A method, device, equipment and storage medium for pre-deploying an application

Abstract

The embodiments of the present invention provide a method, device, equipment and storage medium for pre-deployment of an application, and relate to the field of wireless communication technology. The specific implementation scheme is: determining the service requests received by the Near‑RT RIC within a specified historical time period; wherein each service request is processed by calling an xAPP in each third-party application xAPP; based on the determined service requests, determining the calling frequency of each xAPP within the specified historical time period; based on the calling frequency of each xAPP within the specified historical time period, predicting the calling probability corresponding to each xAPP at the target moment; selecting at least one xAPP to be deployed from each xAPP according to the calling probability corresponding to each xAPP at the target moment; and deploying the selected xAPP to be deployed in the Near‑RT RIC. It can be seen that through this scheme, the hit rate of service requests can be improved, thereby reducing the communication overhead of service processing.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technology, and in particular to a pre-deployment method, device, equipment and storage medium for an application. Background Art

[0002] The O-RAN (Open Radio Access Network) organization proposed RIC (Radio intelligent controller) for RAN (Access Network) virtualization. RIC includes Non-RT RIC (Non-Real-Time Radio intelligent controller) and Near-RT RIC (Near-Real-Time Radio intelligent controller). Among them, Non-RT RIC is deployed on nodes with rich computing power, and the node where Non-RT RIC is located can pre-store the installation files of various xAPPs (third-party independently deployed applications), among which xAPP can be embedded with AI (Artificial Intelligence) models for implementing specified services; Near-RT RIC is deployed on nodes with limited computing power, and Near-RT RIC is responsible for processing services with high latency requirements.

[0003] In order to ensure the real-time performance of service processing, xAPP can be pre-deployed in the Near-RT RIC, so that the deployed xAPP can be used to respond to service requests from terminals.

[0004] However, due to the limited storage space in the Near-RT RIC, the number of xAPPs that can be pre-deployed in the Near-RT RIC is limited. Then, when the Near-RT RIC receives a service request, if the xAPP required to process the service request is not pre-deployed in the Near-RT RIC, the service request does not hit, and it is necessary to respond to the service request through other distributed Near-RT RICs or Non-RT RICs, resulting in a large communication overhead.

[0005] Therefore, how to reasonably pre-deploy xAPP in Near-RT RIC to improve the hit rate of business requests and thus reduce the communication overhead of business processing has become a technical problem that needs to be solved urgently. Summary of the invention

[0006] The purpose of the embodiment of the present invention is to provide an application deployment method to improve the hit rate of service requests, thereby reducing the communication overhead of service processing. The specific technical solution is as follows:

[0007] In a first aspect, an embodiment of the present invention provides a pre-deployment method for an application, which is applied to a near real-time intelligent controller Near-RT RIC, and the method includes:

[0008] Determine the service requests received by the Near-RT RIC within a specified historical time period; wherein each service request is processed by calling an xAPP among the third-party applications xAPP;

[0009] Based on the determined business requests, determining the calling frequency of each xAPP within the specified historical time period;

[0010] Based on the calling frequency of each xAPP in the specified historical time period, predict the calling probability corresponding to each xAPP at the target time; wherein the target time is the time when the calling of each xAPP in the Near-RT RIC is in a steady-state distribution;

[0011] According to the call probabilities corresponding to the xAPPs at the target time, at least one xAPP to be deployed is selected from the xAPPs; wherein the call probability corresponding to each xAPP to be deployed is higher than the call probability corresponding to other xAPPs except the at least one xAPP to be deployed;

[0012] In the Near-RT RIC, the selected xAPP to be deployed is deployed.

[0013] Optionally, determining the calling frequency of each xAPP in the specified historical time period based on the determined service request includes:

[0014] For each xAPP in each xAPP, count the number of business requests processed by calling the xAPP among the determined business requests, and calculate the ratio of the counted number to the total number of determined business requests as the calling frequency of the xAPP in the specified historical time period.

[0015] Optionally, the predicting the call probability corresponding to each xAPP at the target time based on the call frequency of each xAPP in the specified historical time period includes:

[0016] Using the calling frequency of each xAPP in the specified historical time period, construct a state set for each xAPP; wherein the state set is a set formed after sorting each xAPP according to the calling frequency;

[0017] Based on the state set and the calling frequency of each xAPP, a state transition matrix for each xAPP is constructed; wherein each element in the state transition matrix represents the state transition probability of each xAPP;

[0018] Based on the state transfer matrix, the steady-state probability distribution of each xAPP at the target time is calculated to obtain the call probability corresponding to each xAPP at the target time.

[0019] Optionally, constructing a state transition matrix for each xAPP based on the state set and the calling frequency of each xAPP includes:

[0020] For each element in the state set, using the calling frequency of each xAPP, when a service request occurs based on the state set, the corresponding state transition probability when the element is transferred to each sorting position in the state set is calculated as the state transition probability corresponding to the element;

[0021] A state transfer matrix is ​​constructed based on the state transfer probability corresponding to each element.

[0022] Optionally, the step of calculating the steady-state probability distribution of each xAPP at the target time based on the state transfer matrix to obtain the call probability corresponding to each xAPP at the target time includes:

[0023] The CK equation of the Markov chain is used to calculate the steady-state probability distribution corresponding to the state transfer matrix at the target time, and the call probability corresponding to each xAPP at the target time is obtained.

[0024] Optionally, selecting at least one xAPP to be deployed from each xAPP according to the call probability corresponding to each xAPP at the target time includes:

[0025] Based on the local storage space, determine the number of local xAPPs to be deployed as the specified number;

[0026] According to the call probability corresponding to each xAPP at the target time, a specified number of xAPPs to be deployed are selected from each xAPP.

