Network slice resource adaptive adjustment method, apparatus, storage medium and electronic equipment
By identifying resource conflicts through network slicing service providers and utilizing resource adjustment strategies verified by AI and digital twin simulations, the problems of conflict and SLA guarantee in network slicing resource scheduling are solved. This enables adaptive resource management and scheduling in resource-constrained scenarios, ensuring network quality and service level agreements.
Patent Information
- Application Number
- CN202210964151.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-08-11
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2042-08-11
AI Technical Summary
Existing technologies lack conflict avoidance and SLA guarantee mechanisms for sudden incremental demand for network slices in network slice resource scheduling, resulting in resource scheduling conflicts and ineffective guarantee of service level agreements.
By identifying resource conflicts through network slicing service providers, determining the shared resource requirements and priority information of the target network slice, formulating resource adjustment strategies, and using AI algorithms and network digital twin simulation to verify the effectiveness of the resource adjustment strategies, adaptive resource adjustment is achieved.
In resource-constrained scenarios, it can autonomously detect slice resource conflicts, ensure network quality and SLA, reduce the impact on slice services, and achieve predictive resource management and scheduling of multiple slices.
Smart Images

Figure CN117640386B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of fifth-generation mobile communication technology (5G), specifically to a network slice resource adaptive adjustment method, a network slice resource adaptive adjustment device, a storage medium, and an electronic device. Background Technology
[0002] To provide users with more comprehensive network services, next-generation communication systems can abstract logical functions into network slices (NS). When managing and maintaining network slices, it is necessary to monitor key parameters of both the network slice and its users to ensure end-to-end SLA (Service-Level Agreement) guarantees for slice performance.
[0003] While existing technologies consider using AI for prediction and analysis to help networks make resource allocation and scheduling decisions in advance, they still lack resource scheduling and SLA guarantee technologies to avoid conflicts when slices experience sudden incremental demand.
[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention
[0005] The purpose of this disclosure is to provide a method, apparatus, storage medium, and electronic device for adaptive adjustment of network slice resources, which aims to solve the problem of optimizing the resource allocation of network slices when multiple network slices have resource contention needs.
[0006] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.
[0007] According to one aspect of the embodiments of this disclosure, a method for adaptive adjustment of network slice resources is provided, comprising: receiving a resource adjustment request sent by a network slice service provider when the network slice service provider determines that at least two target network slices have resource conflicts; parsing the resource adjustment request to obtain resource conflict information, and determining the shared resource demand and priority information of each target network slice based on the resource conflict information; formulating a resource adjustment strategy for each target network slice based on the shared resource demand and priority information of each target network slice, and executing the resource adjustment strategy.
[0008] According to some embodiments of this disclosure, based on the foregoing scheme, determining the shared resource demand and priority information of each target network slice based on the resource conflict information includes: determining special target network slices with external event identifiers and ordinary target network slices among the target network slices based on the resource conflict information; calculating the traffic prediction index values of each special target network slice and each ordinary target network slice respectively, and determining the shared resource demand based on the traffic prediction index values; and determining a first sequence of the special target network slices and a second sequence of the ordinary target network slices respectively, and concatenating the first sequence and the second sequence to obtain the priority information.
[0009] According to some embodiments of this disclosure, based on the foregoing scheme, the step of calculating the traffic prediction index values for each of the special target network slices and each of the ordinary target network slices includes: for the special target network slice, identifying the event type based on the external event identifier, and predicting the traffic prediction index value based on the historical traffic data corresponding to the event type; and for the ordinary target network slice, predicting the traffic prediction index value based on the historical traffic data of the ordinary target network slice.
[0010] According to some embodiments of this disclosure, based on the foregoing scheme, determining the shared resource demand based on the traffic volume prediction index value includes: traversing all the target network slices, determining the total resource demand corresponding to the traffic volume prediction index value based on the mapping relationship between traffic volume and resource volume; determining the existing resource volume of the target network slice according to the service level agreement of the target network slice, and calculating the current remaining resource volume of the target network slice based on the existing resource volume and resource utilization rate; and calculating the difference between the total resource demand and the current remaining resource volume as the shared resource demand of the target network slice.
