., the target SDN controller deployment node), after determining the target SDN controller deployment node, if the target SDN controller deployment node is not the same satellite node as the pre-synchronization node, the original controller (i.e., the original SDN controller deployment node) notifies the pre-synchronization node to synchronize static data and quasi-static data to the target SDN controller deployment node.

[0210] The pre-synchronization node synchronizes all static data and quasi-static data to the target SDN controller deployment node. Mainly considering the low-frequency change characteristics of quasi-static data, that is, quasi-static data basically does not change, avoiding repeated verification; only when the quasi-static data actually changes (such as adding a routing policy), the original SDN controller deployment node transmits lightweight incremental data (instead of full retransmission) to the target SDN controller deployment node through the recorded change log to ensure that the latest policy takes effect.

[0211] At the same time, the original SDN controller deployment node determines whether the version of the quasi-static data is the latest version. If it is not the latest version, the SDN controller synchronizes the latest version of the quasi-static data to the optimal node in an incremental transmission manner to reduce the data transmission volume. Dynamic data is updated to the SDN controller and the optimal node simultaneously by each satellite node (i.e., switches in the region).

[0212] Refer to Figure 13 When the pre-synchronization node is consistent with the optimal node (i.e., the target SDN controller deployment node), the original controller (i.e., the original SDN controller deployment node) determines whether the version of the quasi-static data is the latest version. If it is not the latest version, the original SDN controller deployment node only synchronizes the latest version of the quasi-static data to the pre-synchronization node in an incremental transmission manner, and dynamic data is updated to the original SDN controller deployment node and the pre-synchronization node simultaneously by each satellite node in the region.

[0213] (4) New connection and original SDN controller exit phase

[0214] Specifically, during the entire synchronization process, the original SDN controller and the new SDN controller share the state data of the network to ensure that both parties' understanding of the current topology state and network resources remains consistent. Only after all key data has been transmitted and verified can the migration enter the next stage. This data synchronization strategy not only helps the new SDN controller obtain comprehensive network management information, but also minimizes data inconsistencies caused by dynamic topology changes through real-time information synchronization.

[0215] After the synchronization process ends, a status synchronization end notification is sent from the original SDN controller deployment node to the target SDN controller deployment node, so that the target SDN controller deployment node returns a corresponding status synchronization end confirmation message, enabling the target SDN controller deployment node to establish connections with each of the satellite nodes in the target control area respectively. When the target SDN controller deployment node determines that there are satellite nodes that have not established a connection with itself within a preset time, a preset startup fault detection and fallback process is initiated.

[0216] After receiving the synchronization completion signal, the new SDN controller starts to establish SDN connections with all satellite nodes in the area. The new SDN controller sends control plane redirection instructions to all satellite nodes simultaneously through high concurrency, requiring them to update the connection relationship with the SDN controller. This process ensures that the old SDN controller transfers all management tasks to the new SDN controller, thus avoiding overlapping or loss of running tasks on the control plane between the two. After each node receives the instruction from the new SDN controller to establish a connection, it sends an acknowledgment feedback message to the new SDN controller to confirm that it has successfully completed the connection establishment and control plane migration. During the SDN controller migration process, if some nodes fail to complete the connection establishment with the new SDN controller within the predetermined time due to unstable link quality, the new SDN controller will initiate a fault detection and fallback process. Through the retry mechanism, it is ensured that the network management function is not affected, thereby avoiding service interruption or management failure caused by a failed connection establishment process. The implementation of this stage ensures that after the new SDN controller gradually takes over, it can comprehensively manage network affairs in the area. Through this operation step of establishing new connections, this stage realizes a smooth transition of the control function, thus guaranteeing the continuity and stability of network services.

[0217] Receive the migration completion notification message sent by the target SDN controller deployment node in the original SDN controller deployment node, and send a migration completion confirmation message to the target SDN controller deployment node.

[0218] Clear the SDN controller management data locally in the original SDN controller deployment node, so that the original SDN controller deployment node is changed to a satellite node in the target control area, and the target SDN controller deployment node is changed to the current original SDN controller deployment node in the target control area.