[0027] In a second aspect, an embodiment of the present invention provides a pre-deployment device for an application, which is applied to a near real-time intelligent controller Near-RT RIC, and the device includes:

[0028] A first determination module is used to determine the service requests received by the Near-RT RIC within a specified historical time period; wherein each service request is processed by calling an xAPP among the third-party applications xAPP;

[0029] A second determination module is used to determine the calling frequency of each xAPP in the specified historical time period based on the determined business request;

[0030] A prediction module, configured to predict the call probability corresponding to each xAPP at a target time based on the call frequency of each xAPP in the specified historical time period; wherein the target time is a time when the calls for each xAPP in the Near-RT RIC are in a steady-state distribution;

[0031] A selection module, configured to select at least one xAPP to be deployed from each xAPP according to the call probability corresponding to each xAPP at the target time; wherein the call probability corresponding to each xAPP to be deployed is higher than the call probability corresponding to other xAPPs except the at least one xAPP to be deployed;

[0032] A deployment module is used to deploy the selected xAPP to be deployed in the Near-RT RIC.

[0033] Optionally, the second determining module is specifically configured to:

[0034] For each xAPP in each xAPP, count the number of business requests processed by calling the xAPP among the determined business requests, and calculate the ratio of the counted number to the total number of determined business requests as the calling frequency of the xAPP in the specified historical time period.

[0035] Optionally, the prediction module includes:

[0036] A first construction submodule is used to construct a state set for each xAPP by using the call frequency of each xAPP in the specified historical time period; wherein the state set is a set formed by sorting each xAPP according to the call frequency;

[0037] The second construction submodule is used to construct a state transition matrix for each xAPP based on the state set and the calling frequency of each xAPP; wherein each element in the state transition matrix represents the state transition probability of each xAPP;

[0038] The calculation submodule is used to calculate the steady-state probability distribution of each xAPP at the target time based on the state transfer matrix, and obtain the call probability corresponding to each xAPP at the target time.

[0039] Optionally, the second construction submodule is specifically used to:

[0040] For each element in the state set, using the calling frequency of each xAPP, when a service request occurs based on the state set, the corresponding state transition probability when the element is transferred to each sorting position in the state set is calculated as the state transition probability corresponding to the element;

[0041] A state transfer matrix is ​​constructed based on the state transfer probability corresponding to each element.

[0042] Optionally, the computing submodule is specifically used to:

[0043] The CK equation of the Markov chain is used to calculate the steady-state probability distribution corresponding to the state transfer matrix at the target time, and the call probability corresponding to each xAPP at the target time is obtained.

[0044] Optionally, the selection module is specifically used to:

[0045] Based on the local storage space, determine the number of local xAPPs to be deployed as the specified number;

[0046] According to the call probability corresponding to each xAPP at the target time, a specified number of xAPPs to be deployed are selected from each xAPP.

[0047] In a third aspect, an embodiment of the present invention provides an electronic device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0048] Memory, used to store computer programs;

[0049] The processor is used to implement any of the steps of the above-mentioned application pre-deployment method when executing the program stored in the memory.

[0050] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any of the above-mentioned application pre-deployment methods are implemented.

[0051] Beneficial effects of the embodiments of the present invention:

[0052] The application pre-deployment method provided by the embodiment of the present invention determines the calling frequency of each xAPP being called in the specified historical time period based on the service requests received by the Near-RT RIC in the specified historical time period, and predicts the calling probability of each xAPP at the target time based on the calling frequency, so as to select at least one xAPP to be deployed from each xAPP for deployment using the calling probability corresponding to each xAPP at the target time. Since the calling probability corresponding to each xAPP at the target time is the calling probability when the calling of each xAPP is in a steady-state distribution, the calling probability corresponding to each xAPP can be used to select a suitable xAPP for deployment. And when selecting the xAPP to be deployed, the calling probability of the selected xAPP to be deployed is higher than the calling probability corresponding to other xAPPs that have not been selected. By deploying the xAPP with a high calling probability in the Near-RT RIC, the Near-RT RIC can hit more service requests, thereby improving the responsiveness of service requests. It can be seen that through this solution, the hit rate of service requests can be improved, thereby reducing the communication overhead of service processing.

[0053] Of course, it is not necessary to achieve all of the advantages described above at the same time to implement any product or method of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can also be obtained based on these drawings.

[0055] Figure 1 A flowchart of a method for pre-deploying an application provided by an embodiment of the present invention;

[0056] Figure 2 A flowchart for implementing step S103 provided in an embodiment of the present invention;

[0057] Figure 3 A flowchart for implementing step S104 provided in an embodiment of the present invention;

[0058] Figure 4 A timing diagram of a specific example of a method for pre-deploying an application provided in an embodiment of the present invention;

[0059] Figure 5 A schematic diagram of the structure of a pre-deployment device for an application provided in an embodiment of the present invention;

[0060] Figure 6A block diagram of an electronic device for implementing the application pre-deployment method provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field based on this application belong to the scope of protection of the present invention.

[0062] With the deepening of cloud-network integration, core network functional units have gradually begun to cloudify, and research on general-purpose equipment replacing dedicated network equipment is also progressing steadily. Facing the needs of future network business diversification, endogenous design, and open ecology, network intelligence is an important network evolution route.

[0063] The O-RAN organization proposed an intelligent controller RIC for RAN virtualization, in which RIC includes Non-RT RIC and Near-RT RIC. Non-RT RIC and Near-RT RIC adopt a distributed architecture when deployed, that is, a Non-RT RIC can be connected to one or more Near-RT RICs, and Non-RT RIC can send the trained AI model to Near-RT RIC.

[0064] In order to ensure the real-time processing of services, xAPPs for processing related service requests can be pre-deployed in Near-RTRIC, so that when Near-RT RIC receives a service request, it can use xAPPs to quickly complete the processing of the service request. However, due to the limited storage space in Near-RT RIC, the number of xAPPs that can be pre-deployed in Near-RT RIC is limited. Then, when Near-RT RIC receives a service request, if the xAPP required to process the service request is not pre-deployed in Near-RT RIC, the service request will not be hit, and it will be necessary to respond to the service request through other distributed Near-RT RICs or Non-RT RICs, resulting in a large communication overhead.

