SVM-based content distribution network configuration method, system and device

Abstract

The invention relates to the technical field of content distribution networks, and discloses an SVM-based content distribution network configuration method, system and device, and the method comprises the steps: receiving alarm information and a target interruption rate sent by a central cluster, and obtaining initial static configuration data and dynamic data of all domain names of an area where an edge cluster is located; determining a parameter adjustment step length based on the initial static configuration data; obtaining target data based on the initial static configuration data, the dynamic data and the parameter adjustment step length; updating a pre-trained SVM algorithm model based on the target data to obtain a target SVM algorithm model; and determining target static configuration data by adopting the target SVM algorithm model and taking the target interruption rate as a target, and sending the target static configuration data to the central cluster. According to the method and the system, the alarm information is received in time, the priority user discovers the interruption problem, and personalized configuration is carried out for the domain name with the abnormal condition, so that the response speed and stability are improved, the performance of the content distribution network is improved, and the user experience and satisfaction are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of content distribution network, and in particular to a content distribution network configuration method, system and device based on SVM. Background Art

[0002] With the rapid development of Internet technology, Content Delivery Network (CDN) has become a key infrastructure to ensure that users can access websites and applications efficiently and stably. However, in practical applications, CDN faces many challenges, especially in handling user reports and optimizing configuration.

[0003] Currently, common user fault reporting scenarios in CDN services include video playback interruption and web page access failure. The existing solution usually analyzes the problem and adjusts the configuration after the user reports the problem. This passive method not only has a long response time, but also affects the user experience. In addition, due to the significant differences in network environment and user behavior in different regions, the current unified CDN configuration for all regions is difficult to meet the personalized needs of the region. It can be seen that the existing CDN configuration method has the problems of long response time, poor user experience and inability to meet personalized needs. Summary of the invention

[0004] In view of this, the present invention provides a content distribution network configuration method, system and device based on SVM to solve the problems of the existing CDN configuration method having a long response time, affecting the user experience and failing to meet personalized needs.

[0005] In a first aspect, the present invention provides a content distribution network configuration method based on SVM, which is applied to an edge cluster of a content distribution network. The method comprises:

[0006] Receive alarm information and target interruption rate sent by the central cluster of the content distribution network, obtain initial static configuration data and dynamic data of all domain names in the area where the edge cluster is located, and the alarm information indicates that the domain name of the content distribution network is abnormal;

[0007] Determine the parameter adjustment step size based on the initial static configuration data of all domain names;

[0008] Based on the initial static configuration data, dynamic data and parameter adjustment step, the target data is obtained;

[0009] The pre-trained SVM algorithm model is updated based on the target data to obtain the target SVM algorithm model;

[0010] The target SVM algorithm model is adopted, with the target interruption rate as the target, the target static configuration data is determined, and the target static configuration data is sent to the central cluster, so that the central cluster performs configuration optimization according to the target static configuration data.

[0011] The SVM-based content distribution network configuration method provided by the embodiment of the present invention can quickly respond to the abnormal situation of the domain name by receiving the alarm information, and then obtain the initial static configuration data and dynamic data, and determine the parameter adjustment step length based on the initial static configuration data. The determination of the parameter adjustment step length makes the optimization process more refined, so as to flexibly adapt to various situations. The static configuration data, dynamic data and parameter adjustment step length are combined to form target data, and a comprehensive input is provided for subsequent model updates. By updating the SVM algorithm model, it can adapt to the new data distribution, improve the generalization ability of the model on new data, and cope with the ever-changing network environment. Since the target SVM algorithm model has learned the relationship between the static configuration data and the interruption rate, when the target interruption rate is the target, the target SVM algorithm model can accurately determine the target static configuration data by adjusting the parameters, and by timely receiving the alarm information, the user is given priority to discover the interruption problem, so as to perform personalized configuration for the domain name with abnormal situation, improve the response speed and stability, so that the performance of the content distribution network is improved, the interruption rate is reduced, and the user experience and satisfaction are improved.

[0012] In an optional implementation, the initial static configuration data of each domain name includes a plurality of static configuration parameters and their corresponding data;

[0013] Based on the initial static configuration data of all domain names, determine the parameter adjustment step, including:

[0014] Based on the initial static configuration data corresponding to all domain names, for each static configuration parameter in the initial static configuration data, determine an average value of the static configuration parameter;

[0015] Determine a standard deviation of the static configuration parameter based on an average value of the static configuration parameter;

[0016] According to the normal distribution and based on the standard deviation of the static configuration parameters, the tuning step of the static configuration parameters is determined.

[0017] The SVM-based content distribution network configuration method provided in an embodiment of the present invention calculates the average value of each static configuration parameter in the initial static configuration data and then calculates the standard deviation. Therefore, based on the normal distribution and combined with the above standard deviation, the parameter adjustment step size of each static configuration parameter can be determined more accurately. A reasonable parameter adjustment step size helps to maintain the stability of the model and avoid model performance fluctuations caused by improper step size.

[0018] In an optional implementation, before updating the pre-trained SVM algorithm model based on the target data to obtain the target SVM algorithm model, the method further includes:

[0019] Obtain training static data and sample dynamic data, the sample dynamic data includes interruption rate;

[0020] Calculate the average value of the data except the interruption rate in the sample dynamic data according to time and domain name to obtain the training dynamic data;

[0021] The SVM algorithm model is used to make predictions based on static training data and dynamic training data to obtain multiple training interruption rates.

[0022] determining a plurality of training errors between a plurality of training interruption rates and interruption rates in the training dynamics data;

[0023] The SVM algorithm model is trained based on multiple training errors to obtain a pre-trained SVM algorithm model.

