Disaster recovery backup method and device, communication equipment and storage medium

Abstract

The invention relates to a disaster recovery backup method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of obtaining a network topology data set of a data center where a current node is located; the network topology data set comprises node state data of each data node and link state data of each network link; constructing a state space and an action space of the current node based on the state data of each node and the state data of each link, and determining a target alternative node in the data center based on the data center network model, the state space and the action space; the target alternative node is a path node to the target backup node; and transmitting the data to be backed up from the current node to the target alternative node until the data to be backed up is transmitted to the target backup node. By adopting the method, the efficiency of the disaster recovery backup method can be improved.

Description

Technical Field

[0001] The present application relates to the fields of network technology and security technology, and in particular to a disaster recovery backup method, device, communication equipment, storage medium and computer program product. Background Art

[0002] The data center contains data nodes, and network links for data transmission are set between adjacent data nodes. Data nodes include data center nodes and backup nodes. In order to cope with sudden disasters, the data to be backed up in the data center node will be transmitted to the corresponding target backup node, so that when a disaster occurs in the data center node, it can continue to work based on the data in the target backup node.

[0003] In the current disaster recovery backup method, when transmitting the data to be backed up from the data center node to the target backup node, the next data node in each intermediate transmission process is found in the routing table. Alternatively, the data center manager sets a fixed backup link, and the fixed backup link corresponding to each network link is pre-set with a fixed backup data bandwidth. The data nodes on the fixed backup link transmit the data to be backed up based on the fixed backup data bandwidth.

[0004] However, in the current disaster recovery backup method, when a routing table or a fixed backup link is used to determine the data node in the intermediate transmission process, since the network link is also used to transmit application data, it will cause network link congestion, making the transmission efficiency of the data to be backed up slower, thereby reducing the efficiency of the disaster recovery backup method. Summary of the invention

[0005] Based on this, it is necessary to provide a disaster recovery backup method, apparatus, computer equipment, computer readable storage medium and computer program product to address the above technical issues.

[0006] In a first aspect, the present application provides a disaster recovery backup method, comprising:

[0007] Obtaining a network topology data set of a data center where the current node is located; the network topology data set includes node status data of each data node and link status data of each network link;

[0008] Constructing the state space and action space of the current node based on each of the node state data and each of the link state data, and determining a target candidate node in the data center based on the data center network model, the state space and the action space; the target candidate node is a node on the way to the target backup node;

[0009] The data to be backed up is transmitted from the current node to the target candidate node until it is transmitted to the target backup node.

[0010] In one embodiment, constructing the state space and action space of the current node based on each of the node state data and each of the link state data includes:

[0011] Determine a total status data set of the data center based on each of the node status data and each of the link status data;

[0012] Constructing the state space of the current node based on the total state data set, each of the network links and a preset average data ratio;

[0013] The action space of the current node is screened in the data center according to the state space, a preset data volume difference parameter, and a normal service ratio of a network link.

[0014] In one embodiment, each of the data nodes includes each data center node and each backup node; the link status data includes the usage status and transmission bandwidth of the network link, and the node status data includes the source data volume and storage capacity of the data node, and determining the total status data set of the data center based on each of the node status data and each of the link status data includes:

[0015] Determining the remaining storage capacity of the data center according to the storage capacity of each backup node and the amount of source data;

[0016] Determining the amount of backup remaining data of the data center according to the amount of source data of each data center node and the amount of source data of each backup node;

[0017] Determine the total remaining bandwidth of the data center based on the transmission bandwidth of each network link whose usage status is idle;

[0018] A total status data set of the data center is constructed based on the total remaining bandwidth, the amount of backup remaining data, and the remaining storage capacity of the data center.

[0019] In one embodiment, the step of selecting the action space of the current node in the data center according to the state space, a preset data volume difference parameter, and a normal service ratio of a network link includes:

[0020] Constructing a set of constraint conditions according to the state space, a preset data volume difference parameter and a normal service ratio of a network link;

[0021] Based on the constraint condition set, the next hop node of the current node is screened from each data node in the data center to obtain a candidate node set, and the candidate node set is determined as the action space of the current node.

[0022] In one embodiment, determining a target candidate node in the data center based on the data center network model, the state space, and the action space includes:

[0023] Performing prediction processing on the state space and the action space based on the data center network model to obtain an initial reward value;

[0024] Optimizing the initial reward value according to a heuristic optimization algorithm to obtain a reward value;

[0025] A target candidate node is determined in the action space according to the reward value and a probability algorithm.

[0026] In one embodiment, the action space includes candidate nodes, and determining a target candidate node in the action space according to the reward value and the probability algorithm includes:

[0027] For each of the candidate nodes, determining a candidate link between the candidate node and the current node;

[0028] Performing probability calculation on the reward value, the node status data of the candidate node, and the link status data of the candidate link according to a probability algorithm to obtain the probability of the candidate node;

[0029] The candidate node with the highest probability among the candidate nodes is determined as the target candidate node.

[0030] In a second aspect, the present application also provides a disaster recovery backup device, including:

[0031] An acquisition module is used to acquire a network topology data set of a data center where the current node is located; the network topology data set includes node status data of each data node and link status data of each network link;

[0032] A determination module, configured to construct a state space and an action space of the current node based on each of the node state data and each of the link state data, and determine a target candidate node in the data center based on a data center network model, the state space and the action space; the target candidate node is a path node to a target backup node;

[0033] The transmission module is used to transmit the data to be backed up from the current node to the target candidate node until it is transmitted to the target backup node.

[0034] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0035] Obtaining a network topology data set of a data center where the current node is located; the network topology data set includes node status data of each data node and link status data of each network link;

[0036] Constructing the state space and action space of the current node based on each of the node state data and each of the link state data, and determining a target candidate node in the data center based on the data center network model, the state space and the action space; the target candidate node is a node on the way to the target backup node;

[0037] The data to be backed up is transmitted from the current node to the target candidate node until it is transmitted to the target backup node.