[0065] Based on the above content, in order to improve the hit rate of service requests and thus reduce the communication overhead of service processing, the embodiments of the present invention provide a method, apparatus, device and storage medium for pre-deploying an application.

[0066] Below, firstly, a pre-deployment method for an application provided by an embodiment of the present invention is introduced.

[0067] An application pre-deployment method provided in an embodiment of the present invention is applied to a Near-RT RIC. The Near-RTRIC can be deployed in a server, a virtual machine or a container. The Near-RT RIC is used to process services with high latency requirements. It can obtain an installation file for deploying xAPP from a Non-RT RIC and deploy it locally.

[0068] The pre-deployment method of an application provided in an embodiment of the present invention may include the following steps:

[0069] Determine the service requests received by the Near-RT RIC within a specified historical time period; wherein each service request is processed by calling an xAPP among the third-party applications xAPP;

[0070] Based on the determined business requests, determining the calling frequency of each xAPP within the specified historical time period;

[0071] Based on the calling frequency of each xAPP in the specified historical time period, predict the calling probability corresponding to each xAPP at the target time; wherein the target time is the time when the calling of each xAPP in the Near-RT RIC is in a steady-state distribution;

[0072] According to the call probabilities corresponding to the xAPPs at the target time, at least one xAPP to be deployed is selected from the xAPPs; wherein the call probability corresponding to each xAPP to be deployed is higher than the call probability corresponding to other xAPPs except the at least one xAPP to be deployed;

[0073] In the Near-RT RIC, the selected xAPP to be deployed is deployed.

[0074] The solution provided by the embodiment of the present invention determines the calling frequency of each xAPP being called in the specified historical time period based on the service requests received by the Near-RT RIC in the specified historical time period, and predicts the calling probability of each xAPP at the target time based on the calling frequency, so as to select at least one xAPP to be deployed from each xAPP for deployment using the calling probability corresponding to each xAPP at the target time. Since the calling probability corresponding to each xAPP at the target time is the calling probability when the calling of each xAPP is in a steady-state distribution, the calling probability corresponding to each xAPP can be used to select a suitable xAPP for deployment. And when selecting the xAPP to be deployed, the calling probability of the selected xAPP to be deployed is higher than the calling probability corresponding to other xAPPs that have not been selected. By deploying the xAPP with a high calling probability in the Near-RT RIC, the Near-RT RIC can hit more service requests, thereby improving the responsiveness of service requests. It can be seen that through this solution, the hit rate of service requests can be improved, thereby reducing the communication overhead of service processing.

[0075] The following describes the application pre-deployment method provided by the embodiment of the present invention in conjunction with the accompanying drawings.

[0076] like Figure 1 As shown, the application pre-deployment method provided in the embodiment of the present invention is applied to Near-RT RIC and may include steps S101-S105:

[0077] S101, determining the service requests received by the Near-RT RIC within a specified historical time period; wherein each service request is processed by calling an xAPP among various third-party applications xAPP;

[0078] It is understandable that since the Near-RT RIC is responsible for processing services with high latency requirements, and the Near-RT RIC uses its deployed xAPP to process service requests, different types of service requests are processed using different xAPPs. If the xAPP required for a service request is not deployed in the Near-RT RIC, the Near-RT RIC does not hit the service request, resulting in the Near-RT RIC needing to respond to the service request through other distributed Near-RT RICs or Non-RT RICs, resulting in a large communication overhead.

[0079] In order to improve the hit rate of service requests, in this embodiment, by analyzing the service requests received by the Near-RT RIC in the historical time period, the call probability of each xAPP at the target time is predicted, so that the xAPP with a higher call probability is deployed first, thereby improving the hit rate of service requests and reducing the communication overhead of service processing. Therefore, in this embodiment, the service requests received by the Near-RT RIC in the specified historical time period are first determined. Among them, the type of the service request can be a voice service, a video service, a web browsing service, etc., and the embodiment of the present invention does not limit this; the specified historical time period can be a historical time period of any time length, for example, the specified historical time period can be a time period of one week before the current time, or a time period of one month before the current time, etc.; and the third-party application xAPPs can be xAPPs with installation files pre-stored in the node where the Non-RT RIC is located, and at least one of the xAPPs can be deployed in the Near-RT RIC in the specified historical time period.

[0080] In addition, it can be understood that, since each xAPP is embedded with an AI model for implementing a specified service, each service request can be processed by the xAPP embedded with the AI ​​model for implementing the corresponding service. For example, if xAPP1 is embedded with an AI model for implementing a voice service, a service request of the voice service type can be processed by calling xAPP1; if xAPP2 is embedded with an AI model for implementing a video service, a service request of the video service type can be processed by calling xAPP2.

[0081] Furthermore, it should be noted that, within the specified historical time period, at least one xAPP that has been deployed in the Near-RT RIC may be randomly deployed in order to achieve pre-deployment of the application; of course, the pre-deployment process for the application may be a periodic process, in which case the specified historical time period may include the historical period, and at this time, the at least one xAPP that has been deployed in the Near-RT RIC may include the xAPP deployed within the historical period.

[0082] S102, determining the calling frequency of each xAPP in the specified historical time period based on the determined business request;

[0083] In this embodiment, since each service request is processed by the xAPP corresponding to the service request and embedded with the AI ​​model for implementing the corresponding service, after determining the service requests received by the Near-RTRIC in the specified historical time period through step S101, the xAPP required to be called for each service request in the specified time period can be obtained by analyzing the service requests received by the Near-RT RIC in the specified historical time period, thereby calculating the calling frequency of each xAPP in the specified historical time period. Among them, for each service request, the method of identifying the xAPP required to be called for the service request is not limited in the embodiment of the present invention. For example, each service request carries an application identifier of the xAPP required to be called, so that the xAPP required to be called for each service request can be known, but it is certainly not limited to this.