[0219] Specifically, in the stage of the original SDN controller exiting, after all the SDN connections between the new SDN controller and all the satellites in the region are established, a migration completion notification will be sent to the original SDN controller, marking the final completion of the role handover. After receiving this notification, the original SDN controller will no longer publish any SDN controller information to the network, but directly clean and remove the data such as the flow tables, routing policies, and management configurations maintained by itself, and degrade to the role of an ordinary switch, that is, a satellite node without the SDN controller management function. At this point, the new SDN controller has fully mastered the scheduling and management tasks in the region, and the network as a whole smoothly enters a new operating state.

[0220] That is to say, the multi-stage migration method of the LEO constellation network SDN controller provided by the application example of the present application, by first pre-synchronously transmitting static data and original quasi-static data, and then sharing dynamic data when triggering the SDN controller migration, can effectively reduce the resource consumption during the SDN controller migration process, and thus can effectively avoid resource overload during the SDN controller migration, and can effectively improve the reliability and efficiency of the SDN controller migration process; and, based on the data of the change trend of the average transmission delay within the domain and the data of the change trend of the resource utilization rate to obtain the overload prediction value, can effectively improve the accuracy and timeliness of the pre-synchronization start, and can balance the network performance and the stability of the satellite nodes; by using the dynamic threshold determined in advance based on the average value of the resource utilization rates of all the current satellite nodes in the target control region as one of the conditions for triggering the SDN controller migration, establishing a connection between the dynamic threshold and the resource conditions of all the satellite nodes in the region, can effectively prevent the situation that when all the satellites in the region have a collective high load due to high population density, or concentrated traffic, etc., the SDN controller migrates repeatedly among the limited candidate nodes to form frequent migration oscillations, and thus can effectively improve the application stability and reliability after the SDN controller migration.

[0221] From the software level, the present application also provides a multi-stage migration device for the LEO constellation network SDN controller for executing all or part of the multi-stage migration method of the LEO constellation network SDN controller, see Figure 14 , the multi-stage migration device for the LEO constellation network SDN controller specifically includes the following contents:

[0222] The pre-synchronization module 10 is configured to determine whether to start the pre-synchronization process for the current original SDN controller deployment node according to the overload prediction values corresponding to the current intra-domain average transmission delay change trend data and resource utilization rate change trend data of the original SDN controller deployment nodes within the target control area of the low-earth orbit constellation network obtained in real time. If so, a satellite node is selected in the target control area as the pre-synchronization node, and the static data and original quasi-static data in the SDN controller management data corresponding to the original SDN controller deployment node are synchronized to the pre-synchronization node.

[0223] The trigger migration module 20 is configured to determine in real time whether to trigger the SDN controller migration for the original SDN controller deployment node based on a preset dynamic threshold and an average transmission delay threshold. If so, a satellite node is selected in the target control area as the target SDN controller deployment node, where the dynamic threshold is determined based on the average resource utilization rate of all current satellite nodes in the target control area.

[0224] The migration execution module 30 is configured to, if the target SDN controller deployment node and the pre-synchronization node are the same satellite node, share the dynamic data in the SDN controller management data with the original SDN controller deployment node and the target SDN controller deployment node in real time based on each satellite node in the target control area.

[0225] The embodiment of the low-earth orbit constellation network SDN controller multi-stage migration device provided by this application can specifically be used to execute the processing flow of the embodiment of the low-earth orbit constellation network SDN controller multi-stage migration method in the above embodiment, and its functions will not be elaborated here. Reference can be made to the detailed description of the embodiment of the low-earth orbit constellation network SDN controller multi-stage migration method above.

[0226] Part of the multi-stage migration of the low-earth orbit constellation network SDN controller by the low-earth orbit constellation network SDN controller multi-stage migration device can be completed in the original SDN controller deployment node. Specifically, it can be selected according to the processing capacity of the original SDN controller deployment node and the limitations of the user usage scenario, etc. This application does not make any limitations in this regard.

