Method and device for adjusting network topology structure

Abstract

The embodiment of the invention provides a network topology structure adjusting method and device, and the method comprises the steps: firstly obtaining the flow data of a preset key node in a network topology structure, inputting the obtained flow data into a flow prediction model, carrying out the flow feature prediction, outputting a flow parameter and a flow trend sequence, secondly, performing network topology analysis based on the network topology data, the traffic parameters and the traffic trend sequence to obtain key nodes and key paths of a network topology structure, and then generating a node deployment strategy of aggregation nodes in the key nodes according to the key nodes and the key paths; and finally, deployment adjustment is performed on the sink nodes in the network topology structure based on the node deployment strategy, so that flexible adjustment and management of the network topology structure can be realized.

Description

Technical Field

[0001] This document relates to the field of Internet technology, and in particular to a method and device for adjusting network topology. Background Art

[0002] With the continuous development of information technology, the network has become an indispensable infrastructure in modern society. Efficient network management can improve the speed and quality of traffic data transmission, thereby improving the overall service level and user experience. As the core of network management, the adjustment of network topology structure greatly affects the operation efficiency of the network.

[0003] At present, many network management systems manage traffic data and network topology through pre-set configurations to ensure the stable operation of the network. However, with the rapid growth of business and increasingly complex needs, when processing large-scale data or high-concurrency requests, traffic data management based on pre-set configurations may not be able to effectively reduce network latency, and cannot adjust the network topology in time to ensure network operation efficiency. Therefore, how to adjust the network topology to improve traffic data management and transmission efficiency has become a problem that needs to be urgently solved in the current field of Internet technology. Summary of the invention

[0004] An embodiment of the present specification aims to provide a method and device for adjusting a network topology structure, so as to achieve flexible adjustment and management of a network topology structure.

[0005] To solve the above technical problems, an embodiment of this specification is implemented as follows: In a first aspect, an embodiment of the present specification provides a method for adjusting a network topology structure, including: Obtaining traffic data of preset key nodes in the network topology structure, inputting the traffic data into a traffic prediction model to predict traffic characteristics, and outputting traffic parameters and traffic trend sequences; Perform network topology analysis based on network topology data, the traffic parameters and the traffic trend sequence to obtain key nodes and key paths of the network topology structure; Generate a node deployment strategy of a convergence node in the key nodes according to the key nodes and the key paths; The aggregation node is deployed and adjusted in the network topology based on the node deployment strategy.

[0006] In a second aspect, an embodiment of the present specification provides a network topology adjustment device, including: A prediction module is configured to obtain flow data of preset key nodes in the network topology structure, input the flow data into a flow prediction model to predict flow characteristics, and output flow parameters and flow trend sequences; A network topology analysis module is configured to perform network topology analysis based on network topology data, the traffic parameters and the traffic trend sequence to obtain key nodes and key paths of the network topology structure; A strategy generation module is configured to generate a node deployment strategy of a convergence node in the key nodes according to the key nodes and the key paths; The deployment adjustment module is configured to adjust the deployment of the aggregation node in the network topology structure based on the node deployment strategy.

[0007] In a third aspect, another embodiment of the present specification provides a network topology structure adjustment device, comprising: a memory, a processor, and computer executable instructions stored on the memory and executable on the processor, wherein the computer executable instructions, when executed by the processor, implement the steps of the network topology structure adjustment method as described in the first aspect above.

[0008] In a fourth aspect, another embodiment of the present specification provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store computer-executable instructions, and when the computer-executable instructions are executed by a processor, the steps of the network topology adjustment method as described in the first aspect above are implemented.

[0009] In a fifth aspect, another embodiment of the present specification provides a computer program product, wherein the computer program product includes a network topology adjustment program, and the network topology adjustment program is executed by a processor to implement the steps of the network topology adjustment method as described in the first aspect above.

[0010] The present embodiment provides a method for adjusting a network topology structure. First, traffic data of preset key nodes in a network topology structure is obtained, the traffic data is input into a traffic prediction model to predict traffic characteristics, and traffic parameters and traffic trend sequences are output. The traffic data of preset nodes is obtained to provide a data basis for subsequent analysis, while improving the accuracy and timeliness of the data. Secondly, network topology analysis is performed based on the network topology data, traffic parameters and traffic trend sequences to obtain key nodes and key paths of the network topology structure so as to reasonably distribute the traffic data. Then, according to the key nodes and key paths, node deployment strategies of aggregation nodes in key nodes are generated to determine the deployment location and number of aggregation nodes. Finally, based on the node deployment strategies, the aggregation nodes are deployed and adjusted in the network topology structure. The network topology structure is adjusted by adjusting the deployment of the aggregation nodes, thereby achieving flexible adjustment and management of the network topology structure. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in one or more embodiments of the present specification, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0012] Figure 1 A processing flow chart of a network topology adjustment method provided in one or more embodiments of this specification; Figure 2 A processing flow chart of a network topology adjustment method applied to a network topology adjustment scenario provided by one or more embodiments of this specification; Figure 3 A schematic diagram of a network topology adjustment device provided for one or more embodiments of this specification; Figure 4 A schematic diagram of the structure of a network topology adjustment device provided in one or more embodiments of this specification. DETAILED DESCRIPTION

[0013] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will be combined with the drawings in one or more embodiments of this specification to clearly and completely describe the technical solutions in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.

