Network service quality prediction method and apparatus, network element, and storage medium

Abstract

The application discloses a network service quality prediction method and device, a network element and a storage medium. The network service quality prediction method is applied to a Qos prediction function network element, and the method comprises the following steps: receiving a prediction request, wherein the prediction request comprises a QoS prediction index of a user terminal; performing prediction on the QoS prediction index based on the prediction request, so as to obtain a first prediction value of the QoS prediction index; and sending early warning information to a network management device based on the first prediction value.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, and in particular to a network service quality prediction method and device, a network element and a storage medium. BACKGROUND

[0002] A service level agreement (SLA) is a commitment agreement between a network service provider and an industry customer, which is used to explicitly define the related requirements of the industry customer on the service and network provided by the network service provider. In the related art, network SLA indicators are continuously monitored in the whole life cycle of a communication service. After an abnormal fluctuation of an SLA indicator occurs, root cause analysis is performed on the abnormal indicator, and the network is optimized and adjusted. The network adjustment and optimization in the related art is passive, and it is difficult to provide deterministic SLA indicator guarantee in the whole life cycle. SUMMARY

[0003] Therefore, the embodiments of the present application provide a network service quality prediction method and device, a network element and a storage medium, which can guarantee the network service quality of a user terminal.

[0004] The technical scheme of the embodiments of the present application is as follows:

[0005] In one aspect, the embodiments of the present application provide a network service quality prediction method applied to a QoS prediction function network element, which comprises the following steps.

[0006] Receiving a prediction request, wherein the prediction request comprises a QoS prediction indicator of a user terminal;

[0007] Based on the prediction request, predicting the QoS prediction indicator to obtain a first prediction value of the QoS prediction indicator;

[0008] Based on the first prediction value, sending early warning information to a network management device.

[0009] In the above scheme, the step of predicting the QoS prediction indicator based on the prediction request comprises the following steps.

[0010] Based on the QoS prediction indicator, determining the data required for prediction;

[0011] Based on the required data, sending a subscription request to a corresponding data source;

[0012] Based on the data sent by the data source based on the subscription request, predicting the QoS prediction indicator.

[0013] In the above scheme, after determining whether to send early warning information to the network management device based on the first prediction value, the method further comprises the following steps.

[0014] receiving the network parameter of the user terminal sent by the network management device after scheduling the network resource of the user terminal;

[0015] re-performing the prediction of the QoS prediction index based on the network parameter of the user terminal to obtain a second prediction value of the QoS prediction index;

[0016] if the second prediction value is not within a threshold range, sending the second prediction value to a sending end of the prediction request.

[0017] In the above scheme, the sending of the second prediction value to the sending end of the prediction request comprises:

[0018] sending the second prediction value to a preset QoS distribution function network element, and distributing the second prediction value to the sending end of the prediction request through the QoS distribution function network element.

[0019] In the above scheme, the determination of whether to send the early warning information to the network management device based on the first prediction value comprises:

[0020] if the first prediction value is not within a threshold range, sending the early warning information to the network management device.

[0021] On the other hand, an embodiment of the present application provides a network resource scheduling method applied to a network management device, which comprises:

[0022] receiving early warning information sent by a QoS prediction function network element; the early warning information comprises a first prediction value of a QoS prediction index of a user terminal by the QoS prediction function network element;

[0023] scheduling the network resource of the user terminal based on the first prediction value.

[0024] In the above scheme, after the scheduling of the network resource of the user terminal based on the first prediction value, the method further comprises:

[0025] sending the network parameter of the user terminal after the network resource scheduling to the QoS prediction function network element.

[0026] On the other hand, an embodiment of the present application provides a network resource scheduling method applied to a user terminal or an application server, which comprises:

[0027] applied to a user terminal or an application server, the method comprises:

[0028] sending a prediction request to a QoS prediction function network element; the prediction request comprises a QoS prediction index of the user terminal;

[0029] receiving a second predicted value of the QoS prediction index from the QoS prediction function network element;

[0030] adaptively adjusting current running service based on the second predicted value.

[0031] In another aspect, an embodiment of the present application provides a network service quality prediction device, which comprises:

[0032] a first receiving module configured to receive a prediction request, the prediction request comprising a QoS prediction index of a user terminal;

[0033] a prediction module configured to predict the QoS prediction index based on the prediction request, and obtain a first predicted value of the QoS prediction index;

[0034] a first sending module configured to send early warning information to a network management device based on the first predicted value.

[0035] In another aspect, an embodiment of the present application provides a network resource scheduling device, which comprises:

[0036] a second receiving module configured to receive early warning information sent by a QoS prediction function network element, the early warning information comprising a first predicted value of a QoS prediction index of a user terminal from the QoS prediction function network element;

[0037] a scheduling module configured to schedule network resources of the user terminal based on the first predicted value.

[0038] In another aspect, an embodiment of the present application provides a service adjustment device, which comprises:

[0039] a second sending module configured to send a prediction request to a QoS prediction function network element, the prediction request comprising a QoS prediction index of the user terminal;

[0040] a third receiving module configured to receive a second predicted value of the QoS prediction index from the QoS prediction function network element;

[0041] an adjustment module configured to adaptively adjust current running service based on the second predicted value.

[0042] In another aspect, an embodiment of the present application provides a network element, which comprises a processor and a memory, the processor and the memory are connected to each other, wherein the memory is configured to store a computer program, the computer program comprises program instructions, the processor is configured to invoke the program instructions to execute steps of a network service quality prediction method provided by an embodiment of the present application.

