Analysis and prediction method and device related to signaling storm, equipment, medium and product

Abstract

The invention relates to a signaling storm related analysis and prediction method and device, electronic equipment, a computer readable storage medium and a computer program product, relates to the technical field of wireless communication, and can be applied to a scene in which a signaling storm is analyzed and predicted. The method is applied to a core network element, and comprises the following steps: obtaining input data of a signaling storm from a network entity based on received subscription information related to the signaling storm, and performing data analysis on the input data to obtain a signaling storm analysis result, the signaling storm analysis result comprising at least one of a historical statistical value and a future predicted value of the input data. According to the invention, the analysis and prediction of the signaling storm can be realized, and the positioning of the abnormal reason and position of the signaling storm can be assisted; and the possible signaling storm in the future can be predicted.

Description

Technical Field

[0001] The present disclosure relates to the field of wireless communication technology, and in particular to a signaling storm-related analysis and prediction method, a signaling storm-related analysis and prediction device, an electronic device, a computer-readable storage medium, and a computer program product. Background Art

[0002] Signaling storms have always been a concern and a challenge in communications operations. With the continuous enhancement of smart terminal functionality, the volume of mobile service data has grown rapidly, inducing significant signaling overhead. This means that if an anomaly or failure occurs, a signaling storm may ensue.

[0003] The consequences of large-scale signaling storms are often severe. In recent years, numerous network incidents have occurred on carrier networks around the world, impacting operators significantly. Signaling storms can be caused by a variety of factors, but those triggered by large numbers of user registrations are a common and potentially devastating event.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute prior art known to ordinary technicians in the field. Summary of the Invention

[0005] The purpose of the present disclosure is to provide a signaling storm-related analysis and prediction method, a signaling storm-related analysis and prediction device, an electronic device, a computer-readable storage medium, and a computer program product, thereby at least to a certain extent overcoming the problem that related solutions are unable to analyze and predict signaling storms before they occur so as to take preventive measures against signaling storms.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by practice of the present disclosure.

[0007] According to a first aspect of the present disclosure, a signaling storm-related analysis and prediction method is provided, which is applied to a core network network element. The method includes: based on received signaling storm-related subscription information, obtaining signaling storm input data from a network entity, performing data analysis on the input data, and obtaining a signaling storm analysis result, wherein the signaling storm analysis result includes at least one of a historical statistical value and a future prediction value of the input data.

[0008] In an exemplary embodiment of the present disclosure, the network entity includes an access and mobility management network element and / or a unified data management network element, and the obtaining of input data of the signaling storm from the network entity includes: using the input data obtained from the access and mobility management network element as the first input data; and using the input data obtained from the unified data management network element as the second input data.

[0009] In an exemplary embodiment of the present disclosure, the first input data includes one or more of the number of initial registration requests, the number of initial registration successes, the success rate of initial registration requests, and the number of initial registration failures.

[0010] In an exemplary embodiment of the present disclosure, the initial registration failure count includes a registration failure count based on network element classification and a registration failure count based on illegal types.

[0011] In an exemplary embodiment of the present disclosure, the second input data includes one or more of the number of active users, the number of subscribed users, the number of authentication service requests, the number of successful responses to authentication service requests, the number of context management service requests, the success rate of context management service requests, the number of data management service requests, and the success rate of data management service requests.

[0012] In an exemplary embodiment of the present disclosure, the data analysis of the input data to obtain the signaling storm analysis result includes: obtaining a data analysis model; using the data analysis model to perform data analysis on the input data to obtain the signaling storm analysis result; the historical statistical value is used to reflect the occurrence of signaling storms in a specified time period in the past, and the future prediction value is used to determine the prediction result of the signaling storm in a specified time period in the future.

[0013] In an exemplary embodiment of the present disclosure, the method further includes: sending the signaling storm analysis result to a consumer network element.

[0014] According to a second aspect of the present disclosure, a signaling storm-related analysis and prediction method is provided, which is applied to a consumer network element. The method includes: sending subscription information related to the signaling storm to a core network element, and receiving a signaling storm analysis result returned by the core network element based on the subscription information related to the signaling storm. The signaling storm analysis result includes at least one of a historical statistical value and a future prediction value of the input data of the signaling storm. The signaling storm analysis result is used as reference information for the consumer network element to perform signaling storm prevention and / or mitigation operations.

[0015] In an exemplary embodiment of the present disclosure, the signaling storm-related subscription information includes one or more of an analysis identifier, an analysis report target, a preferred analysis accuracy, analysis filter information, an interested location, a reporting threshold, and a time window.

[0016] In an exemplary embodiment of the present disclosure, the above method also includes: obtaining pre-configured judgment conditions, which include joint judgment conditions and / or single judgment conditions; determining the prediction result of the signaling storm based on the joint judgment conditions and the future prediction value; and / or determining the prediction result of the signaling storm based on the single judgment conditions and the future prediction value.

[0017] In an exemplary embodiment of the present disclosure, the prediction result of the signaling storm is determined based on the joint judgment condition and the future prediction value, including one or more of the following: when the predicted value of the number of initial registration requests is greater than the request number threshold and the initial registration request success rate is less than the registration success rate threshold, the prediction result is that a signaling storm will occur within the future specified time period; when the predicted value of the number of authentication service requests is greater than the authentication request number threshold and the predicted value of the number of active users is less than the user number threshold, the prediction result is that a signaling storm will occur within the future specified time period; when the predicted value of the number of context management service requests is greater than the context management service request threshold and the predicted value of the number of active users is less than the user number threshold, the prediction result is that a signaling storm will occur within the future specified time period; when the predicted value of the number of data management service requests is greater than the data management service request threshold and the predicted value of the number of active users is less than the user number threshold, the prediction result is that a signaling storm will occur within the future specified time period.

[0018] In an exemplary embodiment of the present disclosure, determining the prediction result of the signaling storm based on the single judgment condition and the future prediction value includes: numerically comparing the future prediction value of any one of the input data with the matching threshold value to obtain the prediction result.

[0019] In an exemplary embodiment of the present disclosure, the prediction result includes the probability of occurrence of a signaling storm within a specified future time period, or a unique result of whether a signaling storm occurs within a specified future time period.

[0020] In an exemplary embodiment of the present disclosure, the judgment condition includes a threshold, the threshold includes an adaptive threshold and a fixed threshold, and the configuration method of the threshold includes one or more of the following methods: configuring the adaptive threshold according to the analysis result and in accordance with time information and / or location information; configuring the fixed threshold according to the analysis result; configuring the fixed threshold or the adaptive threshold according to the internal logic of the consumer network element; and configuring the threshold by the communication operator.