[0227] As can be seen from the above description, the low-earth orbit constellation network SDN controller multi-stage migration device provided by the embodiment of this application can effectively prevent resource overload during the SDN controller migration and avoid repeated migration of the SDN controller among limited candidate nodes to form a migration oscillation.

[0228] An embodiment of the present application also provides an electronic device, which may include a processor, a memory, a receiver, and a transmitter. The processor is configured to execute the multi-stage migration method of the LEO constellation network SDN controller mentioned in the above embodiment. The processor and the memory may be connected through a bus or other means. Taking the bus connection as an example, the receiver may be connected to the processor and the memory in a wired or wireless manner.

[0229] The processor may be a Central Processing Unit (CPU). The processor may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. chips, or a combination of the above types of chips.

[0230] The memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the multi-stage migration method of the LEO constellation network SDN controller in the embodiment of the present application. The processor executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions, and modules stored in the memory, that is, to implement the multi-stage migration method of the LEO constellation network SDN controller in the above method embodiment.

[0231] The memory may include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory may optionally include a memory remotely provided relative to the processor, and these remote memories may be connected to the processor through a network. Examples of the above networks include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0232] The one or more modules are stored in the memory and, when executed by the processor, execute the multi-stage migration method of the LEO constellation network SDN controller in the embodiment.

[0233] In some embodiments of the present application, the user equipment may include a processor, a memory, and a transceiver unit. The transceiver unit may include a receiver and a transmitter. The processor, the memory, the receiver, and the transmitter may be connected through a bus system. The memory is used to store computer instructions, and the processor is used to execute the computer instructions stored in the memory to control the transceiver unit to transmit and receive signals.

[0234] As an implementation manner, the functions of the receiver and the transmitter in the present application may be considered to be implemented through a transceiver circuit or a dedicated transceiver chip, and the processor may be considered to be implemented through a dedicated processing chip, a processing circuit, or a general-purpose chip.

[0235] As another implementation manner, it may be considered to use a general-purpose computer to implement the server provided in the embodiments of the present application. That is, the program codes for implementing the functions of the processor, the receiver, and the transmitter are stored in the memory, and the general-purpose processor implements the functions of the processor, the receiver, and the transmitter by executing the codes in the memory.

[0236] The embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the foregoing multi-stage migration method of the LEO constellation network SDN controller are implemented. The computer-readable storage medium may be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium well-known in the technical field.

[0237] The embodiments of the present application further provide a computer program product, including a computer program. When the computer program is executed by a processor, the steps of the foregoing multi-stage migration method of the LEO constellation network SDN controller are implemented.

[0238] Those of ordinary skill in the art should understand that the exemplary components, systems, and methods described in combination with the embodiments disclosed herein can be implemented in hardware, software, or a combination of the two. Specifically, whether to execute in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application. When implemented in hardware, it may be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a functional card, and so on. When implemented in software, the elements of the present application are programs or code segments used to execute the required tasks. The program or code segment may be stored in a machine-readable medium, or transmitted through a data signal carried in a carrier wave on a transmission medium or a communication link.

[0239] It should be clear that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions, or change the order between steps after understanding the spirit of the present application.

[0240] In the present application, features described and / or illustrated for one embodiment can be used in the same or a similar manner in one or more other embodiments, and / or combined with the features of other embodiments or replace the features of other embodiments.

[0241] The above are only the preferred embodiments of the present application and are not used to limit the present application. For those skilled in the art, various changes and modifications can be made to the embodiments of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A multi-stage migration method for an SDN controller in a low-earth orbit constellation network, characterized in that Including: Based on the overload prediction value corresponding to the current in-domain average transmission delay change trend data and resource utilization rate change trend data of the original SDN controller deployment node in the target control area of the low-earth orbit constellation network obtained in real time, determine whether to initiate a pre-synchronization process for the original SDN controller deployment node at present. If so, select a satellite node in the target control area as the pre-synchronization node, and synchronize the static data and original quasi-static data in the SDN controller management data corresponding to the original SDN controller deployment node to the pre-synchronization node; Based on a preset dynamic threshold and average transmission delay threshold, determine in real time whether to trigger the migration of the SDN controller for the original SDN controller deployment node. If so, select a satellite node in the target control area as the target SDN controller deployment node, where the dynamic threshold is determined based on the average resource utilization rate of all current satellite nodes in the target control area; If the target SDN controller deployment node and the pre-synchronization node are the same satellite node, based on each satellite node in the target control area, share the dynamic data in the SDN controller management data with the original SDN controller deployment node and the target SDN controller deployment node in real time.