[0043] In another aspect, an embodiment of the present application provides a network management device, comprising a processor and a memory, which are connected to each other, wherein the memory is configured to store a computer program, the computer program comprises program instructions, and the processor is configured to invoke the program instructions to perform the steps of the network resource scheduling method provided by an embodiment of the present application.

[0044] In another aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory, which are connected to each other, wherein the memory is configured to store a computer program, the computer program comprises program instructions, and the processor is configured to invoke the program instructions to perform the steps of the service adjustment method provided by an embodiment of the present application.

[0045] In another aspect, an embodiment of the present application provides a computer readable storage medium, comprising: the computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the steps of the network service quality prediction method provided by an embodiment of the present application, or to implement the steps of the network resource scheduling method, or to implement the steps of the service adjustment method.

[0046] The QoS prediction function network element of the embodiment of the present application receives a prediction request, performs prediction of a QoS prediction index based on the prediction request, and obtains a first prediction value of the QoS prediction index. Whether to send early warning information to a network management device is determined based on the first prediction value, so that the network management device schedules network resources of a user terminal according to the first prediction value, and guarantees network SLA indexes of the user terminal. The embodiment of the present application predicts the network QoS of the user terminal, sends early warning information to the network management device based on the first prediction value, so that the network management device can proactively schedule the network resources of the user terminal in advance, and high-priority guarantee of the network SLA indexes of the user terminal is achieved through the pre-scheduling, and the network experience of the user is improved. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 FIG. 1 is a schematic diagram of an SLA guarantee system logical management architecture provided by an embodiment of the present application;

[0048] Figure 2 FIG. 2 is a schematic diagram of an implementation process of a network service quality prediction method provided by an embodiment of the present application;

[0049] Figure 3 FIG. 3 is a schematic diagram of an implementation process of a network resource scheduling method provided by an embodiment of the present application;

[0050] Figure 4 FIG. 4 is a schematic diagram of an implementation process of a service adjustment method provided by an embodiment of the present application;

[0051] Figure 5This is a schematic diagram of a network service quality prediction structure in a 5G system provided by an embodiment of the present invention;

[0052] Figure 6 This is a flowchart illustrating a method for ensuring network service quality for vehicle applications according to an embodiment of the present invention.

[0053] Figure 7 This is a schematic diagram of a network service quality prediction device provided in an embodiment of the present invention;

[0054] Figure 8 This is a schematic diagram of the network resource scheduling device provided in an embodiment of the present invention;

[0055] Figure 9 This is a schematic diagram of the service adjustment device provided in an embodiment of the present invention;

[0056] Figure 10 This is a schematic diagram of a network element provided in an embodiment of the present invention;

[0057] Figure 11 This is a schematic diagram of the network management device provided in an embodiment of the present invention;

[0058] Figure 12 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0059] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0060] A Service Provider Agreement (SLA) is a commitment agreement between a network service provider (ISP) and an industry customer. It clarifies the industry customer's service and network requirements from the ISP. SLA guarantees help address existing issues such as the inability to accurately match industry customer needs and the inability to guarantee network slicing effectiveness. They meet the precise and deterministic service or network requirements of industry customers throughout the entire lifecycle, providing deterministic SLA metric guarantees. SLA metrics include service SLA metrics and network SLA metrics. Service SLA metrics define user experience from the perspective of user services, such as video buffering and jitter. Network SLA metrics primarily consider network-level parameters, such as user bandwidth (speed), end-to-end latency, packet reliability, and network availability.

[0061] like Figure 1 As shown, Figure 1is a schematic diagram of a logical management architecture of an SLA guarantee system provided by an embodiment of the present application. The SLA guarantee solution is mainly realized by relying on the logical management architecture of a network slice, as shown in Figure 1 The entities such as a communication service management function (CSMF), a network slice management function (NSMF), a network slice subnet management function (NSSMF), a management and orchestration (MANO), an element management system (EMS), an orchestrator (SDN-O), an SDN controller (SDN-C), an NFV orchestrator (NFVO), a VNF manager (VNFM), and a virtualized infrastructure manager (VIM) are defined by organizations such as the 3rd Generation Partnership Project (3GPP), and these entities jointly complete the full life cycle management of an SLA or a network slice. An industry customer inputs a business SLA requirement (a business SLA index) to the CSMF, and the CSMF completes the conversion of the business requirement to a network SLA index. The NSMF entity decomposes the converted end-to-end network index to a radio network (AN), a transport network (TN), and a core network (CN), and performs parameter configuration and instantiation of an in-domain sub-slice through a NSSMF entity (AN-NSSMF, TN-NSSMF, CN-NSSMF) of each domain. Then, entities such as the MANO (including the NFVO, the VNFM, and the VIM), the EMS, and the SDN-O / C complete the deployment and configuration of each sub-slice and required network, computing, and storage resources. After the slice deployment is completed, the management system notifies a communication service customer, and continuously monitors network SLA index changes in the full life cycle of the communication service, completes root cause analysis on abnormal indexes, and optimizes and adjusts the network.

[0062] The Internet of Vehicles or automatic driving industry customers have strong demand for SLA index guarantee of mobile communication network due to high mobility, high business continuity requirement, high security requirement and other characteristics. The existing Internet of Vehicles SLA guarantee technical solution is mainly realized through closed-loop guarantee logic of monitoring, analyzing, deciding and executing, that is, the network management system continuously monitors SLA index fluctuation, analyzes the root cause after the SLA index appears abnormal fluctuation, receives analysis information to make a decision on adjustment scheme, and finally the network passively executes adjustment and optimization. The existing Internet of Vehicles SLA guarantee solution does not consider prediction and initiative scheduling of customer network quality of service (QoS), only takes passive adjustment and optimization, and is difficult to provide deterministic SLA index guarantee in the whole life cycle. No corresponding mechanism is designed to complete network QoS prediction, network resource scheduling and adaptability adjustment of vehicle end application.