[0021] In an exemplary embodiment of the present disclosure, the signaling storm prevention and / or mitigation operation includes one or more of the following operations: rejecting new user registration requests; extending the duration of a backoff timer; and adjusting access and mobility management policies.

[0022] According to a third aspect of the present disclosure, a signaling storm-related analysis and prediction device is provided, which is applied to a core network network element. The device includes: a first analysis and prediction module, which is used to obtain input data of the signaling storm from a network entity based on received subscription information related to the signaling storm, perform data analysis on the input data, and obtain a signaling storm analysis result, wherein the signaling storm analysis result includes at least one of a historical statistical value and a future prediction value of the input data.

[0023] In an exemplary embodiment of the present disclosure, the network entity includes an access and mobility management network element and / or a unified data management network element, and the first analysis and prediction module includes an input data acquisition unit, which is used to: use the input data obtained from the access and mobility management network element as the first input data; and use the input data obtained from the unified data management network element as the second input data.

[0024] In an exemplary embodiment of the present disclosure, the first analysis and prediction module includes a first analysis and prediction unit, which is used to: obtain a data analysis model; use the data analysis model to perform data analysis on the input data to obtain the signaling storm analysis result; the historical statistical value is used to reflect the occurrence of signaling storms in a specified time period in the past, and the future prediction value is used to determine the prediction result of the signaling storm in a specified time period in the future.

[0025] In an exemplary embodiment of the present disclosure, the above-mentioned signaling storm-related analysis and prediction device further includes a result sending module, which is used to: send the signaling storm analysis result to the consumer network element.

[0026] According to a fourth aspect of the present disclosure, a signaling storm-related analysis and prediction device is provided, which is applied to a consumer network element. The device includes: a second analysis and prediction module, which is used to send subscription information related to the signaling storm to a core network element, and receive a signaling storm analysis result returned by the core network element based on the subscription information related to the signaling storm, wherein the signaling storm analysis result includes at least one of a historical statistical value and a future prediction value of the input data of the signaling storm, and the signaling storm analysis result is used as reference information for the consumer network element to perform signaling storm prevention and / or mitigation operations.

[0027] In an exemplary embodiment of the present disclosure, the signaling storm-related analysis and prediction device also includes a prediction result determination module, which is used to: obtain pre-configured judgment conditions, the judgment conditions including joint judgment conditions and / or single judgment conditions; determine the prediction result of the signaling storm based on the joint judgment conditions and the future prediction value; and / or determine the prediction result of the signaling storm based on the single judgment condition and the future prediction value.

[0028] In an exemplary embodiment of the present disclosure, the prediction result determination module includes a first prediction result determination unit, which is used to determine the prediction result for one or more of the following items: when the predicted value of the number of initial registration requests is greater than the request number threshold and the initial registration request success rate is less than the registration success rate threshold, the prediction result is that a signaling storm will occur within a specified time period in the future; when the predicted value of the number of authentication service requests is greater than the authentication request number threshold and the predicted value of the number of active users is less than the user number threshold, the prediction result is that a signaling storm will occur within a specified time period in the future; when the predicted value of the number of context management service requests is greater than the context management service request threshold and the predicted value of the number of active users is less than the user number threshold, the prediction result is that a signaling storm will occur within a specified time period in the future; when the predicted value of the number of data management service requests is greater than the data management service request threshold and the predicted value of the number of active users is less than the user number threshold, the prediction result is that a signaling storm will occur within a specified time period in the future.

[0029] In an exemplary embodiment of the present disclosure, the prediction result determination module includes a second prediction result determination unit, which is used to: numerically compare the future prediction value of any one of the input data with the matching threshold value to obtain the prediction result.

[0030] According to a fifth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the signaling storm-related analysis and prediction method according to any one of the above items is implemented.

[0031] According to a sixth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the signaling storm-related analysis and prediction method according to any one of the above items is implemented.

[0032] According to a seventh aspect of an embodiment of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements any one of the above-mentioned signaling storm-related analysis and prediction methods.

[0033] The technical solution provided by the present disclosure may have the following beneficial effects:

[0034] The signaling storm analysis and prediction method in the exemplary embodiments of this disclosure, on the one hand, applies the core network's data analysis capabilities to signaling storm-related solutions, enabling analysis and prediction of signaling storm-related network issues, thereby assisting in locating the cause and location of anomalies based on historical statistics. On the other hand, by providing a signaling storm prediction solution, signaling storms can be prevented before they occur, avoiding uncontrollable signaling bursts in the network and improving the resilience and robustness of the communication network.

[0035] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification, are used to explain the principles of the present disclosure. Obviously, the drawings described below are only some embodiments of the present disclosure, and those skilled in the art can derive other drawings based on these drawings without inventive effort. In the drawings:

[0037] Figure 1 The following schematically illustrates a flow chart of a method for analyzing and predicting signaling storms applied to core network elements according to an exemplary embodiment of the present disclosure;

[0038] Figure 2 The overall flow chart of analyzing and predicting a signaling storm according to an exemplary embodiment of the present disclosure is schematically shown;

[0039] Figure 3 Schematically illustrates a flow chart of a method for analyzing and predicting signaling storms applied to a consumer network element according to an exemplary embodiment of the present disclosure;

[0040] Figure 4 Schematically shows a block diagram of a signaling storm analysis and prediction device applied to a core network element according to an exemplary embodiment of the present disclosure;

[0041] Figure 5 Schematically shows a block diagram of a signaling storm analysis and prediction device applied to a consumer network element according to an exemplary embodiment of the present disclosure;

[0042] Figure 6 A block diagram schematically illustrates an electronic device according to an exemplary embodiment of the present disclosure;

[0043] Figure 7 A schematic diagram schematically illustrates a computer-readable storage medium according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0044] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art. Like reference numerals in the drawings represent like or similar parts, and thus repetitive description thereof will be omitted.

[0045] In addition, the described features, structures or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, well-known structures, methods, devices, implementations, materials or operations are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0046] The blocks shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. Specifically, these functional entities may be implemented in software, or in one or more software-hardened modules, or in different networks and / or processor devices and / or microcontroller devices.

[0047] Promptly monitoring potential signaling storms before they occur, and promptly identifying their causes and locating faulty network elements at the onset, can help operators effectively prevent and mitigate their impact. Intelligent network elements can analyze and reason about historical data to predict future events, helping other network elements make better decisions. In signaling storm situations, the introduction of intelligence can help the network infer potential future signaling storm risks from existing historical data and also assist in locating the cause and location of anomalies based on historical data.