[0014] This specification provides an embodiment of a network topology adjustment method: Reference Figure 1 , which shows a processing flow chart of a network topology structure adjustment method provided in this embodiment. The network topology structure adjustment method provided in this embodiment specifically includes the following steps S102 to S108.

[0015] Step S102, obtaining the flow data of the preset key nodes in the network topology structure, inputting the flow data into the flow prediction model to predict the flow characteristics, and outputting the flow parameters and flow trend sequence.

[0016] The network topology structure in this embodiment refers to the layout of each node in the network and its connection method. Based on the network topology structure, the physical or logical connection method of each node in the network can be described, and the transmission path of traffic data in the network can also be determined based on the network topology structure.

[0017] The traffic prediction model refers to a model that predicts the traffic characteristics of traffic data based on the traffic data in the network topology structure. The input of the traffic prediction model can be traffic data, which may include timestamp, delay, number of data packets, data packet loss rate and / or bandwidth utilization; the output of the traffic prediction model can be traffic parameters and / or traffic trend sequences, wherein the traffic parameters can be traffic peaks, traffic troughs and / or traffic abnormalities. The traffic trend sequence is a series of traffic prediction values ​​that change over time to reflect the changing trend of traffic data in the network topology structure over a period of time in the future. The changing trend of traffic data can be that the traffic data increases, decreases or remains relatively stable over time.

[0018] In the specific implementation, the traffic data of the network topology structure is obtained by monitoring the traffic data of the preset key nodes pre-set in the network topology structure, and the obtained traffic data is input into the trained traffic prediction model to predict the traffic characteristics of the traffic data, thereby obtaining the traffic parameters and traffic trend sequence of the traffic data of the network topology structure.

[0019] During the specific implementation process, in the process of obtaining the flow data of the preset key nodes in the network topology structure, the flow data to be obtained can be determined in advance, such as delay, packet loss rate and / or bandwidth utilization, and then the flow data monitoring software can be configured at the preset key nodes or the Internet of Things (IoT) sensors can be used to obtain the flow data; among them, delay is a measure of network response time, packet loss rate is the proportion of data packets that have not received a response, and bandwidth utilization can be calculated by monitoring the ratio of the total amount of traffic passing through the interface within a certain period of time to the total available bandwidth of the interface.

[0020] In practical applications, in order to manage traffic data more effectively and schedule it more accurately, traffic data can be predicted based on a traffic prediction model, and based on the predicted traffic parameters and / or traffic trend sequence, the nodes and traffic data transmission paths in the network topology can be reasonably planned by identifying traffic peaks, traffic troughs and / or traffic trends in advance.

[0021] Specifically, in order to improve the accuracy and processing efficiency of the traffic prediction model, the traffic prediction model may be trained based on traffic data samples. In an optional implementation provided in this embodiment, the traffic prediction model may be trained in the following manner: Inputting the flow data samples into the model to be trained to predict flow characteristics, and outputting the predicted flow characteristics of at least one data sample in the flow data samples; Evaluate the error between the output predicted traffic features and the actual traffic features to determine the training loss; The model to be trained is adjusted according to the training loss to obtain a traffic prediction model after the training is completed.

[0022] Among them, the traffic data sample can be the traffic data obtained at the preset key nodes mentioned above, and the actual traffic characteristics can be the traffic characteristics of the traffic data obtained by cleaning and aggregating the traffic data obtained at the preset key nodes and analyzing them.

[0023] For example, taking the training of LSTM (Long Short-Term Memory) model as a traffic prediction model as an example, firstly, the traffic data obtained at the preset key nodes stored in the time series database is used as the traffic data sample, and the LSTM model is constructed by defining the LSTM network structure, selecting the number of layers and the number of neurons in each layer. Secondly, the training process of the LSTM model can be configured by selecting the loss function, optimizer, number of training rounds, etc., and the traffic data sample is input into the LSTM model to be trained for traffic feature prediction. The error between the output predicted traffic feature and the actual traffic feature is evaluated and the training loss is determined. The model parameters are updated and iteratively optimized based on the training loss, so that the model to be trained gradually learns the correct mode of predicting traffic features. The process is repeated until the loss function converges. After the loss function converges, the training is completed, and the trained model is used as the traffic feature prediction model.

[0024] For another example, in the process of determining the training loss by evaluating the error between the output predicted traffic features and the actual traffic features, the mean square error (MSE) or the root mean square error (RMSE) can be used to determine the training loss; when the mean square error (MSE) is used to determine the training loss, the calculation formula of the mean square error (MSE) can be as follows: MSE= i - i , in, i is the actual traffic characteristic, i is the traffic feature predicted by the model, and n is the number of traffic data samples.

[0025] Step S104, performing network topology analysis based on the network topology data, the traffic parameters and the traffic trend sequence to obtain key nodes and key paths of the network topology structure.