[0063] In view of the defects of the above related technologies, the embodiment of the present application provides a network service quality prediction method, which predicts the change of network service quality, and actively schedules network resources in advance, so as to achieve high priority guarantee of network SLA index of user terminal through pre-scheduling. In order to describe the technical scheme of the present application, the following will be described through specific embodiments.

[0064] Cellular Vehicle-to-Everything (C-V2X) technology is the mainstream communication technology of vehicle communication, which defines two transmission modes: long-distance communication mode based on cellular mobile network (referred to as Uu interface) and short-distance direct communication mode (referred to as PC5 interface). In this application, the vehicle Internet of Things SLA guarantee mechanism based on 5G cellular mobile network mode is mainly considered. Various auxiliary driving and automatic driving applications at the vehicle end rely on cellular Internet of Vehicles to complete data interaction with the cloud platform, roadside equipment or other vehicles, and various vehicle end applications have specific network quality of service requirements for network connection. Due to the continuous change of network quality and channel, network quality of service (QoS) degradation may occur, and the communication network is difficult to meet the SLA requirements of the vehicle end application. Predictive QoS refers to predicting the change of network service quality at the vehicle end, including the change of indicators such as delay, reliability and data rate. Predictive QoS strategy enables mobile communication network to predict changes and provide in-advance QoS notification (IQN) message to vehicle end application, which enables the vehicle end application to adjust the behavior of the application before QoS changes, and the application can adapt to the new network QoS after adjustment.

[0065] The Internet of Vehicles customers can be divided into two categories:

[0066] 1. Agreement customer who has signed SLA guarantee agreement with network service provider or application service provider;

[0067] 2. Ordinary customer who has not signed SLA guarantee agreement with network service provider or application service provider.

[0068] For the above two types of Internet of Vehicles customers, the application can perform QoS prediction to meet the SLA index requirements of the vehicle end application.

[0069] Figure 2 is a flowchart of an implementation of a network service quality prediction method provided by an embodiment of the application, and the execution subject of the network service quality prediction method is a QoS prediction function (Prediction Function, PF) network element. Referring to Figure 2 , the network service quality prediction method comprises:

[0070] S201, receiving a prediction request, wherein the prediction request comprises a QoS prediction index of a user terminal.

[0071] For example, the user terminal and the application server can send a prediction request to the PF network element, and the prediction request comprises a QoS prediction index of the user terminal that needs to be predicted, i.e., a QoS prediction Key Performance Indicator (Key Performance Indicator, KPI). The QoS prediction index comprises a delay, a reliability, a data rate, etc.

[0072] In actual application, the vehicle V2X application and the V2X application server send an In-advance QoS Notification (IQN) subscription request to the PF network element, and the subscription request is the above-mentioned prediction request. The content of the subscription request can comprise a Protocol Data Unit (Protocol Data Unit, PDU) session ID, a QoS Flow ID, an ID of a single or a group of terminals, a specific QoS prediction KPI, a prediction frequency, a QoS change report threshold (triggering a report when the change exceeds the threshold), and an IQN notification period (notify how many seconds before the QoS changes).

[0073] S202, performing prediction on the QoS prediction index based on the prediction request.

[0074] The PF network element identifies the data required for prediction, which can comprise data from the terminal, a mobile communication network (5G core network, access network, network management system), and a third-party application (Application Framework, AF). The PF sends a subscription request to subscribe to these data, and the data source party responds to the request accordingly.

[0075] The PF network element collects statistical data from the vehicle end, the network and the third party, and performs prediction calculation on the QoS index through machine learning, deep learning and other algorithms. The specific algorithm and steps depend on the specific use case, the KPI of the specific use case and the prediction time limit constraint.

[0076] For example, a supervised learning method such as a support vector machine (SVM) and a deep learning neural network can be used for QoS prediction. These models can learn the complex linear relationship between the network state and the QoS through historical data, and achieve accurate prediction of the QoS.

[0077] In S203, early warning information is sent to a network management device based on the first prediction value.

[0078] For example, if the first prediction value is not within the threshold range, the early warning information is sent to the network management device, and the early warning information includes the first prediction value. In the core network, the network management device is a network management system.

[0079] If the first prediction value is not within the threshold range, it means that the QoS change of the user terminal exceeds the QoS change threshold, affecting the SLA guarantee, and the network management system is triggered to send a QoS change warning to the network management system, and the network management system is notified to schedule the network resources of the user terminal to make the network service quality of the user terminal meet the SLA index.

[0080] The embodiments of the present application can predict the network QoS change, make the network management system actively and proactively schedule the network resources and configure the parameters, and provide network SLA index guarantee for the vehicle V2X application.

[0081] The QoS prediction function network element of the embodiments of the present application receives a prediction request, performs prediction of the QoS prediction index based on the prediction request, and obtains a first prediction value of the QoS prediction index. Based on the first prediction value, it is determined whether to send early warning information to the network management device, so that the network management device schedules the network resources of the user terminal according to the first prediction value to guarantee the network SLA index of the user terminal. Through prediction of the network QoS of the user terminal and sending of early warning information to the network management device based on the first prediction value, the network management device can proactively schedule the network resources of the user terminal in advance, and through the pre-scheduling, the high-priority guarantee of the network SLA index of the user terminal is achieved, and the network experience of the user is improved.