[0048] Based on this, in this example embodiment, a signaling storm analysis and prediction method applied to core network network elements is first provided. The signaling storm analysis and prediction method of the present disclosure can be implemented using a server, or the method of the present disclosure can be implemented using a terminal device. The terminals described in the present disclosure may include mobile terminals such as mobile phones, tablet computers, laptops, PDAs, personal digital assistants (PDAs), and fixed terminals such as desktop computers. Figure 1 The following schematically illustrates a flow chart of a signaling storm analysis and prediction method according to some embodiments of the present disclosure. Figure 1 The signaling storm analysis and prediction method may include the following steps:

[0049] Step S110: Based on the received subscription information related to the signaling storm, the input data of the signaling storm is obtained from the network entity, and the input data is analyzed to obtain a signaling storm analysis result, which includes at least one of a historical statistical value and a future prediction value of the input data.

[0050] According to some exemplary embodiments of the present disclosure, subscription information related to signaling storms may be subscription information for a consumer network element to request analysis related to signaling storms. Input data for a signaling storm may be attribute data related to network communications selected by a core network element from a network entity based on the subscription information for the signaling storm. A signaling storm analysis result may be an analysis result obtained by a network data analysis function in the core network element performing data analysis on specific values of the input data for the signaling storm. Historical statistical values may be statistical values corresponding to the input data for the signaling storm within a specific historical time period. Future predicted values may be predicted values corresponding to the input data for the signaling storm within a specified future time period.

[0051] refer to Figure 2 , Figure 2The overall flow chart for analyzing and predicting a signaling storm according to an exemplary embodiment of the present disclosure is schematically shown. In step S210, the consumer network element (consumer NF) 210 can subscribe to analysis related to the signaling storm. The analysis related to the signaling storm can be an analysis of abnormal user behavior in the network, or an analysis of abnormal network behavior; abnormal user behavior can be a large number of user registration behaviors in a short period of time; abnormal network behavior can include network equipment damage, network parameter configuration errors, etc. The generated signaling storm subscription message is sent to the core network element, such as the core network element can be a network data analysis network element (Network Data Analytics Function, NWDAF) 220. After receiving the signaling storm subscription message, the network data analysis network element 220 obtains the input data of the signaling storm from the network entity 230, and the network entity 230 can return the specific value of the input data to the network data analysis network element 220.

[0052] Furthermore, the network data analysis network element 220 can use a data analysis model to analyze the specific values of the input data to obtain a signaling storm analysis result. Specifically, at least one of the historical statistical value and the future predicted value corresponding to the input data of the signaling storm is used as the signaling storm analysis result. The historical statistical value includes the specific values of each input data item within a certain time period in the past, which can reflect the occurrence of the signaling storm within this time period. The future predicted value includes the predicted value of each input data item within a specified time period in the future, which is used to determine whether a signaling storm will occur within the specified time period in the future. The above analysis results can be used to analyze and predict the signaling storm.

[0053] The signaling storm analysis and prediction method of this example embodiment leverages the core network's data analysis capabilities to address signaling storms, enabling analysis and prediction of signaling storm-related network issues. This helps locate the cause and location of anomalies based on historical statistics. Furthermore, by providing a signaling storm prediction solution, signaling storms can be prevented before they occur, avoiding uncontrollable signaling bursts in the network and improving the resilience and robustness of the communication network.

[0054] The following further describes the signaling storm analysis and prediction method in this exemplary embodiment.

[0055] In an exemplary embodiment of the present disclosure, for step S110, obtaining input data of the signaling storm from the network entity includes: obtaining input data from the access and mobility management network element as the first input data; and obtaining input data from the unified data management network element as the second input data.

[0056] Continue to refer Figure 2 After receiving the signaling storm subscription message, NWDAF can obtain the input data of the signaling storm from the network entity 230, where the network entity can be a physical device that performs specific tasks in a computer network. In this embodiment, the network entity can include at least one of the access and mobility management network element (Access and Mobility Management Function, AMF) 231 and the unified data management network element (Unified Data Management, UDM) 232.

[0057] according to Figure 2 It can be seen that in step S220, NWDAF collects input data related to the signaling storm from the access and mobility management network element 231, and uses the input data collected from the AMF as the first input data. In step S230, NWDAF collects input data related to the signaling storm from the unified data management network element 232, and uses the input data collected from the UDM as the second input data. The first input data and the second input data are both data related to the registration type signaling storm. The input data of the signaling storm can be at least one of the first input data and the second input data. By obtaining the input data of the signaling storm from different network entities, the data basis for analyzing the signaling storm is clarified.

[0058] This embodiment is described using the analysis and prediction scenario of a registration-type signaling storm as an example. It is easy for those skilled in the art to understand that the present disclosure can also be used for the analysis and prediction process of other types of signaling storms. The present disclosure does not impose any special limitation on the specific type of signaling storm.

[0059] In an exemplary embodiment of the present disclosure, the first input data includes one or more of the number of initial registration requests, the number of initial registration successes, the success rate of initial registration requests, and the number of initial registration failures.

[0060] For the analysis and prediction process of registration signaling storms, the first input data collected from the AMF includes at least one of the following: the number of initial registration requests, which can be the number of registration request (REGISTRATION REQUEST) messages sent by the user terminal (User Equipment, UE) received by the AMF, where the value of "5GS registration type" can be "initial registration".

[0061] The number of initial registration successes can be the number of registration complete (REGISTRATION COMPLETE) messages received by the AMF from the UE during the initial registration process. The initial registration request success rate can be determined based on the number of initial registration successes and the number of initial registration requests. The specific calculation method is: initial registration request success rate = number of initial registration successes / number of initial registration requests * 100%. The number of initial registration failures can be the number of registration reject (EGISTRATION REJECT) messages sent by the AMF to the UE during the initial registration process. The above input data are all input data related to the signaling storm collected by NWDAF from AMF, which clarifies the data source of the first input data.

[0062] In an exemplary embodiment of the present disclosure, the number of initial registration failures includes the number of registration failures based on network element classification and the number of registration failures based on illegal types.

[0063] The number of initial registration failures can be further divided into the following two types according to different classification standards: the number of registration failures based on network element classification and the number of registration failures based on illegal types.

[0064] If the AMF can count the reasons for registration rejection, it can continue to count the number of times according to the network element reasons, including: (1) Number of mobility registration failures caused by UE: counted when the initial registration process fails, the failure reason is UE; (2) Number of mobility registration failures caused by AMF: counted when the initial registration fails, the failure reason is AMF; (3) Number of mobility registration failures caused by Authentication Server Function (AUSF): counted when the initial registration fails, the failure reason is AUSF; (4) Number of mobility registration failures caused by UDM: counted when the initial registration fails, the failure reason is UDM;

[0065] And (5) the number of mobility registration failures caused by the Network Slice Selection Function (NSSF); (6) the number of mobility registration failures caused by the Service Discovery Function (NRF); (7) the number of mobility registration failures caused by the User Policy Control Function (PCF); (8) the number of mobility registration failures caused by the Equipment Identity Register (EIR).