[0024] The SVM-based content distribution network configuration method provided in the embodiment of the present invention calculates the average value of sample dynamic data according to time and domain name to obtain training dynamic data, which can smooth out short-term fluctuations and make the training dynamic data more stable. The SVM algorithm model is used to perform prediction based on training static data and training dynamic data to obtain the training interruption rate, thereby determining the training error between the training interruption rate and the actual interruption rate in the training dynamic data, thereby quantifying the prediction error of the model. Therefore, by training based on the training error, the SVM algorithm model can be optimized to improve the prediction accuracy and generalization ability of the model.

[0025] In an optional embodiment, the target data includes an interruption rate;

[0026] The pre-trained SVM algorithm model is updated based on the target data to obtain the target SVM algorithm model, including:

[0027] The target data is predicted using a pre-trained SVM algorithm model to obtain a plurality of first predicted interruption rates;

[0028] determining a plurality of prediction errors between a plurality of first predicted outage rates and outage rates in the target data;

[0029] The pre-trained SVM algorithm model is updated based on multiple prediction errors to obtain a target SVM algorithm model.

[0030] The SVM-based content distribution network configuration method provided in the embodiment of the present invention predicts the target data by using a pre-trained SVM algorithm model to obtain multiple first predicted interruption rates, thereby determining the prediction error between the first predicted interruption rate and the actual interruption rate in the target data, and updating the SVM algorithm model based on the prediction error to obtain the target SVM algorithm model, so that the model learns new data features, and at the same time deeply learns the relationship between static configuration data and interruption rate, thereby improving the prediction accuracy and generalization ability of the model.

[0031] In an optional implementation, a target SVM algorithm model is adopted, with a target interruption rate as a target, to determine target static configuration data, including:

[0032] Selecting initial target data from the target data;

[0033] The target SVM algorithm model is used to predict the initial target data to obtain the second predicted interruption rate;

[0034] When the difference between the second predicted interruption rate and the target interruption rate is greater than the preset error threshold, the static configuration data in the initial target data is adjusted according to the parameter adjustment step, and the prediction process is repeated until the difference between the second predicted interruption rate and the target interruption rate is no greater than the preset error threshold, and the static configuration data in the target data obtained by the last adjustment is used as the target static configuration data.

[0035] The SVM-based content distribution network configuration method provided in the embodiment of the present invention provides a clear starting point for subsequent predictions and adjustments by selecting initial target data, ensuring that the optimization process is carried out in an orderly manner, and then adopts the target SVM algorithm model to predict the initial target data to obtain a second predicted interruption rate. When the difference between the second predicted interruption rate and the target interruption rate is greater than a preset error threshold, the static configuration data in the initial target data is adjusted according to the parameter adjustment step. By gradually adjusting the static configuration data, the prediction result of the model is gradually optimized to ensure that the target interruption rate is finally reached, thereby realizing targeted configuration optimization of domain names with abnormal situations.

[0036] In a second aspect, the present invention provides a content distribution network configuration method based on SVM, which is applied to a central cluster of a content distribution network. The method comprises:

[0037] Monitor the outage rate of all domains in the target area;

[0038] For any domain name, when the interruption rate of the domain name exceeds the preset interruption rate threshold, an alarm message and a target interruption rate corresponding to the domain name are sent to the edge cluster of the content distribution network;

[0039] Receive target static configuration data of an edge cluster of a content distribution network, perform configuration optimization based on the target static configuration data, the target static configuration data is determined by adopting a target SVM algorithm model with a target interruption rate as a target, and the target SVM algorithm model is obtained by updating a pre-trained SVM algorithm model based on the target data obtained based on the static configuration data, dynamic data and parameter adjustment step.

[0040] The SVM-based content distribution network configuration method provided in the embodiment of the present invention monitors the interruption rate in real time. When the interruption rate of any domain name exceeds the threshold, an alarm message is sent to the edge cluster in time, the user is given priority to discover the interruption problem, and the target static configuration data sent by the edge cluster is received to optimize the configuration based on the data, so as to solve the abnormal situation of the domain name and improve the stability and reliability of the network.

[0041] In an optional embodiment, the method further includes:

[0042] Verify whether the actual static configuration of the domain name is consistent with the target static configuration data;

[0043] When the actual static configuration of the domain name is inconsistent with the target static configuration data, the static configuration of the domain name is automatically repaired.

[0044] The SVM-based content distribution network configuration method provided in the embodiment of the present invention verifies whether the actual static configuration of the domain name with abnormal interruption rate is consistent with the target static configuration data after configuration optimization, and automatically repairs it in the event of inconsistency, thereby ensuring that the actual static configuration is completely matched with the optimized target configuration, avoiding problems caused by configuration errors, and improving the reliability and stability of the network.

[0045] In a third aspect, the present invention provides a content distribution network configuration system based on SVM, the system comprising:

[0046] Monitor the outage rate of all domains in the target area;

[0047] For any domain name, when the interruption rate of the domain name exceeds the preset interruption rate threshold, an alarm message and a target interruption rate corresponding to the domain name are sent to the edge cluster of the content distribution network;

[0048] Receive alarm information and target interruption rate sent by the central cluster of the content distribution network, obtain initial static configuration data and dynamic data of all domain names in the area where the edge cluster is located, and the alarm information indicates that the domain name of the content distribution network is abnormal;

[0049] Determine the parameter adjustment step size based on the initial static configuration data of all domain names;

[0050] Based on the initial static configuration data, dynamic data and parameter adjustment step, the target data is obtained;

[0051] The pre-trained SVM algorithm model is updated based on the target data to obtain the target SVM algorithm model;

[0052] Adopting the target SVM algorithm model, taking the target interruption rate as the target, determining the target static configuration data, and sending the target static configuration data to the central cluster, so that the central cluster performs configuration optimization according to the target static configuration data;

[0053] Receive target static configuration data of an edge cluster of a content distribution network, and perform configuration optimization based on the target static configuration data.