[0084] Optionally, in an implementation, determining the calling frequency of each xAPP in the specified historical time period based on the determined service request may include:

[0085] For each xAPP in each xAPP, count the number of business requests processed by calling the xAPP among the determined business requests, and calculate the ratio of the counted number to the total number of determined business requests as the calling frequency of the xAPP in the specified historical time period.

[0086] In this implementation, for the local Near-RT RIC, by counting the calling frequencies of each xAPP in a specified historical time period and analyzing the calling conditions of each xAPP, the xAPP is reasonably pre-deployed for the local Near-RT RIC.

[0087] For example, if the Near-RT RIC receives 100 voice service requests and 300 video service requests within a specified historical time period, and the third-party application used to process the voice service is xAPP1, and the third-party application used to process the video service is xAPP2, then the calling frequency of xAPP1 within the specified historical time period is 0.25, and the calling frequency of xAPP2 is 0.75.

[0088] S103, based on the calling frequency of each xAPP in the specified historical time period, predicting the calling probability corresponding to each xAPP at a target time; wherein the target time is a time when the calling of each xAPP in the Near-RT RIC is in a steady-state distribution;

[0089] In this embodiment, after determining the call frequency of each xAPP in the specified historical time period through step S102, in order to improve the hit rate of business requests, the call situation of each xAPP in the future time period can be estimated based on the call frequency of each xAPP in the specified historical time period, and in order to ensure the stability of the hit rate of business requests, the steady-state distribution of the calls for each xAPP can be estimated. Specifically, the Near-RT RIC can predict the call probability corresponding to each xAPP at the target time based on the call frequency of each xAPP in the specified historical time period, thereby realizing the estimation of the call situation and ensuring the stability of the hit rate of business requests.

[0090] It is understandable that there are multiple ways to predict the call probability corresponding to each xAPP at the target time. For example, the Near-RT RIC can use the call frequency of each xAPP to construct a state set for each xAPP; then, use the state set to construct the state transfer matrix of each xAPP at the initial time, and use the Markov chain to solve the steady-state distribution probability of each xAPP, that is, the call probability of each xAPP at the time when the call is in a steady-state distribution, so as to obtain the call probability corresponding to each xAPP at the target time. It should be noted that for the sake of clarity, the process of predicting the call probability corresponding to each xAPP at the target time based on the call frequency of each xAPP in the specified historical time period will be introduced below, and will not be repeated here.

[0091] S104, selecting at least one xAPP to be deployed from each xAPP according to the call probability corresponding to each xAPP at the target time; wherein the call probability corresponding to each xAPP to be deployed is higher than the call probability corresponding to other xAPPs except the at least one xAPP to be deployed;

[0092] In this embodiment, after obtaining the call probabilities corresponding to each xAPP at the target time in step S103, at least one xAPP can be selected from each xAPP as the xAPP to be deployed according to the call probabilities corresponding to each xAPP. It can be understood that in order to improve the hit rate of business requests, when selecting the at least one xAPP to be deployed, the call probability corresponding to each xAPP to be deployed is higher than the call probability corresponding to other xAPPs except the at least one xAPP to be deployed. Exemplarily, the method of selecting the at least one xAPP to be deployed can be to select the first several xAPPs as the xAPPs to be deployed according to the order of the call probabilities corresponding to each xAPP from high to low.

[0093] S105: deploy the selected xAPP to be deployed in the Near-RT RIC.

[0094] In this embodiment, the node where the Non-RT RIC is located may pre-store installation files embedded with various xAPPs (third-party independently deployed applications), and each xAPP is embedded with an AI model for implementing a specified business. After selecting at least one xAPP to be deployed through step S104, the Near-RT RIC may send a request for the installation file of the xAPP to be deployed to the Non-RT RIC, so that after receiving the request, the Non-RT RIC sends the installation file of the xAPP to be deployed to the node where the Near-RT RIC is located. After receiving the installation file of the xAPP to be deployed, the node where the Near-RT RIC is located installs it to complete the pre-deployment of the xAPP. It can be understood that after the xAPP to be deployed is deployed, since the pre-deployed xAPP is an xAPP with a higher probability of being called, the pre-deployed xAPP can respond to more business requests, thereby improving the hit rate of business requests, thereby reducing the communication overhead of business processing.

[0095] The solution provided by the embodiment of the present invention determines the calling frequency of each xAPP being called in the specified historical time period based on the service requests received by the Near-RT RIC in the specified historical time period, and predicts the calling probability of each xAPP at the target time based on the calling frequency, so as to select at least one xAPP to be deployed from each xAPP for deployment using the calling probability corresponding to each xAPP at the target time. Since the calling probability corresponding to each xAPP at the target time is the calling probability when the calling of each xAPP is in a steady-state distribution, the calling probability corresponding to each xAPP can be used to select a suitable xAPP for deployment. And when selecting the xAPP to be deployed, the calling probability of the selected xAPP to be deployed is higher than the calling probability corresponding to other xAPPs that have not been selected. By deploying the xAPP with a high calling probability in the Near-RT RIC, the Near-RT RIC can hit more service requests, thereby improving the responsiveness of service requests. It can be seen that through this solution, the hit rate of service requests can be improved, thereby reducing the communication overhead of service processing.

[0096] Alternatively, in another embodiment of the present invention, Figure 2 As shown, in the above step S103, based on the calling frequency of each xAPP in the specified historical time period, predicting the calling probability corresponding to each xAPP at the target time may include steps S1031-S1033:

[0097] S1031, constructing a state set for each xAPP by using the call frequency of each xAPP in the specified historical time period; wherein the state set is a set formed by sorting each xAPP according to the call frequency;

[0098] In this implementation, the state set for each xAPP is constructed according to the order of the calling frequency of each xAPP in the specified historical time period from high to low. For example, if the calling frequency of xAPP1 in the specified historical time period is 0.2, the calling frequency of xAPP2 is 0.5, and the calling frequency of xAPP3 is 0.3, then the constructed state set is {xAPP2, xAPP3, xAPP1}.