[0011] According to some embodiments of this disclosure, based on the foregoing scheme, before determining the existing resource quantity of the target network slice according to the service level agreement of the target network slice, the method further includes: traversing all the target network slices, determining whether the traffic prediction index value of the target network slice exceeds the target extreme value of the service level agreement of the target network slice; and adjusting the service level agreement of the target network slice when the traffic prediction index value exceeds the target extreme value.
[0012] According to some embodiments of this disclosure, based on the foregoing scheme, determining the first sequence of the special target network slices and the second sequence of the ordinary target network slices respectively includes: determining the first sequence of the special target network slices according to event priority; and when each of the target network slices has a priority identifier, determining the second sequence of the ordinary target network slices based on the original priority identifier; and when each of the target network slices does not have a priority identifier, determining the second sequence based on the shared resource requirements of each of the ordinary target network slices.
[0013] According to some embodiments of this disclosure, based on the foregoing scheme, the step of formulating a resource adjustment strategy for each target network slice based on the shared resource requirements and priority information of each target network slice includes: determining a target network slice sequence based on the priority information; and formulating a resource expansion strategy and / or flow control strategy for each target network slice in each single domain as the resource adjustment strategy according to the target network slice sequence based on the shared resource requirements of each target network slice; wherein, the single domain includes one or more of the core network (CN), transmission network (TN), and access network (AN).
[0014] According to some embodiments of this disclosure, based on the foregoing scheme, after formulating resource adjustment strategies for each target network slice based on the priority information and shared resource requirements of each target network slice, the method further includes: traversing all the target network slices, evaluating the resource adjustment strategies of the target network slices through network digital twins to obtain evaluation results; and executing the resource adjustment strategies when the evaluation results meet the evaluation pass conditions.
[0015] According to some embodiments of this disclosure, based on the foregoing scheme, the step of evaluating the resource adjustment strategy of the target network slice using network digital twin to obtain the evaluation result includes: collecting actual network data of the target network slice; wherein, the actual network data includes physical data and operational data; performing digital modeling of the target network slice based on the actual network data to obtain virtual network data; using the virtual network data to determine the future state information of each single domain in the target network slice when executing the resource adjustment strategy; and obtaining the evaluation result based on the future state information of each single domain in the target network slice.
[0016] According to some embodiments of this disclosure, based on the foregoing scheme, the method further includes: in response to a monitoring task sent by the network slice service provider, sending service level indicator data of each network slice to the network slice service provider, so that the network slice service provider determines whether the resource conflict exists based on the service level indicator data and external event information obtained from the network slice consumer.
[0017] According to a second aspect of the present disclosure, a network slice resource adaptive adjustment apparatus is provided, comprising: a receiving module, configured to receive a resource adjustment request sent by a network slice service provider when the network slice service provider determines that at least two target network slices have resource conflicts; a parsing module, configured to parse the resource adjustment request to obtain resource conflict information, and determine priority information and shared resource requirements of each target network slice based on the resource conflict information; and a strategy module, configured to formulate a resource adjustment strategy for each target network slice based on the priority information and shared resource requirements of each target network slice, and execute the resource adjustment strategy.
[0018] According to a third aspect of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the network slice resource adaptive adjustment method as described in the above embodiments.
[0019] According to a fourth aspect of the present disclosure, an electronic device is provided, characterized in that it includes: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the network slice resource adaptive adjustment method as described in the above embodiments.
[0020] The exemplary embodiments disclosed herein may have some or all of the following beneficial effects:
[0021] In some embodiments of the present disclosure, the network slicing service provider can identify resource conflicts in network slices, automatically determine the target network slices to be adjusted, and generate resource adjustment requests. Then, after receiving the resource adjustment request, the slice management and orchestration system can determine the priority information and shared resource requirements of each target network slice based on the resource conflict information, and subsequently formulate resource adjustment strategies for each target network slice. On the one hand, this provides a mechanism for autonomously detecting slice resource conflicts and requesting resource adjustments, ensuring network quality and SLA even when resource scheduling issues arise due to sudden surges in traffic demand for services carried by the slices. On the other hand, formulating resource adjustment strategies based on the determined priority information and shared resource requirements of the network slices can solve the problem of predictive resource management and scheduling for multiple slices in resource-constrained scenarios, comprehensively reducing the impact on slice services.