[0066] If the AMF can count the reasons for registration rejection, it can continue to count the number of times according to the illegal type of reasons, including: (1) the number of initial registration failures caused by illegal users: during the initial registration process, the AMF sends a registration rejection message to the UE, where the reason for the registration failure is an illegal user; (2) the number of initial registration failures caused by illegal devices: during the initial registration process, the AMF sends a registration rejection message to the UE, where the reason for the registration failure is an illegal device. Based on the above classification criteria, the different types of data contained in the input data of the number of initial registration failures are clarified.

[0067] In an exemplary embodiment of the present disclosure, the second input data includes one or more of the number of active users, the number of subscribed users, the number of authentication service requests, the number of successful responses to authentication service requests, the number of context management service requests, the success rate of context management service requests, the number of data management service requests, and the success rate of data management service requests.

[0068] The second input data collected from the UDM includes at least one of the following: the number of active users can be the number of active users in the communication network. Active users refer to users who use the communication network and bring some value to the communication network platform. Active users are a concept relative to "churned users."

[0069] The number of subscribed users can be the number of all subscribed users in the communication network, and the number of users who are currently subscribed to a specified service (such as a 5G service). The number of subscribed users specifically includes: the number of AMF mobile management subscribed data users (AM-Data subscribed users) can be the number of 5G access and mobility subscribed users, and the number of users who are currently subscribed to 5G services. The number of SMF session management subscribed data users (SM-Data subscribed users) can be the number of 5G session management subscribed users, and the number of users who are currently subscribed to session data. The number of activated users of the 3rd Generation Partnership Project (3GPP) can be the number of all currently registered users accessed through 3GPP. The number of registered users of the Session Management Function (SMF) can be the number of all currently registered SMF users. The number of SMF registered sessions can be the number of all currently registered sessions of the SMF.

[0070] The number of AUSF authentication service requests may be the total number of authentication service messages sent by the AUSF to the UDM. The number of AUSF authentication service requests may be the sum of at least one of the following messages. Furthermore, at least one of the following information may be counted separately: the number of times the AUSF requests authentication data from the UDM by calling the Nudm_UEAuthentication_Getservice operation. The number of times the AUSF provides authentication results to the UDM by calling the Nudm_UEAuthentication_ResultConfirmation service operation.

[0071] The number of successful responses to AUSF authentication service requests can be the number of successful responses after the UDM receives the above message from the AUSF. The number of failed responses to AUSF authentication service requests can be the number of failed responses after the UDM receives the above message from the AUSF. The AUSF authentication service request success rate is calculated as follows: Request message success rate = number of successful response messages / total number of request messages * 100%.

[0072] The number of UDM context management service requests may be the total number of context management service-related messages sent by a network function (NF) to a UDM or received by a UDM. The number of UDM context management service requests may be the sum of at least one of the following messages. Furthermore, at least one of the following information may also be counted separately:

[0073] Number of times the NF registers the NF serving the UE or PDU Session with the UDM by calling the Nudm_UECM_Registration service operation. Number of times the UDM notifies the NF of the deregistration message by calling the Nudm_UECM_DeregistrationNotification service operation. Number of times the NF requests the UDM to delete the information related to the NF in the UE context by calling the Nudm_UECM_Deregistration service operation.

[0074] Number of times the NF obtained information such as the NF ID from the UDM by calling the Nudm_UECM_Get service operation. Number of times the NF updated UE-related information by calling the Nudm_UECM_Update service operation. Number of times the UDM notified the NF of the need for P-CSCF restoration by calling the Nudm_UECM_PCscfRestoration service operation. Number of times the NF obtained SMS roaming information from the UDM by calling the Nudm_UECM_SendRoutingInfoForSM service operation.

[0075] The number of successful responses to UDM context management service requests can be the number of successful responses received by the UDM after the NF sends the aforementioned message. The number of failed responses to UDM context management service requests can be the number of failed responses received by the UDM after the NF sends the aforementioned message. The UDM context management service request success rate is calculated as follows: Request message success rate = number of successful response messages / total number of request messages * 100%.

[0076] The number of data management service requests is the total number of data management service-related messages sent by the NF to the UDM or received by the UDM. The number of data management service requests is the sum of at least one of the following messages. Furthermore, at least one of the following information can also be counted separately:

[0077] The number of times the NF obtained the contract data from the UDM by calling the Get service operation (Nudm_SDM_Get service operation). The number of times the UDM notified the NF of contract data updates by calling the Notification service operation (Nudm_SDM_Notification service operation). The number of times the NF subscribed to contract data updates from the UDM by calling the Subscribe service operation (Nudm_SDM_Subscribe service operation). The number of times the NF unsubscribed from contract data updates from the UDM by calling the Unsubscribe service operation (Nudm_SDM_Unsubscribe service operation). The number of times the NF provided the UDM with status information about the subscription data management process by calling the Info service operation (Nudm_SDM_Info service operation). The number of times the NF requested the UDM to modify an existing subscription to data change notifications by calling the Modify Subscription service operation (Nudm_SDM_ModifySubscription service operation).

[0078] The number of successful data management service request responses is the number of successful responses received by the UDM from the NF. The number of failed data management service request responses is the number of failed responses received by the UDM from the NF. The data management service request success rate is calculated as follows: Request message success rate = number of successful response messages / total number of request messages * 100%.

[0079] Furthermore, if the consumer NF includes information such as the analysis report target, analysis filter information, and locations of interest in the request information, the NWDAF collects data from the AMF and / or UDM as required, for example, the number of initial registration requests and / or the number of active users within the specified area of the location of interest. The above input data are all input data related to signaling storms collected by the NWDAF from the UDM, clarifying the data source of the second input data.

[0080] Continue to refer Figure 2 After the NWDAF requests the network entity 230 to obtain the input data of the signaling storm, in step S240, the AMF returns the relevant data of the signaling storm, that is, the specific value of the first input data. In step S250, the UDM returns the relevant data of the signaling storm, that is, the specific value of the second input data.

[0081] In an exemplary embodiment of the present disclosure, for step S110, data analysis is performed on the input data to obtain a signaling storm analysis result, including: obtaining a data analysis model; using the data analysis model to perform data analysis on the input data to obtain a signaling storm analysis result; historical statistical values are used to reflect the occurrence of signaling storms in a specified time period in the past, and future prediction values are used to determine the prediction results of signaling storms in a specified time period in the future.