[0026] After the traffic data of the preset key nodes in the network topology structure is obtained above, and the traffic data is input into the traffic prediction model to predict the traffic characteristics, and the traffic parameters and traffic trend sequence are output, in this step, the network topology analysis is performed based on the network topology data, traffic parameters and traffic trend sequence to obtain the key nodes and key paths in the network topology structure; the network topology analysis refers to the process of identifying the key nodes and key paths in the network topology structure by analyzing the data of each node in the network topology structure and the interconnection relationship between each node, the traffic data at each node, etc., so as to optimize the network and allocate resources based on the data information obtained by the analysis; wherein, the key node may be a node that carries higher traffic in the network topology structure or is in a key position in the network topology structure.

[0027] The network topology data refers to data that describes each node in the network topology structure and the interconnection relationship between each node. The network topology data can be the node location data, type data and / or link information data between nodes. In addition, it can also be other data used for node management in the network topology structure.

[0028] In the specific implementation, we first obtain network topology data based on the network topology structure, and perform network topology analysis based on the obtained network topology data and the predicted traffic parameters and traffic trend sequence output by the traffic prediction model to determine the key nodes in the network topology structure and the key paths connecting the key nodes, thereby providing a data basis for the subsequent determination of the deployment strategy of the aggregation node.

[0029] In the specific execution process, after obtaining the predicted traffic characteristics, the network topology structure can be subjected to network topology analysis based on the network topology data and the predicted traffic characteristics to obtain key nodes and key paths of the network topology structure; in an optional implementation manner provided in this embodiment, the network topology analysis is performed based on the network topology data, traffic parameters and traffic trend sequence to obtain key nodes and key paths of the network topology structure, including: Acquire network topology data, and build a network topology graph model based on the network topology data; Based on the evaluation algorithm, the frequency of each node in the network topology model being located on the shortest path is evaluated to obtain high-frequency nodes; Based on the traffic parameters and the traffic trend sequence, key nodes are determined among the high-frequency nodes, and paths between the key nodes are determined as key paths.

[0030] Specifically, the network topology data is first obtained, and a graph model of the network topology structure with network devices as nodes and connection paths as edges is constructed based on the obtained network topology data. Secondly, an evaluation algorithm is used to calculate and count the frequency of each node being on the shortest path in the network topology structure, and nodes with high frequency are determined as high-frequency nodes. Finally, the traffic parameters and traffic trend sequences obtained by predicting the traffic prediction model are combined to identify the nodes among the high-frequency nodes that have a greater impact on the traffic carrying capacity as key nodes, and based on the key nodes, the paths between the key nodes are determined as key paths.

[0031] For example, in the process of evaluating high-frequency nodes, whether a node can be determined as a high-frequency node can be evaluated based on betweenness centrality. Nodes with high betweenness centrality are located on the shortest path more frequently, and nodes with low betweenness centrality are located on the shortest path less frequently.

[0032] Step S106: generating a node deployment strategy of a convergence node in the key nodes according to the key nodes and the key paths.

[0033] In specific implementation, after performing network topology analysis based on network topology data, traffic parameters and traffic trend sequences to obtain key nodes and key paths, the optimal deployment position and optimal deployment number of aggregation nodes in the network topology structure can be calculated based on the obtained key nodes and key paths through the minimum spanning tree algorithm and / or clustering algorithm in graph theory to generate a node deployment strategy for the aggregation nodes.

[0034] Among them, the aggregation node refers to the key node in the network topology structure used to centrally process and forward traffic data. The aggregation node can obtain traffic data from multiple source nodes and forward the obtained traffic data to the next level or destination node.

[0035] In the specific execution process, in order to optimize the network topology structure and thus improve the transmission efficiency of traffic data, the node deployment strategy of the aggregation node can be determined based on the key nodes and key paths in the network topology structure, and the aggregation node can be deployed and adjusted based on the node deployment strategy, thereby achieving optimization adjustment of the network topology structure; in an optional implementation manner provided in this embodiment, according to the key nodes and key paths, the node deployment strategy of the aggregation node in the key nodes is generated, including: Construct the feature space of key nodes based on the location data and flow data of key nodes; Calculate the similarity of key nodes in the feature space according to the clustering algorithm and cluster the key nodes based on the similarity to obtain the cluster center; Generate node deployment strategies at cluster centers based on network configuration data.

[0036] For example, using the Minimum Spanning Tree (MST) and the DBSCAN (Density-Based Spatial Clustering of Applications with Taking the calculation of the deployment location and number of sink nodes using the DBSCAN algorithm as an example, the location data and traffic data of the key nodes are first obtained, and a feature space with the key nodes as vertices, including the spatial coordinates and traffic size of the key nodes, is constructed. Then, the neighborhood size and the minimum number of points are selected, and the key nodes are clustered based on the DBSCAN algorithm according to the spatial proximity and traffic similarity of the key nodes to obtain the cluster centers. Each cluster center can be used as a potential deployment area for a sink node. Then, based on the minimum spanning tree, the network topology graph model is represented as a graph G=(V, E), where V is a set of nodes, E is a set of edges, and the weight of each edge can be the inverse of the connection cost, delay or bandwidth. The minimum spanning tree T is found on the graph G, and in the minimum spanning tree T, nodes with high degrees or nodes on the critical path are selected as candidate locations for the sink nodes. Finally, a specific node deployment strategy for the sink node is generated by comprehensively considering the network status, service quality requirements, cost-effectiveness and / or other network configuration data.

[0037] Step S108: adjusting the deployment of the aggregation node in the network topology structure based on the node deployment strategy.