[0082] In an embodiment, the prediction of the QoS prediction index based on the prediction request comprises:

[0083] Based on the QoS prediction index, data required for prediction is determined;

[0084] sending a subscription request to a corresponding data source based on the required collected data;

[0085] performing the prediction of the QoS prediction index based on the data sent by the data source based on the subscription request.

[0086] The prediction of the QoS needs to rely on the information collected from different sources as the prediction basis. For example, when predicting the QoS of a vehicle, the PF network element can collect the following information from the vehicle, the mobile communication network and the third-party AF

[0087] the information shown in Table 1:

[0088]

[0089]

[0090] Table 1

[0091] The information types mentioned in the above Table 1 can all be used by the PF network element to analyze and generate the prediction of the network QoS.

[0092] In an embodiment, after determining whether to send the early warning information to the network management device based on the first prediction value, the method further comprises:

[0093] receiving the network parameters of the user terminal sent by the network management device after scheduling the network resources of the user terminal;

[0094] re-performing the prediction of the QoS prediction index based on the network parameters of the user terminal to obtain a second prediction value of the QoS prediction index;

[0095] if the second prediction value is not within the threshold range, sending the second prediction value to the sending end of the prediction request.

[0096] The network parameters include the change of the indicators such as the delay, the reliability and the data rate.

[0097] The network management device updates and synchronizes the scheduled network parameters to the PF network element, and after receiving the network parameters from the network management device, the PF re-predicts the QoS change of the user terminal according to the updated network parameters. In actual application, the network management device can also send the scheduling strategy to the PF network element.

[0098] After the PF network element completes the prediction update, if the QoS change of the user terminal exceeds the predetermined change threshold (the second prediction value is not within the threshold range), the PF network element sends the prediction information (the second prediction value) to the sending end of the prediction request. Here, the sending end of the prediction request includes the user terminal and the application server.

[0099] The second prediction value is sent to the sending end of the prediction request, comprising:

[0100] The second prediction value is sent to a preset QoS distribution function network element, and the second prediction value is distributed to the sending end of the prediction request through the QoS distribution function network element.

[0101] In an embodiment, an in-advance QoS notification (IQN) distribution function network element can also be set, the IQN distribution function network element receives QoS prediction information from the PF network element, encapsulates the prediction information into an IQN message, and sends the IQN message to specified user terminals and application servers according to requirements in an IQN subscription request.

[0102] Taking a vehicle as an example, after receiving the IQN message, the vehicle V2X application compares the KPI prediction value in the IQN message with a specific QoS threshold value, judges which level of adaptive adjustment should be made, and completes the adaptive adjustment in cooperation with the V2X application server before the predicted QoS takes effect. For example, if it is predicted that the downlink network data rate will decrease by 30 Mbps after 10 s, the vehicle end high-definition video application will complete a series of operations such as quality adjustment within 10 s in cooperation with the V2X application server, thereby reducing customer bad experience and safety risk

[0103] Figure 3 is a flowchart of an implementation of a network resource scheduling method provided by an embodiment of the application, and an execution subject of the network resource scheduling method is a network management device, which can be a network management system in a core network. Figure 3 The network resource scheduling method comprises the following steps:

[0104] S301, receiving early warning information sent by a QoS prediction function network element; the early warning information comprises a first prediction value of a QoS prediction index of the user terminal by the QoS prediction function network element.

[0105] S302, scheduling network resources of the user terminal based on the first prediction value.

[0106] After receiving the QoS change early warning, the network management system schedules the network resources of the user terminal in advance, and preferentially guarantees the network QoS of the protocol vehicle, so that the QoS value of the user terminal meets the SLA index.

[0107] The network management device schedules the network resources of the user terminal, comprising: increasing resource allocation of the user terminal, increasing bandwidth, etc.

[0108] The embodiment of the application can predict the QoS change of the user terminal in advance through the QoS prediction manner, perform network resource scheduling in advance, improve the priority of the user terminal in occupying network resources, and achieve the purpose of guaranteeing the network SLA of the user terminal.

[0109] Figure 4 is a flowchart of an implementation of a service adjustment method provided by the embodiment of the application, and the execution subject of the service adjustment method is a user terminal or an application server. Referring to Figure 4 , the service adjustment method comprises:

[0110] S401, a prediction request is sent to a QoS prediction function network element; the prediction request comprises a QoS prediction index of the user terminal.

[0111] S402, a second prediction value of the QoS prediction index from the QoS prediction function network element is received;

[0112] S403, the current running service is adaptively adjusted based on the second prediction value.

[0113] Here, the prediction request comprises a QoS prediction index that needs to be predicted, such as a delay, reliability, and data rate.

[0114] Before the second prediction value is received, the network management system performs network resource scheduling according to the first prediction value, after the network resource scheduling, the QoS prediction function network element re-performs the prediction of the QoS prediction index, and if the second prediction value is not located in the threshold range, the second prediction value is sent to the sending end of the prediction request, so that the sending end adaptively adjusts the current running service based on the second prediction value.

[0115] Taking a vehicle application as an example, the PF network element simultaneously sends a reminder to the vehicle whose QoS change exceeds the threshold value and the corresponding V2X application server, and the vehicle-side V2X application and the application server timely adaptively adjust, thereby reducing the bad experience of customers and the safety risk.