[0082] Continue to refer Figure 2 In step S260, NWDAF analyzes the data collected from AMF and / or UDM. For example, a data analysis model is obtained, the input data of the signaling storm is input into the data analysis model, and the input data is analyzed using the data analysis model to obtain a signaling storm analysis result. The data analysis model can be a model directly obtained from other network elements, or a model obtained by training based on the specific numerical values of the input data of the signaling storm. The signaling storm analysis result includes the historical statistical value or future prediction value of at least one of the following information, specifically including:

[0083] Number of initial registration requests; number of initial registration successes; initial registration request success rate; number of initial registration failures; number of mobility registration failures caused by UE; number of mobility registration failures caused by AMF; number of mobility registration failures caused by AUSF; number of mobility registration failures caused by UDM; number of mobility registration failures caused by NSSF; number of mobility registration failures caused by NRF; number of mobility registration failures caused by PCF; number of mobility registration failures caused by EIR. Number of initial registration failures caused by unauthorized users; number of initial registration failures caused by unauthorized devices.

[0084] Number of active users; number of subscribed users; number of AM-Data subscribed users; number of SM-Data subscribed users; number of 3GPP activated users; number of SMF registered users; number of SMF registration sessions; number of AUSF authentication service requests; number of times AUSF calls the Nudm_UEAuthentication_Get service operation; number of times AUSF calls the Nudm_UEAuthentication_ResultConfirmation service operation; number of successful responses to AUSF authentication service requests; number of failed responses to AUSF authentication service requests; success rate of AUSF authentication service requests.

[0085] Number of UDM context management service requests; number of times the NF calls the Nudm_UECM_Registration service operation; number of times the UDM calls the Nudm_UECM_DeregistrationNotification service operation; number of times the NF calls the Nudm_UECM_Deregistration service operation; number of times the NF calls the Nudm_UECM_Get service operation; number of times the NF calls the Nudm_UECM_Update service operation; number of times the UDM calls the Nudm_UECM_PCscfRestoration service operation; number of times the NF calls the Nudm_UECM_SendRoutingInfoForSM service operation; number of successful responses to UDM context management service requests; number of failed responses to UDM context management service requests; success rate of UDM context management service requests.

[0086] Number of data management service requests; number of times the NF calls the Nudm_SDM_Get service operation; number of times the UDM calls the Nudm_SDM_Notification service operation; number of times the NF calls the Nudm_SDM_Subscribeservice operation; number of times the NF calls the Nudm_SDM_Unsubscribe service operation; number of times the NF calls the Nudm_SDM_Info service operation; number of times the NF calls the Nudm_SDM_ModifySubscriptionservice operation; number of successful responses to data management service requests; number of failed responses to data management service requests; success rate of data management service requests.

[0087] Based on the specific values of the above input data, the confidence level, applicable time period, and applicable location can also be determined. The confidence level can be used to indicate the credibility of the prediction result. The confidence level is only provided when it is higher than the analysis accuracy preferred in the request message. The applicable time period refers to the time period to which the above result applies. The applicable time period may be a historical time period in the past, in which case the calculation result is a statistical result; it may also be a time period in the future, in which case the calculation result is a prediction result. The applicable location is the geographical location to which the above result applies, such as the tracking area TAI(s) or cell ID(s). It can also be expressed in the form of a regional area or other forms.

[0088] The intelligent network element (NWDAF) analyzes historical statistical values of signaling storm input data and infers predictions for future signaling storms, helping other network elements make better decisions and providing a basis for signaling storm prevention. Furthermore, analysis of historical statistical values can help locate the cause and location of anomalies that trigger signaling storms.

[0089] In an exemplary embodiment of the present disclosure, the signaling storm analysis result is sent to a consumer network element.

[0090] Continue to refer Figure 2 In step S270, the NWDAF returns the obtained signaling storm analysis result to the consumer network element 210, so that the consumer network element 210 can take corresponding measures according to the specific signaling storm analysis result to prevent the occurrence of the signaling storm.

[0091] Next, in this exemplary embodiment, a signaling storm analysis and prediction method for a consumer network element is also provided. The signaling storm analysis and prediction method of the present disclosure can be implemented using a server, or using a terminal device. Figure 3 The following schematically illustrates a flow chart of a signaling storm analysis and prediction method according to some embodiments of the present disclosure. Figure 3 The signaling storm analysis and prediction method may include the following steps:

[0092] Step S310: Send subscription information related to the signaling storm to the core network element, and receive the signaling storm analysis result returned by the core network element based on the subscription information related to the signaling storm. The signaling storm analysis result includes at least one of the historical statistical value and future prediction value of the input data of the signaling storm. The signaling storm analysis result is used as reference information for the consumer network element to perform signaling storm prevention and / or mitigation operations.

[0093] According to some exemplary embodiments of the present disclosure, a consumer network element sends subscription information related to a signaling storm to a core network element. The core network element may be an NWDAF. For example, the Consumer NF subscribes to or requests data analysis related to the signaling storm from the NWDAF. After receiving the subscription information related to the signaling storm, the NWDAF may obtain input data of the signaling storm from network entities (such as the AMF and the UDM) according to the subscription information related to the signaling storm. The AMF and the UDM return specific values of the input data to the NWDAF, and the NWDAF performs data analysis on the specific values of the input data to obtain a signaling storm analysis result.

[0094] Specifically, the signaling storm analysis results may include at least one of the historical statistical values and future predicted values of the input data of the signaling storm. The historical statistical values can be used to describe the relevant data indicators of the signaling storm within a specific historical time period, and the historical statistical values of the input data can assist in locating the abnormal cause and location of the signaling storm. NWDAF analyzes and processes the historical statistical values to infer future predicted values, and determines the predicted results of future signaling storm events based on the future predicted values, thereby formulating specific preventive measures for possible signaling storms in the future based on the predicted results, so as to perform corresponding signaling storm prevention and / or mitigation operations according to the specific circumstances.

[0095] According to the signaling storm-related analysis and prediction method in this example embodiment, the consumer network element can obtain the signaling storm analysis results based on the subscription information related to the signaling storm, and can infer the possible future signaling storm risks based on the future prediction values in the signaling storm analysis results, thereby assisting other network elements to make signaling storm prevention decisions to prevent signaling storms in advance.

[0096] The following further describes the signaling storm analysis and prediction method in this exemplary embodiment.

[0097] In an exemplary embodiment of the present disclosure, the subscription information related to the signaling storm includes one or more of an analysis identifier, an analysis report target, a preferred analysis accuracy, analysis filter information, an interested location, a reporting threshold, and a time window.