[0038] In specific implementation, the optimal deployment position and optimal deployment number of the aggregation nodes in the network topology structure can be determined based on the generated node deployment strategy, and the deployment of the aggregation nodes in the network topology structure can be adjusted based on the determined deployment position and deployment number of the aggregation nodes, thereby achieving adjustment of the network topology structure.

[0039] During the specific implementation process, in the process of deploying and adjusting the aggregation nodes in the network topology structure based on the node deployment strategy, the aggregation nodes can be added, removed and / or migrated through the SDN (Software-Defined Networking) controller.

[0040] The following provides three methods for adjusting the deployment of aggregation nodes: adding aggregation nodes, removing aggregation nodes, and migrating aggregation nodes, and describes these three methods in detail.

[0041] (1) Adding a sink node Specifically, when the traffic data in the network topology increases significantly and the existing aggregation nodes may not be able to meet the demand, in order to support the new traffic data demand and improve the transmission efficiency of the traffic data, an aggregation node may be added to the network topology. In the first optional implementation mode provided in this embodiment, the aggregation node is deployed and adjusted in the network topology based on the node deployment strategy, including: Determine the deployment location of the new aggregation node through the SDN controller based on the node deployment strategy; Sending a configuration command for a newly added aggregation node to the corresponding network device through the SDN controller to enable the newly added aggregation node at the deployment location; Add new aggregation nodes to the network topology and manage traffic data for the new aggregation nodes.

[0042] In the process of adding new aggregation nodes based on the node deployment strategy, the SDN controller can determine the deployment location of the new aggregation node in the network topology according to the node deployment strategy, and then send configuration commands to the corresponding network devices to enable the new aggregation node at the deployment location, and add the new aggregation node to the network topology, apply traffic management and security policies to the new aggregation node, and ensure that the new aggregation node can operate as expected.

[0043] (2) Remove the sink node Specifically, when a certain aggregation node in the network topology fails, in order to reduce the impact of the aggregation node on the network topology, the aggregation node in the network topology can be removed. In a second optional implementation manner provided in this embodiment, the aggregation node is deployed and adjusted in the network topology based on the node deployment strategy, including: Determine the deployment location of the aggregation node to be removed through the SDN controller based on the node deployment strategy; Modify the flow table in the network topology through the SDN controller to redirect the traffic data of the aggregation node to be removed to other aggregation nodes; Remove the sink node to be removed from the network topology.

[0044] In the process of removing an existing aggregation node (aggregation node to be removed) in the network topology based on the node deployment strategy, the SDN controller can first modify the flow table to redirect the traffic data originally processed by the aggregation node to be removed to other more active aggregation nodes. After confirming that the traffic data has successfully bypassed the aggregation node to be removed, the SDN controller can issue a removal command to remove the aggregation node to be removed from the network topology.

[0045] (3) Migrate the aggregation node Specifically, when the traffic data in the network topology changes, in order to optimize the network topology, the aggregation node in the network topology may be migrated to a more suitable location to achieve better traffic data transmission; in a third optional implementation manner provided in this embodiment, the aggregation node is deployed and adjusted in the network topology based on the node deployment strategy, including: Based on the node deployment strategy, the SDN controller determines the deployment location of the newly added aggregation node and the deployment location of the aggregation node to be migrated; Sending a configuration command for a newly added aggregation node to the corresponding network device through the SDN controller to enable the newly added aggregation node at the deployment location; Modify the flow table in the network topology through the SDN controller to redirect the traffic data of the aggregation node to be migrated to the newly added aggregation node; Remove the aggregation node to be migrated from the network topology.

[0046] In the process of migrating the aggregation nodes in the network topology structure based on the node deployment strategy, it is necessary to involve the addition of new aggregation nodes and the removal of old aggregation nodes. That is, the SDN controller can first configure and activate the newly added aggregation nodes according to the above steps of adding aggregation nodes, and gradually migrate the traffic data from the aggregation nodes to be migrated to the new aggregation nodes by gradually modifying the flow table. After completing the traffic data migration, the SDN controller can remove the aggregation nodes to be migrated according to the above steps of removing aggregation nodes, thereby realizing the migration of the aggregation nodes in the network topology structure.

[0047] In practical applications, after the aggregation nodes are deployed and adjusted based on the node deployment strategy of the aggregation nodes to achieve the adjustment of the network topology structure, in order to enhance the data security and protection capabilities of the network topology structure while maintaining the stability of the network topology structure, the traffic data of the aggregation nodes in the network topology structure can also be encrypted based on the adjusted network topology structure, and an access control mechanism can be configured at the aggregation node to implement access authentication.

[0048] During the specific execution process, after the network topology structure is adjusted, in order to improve the security of traffic data during transmission, the traffic data of the aggregation node may be encrypted and access authentication for access requests to the encrypted data may be performed; in an optional implementation manner provided by this embodiment, after the aggregation node is deployed and adjusted in the network topology structure based on the node deployment strategy, it also includes: Encrypting the traffic data of the aggregation node based on the encryption algorithm to obtain encrypted data; Access authentication is performed based on an access request to encrypted data submitted by an access terminal.