[0054] In a fourth aspect, the present invention provides a content distribution network configuration device based on SVM, which is applied to an edge cluster of a content distribution network, and the device includes:

[0055] A receiving module, used to receive alarm information and a target interruption rate sent by a central cluster of the content distribution network, wherein the alarm information indicates that an abnormality occurs in a domain name of the content distribution network;

[0056] The collection module is used to obtain the initial static configuration data and dynamic data of all domain names in the area where the edge cluster is located;

[0057] An algorithm module is used to determine the parameter adjustment step based on the initial static configuration data of all domain names, obtain the target data based on the initial static configuration data, dynamic data and the parameter adjustment step, update the pre-trained SVM algorithm model based on the target data, obtain the target SVM algorithm model, adopt the target SVM algorithm model, take the target interruption rate as the target, and determine the target static configuration data;

[0058] The upload module is used to send the target static configuration data to the central cluster so that the central cluster performs configuration optimization according to the target static configuration data.

[0059] In a fifth aspect, the present invention provides a content distribution network configuration device based on SVM, which is applied to a central cluster of a content distribution network, and the device includes:

[0060] A monitoring platform to monitor the interruption rate of all domain names in the target area;

[0061] The decision-making platform is used for sending alarm information and a target interruption rate corresponding to a domain name to an edge cluster of a content distribution network for any domain name when the interruption rate of the domain name exceeds a preset interruption rate threshold, receiving target static configuration data of the edge cluster of the content distribution network, and performing configuration optimization based on the target static configuration data, wherein the target static configuration data is determined by adopting a target SVM algorithm model with the target interruption rate as a target, and the target SVM algorithm model is obtained by updating a pre-trained SVM algorithm model with target data obtained based on static configuration data, dynamic data and parameter adjustment step size.

[0062] In a sixth aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to thereby execute the SVM-based content distribution network configuration method of the above-mentioned first aspect or any corresponding embodiment thereof, or to execute the SVM-based content distribution network configuration method of the above-mentioned second aspect or any corresponding embodiment thereof.

[0063] In the seventh aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the SVM-based content distribution network configuration method of the above-mentioned first aspect or any corresponding embodiment thereof, or to execute the SVM-based content distribution network configuration method of the above-mentioned second aspect or any corresponding embodiment thereof.

[0064] In an eighth aspect, the present invention provides a computer program product, comprising computer instructions, wherein the computer instructions are used to enable a computer to execute the SVM-based content distribution network configuration method of the above-mentioned first aspect or any corresponding embodiment thereof, or to execute the SVM-based content distribution network configuration method of the above-mentioned second aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0066] Figure 1 is a schematic diagram of a content distribution network configuration device based on SVM applied to an edge cluster of a content distribution network according to an embodiment of the present invention;

[0067] Figure 2is a flow chart of a content distribution network configuration method based on SVM applied to an edge cluster of a content distribution network according to an embodiment of the present invention;

[0068] Figure 3 is a schematic diagram of a content distribution network configuration device based on SVM applied to a central cluster of a content distribution network according to an embodiment of the present invention;

[0069] Figure 4 is a flow chart of a content distribution network configuration method based on SVM applied to a central cluster of a content distribution network according to an embodiment of the present invention;

[0070] Figure 5 is a flow chart of a content distribution network configuration system based on SVM according to an embodiment of the present invention;

[0071] Figure 6 is a schematic diagram of an SVM algorithm model according to an embodiment of the present invention;

[0072] Figure 7 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0073] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0074] Common user fault reporting scenarios in CDN services include video playback interruption and web page access failure. Existing solutions usually perform problem analysis and configuration adjustments after the user reports the problem. This passive method not only has a long response time, but also affects the user experience. In addition, due to the significant differences in network environment and user behavior in different regions, the current unified CDN configuration for all regions is difficult to meet the personalized needs of the region. It can be seen that the existing CDN configuration method has the problems of long response time, poor user experience and inability to meet personalized needs. The SVM-based content distribution network configuration method provided in an embodiment of the present invention receives alarm information in a timely manner, prioritizes user interruption problems, and performs personalized configuration for domain names where abnormal situations occur, thereby improving response speed and stability, thereby improving the performance of the content distribution network, reducing interruption rates, and improving user experience and satisfaction.

[0075] According to an embodiment of the present invention, an embodiment of a content distribution network configuration method based on SVM is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0076] Figure 1 is a schematic diagram of a content distribution network configuration device based on SVM applied to an edge cluster of a content distribution network according to an embodiment of the present invention, such as Figure 1 As shown, a receiving module is used to receive alarm information and a target interruption rate sent by a central cluster of a content distribution network, wherein the alarm information indicates that an abnormality occurs in a domain name of the content distribution network; a collection module is used to obtain initial static configuration data and dynamic data of all domain names in the area where the edge cluster is located; an algorithm module is used to determine a parameter adjustment step based on the initial static configuration data of all domain names, obtain target data based on the initial static configuration data, dynamic data and parameter adjustment step, update a pre-trained SVM algorithm model based on the target data, obtain a target SVM algorithm model, adopt the target SVM algorithm model, take the target interruption rate as a target, and determine the target static configuration data; an upload module is used to send the target static configuration data to the central cluster, so that the central cluster performs configuration optimization according to the target static configuration data.

[0077] Specifically, the edge cluster includes a receiving module, a collection module, an algorithm module and an upload module. Among them, the receiving module is used to receive information and data sent by the central cluster. The collection module is used to obtain the initial static configuration data and dynamic data of all domain names in the area where the edge cluster is located at the current time. The algorithm module maintains an SVM algorithm model, and a pre-trained SVM algorithm model is obtained by training the SVM algorithm model. After the collection module performs data collection based on the alarm information, the pre-trained model is updated based on the latest data in the area where the edge cluster is located to obtain the target SVM algorithm model, thereby determining the corresponding target static configuration data for the target interruption rate. The upload module is used to send the target static configuration data determined by the algorithm module to the central cluster so that the central cluster can perform corresponding configuration.