[0098] Continue to refer Figure 2 In step S210, the Consumer NF sends subscription information related to the signaling storm to the NWDAF. The Consumer NF may be a PCF, AMF, or other core network element. The subscription information related to the signaling storm provided by the Consumer NF may include at least one of the following information, specifically:

[0099] One or more Analytics IDs. An Analytics ID can be an Analytics ID related to a signaling storm. An Analytics ID can be used to identify abnormal user and network behavior. For example, the Analytics ID can be a brand new Analytics ID related to a signaling storm, or it can be a subscription to one or more existing Analytics IDs related to a signaling storm. If there are multiple Analytics IDs, the following information must be provided separately for each Analytics ID:

[0100] Target of Analytics Reporting: indicates the object for which the analysis information is requested, for example, a specified group of UEs, one or several specific UEs, all UEs, etc.

[0101] The preferred level of accuracy of the analytics is used to indicate the required accuracy of the analysis report. For example, the preferred analysis accuracy can be configured as "Low", "Medium", "High" or "Highest". Analytics Filter Information is used to filter the specified information. The area of interest (AoI) is used to specify the location range of the analysis, such as TAI(s), cell ID(s), or it can be expressed in the form of a geographical area or other forms. The reporting threshold is used to indicate that NWDAF reports the output results when the specified conditions are met. The specified conditions include at least one of the joint judgment conditions and the single judgment conditions.

[0102] The time window is used to indicate the time period for which analysis data is desired. This time period may be in the past or in the future, and may be expressed in the form of Coordinated Universal Time (UTC) time, a period after the send time, or other time formats. The above content defines the specific content of the subscription information related to signaling storms, so that the core network element can return the signaling storm analysis results based on the subscription information related to signaling storms.

[0103] In an exemplary embodiment of the present disclosure, pre-configured determination conditions are obtained, and the determination conditions include joint determination conditions and / or single determination conditions; the prediction result of the signaling storm is determined based on the joint determination conditions and future prediction values; and / or the prediction result of the signaling storm is determined based on the single determination conditions and future prediction values.

[0104] A joint judgment condition can be one in which several values in the signaling storm analysis results simultaneously exceed or fall below a specified threshold, thereby predicting whether a signaling storm is likely to occur in the future. A single judgment condition can be one in which a value in the signaling storm analysis results exceeds or falls below a specified threshold, thereby predicting whether a signaling storm is likely to occur in the future.

[0105] After receiving the signaling storm analysis results, the consumer NF can determine whether a signaling storm is likely to occur in the future based on the future predicted values in the analysis results and according to pre-configured judgment conditions. Specifically, the judgment conditions include joint judgment conditions and / or individual judgment conditions. When the judgment condition is a joint judgment condition, it is necessary to simultaneously determine the relationship between several values in the analysis results and their corresponding specified thresholds to obtain a signaling storm prediction result. When the judgment condition is a individual judgment condition, the relationship between a specific value in the analysis results and its corresponding specified threshold is compared to obtain a signaling storm prediction result. The signaling storm prediction result can be determined based solely on the joint judgment condition, the individual judgment condition, or a combination of the joint judgment condition and the individual judgment condition.

[0106] By comparing multiple values in the analysis results with their corresponding specified thresholds at the same time according to the judgment conditions, or comparing a certain value with the specified threshold, it is possible to analyze and obtain a prediction result on whether a signaling storm will occur in the future, so as to prevent the occurrence of signaling storms in advance.

[0107] In an exemplary embodiment of the present disclosure, the prediction result includes the probability of occurrence of a signaling storm within a specified future time period, or a unique result of whether a signaling storm occurs within a specified future time period.

[0108] Based on the judgment conditions, the future prediction value is inferred and predicted to obtain the prediction result of the signaling storm, and the prediction result can be output in different forms. After the data analysis model analyzes and processes the future prediction value, it can output the probability value of the signaling storm occurring in the specified time period in the future. For example, the data analysis model outputs that the probability of the occurrence of the signaling storm is 75%. In another embodiment, the data analysis model can also output a unique result of whether the signaling storm will occur in the specified time period in the future. For example, the prediction result output by the data analysis model can be: 0 (indicating that it will occur soon), 1 (indicating that it will not occur). The prediction result can be expressed in different output forms so that the consumer network element can perform corresponding operations based on the prediction result.

[0109] In an exemplary embodiment of the present disclosure, a prediction result of a signaling storm is determined based on a joint judgment condition and a future prediction value, including one or more of the following: when the predicted value of the number of initial registration requests is greater than the request number threshold and the initial registration request success rate is less than the registration success rate threshold, the prediction result is that a signaling storm will occur within a specified time period in the future; when the predicted value of the number of authentication service requests is greater than the authentication request number threshold and the predicted value of the number of active users is less than the user number threshold, the prediction result is that a signaling storm will occur within a specified time period in the future; when the predicted value of the number of context management service requests is greater than the context management service request threshold and the predicted value of the number of active users is less than the user number threshold, the prediction result is that a signaling storm will occur within a specified time period in the future; when the predicted value of the number of data management service requests is greater than the data management service request threshold and the predicted value of the number of active users is less than the user number threshold, the prediction result is that a signaling storm will occur within a specified time period in the future.

[0110] The consumer NF provides a method for determining the prediction result of whether a signaling storm occurs based on joint judgment conditions, as shown in Table 1.

[0111] Table 1

[0112]

[0113] The above content provides a prediction result of whether a signaling storm will occur in the future according to the joint determination condition, so that corresponding signaling storm prevention or mitigation operations can be taken according to the prediction result.

[0114] In an exemplary embodiment of the present disclosure, a prediction result of a signaling storm is determined based on a single determination condition and a future prediction value, including: numerically comparing the future prediction value of any input data with a matching threshold value to obtain a prediction result.

[0115] For the specific values of each input data item output in the signaling storm analysis results, a single judgment condition can be used to determine whether a signaling storm will occur in the future. Specifically, the predicted future value of any input data item output in the analysis results is compared with the corresponding specified threshold. If any future predicted value is greater than or less than the corresponding specified threshold, a signaling storm is predicted to occur in the future. This single judgment condition provides an implementation solution for predicting the occurrence of a signaling storm based on a single indicator.

[0116] In an exemplary embodiment of the present disclosure, the configuration method of the threshold includes one or more of the following methods: configuring an adaptive threshold based on the analysis results and in accordance with time information and / or location information; configuring a fixed threshold based on the analysis results; configuring a fixed threshold or an adaptive threshold based on the internal logic of the consumer network element; and configuring the threshold by the communication operator.

[0117] The specified thresholds involved in the judgment conditions can be set in at least one of the following ways: (1) the consumer network element (consumer NF) configures an adaptive threshold according to time and / or location based on the analysis results provided by the NWDAF; (2) the consumer NF configures a fixed threshold based on the analysis results provided by the NWDAF; (3) the consumer NF configures a fixed or adaptive threshold based on its own internal logic; and the communication operator configures the threshold.