[0116] As shown in Table 2, taking the vehicle-side V2X application as an example, the required prediction QoS KPI and the possible adaptive adjustment behavior of these applications when facing the QoS change are listed in Table 2.

[0117]

[0118] Table 2

[0119] In the 5G system, the connection between the vehicle V2X App and the V2X application server is represented by a PDU session, and the PDU session comprises one or more QoS flows, such as Figure 5QoS flow (QoS flow#1, QoS flow#2 and QoS flow#3) is the finest granularity of QoS differentiation in PDU session, and is the finest granularity of QoS differentiation in 5G system. Therefore, the IQN message sent carries prediction information for a single or multiple QoS flows in a PDU. Generally, the following information needs to be included in the IQN:

[0120] 1. QoS flow / PDU session ID to be predicted;

[0121] 2. Predicted QoS KPI (e.g. latency, reliability, data rate, etc.) and predicted change value, for example: "uplink data rate is expected to decrease by 10 Mbps", "latency will increase by 50 ms";

[0122] 3. Time / distance when the prediction takes effect, for example: "after 25 seconds", "after 500 m";

[0123] 4. Duration of the predicted change, for example: "for 15 seconds";

[0124] 5. Accuracy of the prediction, for example: "accuracy reaches 98%".

[0125] In Figure 5 , two network functions / applications functions (NF / AF) of "QoS prediction function (PF)" and "IQN distribution" are introduced, which can be deployed or integrated with other network elements of 5G system. PF is mainly responsible for QoS prediction, and IQN distribution function is mainly to encapsulate and generate IQN message according to the QoS information provided by PF, and distribute it to the relevant vehicle V2X application and V2X application server. To implement predictive QoS strategy, IQN message needs to be sent to the vehicle and V2X application server, which needs the following 3 steps:

[0126] a: Collect data.

[0127] b: PF makes prediction.

[0128] c: Send prediction results.

[0129] Wherein, after the PF makes the first prediction, the first prediction value is sent to the network management system, the network management system analyzes the influence of the current QoS change on the network SLA guarantee of the protocol vehicle application, and the network resources are pre-scheduled, and the network resources are preferentially allocated to the vehicle V2X application to cope with the impending QoS change, and the SLA of the protocol customer vehicle end V2X application is guaranteed. This guarantee method will cause the network resources allocated to the ordinary vehicle V2X application around the protocol vehicle to decrease, so the network management system needs to share the network parameters and resource scheduling strategy in real time to the PF, and the PF will re-predict the QoS of the vehicle application according to the updated collected information. After re-prediction, if the QoS change of the V2X application exceeds the predetermined change threshold, the second prediction value of the re-prediction is sent to the vehicle V2X application and the V2X application server, and after receiving the updated QoS prediction information, the vehicle V2X application and the V2X application server complete the adaptive adjustment of the predicted QoS, so that the vehicle V2X application can complete the timely degradation or switching.

[0130] The embodiment of the application predicts the change of network service quality, pre-actively performs network parameter configuration and network resource scheduling, and achieves high-priority guarantee of network SLA indicators of protocol customers through pre-scheduling. At the same time, the prediction result of network QoS can be sent to the customer vehicle with large QoS change, so that the vehicle end V2X application can complete the adaptive adjustment of network QoS change in time, improve customer experience and reduce safety risk.

[0131] Reference Figure 6 , Figure 6 is a flow diagram of a network service quality guarantee method for a vehicle application provided by the embodiment of the application, wherein:

[0132] Step 1: IQN subscription request.

[0133] The vehicle V2X application and the V2X application server send an IQN subscription request to the PF. The content of the subscription request message can include: PDU session ID, QoS Flow ID, ID of a single or a group of terminals, specific QoS prediction KPI, prediction frequency, QoS change reporting threshold (change exceeding the threshold triggers reporting), and IQN notification period (notify how many seconds before QoS change).

[0134] Step 2: Data monitoring subscription request / response.

[0135] Based on the content of the IQN subscription request message, the PF identifies the data needed for prediction, which can include data from vehicles, mobile communication networks (5G core network, access network, network management system) and third-party AF. The PF sends a subscription request to subscribe to these data, and the data sources respond to the request accordingly.

[0136] Step 3: QoS prediction admission control.

[0137] Considering the content of the IQN subscription request and the available prediction support information (through data monitoring subscription), the PF decides whether the specific IQN subscription request can be supported.

[0138] Step 4: IQN subscription request response (ACK, NACK).

[0139] After determining whether the subscription request of the IQN can be supported, the PF sends a request response confirmation / rejection to the V2X application server or vehicle V2X application.

[0140] Step 5: Data collection.

[0141] The PF collects data according to the support information content required for prediction, and the data sources can be vehicles, mobile communication networks (5G core network, access network, network management system), and third-party AFs.

[0142] Step 6: Make a prediction.

[0143] The PF makes a prediction based on the collected data.

[0144] Step 7: QoS change warning (conditional trigger).

[0145] If the PF predicts that the QoS change of the protocol vehicle exceeds the QoS change threshold, affecting its SLA guarantee, it will trigger a QoS change warning to the network management system.

[0146] Step 8: Network management system pre-scheduling.

[0147] After receiving the QoS change warning, the network management system pre-schedules network resources to prioritize network QoS for protocol vehicles.

[0148] Step 9: Scheduling strategy synchronization.

[0149] The network management system updates and synchronizes the network parameters and scheduling strategies at this time to the PF.

[0150] Step 10: Prediction update.

[0151] After receiving the network parameter and scheduling strategy information from the network management system, the PF re-predicts the QoS changes of all vehicle V2X applications based on the updated information.