[0078] In this embodiment, a content distribution network configuration method based on SVM is provided, which can be used for edge clusters of content distribution networks. Figure 2 is a flow chart of a content distribution network configuration method based on SVM applied to an edge cluster of a content distribution network according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0079] Step S201, receiving the alarm information and target interruption rate sent by the central cluster of the content distribution network, obtaining the initial static configuration data and dynamic data of all domain names in the area where the edge cluster is located, and the alarm information indicates that the domain name of the content distribution network is abnormal. Specifically, the CDN network includes a central cluster and an edge cluster. Among them, the central cluster is the core part of the CDN network, responsible for global management and coordination, usually located in the data center, and has powerful computing and storage resources. The edge cluster is the front-end part of the CDN network, distributed in a geographical location close to the user, usually composed of multiple edge nodes, each node is responsible for user requests in a specific area. When the central cluster monitors any area, it monitors all domain names included in the area. If the interruption rate of any domain name is monitored to be abnormal, assuming that the business type in a region is consistent, the central cluster can randomly select an edge cluster in the region, send the alarm information and the target interruption rate corresponding to the domain name to the edge cluster, so that the edge cluster helps to optimize the configuration of the CDN network to achieve the target interruption rate, thereby solving the abnormal situation of the domain name. Compared with the use of a unified configuration for all regions in the related art, the embodiment of the present invention presets a corresponding target interruption rate for each domain name in each region, that is, it can achieve personalized configuration for each region or each domain name, and the alarm information takes precedence over the user's fault report, and handles abnormal situations in a timely manner to improve the user experience. Optionally, the initial static configuration data includes the TCP (Transmission Control Protocol) packet sending strategy, timeout settings, and buffer (buffer) related configurations of the domain name. These data are all self-regulatory by the CDN network, that is, the interruption rate can be changed by adjusting these data. The dynamic data includes the number of retransmissions, interruption rate, request method, request header size and response header size of each user request for each TCP link. These data are user behaviors and cannot be adjusted. Therefore, if configuration optimization is to be performed, it is necessary to determine the static configuration data.

[0080] Step S202, based on the initial static configuration data of all domain names, determine the parameter adjustment step size. Specifically, analyze the initial static configuration data to determine a suitable parameter adjustment step size, which is used to gradually adjust the parameters during the optimization process to approach the target interruption rate. A reasonable parameter adjustment step size can ensure that the parameter adjustment during the optimization process is more accurate and avoid instability caused by excessive adjustment.

[0081] Step S203, based on the initial static configuration data, dynamic data and parameter adjustment step, obtain target data. Specifically, the initial static configuration data and dynamic data are combined, and the initial static configuration data is gradually adjusted using the parameter adjustment step to generate multiple groups of different data configurations as target data, providing diversified samples for model training.

[0082] Step S204, based on the target data, the pre-trained SVM algorithm model is updated to obtain the target SVM algorithm model. Specifically, the pre-trained SVM algorithm model is obtained by training the SVM algorithm model, and has the ability to accurately predict the interruption rate, and has learned the relationship between the static configuration data and the interruption rate. Through the algorithm module of the edge cluster, the pre-trained SVM algorithm model is trained again using the target data to update the model parameters, so that the model can continuously learn new data features and enhance the prediction accuracy and generalization ability.

[0083] Step S205, using the target SVM algorithm model, taking the target interruption rate as the target, determining the target static configuration data, and sending the target static configuration data to the central cluster, so that the central cluster performs configuration optimization according to the target static configuration data. Specifically, the target SVM algorithm model is used to predict the target data, and the prediction results of the model are gradually optimized by gradually adjusting the static configuration data to ensure that the target interruption rate is finally reached, and the static configuration data at this time is used as the target static configuration data. The target static configuration data is sent to the central cluster through the upload module of the edge cluster, so that the central cluster makes corresponding configuration adjustments, so that the domain name with abnormal conditions reaches the target interruption rate, and the normal network environment is restored to improve the user experience.

[0084] The SVM-based content distribution network configuration method provided by the embodiment of the present invention can quickly respond to the abnormal situation of the domain name by receiving the alarm information, and then obtain the initial static configuration data and dynamic data, and determine the parameter adjustment step length based on the initial static configuration data. The determination of the parameter adjustment step length makes the optimization process more refined, so as to flexibly adapt to various situations. The static configuration data, dynamic data and parameter adjustment step length are combined to form target data, and a comprehensive input is provided for subsequent model updates. By updating the SVM algorithm model, it can adapt to the new data distribution, improve the generalization ability of the model on new data, and cope with the ever-changing network environment. Since the target SVM algorithm model has learned the relationship between the static configuration data and the interruption rate, when the target interruption rate is the target, the target SVM algorithm model can accurately determine the target static configuration data by adjusting the parameters, and by timely receiving the alarm information, the user is given priority to discover the interruption problem, so as to perform personalized configuration for the domain name with abnormal situation, improve the response speed and stability, so that the performance of the content distribution network is improved, the interruption rate is reduced, and the user experience and satisfaction are improved.

[0085] Figure 3 is a schematic diagram of a content distribution network configuration device based on SVM applied to a central cluster of a content distribution network according to an embodiment of the present invention, such as Figure 3As shown, the monitoring platform is used to monitor the interruption rate of all domain names in the target area; the decision platform is used to send an alarm message and a target interruption rate corresponding to the domain name to the edge cluster of the content distribution network for any domain name when the interruption rate of the domain name exceeds a preset interruption rate threshold, receive the target static configuration data of the edge cluster of the content distribution network, and perform configuration optimization based on the target static configuration data. The target static configuration data is determined by adopting a target SVM algorithm model with the target interruption rate as the target. The target SVM algorithm model is obtained by updating the pre-trained SVM algorithm model with the target data obtained based on the static configuration data, the dynamic data and the parameter adjustment step.