[0118] Configuring the specified threshold in the judgment condition according to the actual application scenario can improve the flexibility of signaling storm prediction. The threshold can also be adjusted in time according to the change of the scenario to improve the accuracy of the signaling storm prediction result.

[0119] In an exemplary embodiment of the present disclosure, the signaling storm prevention and / or mitigation operation includes one or more of the following operations: rejecting new user registration requests; extending the duration of the backoff timer; and adjusting access and mobility management policies.

[0120] When the consumer NF determines that a signaling storm is likely to occur in the future, it may take at least one of the following actions: (1) The AMF rejects the registration information from the new UE. (2) The AMF sets a longer back-off timer. (3) The PCF adjusts the AM policy. The above signaling storm prevention and / or mitigation actions can prevent registration-related signaling storms and avoid the adverse effects of signaling storms.

[0121] In summary, the signaling storm analysis and prediction method disclosed herein enables the consumer network element to determine whether a signaling storm may occur in the future based on the signaling storm analysis results, and then adopt corresponding prevention and / or mitigation operations, thereby assisting the network in preventing and mitigating signaling storms.

[0122] It should be noted that although the steps of the method of the present invention are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in this specific order, or that all steps must be performed to achieve the desired results. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0123] In addition, in this exemplary embodiment, a signaling storm related analysis and prediction device is also provided. Figure 4 The signaling storm-related analysis and prediction device 400 may include: a first analysis and prediction module 410.

[0124] Specifically, the first analysis and prediction module 410 is used to obtain input data of the signaling storm from the network entity based on the received subscription information related to the signaling storm, perform data analysis on the input data, and obtain a signaling storm analysis result, which includes at least one of the historical statistical value and future prediction value of the input data.

[0125] In an exemplary embodiment of the present disclosure, the network entity includes an access and mobility management network element and / or a unified data management network element, and the first analysis and prediction module 410 includes an input data acquisition unit, which is used to: use the input data obtained from the access and mobility management network element as the first input data; and use the input data obtained from the unified data management network element as the second input data.

[0126] In an exemplary embodiment of the present disclosure, the first analysis and prediction module 410 includes a first analysis and prediction unit, which is used to: obtain a data analysis model; use the data analysis model to perform data analysis on the input data to obtain a signaling storm analysis result; historical statistical values are used to reflect the occurrence of signaling storms in a specified time period in the past, and future prediction values are used to determine the prediction results of signaling storms in a specified time period in the future.

[0127] In an exemplary embodiment of the present disclosure, the signaling storm-related analysis and prediction device 400 further includes a result sending module, which is configured to send the signaling storm analysis result to a consumer network element.

[0128] Furthermore, in this exemplary embodiment, a signaling storm related analysis and prediction device is also provided. Figure 5The signaling storm-related analysis and prediction device 500 may include: a second analysis and prediction module 510.

[0129] Among them, the second analysis and prediction module 510 is used to send subscription information related to signaling storms to the core network network element, and receive signaling storm analysis results returned by the core network element based on the subscription information related to signaling storms. The signaling storm analysis results include at least one of the historical statistical values and future prediction values of the input data of the signaling storm. The signaling storm analysis results are used as reference information for the consumer network element to perform signaling storm prevention and / or mitigation operations.

[0130] In an exemplary embodiment of the present disclosure, the signaling storm-related analysis and prediction device 500 also includes a prediction result determination module, which is used to: obtain pre-configured judgment conditions, the judgment conditions include joint judgment conditions and / or single judgment conditions; determine the prediction result of the signaling storm based on the joint judgment conditions and future prediction values; and / or determine the prediction result of the signaling storm based on the single judgment conditions and future prediction values.

[0131] In an exemplary embodiment of the present disclosure, the prediction result determination module 510 includes a first prediction result determination unit, which is used to: when the predicted value of the number of initial registration requests is greater than the request number threshold and the initial registration request success rate is less than the registration success rate threshold, the prediction result is that a signaling storm will occur in a specified time period in the future; when the predicted value of the number of authentication service requests is greater than the authentication request number threshold and the predicted value of the number of active users is less than the user number threshold, the prediction result is that a signaling storm will occur in a specified time period in the future; when the predicted value of the number of context management service requests is greater than the context management service request threshold and the predicted value of the number of active users is less than the user number threshold, the prediction result is that a signaling storm will occur in a specified time period in the future; when the predicted value of the number of data management service requests is greater than the data management service request threshold and the predicted value of the number of active users is less than the user number threshold, the prediction result is that a signaling storm will occur in a specified time period in the future.

[0132] In an exemplary embodiment of the present disclosure, the prediction result determination module 510 includes a second prediction result determination unit, which is used to compare the future prediction value of any input data with the matching threshold value to obtain the prediction result.

[0133] The specific details of the virtual modules of the above-mentioned signaling storm-related analysis and prediction devices have been described in detail in the corresponding signaling storm-related analysis and prediction methods, and will not be repeated here.

[0134] It should be noted that although several modules or units of the signaling storm-related analysis and prediction device are mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0135] In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0136] Those skilled in the art will appreciate that various aspects of the present invention may be implemented as systems, methods, or program products. Accordingly, various aspects of the present invention may be implemented as a complete hardware embodiment, a complete software embodiment (including firmware, microcode, etc.), or a combination of hardware and software embodiments, which may be collectively referred to herein as "circuits," "modules," or "systems."

[0137] Reference below Figure 6 6 to describe the electronic device 600 according to such an embodiment of the present disclosure. Figure 6 The electronic device 600 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0138] like Figure 6 As shown, electronic device 600 is implemented as a general-purpose computing device. Components of electronic device 600 may include, but are not limited to, the aforementioned at least one processing unit 610, the aforementioned at least one storage unit 620, a bus 630 connecting various system components (including storage unit 620 and processing unit 610), and a display unit 640.

[0139] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 performs the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification.

[0140] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 621 and / or a cache memory unit 622 , and may further include a read-only memory unit (ROM) 623 .

[0141] The storage unit 620 may include a program / utility 624 having a set (at least one) of program modules 625, such program modules 625 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0142] Bus 630 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0143] The electronic device 600 can also communicate with one or more external devices 670 (e.g., a keyboard, a pointing device, a Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 600, and / or any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., a router, a modem, etc.). Such communication can occur via an input / output (I / O) interface 650. Furthermore, the electronic device 600 can communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 660. As shown, the network adapter 660 communicates with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 600, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0144] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0145] In exemplary embodiments of the present disclosure, a computer-readable storage medium is also provided, storing a program product capable of implementing the aforementioned methods of this specification. In some possible embodiments, various aspects of the present invention may also be implemented in the form of a program product comprising program code. When the program product is executed on a terminal device, the program code is configured to cause the terminal device to perform the steps according to various exemplary embodiments of the present invention described in the "Exemplary Methods" section of this specification.