[0038] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0039] Obtaining a network topology data set of a data center where the current node is located; the network topology data set includes node status data of each data node and link status data of each network link;

[0040] Constructing the state space and action space of the current node based on each of the node state data and each of the link state data, and determining a target candidate node in the data center based on the data center network model, the state space and the action space; the target candidate node is a node on the way to the target backup node;

[0041] The data to be backed up is transmitted from the current node to the target candidate node until it is transmitted to the target backup node.

[0042] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0043] Obtaining a network topology data set of a data center where the current node is located; the network topology data set includes node status data of each data node and link status data of each network link;

[0044] Constructing the state space and action space of the current node based on each of the node state data and each of the link state data, and determining a target candidate node in the data center based on the data center network model, the state space and the action space; the target candidate node is a node on the way to the target backup node;

[0045] The data to be backed up is transmitted from the current node to the target candidate node until it is transmitted to the target backup node.

[0046] The above-mentioned disaster recovery backup method, device, communication equipment, storage medium and computer program product obtain the network topology data set of the data center where the current node is located; the network topology data set includes the node status data of each data node and the link status data of each network link; the state space and action space of the current node are constructed based on each node status data and each link status data, and the target candidate node is determined in the data center based on the data center network model, the state space and the action space; the target candidate node is a path node to the target backup node; the backup data is transmitted from the current node to the target candidate node until it is transmitted to the target backup node. With this method, based on each node status data, link status data and data center network model, a data node with an idle network link and a good node status is selected from each data node in the data center as the next node of the current node, that is, the target candidate node. The data to be backed up is transmitted from the current node to the target candidate node with a good status through an idle network link, which improves the transmission efficiency of the data to be backed up, thereby improving the efficiency of the disaster recovery backup method. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 An application environment diagram of a disaster recovery backup method in an embodiment;

[0048] Figure 2 A schematic diagram of a process flow of a disaster recovery backup method in an embodiment;

[0049] Figure 3 A schematic diagram of a process of constructing a state space and an action space in one embodiment;

[0050] Figure 4 A schematic diagram of a process for determining a total state data set in one embodiment;

[0051] Figure 5 A schematic diagram of a process of screening an action space in one embodiment;

[0052] Figure 6 A schematic diagram of a process for determining a target candidate node in an embodiment;

[0053] Figure 7 is an architectural diagram of a data center network model in one embodiment;

[0054] Figure 8 A schematic diagram of a process for determining a target candidate node based on probability in one embodiment;

[0055] Fig. 9 A schematic diagram of a process for training a reinforcement learning model in one embodiment;

[0056] Fig.10A network topology diagram of a sample network topology model in an embodiment;

[0057] Fig.11 A structural block diagram of a disaster recovery backup device in an embodiment;

[0058] Fig.12 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0060] Figure 1 A schematic diagram of an application scenario of a disaster recovery backup method provided in an embodiment of the present application. Figure 1 As shown, the disaster recovery backup method is applied to a data center 100. The data center 100 includes data nodes 110 and a terminal 120. A network link for transmitting data is provided between adjacent data nodes 110. Each network link is provided with a maximum fixed bandwidth. Each data node 110 is divided into three types of data nodes, namely, a data center node 111, a backup node 112, and an intermediate node 113. The data center node 111 is a data node with a backup requirement, and the data center node 111 is a data node that provides application services. The backup node 112 is a data node that stores backup data. The remaining data nodes are intermediate nodes 113. The terminal 120 is used to execute the disaster recovery backup method, and the backup data to be backed up is transmitted from the data center node 111 to the target backup node. Among them, the terminal 120 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers or servers. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0061] Traditional disaster recovery backup methods have two backup methods. The first backup method is to determine the data center node with backup requirements as the current node and obtain the routing table corresponding to the current node. The routing table contains the addresses of each next-hop node (alternative node) corresponding to the current node. Then, the candidate node with the highest routing priority among the candidate nodes is determined as the target candidate node, and the data to be backed up is transferred from the current node to the target candidate node. The target candidate node is updated to the current node, and it is determined whether the current node is the target backup node. If the current node is not the target backup node, the step of obtaining the routing table corresponding to the current node is executed until the current node is the target backup node.

[0062] The second backup method is to determine the data center node with backup requirements as the starting point and the target backup node as the end point. Then, determine the fixed backup link corresponding to the starting point and the end point, and transmit the data to be backed up from the data center node to the target backup node based on the fixed backup link. Since each network link in the data center is set with a fixed backup data bandwidth, the data nodes on the fixed backup link will transmit the data to be backed up based on the backup data bandwidth.

[0063] In traditional disaster recovery and backup methods, when a routing table or a fixed backup link is used to determine the data node in the intermediate transmission process, since the network link is also used to transmit application data, it will cause network link congestion, making the transmission efficiency of the data to be backed up slow, thereby reducing the efficiency of the disaster recovery and backup method. In addition, at this time, the remaining available data nodes and network links are idle, reducing the resource utilization of the data center.

[0064] Based on the above-mentioned traditional technology, the embodiment of the present application provides a disaster recovery backup method, which selects a data node with an idle network link and a good node status from each data node in the data center based on the node status data, link status data and the data center network model as the next node of the current node, that is, the target candidate node. The data to be backed up is transmitted from the current node to the target candidate node in good status through an idle network link, which improves the transmission efficiency of the data to be backed up, thereby improving the efficiency of the disaster recovery backup method. In addition, the data to be backed up is transmitted through idle network links and data nodes, which improves the resource utilization of the data center.