[0152] Step 11: Send prediction.

[0153] After the PF completes the prediction update, if the QoS of the V2X application changes by more than a predetermined change threshold, the PF sends the prediction information to the "IQN distribution function". The "IQN distribution function" sends the IQN message to the V2X vehicle application and the V2X application server that subscribe to the service.

[0154] Step 12: V2X application adaptive adjustment.

[0155] After receiving the IQN message, the vehicle V2X application compares the KPI prediction value in the IQN message with the specific QoS threshold value, determines which level of adaptive adjustment should be made, and completes the adaptive adjustment with the V2X application server before the predicted QoS takes effect. For example, if the predicted downlink network data rate will decrease by 30 Mbps after 10s, the vehicle end high-definition video application will complete a series of operations such as quality adjustment within 10s in coordination with the V2X application server.

[0156] The embodiment of the present application proposes a predictive QoS assisted Internet of Vehicles SLA guarantee mechanism. The network QoS of a customer is predicted. If the predictive QoS of the protocol customer cannot meet the SLA index requirement of the vehicle end application, pre-network resource scheduling can be performed. When the network resource is insufficient, the network resource scheduling (time-frequency resource, etc.) is used to preferentially meet the SLA of the protocol customer, and after the scheduling, the network QoS is re-predicted. If the predicted network QoS changes by more than a threshold value, the IQN is sent to the protocol customer and the ordinary customer. After receiving the predicted QoS, the customer performs adaptive adjustment on the vehicle end application to adapt to the changed QoS. In summary, based on the scheme, the QoS of the vehicle end application of the protocol customer can be predicted in advance by means of QoS prediction, the network resource scheduling is performed in advance, the priority of the network resource occupation of the protocol customer is improved, the network SLA of the protocol vehicle is guaranteed, and the reminder is sent to the vehicle and the corresponding V2X application server when the QoS changes by more than a threshold value. The vehicle end V2X application and the application server are timely adjusted adaptively, and the customer's bad experience and safety risk are reduced.

[0157] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution. The execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0158] It should be understood that when used in the present specification and the appended claims, the terms "comprise" and "include" indicate the presence of described features, integers, steps, operations, elements, and / or components, but do not exclude one or more other features, integers, steps, operations, elements, components, and / or sets thereof.

[0159] It should be noted that the technical solutions described in the embodiments of the application can be combined arbitrarily without conflict.

[0160] In addition, in the embodiments of the application, "first", "second", and the like are used to distinguish similar objects, and do not necessarily mean a specific order or sequence.

[0161] Reference Figure 7 , Figure 7 is a schematic diagram of a network service quality prediction device provided by an embodiment of the application, which comprises:

[0162] A first receiving module is configured to receive a prediction request, wherein the prediction request comprises a QoS prediction index of a user terminal.

[0163] A prediction module is configured to perform prediction on the QoS prediction index based on the prediction request, and obtain a first prediction value of the QoS prediction index.

[0164] A first sending module is configured to send early warning information to a network management device based on the first prediction value.

[0165] In an embodiment, the prediction module is specifically configured to:

[0166] determine data required to be collected based on the QoS prediction index;

[0167] send a subscription request to a corresponding data source based on the data required to be collected;

[0168] perform prediction on the QoS prediction index based on data sent by the data source based on the subscription request.

[0169] In an embodiment, the device further comprises:

[0170] A network parameter receiving module is configured to receive network parameters of the user terminal sent by the network management device after scheduling network resources of the user terminal.

[0171] A re-prediction module is configured to re-perform prediction on the QoS prediction index based on the network parameters of the user terminal, and obtain a second prediction value of the QoS prediction index.

[0172] A second prediction value sending module is configured to send the second prediction value to a sending end of the prediction request if the second prediction value is not within a threshold range.

[0173] In an embodiment, the second prediction value sending module is specifically configured to:

[0174] The second predicted value is sent to a preset QoS distribution function network element, and the second predicted value is distributed to a sending end of the prediction request through the QoS distribution function network element.

[0175] In an embodiment, the first sending module is specifically configured to:

[0176] If the first predicted value is not within a threshold range, the early warning information is sent to a network management device.

[0177] Reference Figure 8 , Figure 8 is a schematic diagram of a network resource scheduling device provided by an embodiment of the application, and the device comprises:

[0178] A second receiving module is configured to receive early warning information sent by a QoS prediction function network element; the early warning information comprises a first predicted value of a QoS prediction index of a user terminal by the QoS prediction function network element;

[0179] A scheduling module is configured to schedule network resources of the user terminal based on the first predicted value.

[0180] In an embodiment, the device further comprises:

[0181] A network parameter sending module is configured to send network parameters of the user terminal after network resource scheduling to the QoS prediction function network element.

[0182] Reference Figure 9 , Figure 9 is a schematic diagram of a service adjustment device provided by an embodiment of the application, and the device comprises:

[0183] A second sending module is configured to send a prediction request to a QoS prediction function network element; the prediction request comprises a QoS prediction index of a user terminal;

[0184] A third receiving module is configured to receive a second predicted value of the QoS prediction index by the QoS prediction function network element;

[0185] An adjustment module is configured to adaptively adjust a current operating service based on the second predicted value.

[0186] In practical applications, the first receiving module, the prediction module, and the first transmitting module can be implemented by processors in the network element, such as central processing unit (CPU), digital signal processor (DSP), microcontroller unit (MCU), or field-programmable gate array (FPGA).