[0049] (1) Encrypt the traffic data of the aggregation node based on the encryption algorithm to obtain encrypted data Specifically, in order to prevent the flow data from being read and / or modified by unauthorized parties during transmission and to improve the security of the flow data during transmission, the flow data of the aggregation node may be encrypted; in an optional implementation manner provided by this embodiment, the flow data of the aggregation node is encrypted based on an encryption algorithm to obtain encrypted data, including: Generate a key that meets the preset encryption length according to the preset encryption length and a random number generator; The key is transmitted to the sink node and the destination node, and the traffic data of the sink node is encrypted by an encryption algorithm based on the key to obtain encrypted data; Transmit the encrypted data to the destination node.

[0050] During the process of traffic data transmission, in order to improve the security of traffic data transmission, the encryption length of the key can be preset according to actual needs, the key can be generated by a random number generator based on the preset encryption length, and the key can be managed so that the key can be securely transmitted to the aggregation node and the destination node. At the same time, an encryption module can be configured at the aggregation node to encrypt the traffic data to obtain encrypted data, and the encrypted data obtained can be transmitted to the destination node.

[0051] For example, AES (Advanced Encryption Standard) can be used for encryption, and on this basis, AES-128, AES-192, and AES-256 can be selected as the encryption length.

[0052] (2) Access authentication based on the access request to encrypted data submitted by the access terminal Specifically, after the traffic data is encrypted, in order to ensure that only authorized parties can access the encrypted data and reduce the risk of traffic data leakage, access authentication may be performed on the access request to the encrypted data after the traffic data is encrypted; in an optional implementation manner provided by this embodiment, access authentication is performed based on the access request to the encrypted data submitted by the access terminal, including: If an access request submitted by an access terminal is obtained, an authentication prompt is sent to the access terminal; Acquire an authentication factor submitted by the access terminal based on the authentication prompt, and compare the authentication factor with the authentication data to obtain a comparison result; If the comparison result is consistent, the encrypted data is decrypted based on the key and the decrypted traffic data is sent down.

[0053] After the traffic data is encrypted, if the access terminal attempts to access the encrypted data, the access request submitted by the access terminal can be obtained first, and an authentication prompt can be sent to the access terminal based on the access request to require the access terminal to submit an authentication factor based on the authentication prompt, thereby verifying the access rights of the access terminal; after obtaining the authentication factor submitted by the access terminal, the authentication factor can be compared with the pre-stored authentication data, and the authentication data can include the authentication information of all authorized parties. If the comparison result of the authentication factor and the authentication data is consistent, it means that the authentication factor submitted by the access terminal matches the authentication data, that is, the access terminal can be considered to be a verified authorized party; after successful authentication, the decryption module configured in the destination node can decrypt the encrypted data based on the key to restore the encrypted data to the original, readable traffic data, and send the decrypted traffic data to the access terminal.

[0054] For example, the authentication factor may be a knowledge factor, such as a user name and password, an answer to a verification question and / or other information that the accessing party must know; the authentication factor may also be a possession factor, such as a dynamic token, a biometric feature and / or a verification code received by a mobile phone; the authentication factor may also be a biometric factor, such as a fingerprint and / or facial recognition; the authentication factor required to be submitted by the access terminal may be determined based on the importance of the traffic data to be accessed, for example, when the access terminal requests access to traffic data, single-factor authentication may be implemented on the access terminal, that is, the access terminal may be required to submit any one of the knowledge factor, possession factor or biometric factor based on the authentication prompt; for another example, when the access terminal requests access to high-value traffic data or key traffic data, multi-factor authentication may be implemented on the access terminal, that is, the access terminal may be required to submit any two or more of the knowledge factor, possession factor and / or biometric factor based on the authentication prompt.

[0055] In addition, if the comparison result between the authentication factor and the authentication data is inconsistent, it means that the authentication factor submitted by the access terminal does not match the authentication data. In this case, it may be that the access terminal input is incorrect, the access terminal is unauthorized, the authentication information has expired and / or the authentication information has changed. If the authentication factor submitted by the access terminal does not match the authentication data, the access request may be rejected.

[0056] In addition, after the network topology structure is adjusted, in order to improve the security of traffic data during transmission and reduce the delay of traffic data during transmission, the traffic data of the aggregation node can be encrypted based on the encryption algorithm to obtain encrypted data, and the encrypted data can be decrypted after the encrypted data is transmitted to the destination node; in another optional implementation manner provided by this embodiment, after the aggregation node is deployed and adjusted in the network topology structure based on the node deployment strategy, it also includes: Generate a key that meets the preset encryption length according to the preset encryption length and a random number generator; The key is transmitted to the sink node and the destination node, and the traffic data of the sink node is encrypted by an encryption algorithm based on the key to obtain encrypted data; The encrypted data is transmitted to the destination node and decrypted based on the key.

[0057] Specifically, the encryption length of the key can be preset according to actual needs, the key can be generated by a random number generator based on the preset encryption length, and the key can be managed so that the key can be securely transmitted to the aggregation node and the destination node. At the same time, the encryption module and the decryption module can be configured at the aggregation node and the destination node respectively, the traffic data is encrypted at the aggregation node to obtain encrypted data, the obtained encrypted data is transmitted to the destination node, and the encrypted data is decrypted at the destination node based on the key to restore the encrypted data to the original, readable traffic data.