[0086] Specifically, the monitoring platform monitors the interruption rate of all domain names in the target area in real time and transmits it to the decision platform. The decision platform judges the interruption rate of the domain name at a preset frequency, for example, once every 10 minutes. When the interruption rate of any domain name exceeds the preset interruption rate threshold, the network environment of the domain name may be abnormal. At this time, the decision platform generates an alarm message and sends the alarm message and the target interruption rate of the domain name to the edge cluster. When the edge cluster determines the target static configuration data corresponding to the target interruption rate, it receives the data to achieve configuration optimization.

[0087] In this embodiment, a content distribution network configuration method based on SVM is provided, which can be used for the central cluster of the content distribution network. Figure 4 is a flow chart of a content distribution network configuration method based on SVM applied to a central cluster of a content distribution network according to an embodiment of the present invention. Figure 4 As shown, the process includes the following steps:

[0088] Step S401, monitoring the interruption rate of all domain names in the target area. Specifically, the CDN network covers multiple areas, and the target area is any area therein. The monitoring platform monitors the interruption rate of all domain names in the target area in real time.

[0089] Step S402: For any domain name, when the interruption rate of the domain name exceeds the preset interruption rate threshold, an alarm message and the target interruption rate corresponding to the domain name are sent to the edge cluster of the content distribution network. Specifically, the monitoring platform monitors the bandwidth of all domain names at the same time. When the bandwidth remains unchanged, if the interruption rate of any domain name is higher than the preset interruption rate threshold, it means that the network of the domain name is abnormal at this time, and an alarm is issued at this time. The alarm information is domain name + time + interruption rate + target area. The monitoring platform transmits the alarm information and the target interruption rate of the domain name to the decision platform, and the decision platform sends it to the edge cluster corresponding to the target area.

[0090] Step S403, receiving the target static configuration data of the edge cluster of the content distribution network, performing configuration optimization based on the target static configuration data, the target static configuration data is determined by adopting the target SVM algorithm model, taking the target interruption rate as the target, and the target SVM algorithm model is obtained by updating the pre-trained SVM algorithm model based on the target data obtained by the static configuration data, dynamic data and parameter adjustment step. Specifically, after the edge cluster receives the alarm information and the target interruption rate, the target static configuration data is determined through the above steps S201 to S205, and sent to the decision platform of the central cluster. The central cluster also includes a configuration platform, and the decision platform transmits the target static configuration data to the configuration platform, and the configuration platform performs specific configuration operations based on each static configuration parameter in the target static configuration data and its corresponding data. Optionally, the configuration platform can also display the configuration interface during configuration, and can provide historical configuration records. By configuring according to the target static configuration data, the domain name with abnormal interruption rate reaches the target interruption rate, the normal network environment is restored, and the stability of the network is maintained.

[0091] The SVM-based content distribution network configuration method provided in the embodiment of the present invention monitors the interruption rate in real time. When the interruption rate of any domain name exceeds the threshold, an alarm message is sent to the edge cluster in time, the user is given priority to discover the interruption problem, and the target static configuration data sent by the edge cluster is received to optimize the configuration based on the data, so as to solve the abnormal situation of the domain name and improve the stability and reliability of the network.

[0092] In this embodiment, a content distribution network configuration system based on SVM is provided, which includes an edge cluster and a central cluster of a content distribution network. Figure 5 is a flow chart of a content distribution network configuration system based on SVM according to an embodiment of the present invention. Figure 5As shown, the central cluster monitors the interruption rate of all domain names in the target area; for any domain name, when the interruption rate of the domain name exceeds the preset interruption rate threshold, the central cluster sends an alarm message and a target interruption rate corresponding to the domain name to the edge cluster of the content distribution network; the edge cluster receives the alarm message and the target interruption rate sent by the central cluster of the content distribution network, and obtains the initial static configuration data and dynamic data of all domain names in the area where the edge cluster is located, and the alarm message indicates that the domain name of the content distribution network is abnormal; the edge cluster determines the parameter adjustment step based on the initial static configuration data of all domain names; the edge cluster obtains the target data based on the initial static configuration data, the dynamic data and the parameter adjustment step; the edge cluster updates the pre-trained SVM algorithm model based on the target data to obtain the target SVM algorithm model; the edge cluster adopts the target SVM algorithm model, takes the target interruption rate as the target, determines the target static configuration data, and sends the target static configuration data to the central cluster, so that the central cluster performs configuration optimization according to the target static configuration data; the central cluster receives the target static configuration data of the edge cluster of the content distribution network, and performs configuration optimization based on the target static configuration data.

[0093] In some optional implementations, the SVM-based content distribution network configuration system includes an edge cluster and a central cluster of the content distribution network, and the detailed process of the system includes the following steps:

[0094] Step S501: The central cluster monitors the interruption rate of all domain names in the target area. Figure 4 Step S401 of the illustrated embodiment will not be described in detail here.

[0095] Step S502: For any domain name, when the interruption rate of the domain name exceeds the preset interruption rate threshold, the central cluster sends an alarm message and the target interruption rate corresponding to the domain name to the edge cluster of the content distribution network. Figure 4 Step S402 of the illustrated embodiment will not be described in detail here.

[0096] Step S503: The edge cluster receives the alarm information and target interruption rate sent by the central cluster of the content distribution network, and obtains the initial static configuration data and dynamic data of all domain names in the area where the edge cluster is located. The alarm information indicates that the domain name of the content distribution network is abnormal. For details, please refer to Figure 2 Step S201 of the illustrated embodiment will not be described in detail here.

[0097] In step S504, the edge cluster determines the parameter adjustment step based on the initial static configuration data of all domain names. The initial static configuration data of each domain name includes multiple static configuration parameters and their corresponding data.