[0065] It should be noted that the beneficial effects brought about by the embodiments of the present application or the technical problems solved are not limited to this one, but may also include other implicit or related problems. For details, please refer to the description of the following embodiments.

[0066] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0067] In one embodiment, Figure 2 As shown, a disaster recovery backup method is provided, which is applied to Figure 1 The terminal 120 (hereinafter, the reference numeral is omitted, referred to as the terminal) in the embodiment is used as an example to illustrate, and the following steps are included:

[0068] Step 202: Obtain a network topology dataset of the data center where the current node is located.

[0069] The network topology data set includes node status data of each data node and link status data of each network link.

[0070] In implementation, the terminal determines the data center where the current node is located, and obtains the network topology map of the data center, the node status data of each data node, and the link status data of each network link to obtain the network topology data set of the data center.

[0071] Specifically, when a data center node in a data center needs to transmit data to be backed up to a target backup node, the terminal determines the data center node as the current node. Then, the terminal obtains the node status data and network link status data of each data node in the data center where the current node is located, and obtains the network topology data set of the data center.

[0072] In an exemplary embodiment, the terminal obtains the source data volume and storage capacity of each data node in the data center, and constructs the node status data of the data node based on the source data volume and storage capacity. Among them, the storage capacity is the amount of data that the data node can store, and the source data volume is the amount of data stored in the data node. At the same time, the terminal obtains the usage status and transmission bandwidth of each network link, and constructs the link status data of the network link based on the usage status and transmission bandwidth. The usage status indicates whether the network link is transmitting data, that is, whether the network link is in use. The transmission bandwidth is the maximum bandwidth of the network link. The terminal constructs the network topology data set of the data center based on the node status data of each data node and the link status data of each network link.

[0073] For example, the terminal obtains the network topology of the data center where the current node is located V represents each data node in the data group center, and E represents the connection relationship between each data node, that is, the network link. Indicates the data center nodes that require backup. Indicates the number of data center nodes in the data center. To represent the backup node in the data center. Indicates the number of backup nodes in the data center. The terminal obtains the source data volume and storage capacity of each data node in the data center and obtains the node status data of each data node. , Storage capacity of backup nodes At the same time, the terminal obtains the transmission bandwidth and usage status of each network link in the data center and obtains the link status data of each network link. Among them, the transmission bandwidth of the network link is . Indicates a data center node To the backup node No. transmission paths, and the set P is the set of all backup transmission links. The transmission bandwidth is used Indicates. Then , indicating all transmission paths In the link The total bandwidth used on Used to indicate backup link Whether the backup link is used also indicates the usage status of the network link.

[0074] Optionally, the node status data also includes the inflow and outflow traffic of the data node, and the link status data also includes the remaining bandwidth of the network link. The embodiment of the present application does not limit the data included in the node status data and the link status data.

[0075] Step 204 , constructing the state space and action space of the current node based on the state data of each node and the state data of each link, and determining the target candidate node in the data center based on the data center network model, the state space and the action space.

[0076] The target candidate node is a node on the way to the target backup node, and the target backup node is the end point of the data to be backed up.

[0077] In the implementation, the terminal takes the transmission flow maximization as the goal, and constructs the state space of the current node and the action space of the current node based on the state data of each node and each link state data. Then, the terminal selects the target candidate node from each data node in the data center based on the network-centric network model, state space and action space.

[0078] Step 206: The data to be backed up is transmitted from the current node to the target candidate node until it is transmitted to the target backup node.

[0079] In implementation, the terminal transfers the backup data from the current node to the target candidate node, and updates the target candidate node to the current node. Then, the terminal determines whether the current node is the target backup node. If the current node is not the target backup node, the terminal executes the step of obtaining the network topology data set of the data center where the current node is located. If the current node is the target backup node, the terminal stops executing the disaster recovery backup method. At this time, the target backup node will receive the data to be backed up and save the data to be backed up, thereby realizing disaster recovery backup of the data.

[0080] In the above disaster recovery backup method, based on the node status data, link status data and data center network model, a data node with an idle network link and a good node status is selected from each data node in the data center as the next node of the current node, that is, the target candidate node. The data to be backed up is transmitted from the current node to the target candidate node in good status through the idle network link, which improves the transmission efficiency of the data to be backed up, thereby improving the efficiency of the disaster recovery backup method.

[0081] In an exemplary embodiment, Figure 3 As shown, the specific processing process of constructing the state space and action space of the current node based on the state data of each node and the state data of each link in step 202 includes steps 302 to 306. Among them:

[0082] Step 302: determine a total status data set of the data center based on the status data of each node and the status data of each link.

[0083] The node status data of each data node includes the storage capacity and source data volume of the data node.

[0084] In implementation, the terminal determines the backup remaining data volume and the remaining storage capacity of the data center based on each storage capacity and each source data volume. Then, the terminal determines the total remaining bandwidth of the data center based on each link state data. The terminal constructs a total state data set of the data center based on the total remaining bandwidth, the backup remaining data volume and the remaining storage capacity.

[0085] Specifically, the terminal determines the amount of backup remaining data of the data center based on the storage capacity and source data volume of each backup node. Then, the terminal determines the amount of backup remaining data of the data center based on the source data volume of the data center node and the source data volume of the backup node. Then, the terminal determines the total remaining bandwidth of the data center based on the usage status and transmission bandwidth of each network link in each link status data. The terminal combines the total remaining bandwidth, the amount of backup remaining data, and the remaining storage capacity to obtain a total status data set of the data center. Through the total remaining bandwidth, the amount of backup remaining data, and the remaining storage capacity, the node status of each data node and the link status of the network link can be clearly defined.

[0086] Step 304: construct the state space of the current node based on the total state data set, each network link and a preset average data ratio.