[0146] refer to Figure 7 As shown, a program product 700 for implementing the above method according to an embodiment of the present invention is described. The program product 700 may be a portable compact disk read-only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0147] The program product may be implemented in any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0148] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0149] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0150] The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, and the like, as well as conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0151] Furthermore, the above-described figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention and are not intended to be limiting. It is readily understood that the processes illustrated in the above-described figures do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0152] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow from the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the claims.

[0153] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A signaling storm related analysis and prediction method, characterized in that: Applied to a core network element, the method includes: Based on the received subscription information related to the signaling storm, input data of the signaling storm is obtained from the network entity, and data analysis is performed on the input data to obtain a signaling storm analysis result, wherein the signaling storm analysis result includes at least one of a historical statistical value and a future prediction value of the input data.

2. The method according to claim 1, characterized in that The network entity includes an access and mobility management network element and / or a unified data management network element, and the acquiring of input data of the signaling storm from the network entity includes: using the input data obtained from the access and mobility management network element as first input data; The input data obtained from the unified data management network element is used as the second input data.

3. The method according to claim 2, characterized in that The first input data includes one or more of the number of initial registration requests, the number of initial registration successes, the success rate of initial registration requests, and the number of initial registration failures.

4. The method according to claim 3, characterized in that The number of initial registration failures includes the number of registration failures based on network element classification and the number of registration failures based on illegal types.

5. The method according to claim 2, characterized in that The second input data includes one or more of the number of active users, the number of subscribed users, the number of authentication service requests, the number of successful responses to authentication service requests, the number of context management service requests, the success rate of context management service requests, the number of data management service requests, and the success rate of data management service requests.

6. The method according to claim 1, characterized in that The performing data analysis on the input data to obtain a signaling storm analysis result includes: Obtain data analysis models; The data analysis model is used to perform data analysis on the input data to obtain the signaling storm analysis result; the historical statistical value is used to reflect the occurrence of signaling storms in the past specified time period, and the future prediction value is used to determine the prediction result of signaling storms in the future specified time period.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: The signaling storm analysis result is sent to the consumer network element.

8. A signaling storm related analysis and prediction method, characterized in that: Applied to a consumer network element, the method includes: Send subscription information related to signaling storm to the core network network element, receive the signaling storm analysis result returned by the core network network element based on the subscription information related to the signaling storm, the signaling storm analysis result includes at least one of the historical statistical value and future prediction value of the input data of the signaling storm, and the signaling storm analysis result is used as reference information for the consumer network element to perform signaling storm prevention and / or mitigation operations.

9. The method according to claim 8, characterized in that The subscription information related to the signaling storm includes one or more of an analysis identifier, an analysis report target, a preferred analysis accuracy, analysis filter information, an interested location, a reporting threshold, and a time window.

10. The method according to claim 8, characterized in that The method further comprises: Acquiring pre-configured determination conditions, wherein the determination conditions include joint determination conditions and / or individual determination conditions; determining a prediction result of the signaling storm according to the joint determination condition and the future prediction value; and / or The prediction result of the signaling storm is determined according to the single determination condition and the future prediction value.

11. The method according to claim 10, characterized in that Determining the prediction result of the signaling storm according to the joint determination condition and the future prediction value includes one or more of the following: When the predicted value of the number of initial registration requests is greater than the request number threshold and the initial registration request success rate is less than the registration success rate threshold, the prediction result is that a signaling storm will occur in the specified future time period; When the predicted value of the number of authentication service requests is greater than the authentication request number threshold and the predicted value of the number of active users is less than the user number threshold, the prediction result is that a signaling storm will occur in a specified future time period; When the predicted value of the number of context management service requests is greater than the context management service request threshold and the predicted value of the number of active users is less than the user number threshold, the prediction result is that a signaling storm will occur within a specified future time period; When the predicted value of the number of data management service requests is greater than the data management service request threshold and the predicted value of the number of active users is less than the user number threshold, the prediction result is that a signaling storm will occur in a specified future time period.

12. The method according to claim 10, characterized in that The determining, according to the single determination condition and the future prediction value, a prediction result of the signaling storm includes: The future predicted value of any one of the input data is numerically compared with the matching threshold value to obtain the predicted result.

13. The method according to any one of claims 10 to 12, characterized in that: The prediction result includes the probability of occurrence of a signaling storm in a future specified time period, or a unique result of whether a signaling storm occurs in a future specified time period.

14. The method according to claim 10, characterized in that The determination condition includes a threshold value, which includes an adaptive threshold value and a fixed threshold value. The configuration method of the threshold value includes one or more of the following methods: configuring the adaptive threshold according to the analysis result and in accordance with time information and / or location information; configuring the fixed threshold according to the analysis result; configuring the fixed threshold or the adaptive threshold according to the internal logic of the consumer network element; as well as The threshold is configured by the communication operator.

15. The method according to claim 8, characterized in that The signaling storm prevention and / or mitigation operations include one or more of the following operations: Reject new user registration requests; Extend the backoff timer; and Adjust access and mobility management policies.

16. A signaling storm related analysis and prediction device, characterized in that: Applied to a core network element, the device includes: The first analysis and prediction module is used to obtain input data of the signaling storm from the network entity based on the received subscription information related to the signaling storm, perform data analysis on the input data, and obtain a signaling storm analysis result, wherein the signaling storm analysis result includes at least one of a historical statistical value and a future prediction value of the input data.

17. A signaling storm related analysis and prediction device, characterized in that: Applied to a consumer network element, the device includes: The second analysis and prediction module is used to send subscription information related to signaling storms to the core network network element, and receive signaling storm analysis results returned by the core network element based on the subscription information related to the signaling storm, wherein the signaling storm analysis results include at least one of historical statistical values and future prediction values of the input data of the signaling storm, and the signaling storm analysis results are used as reference information for the consumer network element to perform signaling storm prevention and / or mitigation operations.

18. An electronic device, characterized in that: include: processor; as well as A memory having computer-readable instructions stored thereon, wherein the computer-readable instructions, when executed by the processor, implement the signaling storm-related analysis and prediction method according to any one of claims 1 to 15.

19. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the signaling storm-related analysis and prediction method according to any one of claims 1 to 15 is implemented.

20. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the signaling storm-related analysis and prediction method according to any one of claims 1 to 15 is implemented.

Images