[0099] S1032, constructing a state transition matrix for each xAPP based on the state set and the calling frequency of each xAPP; wherein each element in the state transition matrix represents the state transition probability of each xAPP;

[0100] It can be understood that, since the state set is constructed using the call frequency of each xAPP in the specified historical time period, based on the state set and the call frequency of each xAPP, a state transition matrix at the initial moment can be constructed, and each element in the state transition matrix represents the state transition probability of each xAPP. Among them, the initial moment can be the moment when a service request occurs for the first time based on the state set. Exemplarily, if the state set is {xAPP2, XAPP3, xAPP1}, the calling frequency of xAPP1 is 0.2, the calling frequency of xAPP2 is 0.5, and the calling frequency of xAPP3 is 0.3, then if xAPP1 is called at the initial moment, the position ranking of xAPP1 in the set is promoted to the first place. Since the calling frequency of xAPP1 is 0.2, at this time, the state transition probability of xAPP1 transferring from position 3 to position 1 is 0.2, that is, at the initial moment there is a probability of 0.2 that xAPP1 transfers from position 3 to position 1; if xAPP2 or xAPP3 is called at the initial moment, the position ranking of xAPP1 in the set is still the last place, and the probability that the position of xAPP1 remains unchanged is the sum of the calling frequencies of all xAPPs ranked before xAPP1, that is, the sum of the calling probability of xAPP2 and the calling frequency of xAPP3 in this state set, which is 0.8.

[0101] Exemplarily, in a specific implementation, based on the state set and the calling frequency of each xAPP, constructing a state transition matrix for each xAPP may include steps A1-A2:

[0102] A1, for each element in the state set, using the calling frequency of each xAPP, calculate the corresponding state transition probability when the element is transferred to each sorting position in the state set when a service request occurs based on the state set, as the state transition probability corresponding to the element;

[0103] In this implementation, each element in the state set is a xAPP sorted from high to low according to the calling frequency. If an xAPP is called at a certain moment, the ranking position of the xAPP in the state set is promoted to the first place; if the xAPP located before the position of the xAPP in the state set is called, the ranking position of the xAPP in the state set remains unchanged; if the xAPP located after the position of the xAPP in the state set is called, the ranking position of the xAPP in the state set is moved back by one place. Since the calling frequency of each element in the state set is calculated using the number of calls of the xAPP in the specified historical time period, the calling frequency of each xAPP can be used to calculate the state transition probability of each element at the initial moment, and the probability of each element transferring to the first ranking position in the state set at the initial moment is the calling frequency of the element. For example, if the calling frequency of xAPP1 is 0.2, the calling frequency of xAPP2 is 0.5, and the calling frequency of xAPP3 is 0.3, then at the initial moment, the probability of xAPP1 transferring to the first sorted position in the state set is 0.2, the probability of xAPP2 transferring to the first sorted position in the state set is 0.5, and the probability of xAPP3 transferring to the first sorted position in the state set is 0.3.

[0104] In addition, it can be understood that, for any element other than the first sorting position in the state set, if any xAPP sorted before the element is called at the initial moment, the sorting position of the element in the state set sorted by the call frequency of each xAPP at the initial moment remains unchanged, so the probability that the sorting position of the element remains unchanged is the sum of the call frequencies of all xAPPs sorted before the element. For any element other than the last sorting position in the state set, if any xAPP sorted after the element is called at the initial moment, the sorting position of the element in the state set sorted by the call frequency of each xAPP at the initial moment moves back by one position, so the probability that the sorting position of the element at the initial moment moves back by one position is the sum of the call frequencies of all xAPPs sorted after the element.

[0105] A2, constructing a state transfer matrix based on the state transfer probability corresponding to each element.

[0106] After calculating the state transition probability corresponding to each element in the state set, we can construct a state transition matrix with row dimensions representing each xAPP and column dimensions representing the probability of the xAPP transferring to each sorted position in the state set. For example, if the call frequency of xAPP1 is 0.6, the call frequency of xAPP2 is 0.3, and the call frequency of xAPP3 is 0.1, then the state set is {xAPP1, xAPP2, xAPP3}. The state transition matrix Among them, P 11 represents the probability that xAPP1 remains unchanged in the state set, P 12 represents the probability that xAPP1 moves from the first position to the second position in the state set, P 21 represents the probability that xAPP2 is promoted to the first position in the state set, P 22 Characterizes the probability that xAPP2 remains unchanged in the state set, P 23 represents the probability that xAPP2 moves down one position in the state set, P 31 represents the probability that xAPP3 is promoted to the first position in the state set, P 33 Characterizes the probability that xAPP3 moves down one position in the state set.

[0107] S1033, based on the state transfer matrix, calculating the steady-state probability distribution of each xAPP at the target time, and obtaining the call probability corresponding to each xAPP at the target time.

[0108] It can be understood that after the initial state transition matrix is ​​constructed through step S1032, as time goes by, the sorting position of each xAPP in the state set continues to change, and the state transition probability of each xAPP continues to change, and finally the state transition probability of each xAPP will tend to be stable. At this time, the steady-state probability distribution of each xAPP can be obtained, that is, the call probability corresponding to each xAPP at the target time.

[0109] Exemplarily, in a specific implementation, based on the state transfer matrix, the steady-state probability distribution of each xAPP at the target time is calculated to obtain the call probability corresponding to each xAPP at the target time, including:

[0110] The CK equation of the Markov chain is used to calculate the steady-state probability distribution corresponding to the state transfer matrix at the target time, and the call probability corresponding to each xAPP at the target time is obtained.

[0111] In this implementation, the traversability of the Markov chain is utilized. After n-step state transfer, the state transfer matrix has a limit distribution, that is, each element in the state transfer matrix has a steady-state probability distribution. By solving the CK equation, the steady-state probability distribution corresponding to the state transfer matrix at the target time can be obtained. It should be noted that the CK equation, also known as the Chapman-Kolmogorov equation, has the formula πP=π, where π is the steady-state probability distribution of each xAPP, P is the n-step state transfer matrix of xAPP, and n is a positive integer.