[0087] In implementation, the terminal is pre-set with an average data ratio. The average data ratio is the average ratio of the amount of data stored in the target backup node to the total amount of backup data. The terminal aims to maximize the transmission of data and constructs the state space of the current node based on the total state data set, each network link and the preset average data ratio.

[0088] In an exemplary embodiment, the total status data set includes the total remaining bandwidth , Back up the remaining data and remaining storage capacity The average data ratio pre-set in the terminal is The terminal determines the data center node to which data needs to be transmitted as the target data center node, and determines each backup transmission path from the target data center node to the target backup node. Indicates a data center node To the backup node No. The set P is the set of all backup transmission links. The bandwidth of each network link is Indicates. Then , indicating all backup transmission paths In the link The total bandwidth used on the Indicates whether the backup link is used. The total remaining bandwidth is Then, the network link The corresponding maximum flow is shown in the following formula (1):

[0089]

[0090] In the above formula (1), Indicates that the node is from the data center To the backup node The traffic on the network link. For slave data center nodes To the backup node The minimum bandwidth of the network link that needs to be consumed during the process.

[0091] Therefore, in order to shorten the backup time to the greatest extent, the objective function of the entire backup process is to maximize the maximum flow. The objective function is shown in the following formula (2):

[0092]

[0093] In the above formula (2), Indicates that the node is from the data center To the backup node The traffic on the network link. For slave data center nodes To the backup node The sum of the bandwidths of each network link on the backup transmission link.

[0094] The terminal constructs each of the above network links into a network link set The terminal is based on the network link set and the total remaining bandwidth. , Back up the remaining data , Remaining storage capacity The average ratio of the sum data is Construct the state space of the current node .

[0095] Step 306 , filtering the action space of the current node in the data center according to the state space, the preset data volume difference parameter, and the normal service ratio of the network link.

[0096] In implementation, the terminal constructs a screening condition set according to the state space, preset data volume difference parameters and the normal service ratio of the network link, and screens each candidate node in each data node of the data center based on the screening condition set to obtain the action space of the current node.

[0097] In this embodiment, the total state data set is determined by the node state data and the link state data, and the state of the data center is clarified. The state space is constructed by the total state data set, and the next hop node of the current node is screened based on the state space to obtain the action space, and the next hop node of the current node is preliminarily determined, which is convenient for determining the target candidate node in the action space later. In addition, the state space is constructed by transmission flow, which improves the transmission efficiency of the data to be backed up and improves the efficiency of the disaster recovery backup method.

[0098] In an exemplary embodiment, Figure 4 As shown, each data node includes each data center node and each backup node; the link status data includes the usage status and transmission bandwidth of the network link, and the node status data includes the source data volume and storage capacity of the data node. The specific processing process of step 302 includes steps 402 to 408. Among them:

[0099] Step 402: Determine the remaining storage capacity of the data center according to the storage capacity of each backup node and the amount of source data.

[0100] In implementation, the terminal performs difference processing on the storage capacity of each backup node and the amount of source data to obtain the remaining storage capacity of the backup node. Then, the terminal performs addition processing on the remaining storage capacity of each backup node to obtain the remaining storage capacity of the data center.

[0101] Specifically, the terminal selects each backup node from each data node. Then, for each backup node, the terminal performs difference processing on the storage capacity of the backup node and the amount of source data to obtain the remaining storage capacity of the backup node. Then, the terminal performs addition operation on the remaining storage capacity of each backup node to obtain the remaining storage capacity of the data center. The remaining storage capacity of the data center represents the amount of backup data that can be stored in the data center.

[0102] Step 404, determining the backup remaining data volume of the data center according to the source data volume of each data center node and the source data volume of each backup node.

[0103] In the implementation, the terminal performs addition processing on the source data volume of each data center node to obtain the total backup data volume of the data center, and performs addition processing on the source data volume of each backup node to obtain the backed up data volume. Then, the terminal performs difference processing on the total backup data volume and the backed up data volume to obtain the backup remaining data volume of the data center.

[0104] Step 406: determine the total remaining bandwidth of the data center based on the transmission bandwidth of each network link in the idle state.

[0105] In implementation, the terminal selects idle network links whose usage status is idle from among the network links, and obtains the total remaining bandwidth of the data center by performing an addition operation on the status of each idle network link.

[0106] Specifically, the usage status of the network link includes an idle state and a non-idle state. The idle state indicates that the network link is in an idle state and is not transmitting data. The non-idle state indicates that the network link is transmitting data. For each network link, the terminal determines whether the usage status of the network link is an idle state. If the usage status of the network link is an idle state, the terminal determines the network link as an idle network link. Then, the terminal performs an addition operation on the status of each idle network link to obtain the total remaining bandwidth of the data center.

[0107] In an exemplary embodiment, each network link The transmission bandwidth is used Indicates. Among them, , V represents each data node. Indicates a data center node To the backup node No. backup transmission paths, and set P is the set of all backup transmission links. Then , indicating all backup transmission paths In the network link The total bandwidth used on the Used to indicate backup transmission link Whether to use it. If the backup transmission link is used, all network links on the backup transmission link are in a non-idle state. If the backup transmission link is not used, all network links on the backup transmission link are in an idle state. The total remaining bandwidth is .

[0108] Step 408: construct a total status data set of the data center based on the total remaining bandwidth, the amount of backup remaining data, and the remaining storage capacity of the data center.

[0109] In implementation, the terminal combines the total remaining bandwidth, the amount of backup remaining data, and the remaining storage capacity of the data center to construct a total status data set of the data center.

[0110] In this embodiment, the total remaining bandwidth, the amount of backup remaining data, and the remaining storage capacity of the data center are determined through the node status data and the link status data, and the overall state of the data center is clarified, which facilitates the subsequent construction of the state space and action space.