[0098] Specifically, the above step S504 includes:

[0099] Step S5041, based on the initial static configuration data corresponding to all domain names, for each static configuration parameter in the initial static configuration data, determine the average value of the static configuration parameter. Specifically, the static configuration parameters include TCP packet sending strategy, timeout setting, and buffer related configuration. Taking the timeout setting as an example, assuming that there are 3 domain names in the area where the edge cluster is located, the timeout settings of the 3 domain names at the current time are obtained as: 10 seconds, 15 seconds, and 12 seconds, respectively, and the average value of the timeout setting is 12.33 seconds.

[0100] Step S5042: Determine the standard deviation of the static configuration parameters based on the average value of the static configuration parameters. Specifically, taking the average value of the timeout setting of 12.33 seconds as an example, according to the standard deviation calculation formula, the standard deviation of the timeout setting is 2.055 seconds.

[0101] Step S5043, according to the normal distribution, based on the standard deviation of the static configuration parameters, determine the parameter adjustment step of the static configuration parameters. Specifically, assuming that the timeout setting conforms to the normal distribution, the interval between 0 standard deviation and 1 standard deviation is usually selected as the parameter adjustment interval, for example [12.33-2.055, 12.33+2.055], that is, [10.275, 14.385]. The parameter adjustment interval is divided into several parts, and the length of each part is the parameter adjustment step. For example, it is divided into 5 parts, and the length of each part is 0.822 seconds, that is, the parameter adjustment step of the timeout setting is 0.822 seconds. The purpose of using the normal distribution is to quickly obtain the default value of the static configuration data with the highest utilization rate of the edge nodes in the edge cluster, so as to be more suitable for the current domain name.

[0102] In step S505, the edge cluster obtains the target data based on the initial static configuration data, dynamic data and parameter adjustment step. Specifically, according to the parameter adjustment interval and parameter adjustment step of the timeout setting, the value interval corresponding to the timeout setting can be obtained as [10.275, 11.097, 11.919, 12.741, 13.563, 14.385]. The TCP packet sending strategy and buffer-related configurations in the initial static configuration data are obtained according to the corresponding parameter adjustment step in step S504 above, and then the corresponding value interval is obtained. By combining the initial static configuration data with the dynamic data, a rich amount of target data can be obtained for subsequent model updates.

[0103] In step S506, the edge cluster obtains training static data and sample dynamic data, and the sample dynamic data includes the interruption rate. Specifically, the SVM algorithm model is trained through steps S506 to S510 to obtain a pre-trained SVM algorithm model that accurately predicts the interruption rate. More specifically, sample data for training is first obtained, including training static data and sample dynamic data, which are consistent with the data type in step S201.

[0104] In step S507, the edge cluster calculates the average value of the data in the sample dynamic data except the interruption rate according to time and domain name to obtain training dynamic data. Specifically, the sample dynamic data may be data of multiple domain names in a certain historical period, so it can be averaged according to time and domain name to obtain training dynamic data per minute for each domain name, including the average number of TCP link retransmissions, the average user request header size, the average user response header size, and the average request method.

[0105] In step S508, the edge cluster uses the SVM algorithm model to predict based on the training static data and the training dynamic data to obtain multiple training interruption rates. Specifically, the SVM algorithm model uses the existing SVM (Support Vector Machine) algorithm to predict based on the training static data and the training dynamic data to obtain the training interruption rate corresponding to each set of training static data and training dynamic data. Optionally, the implementation process of the SVM algorithm is a prior art and will not be repeated here.

[0106] Step S509: The edge cluster determines multiple training errors between multiple training interruption rates and the interruption rates in the training dynamic data. Specifically, each training dynamic data includes an actual interruption rate, and the training error is obtained by calculating the variance and standard deviation with the predicted training interruption rate.

[0107] In step S510, the edge cluster trains the SVM algorithm model based on multiple training errors to obtain a pre-trained SVM algorithm model. Specifically, the training error is used as feedback, and a suitable optimization method is selected to update the model parameters, such as the gradient descent method and the stochastic gradient descent method, so that the adjusted model repeats the above steps S508 and S509, so that the training error is less than a certain threshold, and the final pre-trained SVM algorithm model is obtained, which can accurately predict the interruption rate and learn the relationship between the static configuration data and the interruption rate.

[0108] In some optional embodiments, Figure 6 Schematic diagram of the SVM algorithm model according to an embodiment of the present invention. Figure 6 As shown, the training static data and the training dynamic data are input into the SVM algorithm model. The training static data includes TCP packet sending strategy, timeout setting and buffer related configuration. The training dynamic data includes the average number of TCP link retransmissions, the average user request header size, the average user response header size, the average request method and the interruption rate. The SVM algorithm model is predicted based on the above data to obtain the training interruption rate. Training is performed based on the input interruption rate and the predicted interruption rate to obtain a pre-trained SVM algorithm model.

[0109] Step S511: The edge cluster updates the pre-trained SVM algorithm model based on the target data to obtain a target SVM algorithm model, where the target data includes an interruption rate.

[0110] Specifically, the above step S511 includes:

[0111] Step S5111, use the pre-trained SVM algorithm model to predict the target data and obtain multiple first predicted interruption rates. Specifically, load the pre-trained SVM algorithm model that has been trained, and the model enters a dormant state to save CPU resources when the edge cluster does not receive alarm information. Since the model has been trained on sample data, the relationship between static configuration data and interruption rate is learned. Use the pre-trained SVM model to predict the latest target data, and output the interruption rate prediction value of each target data, that is, the first predicted interruption rate.

[0112] Step S5112, determining multiple prediction errors between multiple first predicted outage rates and outage rates in the target data. Specifically, the target data includes actual outage rates, and the variance and standard deviation between the first predicted outage rates and the actual outage rates in the target data are calculated as prediction errors.

[0113] Step S5113, based on the multiple prediction errors, the pre-trained SVM algorithm model is updated to obtain a target SVM algorithm model. Specifically, referring to step S510, the pre-trained SVM algorithm model is updated to obtain a target SVM algorithm model, so that its prediction performance on the new target data is improved, and at the same time, the relationship between the static configuration data and the interruption rate is deeply learned again.