[0112] It can be seen that through this solution, the Markov chain is used to solve the steady-state distribution probability of each xAPP, that is, the call probability of each xAPP at the time when the call is in a steady-state distribution, and the call probability corresponding to each xAPP at the target time is obtained. Therefore, the call probability corresponding to each xAPP at the target time can be used to select at least one xAPP to be deployed from each xAPP for deployment, so as to improve the hit rate of service requests and reduce the communication overhead of service processing.

[0113] Alternatively, in another embodiment of the present invention, Figure 3 As shown, in the above step S104, according to the call probability corresponding to each xAPP at the target time, at least one xAPP to be deployed is selected from each xAPP, which may include steps S1041-S1042:

[0114] S1041, based on the local storage space, determining the number of local xAPPs to be deployed as the designated number;

[0115] In this embodiment, when selecting xAPPs to be deployed, the number of xAPPs to be deployed may be determined according to the local storage space, that is, the remaining local memory space.

[0116] S1042 , selecting a specified number of xAPPs to be deployed from each xAPP according to the call probability corresponding to each xAPP at the target time.

[0117] Exemplarily, if two xAPPs can be deployed in the local storage space, and it is determined that the specified number is 2, the first two xAPPs with the highest calling probability can be selected from the xAPPs as the xAPPs to be deployed.

[0118] It can be seen that through this solution, the xAPP in the Near-RT RIC can be reasonably deployed according to the size of the actual storage space in the Near-RT RIC, so as to maximize the use of the storage space of the Near-RT RIC to deploy the xAPP, thereby further improving the hit rate of the Near-RT RIC for business requests.

[0119] In order to better understand the content of the embodiments of the present invention, Figure 4 Specific examples of embodiments of the present invention are introduced.

[0120] The existing O-RAN organization's discussion on RIC is mostly considered from the perspective of interfaces and application scenarios, and there is little research on service scheduling related to Non-RT RIC and Near-RTRIC. From the perspective of saving resources, the embodiment of the present invention uses a discrete Markov chain to calculate the steady-state probability of xAPP demand for service scenarios, and sorts them according to the size of the steady-state probability, and pre-deploys the corresponding xAPP in the Near-RT RIC to improve the hit rate of service requests.

[0121] Figure 4 The timing diagram of a specific example of the pre-deployment method for implementing the application provided by the embodiment of the present invention is shown. This example takes the Near-RT RIC deployed on a certain node as an example to illustrate the pre-deployment process of the Non-RT RIC to the Near-RT RIC node. Figure 4 As shown, the following steps are included:

[0122] (1) Service request collection: Near-RT RIC collects service requests in a specified historical time period. Each service request is processed by calling one of the xAPPs. Based on the number of service requests, the frequency with which each xAPP is used in the time period is calculated, i.e., the calling frequency of the xAPP. The specific calculation process is as follows: Suppose the total number of service requests received by the Near-RT RIC in the specified historical time period is m, and a certain xAPP is called n times, then the calling frequency of the xAPP is P. 初始 =n / m.

[0123] (2) Constructing the initial probability distribution of xAPP: Constructing the initial probability distribution of each xAPP, that is, the state transfer matrix of each xAPP at the initial time, including steps B1-B2:

[0124] B1, according to the calculated calling frequencies of the xAPPs, sort the xAPPs from high to low according to the calling frequencies to form a state set C = {1, 2, 3, ..., t, t+1, ..., x}.

[0125] B2, construct the state transfer matrix P of each xAPP at the initial moment;

[0126] In the obtained state set ranking, if the xAPP at the tth position at the initial moment is called, the ranking of the xAPP at the tth position in the state set C at that moment is promoted to the first place. Therefore, the state of the xAPP at the tth position in the set C is: if the xAPP before the xAPP at the tth position is called at a certain moment, the state of the xAPP at the tth position is still at the tth position; if the xAPP behind the xAPP at the tth position is called, the xAPP behind is ranked first, and the state of the xAPP at the tth position is transferred to the t+1th position. Moreover, for the xAPP at the tth position in the set C, if the xAPP is called at a certain moment, the probability of being called is P t→1 =P 初始 , where P t→1 The state transition probability that represents the state of xAPP in set C changes from the tth position to the first position, P 初始 is the calling frequency of the xAPP in the specified historical time period. If the state of the xAPP in set C is transferred from the tth position to the t+1th position at a certain moment, the probability of the state shifting down is the sum of the calling frequencies of all xAPPs after the tth position in set C, then P t→t+1 =∑P s , s∈[t+1,x], where P t→t+1 The state transition probability of xAPP in set C from the tth position to the t+1th position, ∑P s is the sum of the calling frequencies of all xAPPs after the t-th position is called at the initial moment. If the state of the xAPP in set C at a certain moment is to maintain the t-th position from the t-th position, the probability that the state remains unchanged is the sum of the calling frequencies of all xAPPs before the t-th position in set C, P t→t =∑P s ,s∈[1,t-1], where P t→t The state transition probability of xAPP in set C from the tth position to the tth position, ∑P s It is the sum of the calling frequencies of all xAPPs before the t-th position is called at the initial moment.

[0127] In addition, for the first xAPP in the state set C, it has only two transition states: the order remains unchanged or moves down one position. For the last xAPP in the state set C, it also has only two transition states: the order is raised to the first position or remains unchanged. From the above analysis, it can be concluded that the state transition probability of the t-th xAPP in the set C can always satisfy P t→1 +P t→t +P t→t+1 =1.

[0128] After calculating the state transition probability of each xAPP, the state transition matrix P of each xAPP at the initial moment can be constructed.

[0129] The above process is described below in conjunction with a 5*5 state transfer matrix.