[0111] In an exemplary embodiment, Figure 5 As shown, the specific processing process of step 306 includes steps 502 to 504. Among them:

[0112] Step 502: construct a set of constraint conditions according to the state space, the preset data volume difference parameter and the normal service ratio of the network link.

[0113] In implementation, a data volume difference parameter is pre-set in the terminal. The data volume difference parameter is the difference threshold between the data volumes received by each backup node. The normal ratio of the network link is the bandwidth ratio used to transmit normal business data. The terminal constructs the first filtering condition with the transmission flow being a non-negative number as the target. Then, the terminal constructs the second filtering condition with the target that each flow must not be greater than the transmission bandwidth between the two nodes, and constructs the third filtering condition with the target that the bandwidth allocation is a non-negative number. The terminal constructs the fourth filtering condition based on the normal business ratio of the network link, and constructs the fifth filtering condition based on the data volume difference parameter and the average ratio of data in the state space. The terminal constructs the sixth filtering condition based on the data reception volume and storage capacity of each backup node, and constructs the seventh filtering condition based on the input flow and output flow of each data node. The terminal constructs a constraint condition set based on the above-mentioned filtering conditions.

[0114] Specifically, the terminal transmission flow is a non-negative number to construct a first constraint condition set, and the second filtering condition is constructed based on the goal that the transmission flow between each network link must not be greater than the transmission bandwidth of the network link. Then, the terminal constructs a third filtering condition with the bandwidth allocation being a non-negative number as the goal. The terminal constructs a fourth filtering condition with the goal that the bandwidth ratio of the transmission backup data on each network link and the normal business ratio of the network link is less than or equal to 1. Then, the terminal constructs a fifth filtering condition with the goal that the difference between the amount of data received by each backup node is less than the data volume difference parameter. The terminal constructs a sixth filtering condition with the goal that the amount of data received by each backup node is less than or equal to the storage capacity of the data node. At the same time, the terminal constructs a seventh filtering condition with the goal that the input flow of each data node is equal to the output flow. The terminal constructs a constraint condition set based on the first to seventh filtering conditions. Among them, the constraint condition set is shown in the following formula group (3):

[0115] (3)

[0116] Among them, in the above formula group (3), Represents a constraint. The constraint set contains seven constraints, namely the first constraint (3.1), the second constraint (3.2), the third constraint (3.3), the fourth constraint (3.4), the fifth constraint (3.5), the sixth constraint (3.6) and the seventh constraint (3.7). In the above formula (3.1) represents the traffic transmitted by the nth network link. In the above formula (3.2), Indicates the traffic value transmitted by the network link. Indicates the transmission bandwidth corresponding to the network link. In the above formula (3.3), The transmission bandwidth allocated to the network link. In the above formula (3.4), Indicates the backup link bandwidth used to transmit the data to be backed up on the network link. Indicates the transmission bandwidth of the network link. is the normal service ratio of the network link. In the above formula (3.5), Represents the average proportion of data in state space. Represents each backup node in a data center. Indicates a backup node. Represents each data center node in the data center, Indicates a data center node. Indicates that the node is from the data center To the backup node backup transmission link. Indicates that the node is from the data center To the backup node of transmission traffic. Backup Node storage capacity. is the data volume difference parameter. In the above formula (3.6), Represents each backup node in a data center. Indicates a backup node. Represents each data center node in the data center, Indicates a data center node. Indicates that the node is from the data center To the backup node backup transmission link. Indicates that the node is from the data center To the backup node of transmission traffic. Backup Node In the above formula (3.7), Represents the slave data node To the data node Medium data node The input flow rate, Represents the slave data node To the data node Medium data node If the input flow is greater than the output flow, the data node is the backup node. If the output flow is greater than the output flow, the data node is a data center node. If the output flow is equal to the input flow, then the data node The intermediate node.

[0117] Step 504 , based on the constraint condition set, the next hop node of the current node is screened from the data nodes in the data center to obtain a candidate node set, and the candidate node set is determined as the action space of the current node.

[0118] In the implementation, the terminal selects the next hop node with a network link to the current node from each data node in the data center to obtain an initial candidate node set. The terminal selects each candidate node that meets the constraint condition set from the initial candidate node set to obtain a candidate node set. Then, the terminal determines the candidate node set as the action space of the current node.

[0119] Specifically, the terminal selects the next hop node that has a network link with the current node from each data node in the data center based on the network topology diagram of the data node, and obtains an initial candidate node set. Then, for each initial candidate node in the initial candidate node set, the terminal determines the initial candidate network link between the initial candidate node and the current node. The terminal determines whether the initial candidate node satisfies the constraint condition set based on the node status data of the initial candidate node and the link status data of the initial candidate network link. If the initial candidate node satisfies the constraint condition set, the terminal determines the initial candidate node as the candidate node. The terminal constructs a candidate node set based on each candidate node.

[0120] In this embodiment, a constraint set is constructed through capacity limitation, bandwidth limitation, and load balancing, and the next hop node of the current node is screened in each data node based on the constraint set, so that each candidate node that meets each constraint condition is obtained, which facilitates the subsequent determination of the target candidate node in the candidate node set. The target candidate node can effectively shorten the backup time and achieve balanced storage load.

[0121] In an exemplary embodiment, Figure 6 As shown, the specific processing process of determining the target candidate node in the data center based on the data center network model, state space and action space in step 204 includes steps 602 to 606. Among them:

[0122] Step 602: Predict the state space and action space based on the data center network model to obtain an initial reward value.

[0123] Among them, the data center network model is obtained by training the reinforcement learning model based on the sample network topology dataset.