[0058] In actual applications, in order to further prevent unauthorized parties from accessing traffic data and ensure that only verified and authorized access terminals can access traffic data, access control and authentication mechanisms can also be implemented before access authentication is performed based on access requests submitted by access terminals.

[0059] For example, first implement Network Access Control (NAC), configure 802.1X authentication at the aggregation node, make authentication requests to all access terminals that attempt to access traffic data, and store user credentials and access policies. Then configure Access Control List (ACL), define ACL on the aggregation node, set ACL rules based on source address, destination address, service type and other conditions to allow or deny specific access terminals, and ensure that only authorized access terminals can access traffic data.

[0060] It should be noted that after the network topology is adjusted based on the node deployment strategy of the aggregation node, the adjusted network topology can also be monitored and managed; specifically, the operating status of the network topology can be monitored by deploying an alarm system and an integrated management interface, and data indicators in the network topology can be fed back in real time. Traffic data analysis can be performed based on the data indicators obtained from the monitoring, so as to troubleshoot and optimize the performance of the network topology. Finally, the effectiveness of the node deployment strategy can be regularly evaluated from the perspective of network topology operating efficiency, cost-benefit analysis and / or service quality, and the node deployment strategy can be iteratively optimized based on the evaluation results to continuously deploy and adjust the aggregation nodes, thereby achieving continuous optimization of the network topology.

[0061] In summary, the present embodiment provides a method for adjusting a network topology structure. First, the traffic data of preset key nodes in the network topology structure is obtained, the traffic data is input into a traffic prediction model to predict traffic characteristics, and traffic parameters and traffic trend sequences are output. The traffic data of preset nodes is obtained to provide a data basis for subsequent analysis, while improving the accuracy and timeliness of the data. Secondly, a network topology analysis is performed based on the network topology data, traffic parameters and traffic trend sequences to obtain key nodes and key paths of the network topology structure to reasonably distribute the traffic data. Then, according to the key nodes and key paths, a node deployment strategy for the aggregation nodes in the key nodes is generated to determine the deployment location and number of the aggregation nodes. Finally, based on the node deployment strategy, the aggregation nodes are deployed and adjusted in the network topology structure to add, remove and migrate the aggregation nodes, etc. Flexible adjustment and management of the network topology structure are achieved through deployment adjustment of the aggregation nodes.

[0062] The following combination Figure 2 , taking the application of the network topology structure adjustment method provided in this embodiment in the network topology structure adjustment scenario as an example, the network topology structure adjustment method provided in this embodiment is further described. Figure 2 The network topology structure adjustment method applied to the network topology structure adjustment scenario specifically includes steps S202 to S224.

[0063] Step S202, obtaining flow data of preset key nodes in the network topology.

[0064] Step S204, input the flow data into the flow prediction model to predict flow characteristics, and output flow parameters and flow trend sequences.

[0065] Step S206, acquiring network topology data and constructing a network topology graph model based on the network topology data.

[0066] Step S208, evaluating the frequency of each node in the network topology model being located on the shortest path based on an evaluation algorithm to obtain high-frequency nodes.

[0067] Step S210, determining key nodes among high-frequency nodes based on traffic parameters and traffic trend sequences, and determining paths between key nodes as key paths.

[0068] Step S212: constructing a feature space of the key nodes based on the location data and flow data of the key nodes.

[0069] Step S214, calculating the similarity of the key nodes in the feature space according to the clustering algorithm and clustering the key nodes based on the similarity to obtain the cluster center.

[0070] Step S216: Generate a node deployment strategy at the cluster center based on the network configuration data.

[0071] Step S218: adjusting the deployment of the aggregation node in the network topology structure based on the node deployment strategy to adjust the network topology structure.

[0072] Step S220, generating a key that meets the preset encryption length according to the preset encryption length and a random number generator, and transmitting the key to the aggregation node and the destination node.

[0073] Step S222: encrypt the traffic data of the aggregation node based on an encryption algorithm to obtain encrypted data.

[0074] Step S224, transmitting the encrypted data to the destination node.

[0075] It should be noted that after executing step S224, if an access request submitted by the access terminal is obtained, first, an authentication prompt can be sent to the access terminal in response to the access request, and then the authentication factor submitted by the access terminal based on the authentication prompt is obtained, and the authentication factor is compared with the authentication data. If the comparison result is consistent, the encrypted data is decrypted based on the key and the decrypted traffic data is sent down.

[0076] It should be noted that any one of steps S202 to S224 or any combination of multiple steps can be combined into a new implementation method by selecting any one of steps S102 to S108 or any combination of multiple steps according to the needs of implementation deployment; and any one or multiple technical features in the technical scheme composed of steps S202 to S224 can be combined into a new implementation method by selecting any one of the technical features in the technical scheme composed of steps S102 to S108 according to the needs of actual deployment, or the technical features in one or more optional implementation methods provided by steps S102 to S108 can be combined into a new implementation method, which will not be elaborated here one by one.

[0077] Figure 3 A schematic diagram of a network topology adjustment device provided by an embodiment of the present invention is shown in FIG. Figure 3 As shown, the device comprises: The prediction module 302 is configured to obtain the flow data of the preset key nodes in the network topology structure, input the flow data into the flow prediction model to predict the flow characteristics, and output the flow parameters and flow trend sequence; The network topology analysis module 304 is configured to perform network topology analysis based on the network topology data, the traffic parameters and the traffic trend sequence to obtain key nodes and key paths of the network topology structure; A strategy generation module 306 is configured to generate a node deployment strategy of a sink node in the key node according to the key node and the key path; The deployment adjustment module 308 is configured to adjust the deployment of the aggregation node in the network topology structure based on the node deployment strategy.