[0114] Step S512 , the edge cluster adopts the target SVM algorithm model, takes the target interruption rate as the target, determines the target static configuration data, and sends the target static configuration data to the central cluster, so that the central cluster performs configuration optimization according to the target static configuration data.

[0115] In some optional implementations, in step S512, the edge cluster adopts a target SVM algorithm model, takes a target interruption rate as a target, and determines target static configuration data, including:

[0116] Step S5121, select initial target data from the target data. Specifically, the initial target data can be randomly selected from the target data as the starting point of parameter adjustment, or the average value of the initial static configuration data in step S5041 and its corresponding dynamic data can be used as the initial target data.

[0117] Step S5122: Use the target SVM algorithm model to predict the initial target data to obtain a second predicted interruption rate. Specifically, use the updated target SVM algorithm model to predict the initial target data to obtain a second predicted interruption rate.

[0118] Step S5123, when the difference between the second predicted interruption rate and the target interruption rate is greater than the preset error threshold, the static configuration data in the initial target data is adjusted according to the parameter adjustment step, and the prediction process is repeated until the difference between the second predicted interruption rate and the target interruption rate is not greater than the preset error threshold, and the static configuration data in the target data obtained by the last adjustment is used as the target static configuration data. Specifically, since the target SVM algorithm model has been updated based on the target data and the relationship between the static configuration data and the interruption rate has been learned again, when the target interruption rate is the target, if the difference between the second predicted interruption rate and the target interruption rate is greater than the preset error threshold, the target SVM algorithm model will automatically adjust the parameters, that is, change the static configuration data, and predict again until the difference between the second predicted interruption rate and the target interruption rate is not greater than the preset error threshold, and the target static configuration data is obtained at this time. The preset error threshold should be as close to 0 as possible so that the second predicted interruption rate is close enough to the target interruption rate. In the automatic parameter adjustment process, the target SVM algorithm model increases or decreases the data of each static configuration parameter according to the parameter adjustment step corresponding to each static configuration parameter calculated in the above step S5043.

[0119] Step S513: The central cluster receives the target static configuration data of the edge cluster of the content distribution network, and performs configuration optimization based on the target static configuration data. Figure 4 Step S403 of the illustrated embodiment will not be described in detail here.

[0120] Step S514, the central cluster verifies whether the actual static configuration of the domain name is consistent with the target static configuration data. Specifically, the central cluster also includes a verification platform. The configuration platform adjusts the configuration of the domain name with abnormal interruption rate according to the target static configuration data received by the decision platform. More specifically, the TCP packet sending strategy, timeout setting and buffer-related configuration are adjusted according to the target static configuration data so that the interruption rate of the domain name reaches the target interruption rate and restores the normal network environment. The verification platform is used to supervise the effect of configuration changes and configuration consistency, that is, to verify whether the actual static configuration of the domain name is consistent with the target static configuration data.

[0121] Step S515, when the actual static configuration of the domain name is inconsistent with the target static configuration data, the central cluster automatically repairs the static configuration of the domain name. Specifically, when the actual static configuration is inconsistent with the target static configuration data, the verification platform notifies the configuration platform to automatically repair the actual static configuration so that the actual static configuration is consistent with the target static configuration data.

[0122] In some optional implementations, the central cluster also includes a scheduling platform, which is associated with the decision platform. When the decision platform believes that the edge cluster needs to adjust the regional coverage service, it prioritizes adjusting the adjacent nodes in the current area to enter the service and records the change data.

[0123] The SVM-based content distribution network configuration method provided by the embodiment of the present invention can quickly respond to the abnormal situation of the domain name by receiving the alarm information, and then obtain the initial static configuration data and dynamic data, and determine the parameter adjustment step length based on the initial static configuration data. The determination of the parameter adjustment step length makes the optimization process more refined, so as to flexibly adapt to various situations. The static configuration data, dynamic data and parameter adjustment step length are combined to form target data, and a comprehensive input is provided for subsequent model updates. By updating the SVM algorithm model, it can adapt to the new data distribution, improve the generalization ability of the model on new data, and cope with the ever-changing network environment. Since the target SVM algorithm model has learned the relationship between the static configuration data and the interruption rate, when the target interruption rate is the target, the target SVM algorithm model can accurately determine the target static configuration data by adjusting the parameters, and by timely receiving the alarm information, the user is given priority to discover the interruption problem, so as to perform personalized configuration for the domain name with abnormal situation, improve the response speed and stability, so that the performance of the content distribution network is improved, the interruption rate is reduced, and the user experience and satisfaction are improved.

[0124] The SVM-based content distribution network configuration device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0125] The embodiment of the present invention also provides a computer device, see Figure 7 , Figure 7 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 7As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0126] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0127] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0128] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0129] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0130] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0131] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0132] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0133] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A content distribution network configuration method based on SVM, characterized in that: Applied to an edge cluster of a content distribution network, the method comprises: Receiving alarm information and a target interruption rate sent by a central cluster of the content distribution network, and obtaining initial static configuration data and dynamic data of all domain names in the area where the edge cluster is located, wherein the alarm information indicates that an abnormality occurs in the domain name of the content distribution network; Determine the parameter adjustment step size based on the initial static configuration data of all domain names; Obtaining target data based on the initial static configuration data, the dynamic data, and the parameter adjustment step; Updating the pre-trained SVM algorithm model based on the target data to obtain a target SVM algorithm model; The target SVM algorithm model is adopted, the target interruption rate is taken as a target, target static configuration data is determined, and the target static configuration data is sent to the central cluster, so that the central cluster performs configuration optimization according to the target static configuration data.