[0124] In the implementation, a reinforcement learning model is pre-set in the terminal. The reinforcement learning model is Deep Q-Learning, referred to as DQL, which is a reinforcement learning algorithm based on deep learning. The terminal trains the reinforcement learning model based on the sample network topology data set to obtain a data center network model. The terminal inputs the state space and action space into the data center network model, and predicts the state space and action space through the data center network model to obtain the initial reward value.

[0125] In an optional embodiment, if the current node is not a data center node, the terminal contains a reward value corresponding to the previous data node. The terminal inputs the state space, action space and reward value corresponding to the previous data node into the data center network model, and predicts the reward value state space and action space corresponding to the previous data node through the data center network model to obtain an initial reward value.

[0126] In an exemplary embodiment, Figure 7FIG. 1 is an architecture diagram of a data center network model in an embodiment. Figure 7 As shown in the figure, the terminal determines the state space and action space based on the network topology data set representing the data center network environment. The terminal inputs the state space and action space into the data center network model (Q-net), predicts the state space and action space through Q-net, obtains the initial reward value, and optimizes the initial reward value based on the PSO algorithm to obtain the reward value.

[0127] Step 604: Optimize the initial reward value according to the heuristic optimization algorithm to obtain a reward value.

[0128] Among them, the heuristic optimization algorithm is the particle swarm optimization algorithm (PSO algorithm).

[0129] In implementation, the terminal optimizes the initial reward value through a particle swarm optimization algorithm to obtain a reward value.

[0130] Specifically, the initial return value is The terminal determines the initial reward value as the position of each particle of the PSO algorithm, and the velocity set of the initialized particles is Then, the terminal updates the particle speed based on the speed update algorithm to obtain the updated particle speed. Then, the terminal updates the particle position based on the position update algorithm to obtain the updated particle position, and determines the updated particle position as the reward value. The speed update algorithm is shown in the following formula (4):

[0131] (4)

[0132] In the above formula (4), is the particle velocity set, is the inertia weight, and is the learning factor, and is a random number. Inertia weight, learning factor and random number are all parameters in the particle swarm optimization algorithm. is the individual optimal position of the particle. is the updated particle velocity.

[0133] The location update algorithm is shown in the following formula (5):

[0134] (5)

[0135] In the above formula (5), is the velocity of the particle. is the particle position. is the updated particle position.

[0136] Step 606, determining target candidate nodes in the action space according to the reward value and the probability algorithm.

[0137] The action space is a candidate node set, which contains all candidate nodes.

[0138] In implementation, the terminal calculates the probability of each candidate node according to the reward value and the probability algorithm, and determines the candidate node with the highest probability as the target candidate node.

[0139] Specifically, for each candidate node in the action space, the terminal determines the candidate link corresponding to the candidate node and determines the link state data of the candidate link. Then, the terminal performs a probability operation on the reward value, the node state data of the candidate node, and the link state data of the candidate link based on the probability algorithm to obtain the probability of the candidate node. Then, the terminal determines the target candidate node in the action space based on each probability.

[0140] In this embodiment, by combining the heuristic optimization algorithm with the data center network model, the effects of the sparse rewards and limited exploration ability of the data center network model are alleviated, the exploration ability of the data center network model is improved, and it is avoided to fall into the local optimum, thereby improving the performance of the data center network model. At the same time, based on the data center network model, the state space and action space are predicted and processed to determine the target candidate node, which solves the high-dimensional data center network disaster recovery backup problem, improves the transmission efficiency of the data to be backed up, and thus improves the efficiency of the disaster recovery backup method.

[0141] In an exemplary embodiment, Figure 8 As shown, the action space includes various candidate nodes, and the specific processing process of step 606 includes steps 802 to 806. Among them:

[0142] Step 802: for each candidate node, determine a candidate link between the candidate node and the current node.

[0143] In implementation, the terminal determines, for each candidate node, a candidate link connecting the candidate node and the current node in each network link, and determines link status data corresponding to the candidate link.

[0144] Step 804 , performing probability calculation on the reward value, the node status data of the candidate node, and the link status data of the candidate link according to the probability algorithm to obtain the probability of the candidate node.

[0145] The probability algorithm is determined based on the Russian roulette algorithm and the heuristic factor. The node status data includes the source data volume and storage capacity of the candidate node. The link status data includes the remaining bandwidth of the candidate link.

[0146] In implementation, the terminal performs a difference operation on the storage capacity and source data volume of each candidate node to obtain the remaining capacity of the candidate node. Then, the terminal performs an addition operation on the remaining capacity of each candidate node to obtain the sum of the remaining capacities. The terminal performs a probability operation on the reward value, the remaining capacity of the candidate node, the sum of the remaining capacities, and the remaining bandwidth according to the probability algorithm to obtain the probability of the candidate node.

[0147] Among them, the probability algorithm is shown in the following formula (6):

[0148] (6)

[0149] In the above formula (6), For alternative nodes probability. It is the preset control parameter. Indicates the remaining capacity of the candidate node. is the sum of the remaining capacities of all candidate nodes. is the reward value of each candidate node. is the sum of the remaining bandwidths of all candidate links. is the reward value of the candidate node. is the remaining bandwidth of the candidate node.

[0150] Step 806: Determine the candidate node with the highest probability among the candidate nodes as the target candidate node.

[0151] In implementation, the terminal determines the highest probability among various probabilities, and determines the candidate node corresponding to the highest probability as the target candidate node.

[0152] In this embodiment, the probability of each candidate node is determined by the probability algorithm for the reward value, node status data and link status data, the probability of each candidate node being selected is clarified, and the candidate node with the highest probability is determined as the target candidate node, and the target candidate node with good node status and idle network link is obtained. Then, the data to be backed up is transmitted from the current node to the target candidate node in good status through the idle network link, which improves the transmission efficiency of the data to be backed up, and thus improves the efficiency of the disaster recovery backup method.