[0078] The network topology structure adjustment device provided in this embodiment first runs the prediction module 302 to obtain the traffic data of the preset key nodes in the network topology structure, inputs the traffic data into the traffic prediction model to predict the traffic characteristics, and outputs the traffic parameters and traffic trend sequence. Secondly, the network topology analysis module 304 is run to perform network topology analysis based on the network topology data, traffic parameters and traffic trend sequence to obtain the key nodes and key paths of the network topology structure. Then, the strategy generation module 306 is run to generate the node deployment strategy of the aggregation node in the key node according to the key nodes and key paths. Finally, the deployment adjustment module 308 is run to adjust the deployment of the aggregation node in the network topology structure based on the node deployment strategy. By adjusting the deployment of the aggregation node, flexible adjustment and management of the network topology structure can be achieved.

[0079] The network topology adjustment device provided in one embodiment of this specification can implement each process in the aforementioned method embodiment and achieve the same functions and effects, which will not be repeated here.

[0080] Furthermore, an embodiment of the present specification also provides a network topology adjustment device, Figure 4 A schematic diagram of a network topology adjustment device provided in one embodiment of this specification is shown in FIG. Figure 4 As shown, the device includes: a memory 401, a processor 402, a bus 403 and a communication interface 404. The memory 401, the processor 402 and the communication interface 404 communicate through the bus 403, and the communication interface 404 may include an input and output interface, which includes but is not limited to a keyboard, a mouse, a display, a microphone, a loudspeaker, etc.

[0081] Figure 4 In the embodiment, the memory 401 stores computer executable instructions that can be run on the processor 402. When the computer executable instructions are executed by the processor 402, the following process is implemented: Obtaining traffic data of preset key nodes in the network topology structure, inputting the traffic data into a traffic prediction model to predict traffic characteristics, and outputting traffic parameters and traffic trend sequences; Perform network topology analysis based on network topology data, the traffic parameters and the traffic trend sequence to obtain key nodes and key paths of the network topology structure; Generate a node deployment strategy of a convergence node in the key nodes according to the key nodes and the key paths; The aggregation node is deployed and adjusted in the network topology based on the node deployment strategy.

[0082] The network topology adjustment device provided in this embodiment, through the cooperation of the memory 401, the processor 402, the bus 403 and the communication interface 404, first obtains the flow data of the preset key nodes in the network topology structure, inputs the flow data into the flow prediction model to predict the flow characteristics, and outputs the flow parameters and flow trend sequence. Secondly, the network topology analysis is performed based on the network topology data, the flow parameters and the flow trend sequence to obtain the key nodes and key paths of the network topology structure, and then the node deployment strategy of the aggregation node in the key node is generated according to the key nodes and the key paths. Finally, the aggregation node is deployed and adjusted in the network topology structure based on the node deployment strategy. The network topology structure is adjusted by adjusting the deployment of the aggregation node, thereby realizing flexible adjustment and management of the network topology structure.

[0083] The network topology adjustment device provided in one embodiment of this specification can implement each process in the aforementioned method embodiment and achieve the same functions and effects, which will not be repeated here.

[0084] Furthermore, another embodiment of the present specification provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store computer-executable instructions, and when the computer-executable instructions are executed by a processor, the following process is implemented: Obtaining traffic data of preset key nodes in the network topology structure, inputting the traffic data into a traffic prediction model to predict traffic characteristics, and outputting traffic parameters and traffic trend sequences; Perform network topology analysis based on network topology data, the traffic parameters and the traffic trend sequence to obtain key nodes and key paths of the network topology structure; Generate a node deployment strategy of a convergence node in the key nodes according to the key nodes and the key paths; The aggregation node is deployed and adjusted in the network topology based on the node deployment strategy.

[0085] The computer-readable storage medium provided in this embodiment first obtains traffic data of preset key nodes in the network topology structure, inputs the obtained traffic data into the traffic prediction model to predict traffic characteristics, and outputs traffic parameters and traffic trend sequences. Secondly, the network topology analysis is performed based on the network topology data, traffic parameters and traffic trend sequences to obtain key nodes and key paths of the network topology structure. Then, based on the key nodes and key paths, a node deployment strategy for the aggregation nodes in the key nodes is generated. Finally, based on the node deployment strategy, the aggregation nodes are deployed and adjusted in the network topology structure. The network topology structure is adjusted by adjusting the deployment of the aggregation nodes, thereby achieving flexible adjustment and management of the network topology structure.

[0086] The computer-readable storage medium includes a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0087] The computer-readable storage medium provided in an embodiment of this specification can implement each process in the aforementioned method embodiment and achieve the same functions and effects, which will not be repeated here.