[0130]

[0131] Each row in the matrix represents each xAPP, and each element in each row represents the corresponding state transition probability when transferring to each sorted position in the state set. 23 It represents the probability that the state of xAPP currently located at the second position in the state set will be transferred to the third position in the state set. From the matrix, it can be seen that the first and last rows have only two non-zero elements, and the other rows have three non-zero elements. Taking the third row as an example, P31 = P 初始3 ; P33 = P 初始1 +P 初始2 , where P 初始1 is the calling frequency of xAPP1 in the specified historical time period, P 初始2 is the calling frequency of xAPP2 in the specified historical time period, P 初始3 The calling frequency of xAPP3 in the specified historical time period.

[0132] (3) Calculate the steady-state probability distribution of xAPP: Calculate the steady-state probability distribution of each xAPP according to the CK equation, that is, the call probability corresponding to each xAPP at the target time. That is, according to the formula πP=π, calculate the steady-state probability distribution π of each xAPP. The steady-state probability distribution π obtained by the formula πP=π is a one-dimensional matrix, and ∑π i =1, where i is the identifier of each xAPP.

[0133] (4) Determine the xAPP to be deployed based on the steady-state probability distribution and the storage space size: According to the steady-state probability distribution calculated in π and the remaining storage space in the node where the current Near-RT RIC is located, select a specified number of xAPPs whose steady-state probability distributions are sorted from high to low as the xAPPs to be deployed.

[0134] (5) Sending a request for the installation file of the xAPP to be deployed: The Near-RT RIC sends a request for the installation file of the xAPP to be deployed to the Non-RT RIC based on the selected xAPP to be deployed.

[0135] (6) Responding to the request sent by the Near-RT RIC: The Non-RT RIC responds to the request sent by the Near-RT RIC.

[0136] (7) Sending the image and configuration file of the xAPP to be deployed: The Non-RT RIC sends the image and configuration file of the xAPP to be deployed to the node where the Near-RT RIC is located according to the request. After receiving the image and configuration file of the xAPP to be deployed, the node where the Near-RT RIC is located installs the xAPP to complete the pre-deployment of the xAPP.

[0137] It can be seen that through this solution, the steady-state probability distribution of xAPP can be predicted based on the historical data of business requests, so that xAPP can be pre-deployed according to the actual storage space size of the node where Near-RT RIC is located and the size of the steady-state probability distribution, which makes up for the xAPP pre-deployment mechanism of the Near-RT RIC node, improves the hit rate of business requests, and thus reduces the communication overhead of business processing. In addition, the algorithm has low complexity, is easy to deploy, and can improve the business service rate.

[0138] Corresponding to the above method embodiment, the present invention also provides a pre-deployment device for application, which is applied to a near real-time intelligent controller Near-RT RIC, such as Figure 5 As shown, the device comprises:

[0139] A first determination module 510 is used to determine the service requests received by the Near-RT RIC within a specified historical time period; wherein each service request is processed by calling an xAPP among the third-party applications xAPP;

[0140] A second determination module 520 is used to determine the calling frequency of each xAPP in the specified historical time period based on the determined business request;

[0141] A prediction module 530 is used to predict the call probability corresponding to each xAPP at a target time based on the call frequency of each xAPP in the specified historical time period; wherein the target time is a time when the calls for each xAPP in the Near-RT RIC are in a steady-state distribution;

[0142] A selection module 540 is used to select at least one xAPP to be deployed from each xAPP according to the call probability corresponding to each xAPP at the target time; wherein the call probability corresponding to each xAPP to be deployed is higher than the call probability corresponding to other xAPPs except the at least one xAPP to be deployed;

[0143] The deployment module 550 is used to deploy the selected xAPP to be deployed in the Near-RT RIC.

[0144] Optionally, the second determining module is specifically configured to:

[0145] For each xAPP in each xAPP, count the number of business requests processed by calling the xAPP among the determined business requests, and calculate the ratio of the counted number to the total number of determined business requests as the calling frequency of the xAPP in the specified historical time period.

[0146] Optionally, the prediction module includes:

[0147] A first construction submodule is used to construct a state set for each xAPP by using the call frequency of each xAPP in the specified historical time period; wherein the state set is a set formed by sorting each xAPP according to the call frequency;

[0148] The second construction submodule is used to construct a state transition matrix for each xAPP based on the state set and the calling frequency of each xAPP; wherein each element in the state transition matrix represents the state transition probability of each xAPP;

[0149] The calculation submodule is used to calculate the steady-state probability distribution of each xAPP at the target time based on the state transfer matrix, and obtain the call probability corresponding to each xAPP at the target time.

[0150] Optionally, the second construction submodule is specifically used to:

[0151] For each element in the state set, using the calling frequency of each xAPP, when a service request occurs based on the state set, the corresponding state transition probability when the element is transferred to each sorting position in the state set is calculated as the state transition probability corresponding to the element;

[0152] A state transfer matrix is ​​constructed based on the state transfer probability corresponding to each element.

[0153] Optionally, the computing submodule is specifically used to:

[0154] The CK equation of the Markov chain is used to calculate the steady-state probability distribution corresponding to the state transfer matrix at the target time, and the call probability corresponding to each xAPP at the target time is obtained.

[0155] Optionally, the selection module is specifically used to:

[0156] Based on the local storage space, determine the number of local xAPPs to be deployed as the specified number;

[0157] According to the call probability corresponding to each xAPP at the target time, a specified number of xAPPs to be deployed are selected from each xAPP.

[0158] The embodiment of the present invention further provides an electronic device, such as Figure 6 As shown, it includes a processor 601, a communication interface 602, a memory 603 and a communication bus 604, wherein the processor 601, the communication interface 602, and the memory 603 communicate with each other through the communication bus 604.

[0159] Memory 603, used for storing computer programs;

[0160] The processor 601 is used to implement the steps of the application pre-deployment method described in any of the above embodiments when executing the program stored in the memory 603.

[0161] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0162] The communication interface is used for communication between the above electronic device and other devices.

[0163] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0164] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0165] In another embodiment provided by the present invention, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, the steps of the application pre-deployment method described in any of the above embodiments are implemented.

[0166] In another embodiment of the present invention, a computer program product including instructions is provided. When the computer program product is executed on a computer, the computer executes the application pre-deployment method described in any one of the above embodiments.