[0153] In an exemplary embodiment, Fig. 9 As shown, before the target candidate node is determined in the data center based on the data center network model, the state space and the action space in step 204, the specific processing process of the disaster recovery backup method includes steps 902 to 904. Among them:

[0154] Step 902: Initialize a sample network topology model and a sample network topology data set of the sample network topology model.

[0155] In implementation, the terminal generates a sample network topology model based on a random network topology generation model. Then, the terminal initializes a sample network topology data set of the sample network topology model.

[0156] Specifically, the random network topology generation model is the Waxman-Salama model (a model for generating random network topology). The terminal generates a sample network topology model based on the Waxman-Salama model, and generates a network topology graph G(V,E) of the sample network topology model on the Python (a code language) platform. The sample network topology model is a network topology model of a sample data center. V represents each sample data node of the sample data center, and E represents the connection relationship between the sample data nodes. The terminal initializes the sample node status data of each data node and the sample link status data of each sample network link, and constructs a sample network topology data set of the sample network topology model based on each sample node status data and each sample link status data.

[0157] In an exemplary embodiment, Fig.10 FIG. 1 is a network topology diagram of a sample network topology model in an embodiment. Fig.10 As shown in Figure 1, the sample data center contains 30 sample data nodes. The terminal randomly selects As a sample data center node, As sample backup nodes, the remaining nodes are sample intermediate nodes. Indicates the sample data center node with backup requirements. The amount of backup data corresponding to the sample data center node is . To represent the sample backup node. The terminal initializes the source data volume of each sample data node , Storage Capacity The transmission bandwidth between the sample data nodes Terminal confirmation For the sample data center node To the sample backup node No. transmission paths, and the set P is the set of all backup transmission links. The terminal is each sample network link The allocated bandwidth is used Indicates. Then , indicating all transmission paths In the link The total bandwidth used on the Used to indicate backup link Whether the backup link is used. The remaining bandwidth is .

[0158] Step 904: Train a preset reinforcement learning model based on the sample network topology data set to obtain a data center network model.

[0159] In implementation, a reinforcement learning model is pre-set in the terminal. The terminal randomly determines each data center node as each sample current node in the sample network topology model, and constructs a sample state space and a sample action space of each sample current node based on the sample network topology data set. The terminal trains the reinforcement learning model based on the sample state space and sample action space of each sample current node until the reinforcement learning model meets the preset training completion conditions. The terminal determines the reinforcement learning model as a data center network model. Among them, the specific processing process of constructing the sample state space and the sample action space is the same as the processing process of constructing the state space and the sample space, please refer to the above-mentioned step 204 or step 302 to step 306.

[0160] Specifically, the terminal inputs the sample state space and sample action space of each sample current node into the reinforcement learning model to obtain the first initial output result, and optimizes the initial output result through the PSO algorithm to obtain the first output result. Then, the terminal determines the sample target candidate node of the sample current node based on the output result, and updates the sample target candidate node to the sample current node. The terminal constructs the sample state space and sample action space of the sample current node based on the sample network topology data set, and inputs the sample state space and sample action space into the reinforcement learning model to obtain the second initial output result. Then, the terminal optimizes the first initial output result through the PSO algorithm to obtain the second output result. The terminal calculates the first output result and the second output result through the loss function algorithm to obtain the loss value. Among them, the loss function algorithm is shown in the following formula group (7):

[0161] (7)

[0162] Among them, in the above formula group (7), is the first output result, is the second output result. is the loss value.

[0163] The terminal determines whether the loss value reaches a preset loss threshold. If the loss value reaches the loss threshold, the terminal determines that the reinforcement learning model meets the preset training completion condition, and determines that the reinforcement learning model is a data center network model. If the loss value does not reach the loss threshold, the terminal determines the second initial output result as the first initial output result, and determines the first output result as the second output result. Then, the terminal determines that the reinforcement learning model does not meet the training completion condition, and continues to execute the steps of constructing the sample state space and sample action space of each sample current node based on the sample network topology data set until the loss value reaches the preset loss threshold.

[0164] In this embodiment, a preset reinforcement learning model is trained by a sample network topology data set to obtain a data center network model, thereby improving the accuracy of the data center network model. Furthermore, target candidate nodes are determined based on the data center network model, thereby improving the accuracy of the target candidate nodes.

[0165] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0166] Based on the same inventive concept, the embodiment of the present application also provides a disaster recovery backup device for implementing the disaster recovery backup method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more disaster recovery backup device embodiments provided below can refer to the limitations on the disaster recovery backup method above, and will not be repeated here.

[0167] In an exemplary embodiment, Fig.11 As shown, a disaster recovery backup device 1100 is provided, including: an acquisition module 1101, a determination module 1102 and a transmission module 1103, wherein:

[0168] The acquisition module 1101 is used to acquire a network topology data set of the data center where the current node is located; the network topology data set includes node status data of each data node and link status data of each network link.

[0169] Determination module 1102 is used to construct the state space and action space of the current node based on the state data of each node and the state data of each link, and determine the target candidate node in the data center based on the data center network model, state space and action space; the target candidate node is the path node to the target backup node.

[0170] The transmission module 1103 is used to transmit the data to be backed up from the current node to the target candidate node until it is transmitted to the target backup node.

[0171] In an exemplary embodiment, the determination module 1102 includes a first construction submodule and a first determination submodule. The first construction submodule includes:

[0172] The second determination submodule is used to determine a total status data set of the data center based on the status data of each node and the status data of each link.

[0173] The second construction submodule is used to construct the state space of the current node based on the total state data set, each network link and a preset average data ratio.

[0174] The first screening submodule is used to screen the action space of the current node in the data center according to the state space, a preset data volume difference parameter and a normal service ratio of the network link.