2. The multi-stage migration method of the LEO constellation network SDN controller according to claim 1, wherein, Also including: If the target SDN controller deployment node and the pre-synchronization node are different satellite nodes respectively, control the pre-synchronization node to transmit the static data and original quasi-static data to the target SDN controller deployment node; Based on each satellite node in the target control area, share the dynamic data in the SDN controller management data with the original SDN controller deployment node and the target SDN controller deployment node in real time.

3. The multi-stage migration method of the LEO constellation network SDN controller according to claim 1 or 2, characterized in that, Before determining in real time whether to trigger the migration of the SDN controller for the original SDN controller deployment node based on the preset dynamic threshold and average transmission delay threshold, it also includes: During the process of synchronizing the static data and original quasi-static data to the pre-synchronization node, record the version number of the original quasi-static data in the original SDN controller; Correspondingly, before sharing the dynamic data in the SDN controller management data with the original SDN controller deployment node and the target SDN controller deployment node based on each satellite node in the target control area in real time, it also includes: According to the version number of the original quasi-static data, determine whether the original quasi-static data transmitted to the target SDN controller deployment node at present is the latest version. If not, transmit the incremental data of the latest version of the quasi-static data relative to the original quasi-static data to the target SDN controller deployment node.

4. The multi-stage migration method of the LEO constellation network SDN controller according to claim 1, wherein Before determining whether to initiate a pre-synchronization process for the original SDN controller deployment node based on the overload prediction value corresponding to the current in-domain average transmission delay change trend data and resource utilization rate change trend data of the original SDN controller deployment node in the target control area of the low-earth orbit constellation network obtained in real time, it also includes: Obtain the current average intra-domain transmission delay of the original SDN controller deployment node and the change rate of the average intra-domain transmission delay per unit time to form corresponding average intra-domain transmission delay change trend data; And, obtain the current resource utilization rate of the original SDN controller deployment node and the change rate of the resource utilization rate per unit time to form corresponding resource utilization rate change trend data; Determine a delay prediction value according to the average intra-domain transmission delay change trend data, a preset average transmission delay threshold, and a first weighting coefficient, and determine a resource prediction value according to the resource utilization rate change trend data, a preset dynamic threshold, and a second weighting coefficient; wherein, the sum of the first weighting coefficient and the second weighting coefficient is equal to 1; Add the delay prediction value and the resource prediction value to obtain a corresponding overload prediction value; Correspondingly, judging whether to start a pre-synchronization process for the original SDN controller deployment node according to the resource overload prediction value corresponding to the current average intra-domain transmission delay change trend data and resource utilization rate change trend data of the original SDN controller deployment node in the target control area of the low-earth orbit constellation network obtained in real time, including: Judge whether the overload prediction value is equal to or greater than 1, if so, determine whether to start a pre-synchronization process for the original SDN controller deployment node.

5. The multi-stage migration method of the LEO constellation network SDN controller according to claim 4, characterized in that, Selecting a satellite node in the target control area as a pre-synchronization node includes: Obtain the current respective resource utilization rates of each satellite node in the target control area; And, obtain the current respective longitudes and latitudes of each satellite node in the target control area to obtain the angles between each satellite node with the earth's center as the vertex and the center of the target control area in the target control area; According to the current respective resource utilization rates, the angles, the longitude and latitude of the area center of each satellite node in the target control area, respectively determine the comprehensive scores of each satellite node in the target control area at the current moment; Based on the comprehensive scores of each satellite node in the target control area at the current moment and the change rate of the comprehensive scores corresponding to each satellite node in the target control area, determine the predicted comprehensive scores of each satellite node in the target control area after the prediction time period; Select a satellite node in the target control area as a pre-synchronization node according to the predicted comprehensive scores corresponding to each satellite node in the target control area.