2. The method according to claim 1, characterized in that The initial static configuration data of each domain name includes a plurality of static configuration parameters and their corresponding data; The step of determining the parameter adjustment step based on the initial static configuration data of all domain names includes: Based on the initial static configuration data corresponding to all domain names, for each static configuration parameter in the initial static configuration data, determining an average value of the static configuration parameter; Determining a standard deviation of the static configuration parameter based on an average value of the static configuration parameter; According to the normal distribution, based on the standard deviation of the static configuration parameters, the parameter adjustment step size of the static configuration parameters is determined.

3. The method according to claim 1, characterized in that Before updating the pre-trained SVM algorithm model based on the target data to obtain the target SVM algorithm model, the method further includes: Acquire training static data and sample dynamic data, wherein the sample dynamic data includes an interruption rate; Calculate the average value of the data except the interruption rate in the sample dynamic data according to time and domain name to obtain training dynamic data; Using the SVM algorithm model, prediction is performed based on the training static data and the training dynamic data to obtain multiple training interruption rates; determining a plurality of training errors between the plurality of training interruption rates and interruption rates in the training dynamics data; The SVM algorithm model is trained based on the multiple training errors to obtain the pre-trained SVM algorithm model.

4. The method according to claim 1, characterized in that The target data includes an interruption rate; The method of updating the pre-trained SVM algorithm model based on the target data to obtain a target SVM algorithm model includes: Using the pre-trained SVM algorithm model to predict the target data, to obtain a plurality of first predicted interruption rates; determining a plurality of prediction errors between the plurality of first predicted outage rates and outage rates in the target data; The pre-trained SVM algorithm model is updated based on the multiple prediction errors to obtain the target SVM algorithm model.

5. The method according to claim 1, characterized in that The adopting the target SVM algorithm model and taking the target interruption rate as a target to determine the target static configuration data includes: selecting initial target data from the target data; Using the target SVM algorithm model, predicting the initial target data to obtain a second predicted interruption rate; When the difference between the second predicted interruption rate and the target interruption rate is greater than a preset error threshold, the static configuration data in the initial target data is adjusted according to the parameter adjustment step, and the prediction process is repeated until the difference between the second predicted interruption rate and the target interruption rate is no greater than the preset error threshold, and the static configuration data in the target data obtained by the last adjustment is used as the target static configuration data.

6. A content distribution network configuration method based on SVM, characterized in that: Applied to a central cluster of a content distribution network, the method comprises: Monitor the outage rate of all domains in the target area; For any domain name, when the interruption rate of the domain name exceeds a preset interruption rate threshold, sending alarm information and a target interruption rate corresponding to the domain name to an edge cluster of the content distribution network; Receive target static configuration data of the edge cluster of the content distribution network, and perform configuration optimization based on the target static configuration data, wherein the target static configuration data is determined by adopting a target SVM algorithm model with the target interruption rate as the target, and the target SVM algorithm model is obtained by updating a pre-trained SVM algorithm model based on the target data obtained based on the static configuration data, dynamic data and parameter adjustment step.

7. The method according to claim 6, characterized in that The method further comprises: Verify whether the actual static configuration of the domain name is consistent with the target static configuration data; When the actual static configuration of the domain name is inconsistent with the target static configuration data, the static configuration of the domain name is automatically repaired.

8. A content distribution network configuration system based on SVM, characterized in that: The system comprises: Monitor the outage rate of all domains in the target area; For any domain name, when the interruption rate of the domain name exceeds a preset interruption rate threshold, sending alarm information and a target interruption rate corresponding to the domain name to an edge cluster of the content distribution network; Receiving alarm information and a target interruption rate sent by a central cluster of the content distribution network, and obtaining initial static configuration data and dynamic data of all domain names in the area where the edge cluster is located, wherein the alarm information indicates that an abnormality occurs in the domain name of the content distribution network; Determine the parameter adjustment step size based on the initial static configuration data of all domain names; Obtaining target data based on the initial static configuration data, the dynamic data, and the parameter adjustment step; Updating the pre-trained SVM algorithm model based on the target data to obtain a target SVM algorithm model; Adopting the target SVM algorithm model, taking the target interruption rate as a target, determining target static configuration data, and sending the target static configuration data to the central cluster, so that the central cluster performs configuration optimization according to the target static configuration data; Receive target static configuration data of an edge cluster of the content distribution network, and perform configuration optimization based on the target static configuration data.

9. A content distribution network configuration device based on SVM, characterized in that: Applied to an edge cluster of a content distribution network, the device comprises: A receiving module, configured to receive an alarm message and a target interruption rate sent by a central cluster of the content distribution network, wherein the alarm message indicates that an abnormality occurs in a domain name of the content distribution network; A collection module, used to obtain initial static configuration data and dynamic data of all domain names in the area where the edge cluster is located; An algorithm module, used to determine a parameter adjustment step based on initial static configuration data of all domain names, obtain target data based on the initial static configuration data, the dynamic data and the parameter adjustment step, update a pre-trained SVM algorithm model based on the target data to obtain a target SVM algorithm model, adopt the target SVM algorithm model, and determine target static configuration data with the target interruption rate as the target; The upload module is used to send the target static configuration data to the central cluster, so that the central cluster performs configuration optimization according to the target static configuration data.

10. A content distribution network configuration device based on SVM, characterized in that: Applied to a central cluster of a content distribution network, the device comprises: A monitoring platform to monitor the interruption rate of all domain names in the target area; A decision-making platform is used for sending alarm information and a target interruption rate corresponding to any domain name to an edge cluster of the content distribution network when the interruption rate of the domain name exceeds a preset interruption rate threshold, receiving target static configuration data of the edge cluster of the content distribution network, and performing configuration optimization based on the target static configuration data, wherein the target static configuration data is determined by adopting a target SVM algorithm model with the target interruption rate as a target, and the target SVM algorithm model is obtained by updating a pre-trained SVM algorithm model with target data obtained based on static configuration data, dynamic data and parameter adjustment step size.

Images