[0175] In an exemplary embodiment, each data node includes each data center node and each backup node; the link status data includes the usage status and transmission bandwidth of the network link, and the node status data includes the source data volume and storage capacity of the data node. The second determination submodule includes:

[0176] The third determination submodule is used to determine the remaining storage capacity of the data center according to the storage capacity of each backup node and the amount of source data.

[0177] The fourth determination submodule is used to determine the amount of backup remaining data of the data center according to the amount of source data of each data center node and the amount of source data of each backup node.

[0178] The fifth determining submodule is used to determine the total remaining bandwidth of the data center based on the transmission bandwidth of each network link whose usage status is an idle state.

[0179] The third construction submodule is used to construct a total status data set of the data center based on the total remaining bandwidth, the backup remaining data volume and the remaining storage capacity of the data center.

[0180] In an exemplary embodiment, the first screening submodule includes:

[0181] The fourth construction submodule is used to construct a constraint condition set according to the state space, a preset data volume difference parameter and a normal service ratio of the network link.

[0182] The second screening submodule is used to screen the next hop node of the current node in each data node of the data center based on the constraint condition set to obtain a candidate node set, and determine the candidate node set as the action space of the current node.

[0183] In an exemplary embodiment, the first determining submodule includes:

[0184] The first processing submodule is used to perform prediction processing on the state space and action space based on the data center network model to obtain an initial reward value.

[0185] The second processing submodule is used to optimize the initial reward value according to the heuristic optimization algorithm to obtain the reward value.

[0186] The sixth determination submodule is used to determine the target candidate node in the action space according to the reward value and the probability algorithm.

[0187] In an exemplary embodiment, the sixth determining submodule includes:

[0188] The seventh determination submodule is used to determine, for each candidate node, a candidate link between the candidate node and the current node.

[0189] The first operation submodule is used to perform probability operation on the reward value, the node status data of the candidate node and the link status data of the candidate link according to the probability algorithm to obtain the probability of the candidate node.

[0190] The eighth determination submodule is used to determine the candidate node with the highest probability among the candidate nodes as the target candidate node.

[0191] Each module in the above-mentioned disaster recovery backup device can be implemented in whole or in part by software, hardware and their combination. Each module can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0192] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig.12As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a disaster recovery backup method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0193] Those skilled in the art will understand that Fig.12 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0194] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0195] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0196] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0197] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0198] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0199] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A disaster recovery backup method, characterized in that: The method comprises: Obtaining a network topology data set of a data center where the current node is located; the network topology data set includes node status data of each data node and link status data of each network link; Constructing the state space and action space of the current node based on each of the node state data and each of the link state data, and determining a target candidate node in the data center based on the data center network model, the state space and the action space; the target candidate node is a node on the way to the target backup node; The data to be backed up is transmitted from the current node to the target candidate node until it is transmitted to the target backup node.

2. The method according to claim 1, characterized in that The constructing the state space and action space of the current node based on each of the node state data and each of the link state data comprises: Determine a total status data set of the data center based on each of the node status data and each of the link status data; Constructing the state space of the current node based on the total state data set, each of the network links and a preset average data ratio; The action space of the current node is screened in the data center according to the state space, a preset data volume difference parameter, and a normal service ratio of a network link.

3. The method according to claim 2, characterized in that Each of the data nodes includes each data center node and each backup node; the link status data includes the usage status and transmission bandwidth of the network link, and the node status data includes the source data volume and storage capacity of the data node. The total status data set of the data center is determined based on each of the node status data and each of the link status data, including: Determining the remaining storage capacity of the data center according to the storage capacity of each backup node and the amount of source data; Determining the amount of backup remaining data of the data center according to the amount of source data of each data center node and the amount of source data of each backup node; Determine the total remaining bandwidth of the data center based on the transmission bandwidth of each network link whose usage status is idle; A total status data set of the data center is constructed based on the total remaining bandwidth, the amount of backup remaining data, and the remaining storage capacity of the data center.

4. The method according to claim 2, characterized in that: The step of screening the action space of the current node in the data center according to the state space, a preset data volume difference parameter, and a normal service ratio of a network link includes: Constructing a set of constraint conditions according to the state space, a preset data volume difference parameter and a normal service ratio of a network link; Based on the constraint condition set, the next hop node of the current node is screened from each data node in the data center to obtain a candidate node set, and the candidate node set is determined as the action space of the current node.

5. The method according to claim 1, characterized in that The determining of a target candidate node in the data center based on the data center network model, the state space, and the action space includes: Performing prediction processing on the state space and the action space based on the data center network model to obtain an initial reward value; Optimizing the initial reward value according to a heuristic optimization algorithm to obtain a reward value; A target candidate node is determined in the action space according to the reward value and a probability algorithm.

6. The method according to claim 5, characterized in that The action space includes candidate nodes, and determining a target candidate node in the action space according to the reward value and the probability algorithm includes: For each of the candidate nodes, determining a candidate link between the candidate node and the current node; Performing probability calculation on the reward value, the node status data of the candidate node, and the link status data of the candidate link according to a probability algorithm to obtain the probability of the candidate node; The candidate node with the highest probability among the candidate nodes is determined as the target candidate node.

7. A disaster recovery backup device, characterized in that: The device comprises: An acquisition module is used to acquire a network topology data set of a data center where the current node is located; the network topology data set includes node status data of each data node and link status data of each network link; A determination module, configured to construct a state space and an action space of the current node based on each of the node state data and each of the link state data, and determine a target candidate node in the data center based on a data center network model, the state space and the action space; the target candidate node is a path node to a target backup node; The transmission module is used to transmit the data to be backed up from the current node to the target candidate node until it is transmitted to the target backup node.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images