6. The multi-stage migration method of the LEO constellation network SDN controller according to claim 5, characterized in that The obtaining the current resource utilization rate of the original SDN controller deployment node includes: Determine the current resource utilization rate of the original SDN controller deployment node according to the current battery energy utilization rate and multi-dimensional resource load of the original SDN controller deployment node, wherein the multi-dimensional resource load includes: bandwidth utilization rate, CPU utilization rate, and memory utilization rate; Correspondingly, the obtaining the current respective resource utilization rates of each satellite node in the target control area includes: Based on the current battery energy usage rates and multi-dimensional resource loads respectively corresponding to each satellite node within the target control area, determine the resource usage rates currently corresponding to each satellite node within the target control area respectively.

7. The multi-stage migration method of the LEO constellation network SDN controller according to claim 1, characterized in that The real-time determination of whether to trigger the migration of the SDN controller for the original SDN controller deployment node based on a preset dynamic threshold and an average transmission delay threshold. If so, select a satellite node within the target control area as the target SDN controller deployment node, including: Determine the current dynamic threshold according to the average value of the resource usage rates of all satellite nodes within the target control area currently and a preset multiple coefficient of the resource load threshold. Real-time determine whether the current intra-domain average transmission delay of the original SDN controller deployment node exceeds the preset average transmission delay threshold, and real-time determine whether the current resource usage rate of the original SDN controller deployment node exceeds the dynamic threshold. If it is determined through judgment that the current intra-domain average transmission delay of the original SDN controller deployment node exceeds the preset average transmission delay threshold, and / or the current resource usage rate of the original SDN controller deployment node exceeds the dynamic threshold, then determine that the migration of the SDN controller for the original SDN controller deployment node is triggered currently, and select a satellite node within the target control area as the target SDN controller deployment node.

8. The multi-stage migration method of the LEO constellation network SDN controller according to claim 1 or 7, characterized in that The selection of a satellite node within the target control area as the target SDN controller deployment node includes: Based on the resource usage rates, included angles, longitudes and latitudes of the regional centers of the target control area respectively corresponding to each satellite node within the target control area, determine the comprehensive scores of each satellite node within the target control area at the current moment respectively. Based on the comprehensive scores and corresponding weight coefficients of each satellite node within the target control area at the current moment respectively, and the change rates and corresponding weight coefficients of the comprehensive scores respectively corresponding to each satellite node within the target control area, determine the final comprehensive scores respectively corresponding to each satellite node within the target control area. According to the final comprehensive scores respectively corresponding to each satellite node within the target control area, select a satellite node within the target control area as the target SDN controller deployment node.

9. A multi-stage migration device for a low-earth orbit constellation network SDN controller, characterized in that, Including: A pre-synchronization module, which is used to judge whether to start the pre-synchronization process for the original SDN controller deployment node according to the overload prediction values corresponding to the current intra-domain average transmission delay change trend data and resource usage rate change trend data of the original SDN controller deployment node within the target control area of the low-earth orbit constellation network obtained in real time. If so, select a satellite node within the target control area as the pre-synchronization node, and synchronize the static data and original quasi-static data in the SDN controller management data corresponding to the original SDN controller deployment node to the pre-synchronization node. A trigger migration module, configured to determine in real time whether to trigger the migration of the SDN controller for the original SDN controller deployment node based on a preset dynamic threshold and an average transmission delay threshold. If so, a satellite node is selected in the target control area as the target SDN controller deployment node, where the dynamic threshold is determined based on the average resource utilization rate of all current satellite nodes in the target control area; A migration execution module, configured to, if the target SDN controller deployment node and the pre-synchronization node are the same satellite node, share the dynamic data in the SDN controller management data with the original SDN controller deployment node and the target SDN controller deployment node in real time based on each satellite node in the target control area.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the multi-stage migration method of the SDN controller for the low-earth orbit constellation network according to any one of claims 1 to 8.

Images