[0187] It should be noted that the network service quality prediction device provided in the above embodiments is only illustrated by the division of the above modules when performing information processing. In actual applications, the above processing can be assigned to different modules as needed, that is, the internal structure of the device can be divided into different modules to complete all or part of the processing described above. In addition, the network service quality prediction device and the network service quality prediction method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0188] The aforementioned network service quality prediction device can be in the form of an image file. After execution, the image file can run as a container or virtual machine to implement the network service quality prediction method described in this application. However, it is not limited to the image file format; any software implementation capable of the network service quality prediction method described in this application is within the scope of protection of this application.

[0189] Based on the hardware implementation of the above program modules, and in order to implement the method of the embodiments of this application, the embodiments of this application also provide a network element, wherein the above network service quality prediction method is implemented by the processor of the network element.

[0190] Figure 10 This is a schematic diagram of the hardware composition structure of the network element in an embodiment of this application, as shown below. Figure 10 As shown, the network elements include:

[0191] The communication interface enables information exchange with other devices, such as network management devices.

[0192] The processor, connected to the communication interface, enables information interaction with other devices and, when running a computer program, executes the methods provided by one or more technical solutions on the network element side. The computer program is stored in memory.

[0193] Of course, in practical applications, the various components within a network element are coupled together through a bus system. It can be understood that the bus system is used to implement communication and connection between these components. In addition to the data bus, the bus system also includes a power bus, a control bus, and a status signal bus. However, for clarity, in...Figure 10 In the specific embodiments of the present application, all kinds of buses are marked as bus systems.

[0194] The memory in the embodiments of the present application is used to store various types of data to support the operation of the network element. Examples of these data include: any computer programs used to operate on the network element.

[0195] In the present application, the network element can be a single hardware device, or a cluster composed of multiple hardware devices, such as a cloud computing platform. The so-called cloud computing platform is a cluster device that organizes multiple independent server physical hardware resources into a pool of resources, and provides the required virtual resources and services externally.

[0196] The memory in the embodiments of the present application is used to store various types of data to support the operation of the network element. Examples of these data include: any computer programs used to operate on the network element.

[0197] The embodiments of the present application also provide a network management device, and the network resource scheduling method is realized by a processor of the network management device. Figure 11 The hardware component structure diagram of the network management device in the embodiments of the present application is shown in FIG. 1. Figure 11 As shown in FIG. 1, the network management device includes:

[0198] The communication interface can interact with other devices.

[0199] The processor is connected with the communication interface to realize the information interaction with other devices, and is used to run the computer program to execute the method provided by one or more technical solutions of the network management device. The computer program is stored on the memory.

[0200] Of course, in actual application, various components in the network management device are coupled together through the bus system. It can be understood that the bus system is used to realize the connection and communication between the components. The bus system includes not only a data bus, but also a power bus, a control bus and a state signal bus. However, in order to clearly illustrate, in the specific embodiments of the present application, all kinds of buses are marked as bus systems. Figure 11

[0201] The embodiments of the present application also provide an electronic device, and the service adjustment method is realized by a processor of the electronic device. Figure 12 The hardware component structure diagram of the electronic device in the embodiments of the present application is shown in FIG. 2. The electronic device includes a vehicle terminal and an application server. Figure 12 As shown in FIG. 2, the electronic device includes:

[0202] The communication interface can interact with other devices.

[0203] ​The processor is connected with the communication interface to realize information interaction with other devices, and is used for running a computer program to execute the method provided by one or more technical solutions of the electronic device. The computer program is stored in the memory.

[0204] Of course, in actual application, various components in the electronic device are coupled together through a bus system. It can be understood that the bus system is used to realize the connection and communication between the components. In addition to the data bus, the bus system also includes a power bus, a control bus and a state signal bus. However, in order to clearly illustrate, all kinds of buses are marked as a bus system in the Figure 11 .

[0205] It can be appreciated that the memory can be a volatile memory or a nonvolatile memory, and can also include both volatile and nonvolatile memory. Among them, the nonvolatile memory can be a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a ferromagnetic random access memory (FRAM), a Flash Memory, a magnetic surface memory, an optical disc, or a Compact Disc Read-Only Memory (CD-ROM). The magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a Random Access Memory (RAM) used as an external cache. By way of example and not limitation, many forms of RAM can be used, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDR SDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), Sync Link Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM). The memory described in the embodiments of the present application is intended to include but not limited to these and any other suitable types of memory.

[0206] The method disclosed in the embodiments of the present application can be applied to a processor or implemented by the processor. The processor can be an integrated circuit chip with a signal processing capability. In the implementation process, the steps of the method disclosed above can be completed by an integrated logic circuit or a software form of an instruction in the processor. The processor can be a general-purpose processor, a DSP, or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. The processor can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiments of the present application, the steps can be directly embodied as a hardware code executed by the processor, or a combination of hardware and software modules in the processor. The software module can be located in a storage medium, which is located in a memory, and the processor reads the program in the memory to complete the steps of the foregoing method in combination with the hardware.

[0207] Alternatively, the processor implements the corresponding procedures realized by the network element in each method of the embodiments of the present application when executing the program, which is not described herein again for brevity.

[0208] In the exemplary embodiments, the embodiments of the present application further provide a storage medium, that is, a computer storage medium, specifically a computer readable storage medium, for example, a first memory for storing a computer program, and the computer program can be executed by a processor of a network element to complete the steps of the foregoing method. The computer readable storage medium can be an FRAM, a ROM, a PROM, an EPROM, an EEPROM, a Flash Memory, a magnetic surface memory, an optical disc, or a CD-ROM, etc.