[0167] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

[0168] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0169] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0170] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A method for pre-deploying an application, characterized in that: Applied to a near real-time intelligent controller Near-RT RIC, the method comprises: Determine the service requests received by the Near-RT RIC within a specified historical time period; wherein each service request is processed by calling an xAPP among the third-party applications xAPP; Based on the determined business requests, determining the calling frequency of each xAPP within the specified historical time period; Based on the calling frequency of each xAPP in the specified historical time period, predict the calling probability corresponding to each xAPP at the target time; wherein the target time is the time when the calling of each xAPP in the Near-RT RIC is in a steady-state distribution; According to the call probabilities corresponding to the xAPPs at the target time, at least one xAPP to be deployed is selected from the xAPPs; wherein the call probability corresponding to each xAPP to be deployed is higher than the call probability corresponding to other xAPPs except the at least one xAPP to be deployed; In the Near-RT RIC, the selected xAPP to be deployed is deployed.

2. The method according to claim 1, characterized in that The determining, based on the determined service request, the calling frequency of each xAPP within the specified historical time period includes: For each xAPP in each xAPP, count the number of business requests processed by calling the xAPP among the determined business requests, and calculate the ratio of the counted number to the total number of determined business requests as the calling frequency of the xAPP in the specified historical time period.

3. The method according to claim 1, characterized in that The predicting the calling probability corresponding to each xAPP at the target time based on the calling frequency of each xAPP in the specified historical time period includes: Using the calling frequency of each xAPP in the specified historical time period, construct a state set for each xAPP; wherein the state set is a set formed after sorting each xAPP according to the calling frequency; Based on the state set and the calling frequency of each xAPP, a state transition matrix for each xAPP is constructed; wherein each element in the state transition matrix represents the state transition probability of each xAPP; Based on the state transfer matrix, the steady-state probability distribution of each xAPP at the target time is calculated to obtain the call probability corresponding to each xAPP at the target time.

4. The method according to claim 3, characterized in that The step of constructing a state transfer matrix for each xAPP based on the state set and the calling frequency of each xAPP includes: For each element in the state set, using the calling frequency of each xAPP, when a service request occurs based on the state set, the corresponding state transition probability when the element is transferred to each sorting position in the state set is calculated as the state transition probability corresponding to the element; A state transfer matrix is ​​constructed based on the state transfer probability corresponding to each element.

5. The method according to claim 3, characterized in that: The step of calculating the steady-state probability distribution of each xAPP at the target time based on the state transfer matrix to obtain the call probability corresponding to each xAPP at the target time includes: The CK equation of the Markov chain is used to calculate the steady-state probability distribution corresponding to the state transfer matrix at the target time, and the call probability corresponding to each xAPP at the target time is obtained.

6. The method according to any one of claims 1 to 5, characterized in that: The selecting at least one xAPP to be deployed from each xAPP according to the call probability corresponding to each xAPP at the target time includes: Based on the local storage space, determine the number of local xAPPs to be deployed as the specified number; According to the call probability corresponding to each xAPP at the target time, a specified number of xAPPs to be deployed are selected from each xAPP.

7. A pre-deployment device for an application, characterized in that: Applied to a near real-time intelligent controller Near-RT RIC, the device comprises: A first determination module is used to determine the service requests received by the Near-RT RIC within a specified historical time period; wherein each service request is processed by calling an xAPP among the third-party applications xAPP; A second determination module is used to determine the calling frequency of each xAPP in the specified historical time period based on the determined business request; A prediction module, configured to predict the call probability corresponding to each xAPP at a target time based on the call frequency of each xAPP in the specified historical time period; wherein the target time is a time when the calls for each xAPP in the Near-RT RIC are in a steady-state distribution; A selection module, configured to select at least one xAPP to be deployed from each xAPP according to the call probability corresponding to each xAPP at the target time; wherein the call probability corresponding to each xAPP to be deployed is higher than the call probability corresponding to other xAPPs except the at least one xAPP to be deployed; A deployment module is used to deploy the selected xAPP to be deployed in the Near-RT RIC.

8. The device according to claim 7, characterized in that The second determining module is specifically used to: For each xAPP in each xAPP, count the number of business requests processed by calling the xAPP among the determined business requests, and calculate the ratio of the counted number to the total number of determined business requests as the calling frequency of the xAPP in the specified historical time period.

9. The device according to claim 7, characterized in that The prediction module comprises: A first construction submodule is used to construct a state set for each xAPP by using the call frequency of each xAPP in the specified historical time period; wherein the state set is a set formed by sorting each xAPP according to the call frequency; The second construction submodule is used to construct a state transition matrix for each xAPP based on the state set and the calling frequency of each xAPP; wherein each element in the state transition matrix represents the state transition probability of each xAPP; The calculation submodule is used to calculate the steady-state probability distribution of each xAPP at the target time based on the state transfer matrix, and obtain the call probability corresponding to each xAPP at the target time.

10. The device according to claim 9, characterized in that The second construction submodule is specifically used for: For each element in the state set, using the calling frequency of each xAPP, when a service request occurs based on the state set, the corresponding state transition probability when the element is transferred to each sorting position in the state set is calculated as the state transition probability corresponding to the element; A state transfer matrix is ​​constructed based on the state transfer probability corresponding to each element.

11. The device according to claim 9, characterized in that The computing submodule is specifically used for: The CK equation of the Markov chain is used to calculate the steady-state probability distribution corresponding to the state transfer matrix at the target time, and the call probability corresponding to each xAPP at the target time is obtained.

12. The device according to any one of claims 7 to 11, characterized in that: The selection module is specifically used for: Based on the local storage space, determine the number of local xAPPs to be deployed as the specified number; According to the call probability corresponding to each xAPP at the target time, a specified number of xAPPs to be deployed are selected from each xAPP.

13. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, for implementing the method steps described in any one of claims 1 to 6 when executing a program stored in a memory.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in any one of claims 1 to 6 are implemented.

Images