[0088] Furthermore, another embodiment of the present specification also provides a computer program product, which implements the following process when executed by a processor: Obtaining traffic data of preset key nodes in the network topology structure, inputting the traffic data into a traffic prediction model to predict traffic characteristics, and outputting traffic parameters and traffic trend sequences; Perform network topology analysis based on network topology data, the traffic parameters and the traffic trend sequence to obtain key nodes and key paths of the network topology structure; Generate a node deployment strategy of a convergence node in the key nodes according to the key nodes and the key paths; The aggregation node is deployed and adjusted in the network topology based on the node deployment strategy.

[0089] The computer program product provided in this embodiment first obtains the traffic data of preset key nodes in the network topology structure, inputs the obtained traffic data into the traffic prediction model to predict the traffic characteristics, and outputs the traffic parameters and traffic trend sequence. Secondly, the network topology analysis is performed based on the network topology data, traffic parameters and traffic trend sequence to obtain the key nodes and key paths of the network topology structure. Then, according to the key nodes and key paths, the node deployment strategy of the aggregation node in the key node is generated. Finally, based on the node deployment strategy, the aggregation node is deployed and adjusted in the network topology structure. The network topology structure is adjusted by adjusting the deployment of the aggregation node, thereby realizing flexible adjustment and management of the network topology structure.

[0090] The computer program product provided in one embodiment of this specification can implement each process in the aforementioned method embodiment and achieve the same functions and effects, which will not be repeated here.

[0091] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0092] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0093] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0094] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0095] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0096] Memory may include non-permanent storage in a computer-readable storage medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable storage medium.

[0097] Computer-readable storage media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer-readable storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable storage media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0098] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0099] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0100] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A network topology adjustment method, characterized in that: The method comprises: Obtaining traffic data of preset key nodes in the network topology structure, inputting the traffic data into a traffic prediction model to predict traffic characteristics, and outputting traffic parameters and traffic trend sequences; Perform network topology analysis based on network topology data, the traffic parameters and the traffic trend sequence to obtain key nodes and key paths of the network topology structure; Generate a node deployment strategy of a convergence node in the key nodes according to the key nodes and the key paths; The aggregation node is deployed and adjusted in the network topology based on the node deployment strategy.

2. The network topology adjustment method according to claim 1, after the step of adjusting the deployment of the aggregation node in the network topology based on the node deployment strategy is performed, further comprising: Encrypting the traffic data of the aggregation node based on an encryption algorithm to obtain encrypted data; Access authentication is performed based on an access request for the encrypted data submitted by an access terminal.

3. The network topology adjustment method according to claim 1, wherein the network topology analysis is performed based on the network topology data, the traffic parameters and the traffic trend sequence to obtain the key nodes and key paths of the network topology structure, including: Acquire the network topology data, and construct a network topology graph model based on the network topology data; Based on the evaluation algorithm, the frequency of each node in the network topology model being located on the shortest path is evaluated to obtain high-frequency nodes; The key nodes are determined among the high-frequency nodes based on the traffic parameters and the traffic trend sequence, and the paths between the key nodes are determined as the key paths.

4. The network topology adjustment method according to claim 1, wherein generating a node deployment strategy of a sink node in the key node according to the key node and the key path comprises: Constructing a feature space of the key node based on the position data and flow data of the key node; Calculating the similarity of the key nodes in the feature space according to a clustering algorithm and clustering the key nodes based on the similarity to obtain cluster centers; The node deployment strategy is generated at the cluster center based on network configuration data.

5. The network topology adjustment method according to claim 2, wherein the step of encrypting the flow data of the aggregation node based on an encryption algorithm to obtain encrypted data comprises: Generate a key that meets the preset encryption length according to the preset encryption length and a random number generator; The key is transmitted to the aggregation node and the destination node, and the traffic data of the aggregation node is encrypted by the encryption algorithm based on the key to obtain the encrypted data; The encrypted data is transmitted to the destination node.

6. The network topology adjustment method according to claim 5, wherein the access authentication based on the access request for the encrypted data submitted by the access terminal comprises: If the access request submitted by the access terminal is obtained, an authentication prompt is sent to the access terminal; Acquire an authentication factor submitted by the access terminal based on the authentication prompt, and compare the authentication factor with the authentication data to obtain a comparison result; If the comparison result is consistent, the encrypted data is decrypted based on the key and the decrypted traffic data is sent down.

7. A network topology adjustment device, characterized in that: The device comprises: A prediction module is configured to obtain flow data of preset key nodes in the network topology structure, input the flow data into a flow prediction model to predict flow characteristics, and output flow parameters and flow trend sequences; A network topology analysis module is configured to perform network topology analysis based on network topology data, the traffic parameters and the traffic trend sequence to obtain key nodes and key paths of the network topology structure; A strategy generation module is configured to generate a node deployment strategy of a convergence node in the key nodes according to the key nodes and the key paths; The deployment adjustment module is configured to adjust the deployment of the aggregation node in the network topology structure based on the node deployment strategy.

8. A network topology adjustment device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer executable instructions, and when the computer executable instructions are executed on the processor, the steps of the method described in any one of claims 1 to 6 can be implemented.

9. A computer-readable storage medium having computer-executable instructions stored therein, characterized in that: When the computer executable instructions are executed by a processor, the steps of the method described in any one of claims 1 to 6 can be implemented.

10. A computer program product, characterized in that The computer program product includes a network topology adjustment program, and when the network topology adjustment program is executed by a processor, the steps of the method described in any one of claims 1 to 6 can be implemented.

Images