[0209] In several embodiments provided in the present application, it should be understood that the disclosed apparatus, network element, and method can be implemented by other manners. The apparatus embodiments described above are merely schematic, for example, the division of the units is merely a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed components can be through some interfaces, indirect coupling or communication connection of the devices or units, which can be electrical, mechanical, or other forms.

[0210] The units described as separate components above can or can not be physically separate, and the components shown as units can or can not be physical units, that is, can be located in one place or distributed on multiple network units; part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0211] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be realized in the form of hardware or in the form of hardware plus software functional unit.

[0212] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware, and the above-mentioned program can be stored in a computer readable storage medium, and the program executes the steps including the above-mentioned method embodiments when executed; and the above-mentioned storage medium includes mobile storage device, ROM, RAM, magnetic disc or optical disc and various storage program codes.

[0213] Alternatively, the integrated unit of the present application, if realized in the form of software function module and sold or used as an independent product, can also be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application can be embodied in the form of software product, which is stored in a storage medium and includes a plurality of instructions for making a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the methods described in the embodiments of the present application. The above-mentioned storage medium includes mobile storage device, ROM, RAM, magnetic disc or optical disc and various storage program codes.

[0214] It should be noted that the technical solutions described in the embodiments of the present application can be combined arbitrarily without conflict.

[0215] In addition, in the present application, "first", "second", etc. are used to distinguish similar objects, and do not necessarily describe a specific order or sequence.

[0216] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and any skilled person in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A network service quality prediction method, applied to a quality of service (QoS) prediction function network element, characterized in that, The method comprises: receiving a prediction request, the prediction request comprising a QoS prediction index of a user terminal; based on the prediction request, performing prediction of the QoS prediction index to obtain a first prediction value of the QoS prediction index; sending early warning information to a network management device based on the first prediction value; receiving network parameters of the user terminal sent by the network management device after scheduling network resources of the user terminal; based on the network parameters of the user terminal, re-performing prediction of the QoS prediction index to obtain a second prediction value of the QoS prediction index; if the second prediction value is not within a threshold range, sending the second prediction value to the sending end of the prediction request.

2. The method of claim 1, wherein, The method comprises: based on the QoS prediction index, determining the data required for prediction; based on the required data, sending a subscription request to the corresponding data source; based on the data sent by the data source based on the subscription request, performing prediction of the QoS prediction index.

3. The method of claim 1, wherein, The method comprises: sending the second prediction value to a preset QoS distribution function network element, and distributing the second prediction value to the sending end of the prediction request through the QoS distribution function network element.

4. The method of claim 1, wherein, The method comprises: if the first prediction value is not within a threshold range, sending the early warning information to the network management device.

5. A network resource scheduling method, applied to a network management device, characterized in that, The method comprises: receiving early warning information sent by a QoS prediction function network element; the early warning information comprising a first prediction value of a QoS prediction index of a user terminal by the QoS prediction function network element; scheduling network resources of the user terminal based on the first prediction value; sending network parameters of the user terminal after network resource scheduling to the QoS prediction function network element.

6. A traffic adjustment method characterized by comprising: The method comprises: sending a prediction request to a QoS prediction function network element; the prediction request comprising a QoS prediction index of a user terminal; receiving a second prediction value of the QoS prediction index by the QoS prediction function network element; based on the second prediction value, adaptively adjusting the current service.

7. A network service quality prediction apparatus characterized by comprising: The method comprises: a first receiving module for receiving a prediction request, the prediction request comprising a QoS prediction index of a user terminal; a prediction module for performing prediction of the QoS prediction index based on the prediction request to obtain a first prediction value of the QoS prediction index; a first sending module for sending early warning information to a network management device based on the first prediction value; a network parameter receiving module for receiving network parameters of the user terminal sent by the network management device after scheduling network resources of the user terminal; a re-prediction module for re-performing prediction of the QoS prediction index based on the network parameters of the user terminal to obtain a second prediction value of the QoS prediction index; The second prediction value sending module is configured to send the second prediction value to a sending end of the prediction request if the second prediction value is not within a threshold range.

8. A network resource scheduling apparatus, characterized by comprising: The method comprises the following steps: The second receiving module is configured to receive early warning information sent by a QoS prediction function network element. The early warning information comprises a first prediction value of a QoS prediction index of a user terminal by the QoS prediction function network element. The scheduling module is configured to schedule network resources of the user terminal based on the first prediction value. The network parameter sending module is configured to send network parameters of the user terminal after network resource scheduling to the QoS prediction function network element.

9. A service adjustment apparatus characterized by comprising: The method comprises the following steps: The second sending module is configured to send a prediction request to a QoS prediction function network element; the prediction request comprises a QoS prediction index of a user terminal. The third receiving module is configured to receive a second prediction value of the QoS prediction index by the QoS prediction function network element. The adjustment module is configured to adaptively adjust a current service based on the second prediction value.

10. A network element comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor implements the steps of the network service quality prediction method according to any one of claims 1 to 4 when executing the computer program.

11. A network management device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein, The processor implements the steps of the network resource scheduling method according to claim 5 when executing the computer program.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor implements the steps of the service adjustment method according to claim 6 when executing the computer program.

13. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program comprises program instructions; when the program instructions are executed by the processor, the processor executes the steps of the network service quality prediction method according to any one of claims 1 to 4, or executes the steps of the network resource scheduling method according to claim 5, or executes the steps of the service adjustment method according to claim 6.

Images