[0022] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description
[0023] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:
[0024] Figure 1 The illustration shows a flowchart of a network slice resource adaptive adjustment method in an exemplary embodiment of the present disclosure;
[0025] Figure 2 The illustration schematically shows a flowchart of a method for determining priority information and shared resource requirements in an exemplary embodiment of the present disclosure;
[0026] Figure 3 This schematic diagram illustrates the composition of a network digital twin system in an exemplary embodiment of the present disclosure;
[0027] Figure 4 This schematic diagram illustrates the composition of a network slice resource adaptive adjustment system in an exemplary embodiment of the present disclosure.
[0028] Figure 5 This schematic diagram illustrates a data interaction diagram of a network slice resource adaptive adjustment system in an exemplary embodiment of the present disclosure;
[0029] Figure 6 This schematic diagram illustrates the composition of a network slice resource adaptive adjustment device in an exemplary embodiment of the present disclosure.
[0030] Figure 7 This schematic diagram illustrates a computer-readable storage medium according to an exemplary embodiment of the present disclosure;
[0031] Figure 8 The schematic diagram illustrates the structure of a computer system of an electronic device according to an exemplary embodiment of the present disclosure. Detailed Implementation
[0032] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art.
[0033] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.
[0034] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.
[0035] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.
[0036] The implementation details of the technical solutions of the embodiments of this disclosure are described in detail below.
[0037] Figure 1 This schematically illustrates a flowchart of a network slice resource adaptive adjustment method according to an exemplary embodiment of this disclosure. Figure 1 As shown, the adaptive adjustment method for network slice resources includes steps S101 to S103:
[0038] Step S101: When the network slicing service provider determines that at least two target network slices have resource conflicts, receive the resource adjustment request sent by the network slicing service provider;
[0039] Step S102: Parse the resource adjustment request to obtain resource conflict information, and determine the priority information and shared resource requirements of each target network slice based on the resource conflict information;
[0040] Step S103: Formulate a resource adjustment strategy for each target network slice based on the priority information and shared resource requirements of each target network slice, and execute the resource adjustment strategy.
[0041] In some embodiments of the present disclosure, the network slicing service provider can identify resource conflicts in network slices, automatically determine the target network slices to be adjusted, and generate resource adjustment requests. Then, after receiving the resource adjustment request, the slice management and orchestration system can determine the priority information and shared resource requirements of each target network slice based on the resource conflict information, and subsequently formulate resource adjustment strategies for each target network slice. On the one hand, this provides a mechanism for autonomously detecting slice resource conflicts and requesting resource adjustments, ensuring network quality and SLA even when resource scheduling issues arise due to sudden surges in traffic demand for services carried by the slices. On the other hand, formulating resource adjustment strategies based on the determined priority information and shared resource requirements of the network slices can solve the problem of predictive resource management and scheduling for multiple slices in resource-constrained scenarios, comprehensively reducing the impact on slice services.
[0042] The following will describe in more detail each step of the network slice resource adaptive adjustment method in this example embodiment, with reference to the accompanying drawings and embodiments.
[0043] In step S101, when the network slicing service provider determines that at least two target network slices have resource conflicts, a resource adjustment request sent by the network slicing service provider is received.
[0044] In one embodiment of this disclosure, a Network Services Provider (NSP) provides or sells services such as network access and bandwidth by offering multiple network slices (NS).
[0045] When a network slicing service provider determines that at least two target network slices have resource conflicts, it will generate a resource adjustment request and send it to the slice management and orchestration system. After receiving the resource adjustment request, the slice management and orchestration system will begin to formulate resource adjustment strategies for each NS.
[0046] Therefore, the method further includes: in response to a monitoring task sent by the network slice service provider, sending service level indicator data of each network slice to the network slice service provider, so that the network slice service provider can determine whether the resource conflict exists based on the service level indicator data and external event information obtained from the network slice consumer.
[0047] Specifically, network slicing service provider NSP needs two types of data to determine whether resource conflicts exist.
[0048] One requirement is to continuously receive Service Level Indicator (SLI) data for each network slice (NS) from the slice management and orchestration system. SLI data mainly refers to key performance monitoring metrics of network slice instances, such as end-to-end latency, number of service slice users, number of PDU sessions, and traffic.
[0049] In order to continuously receive service level indicator data, the network slicing service provider (NSP) needs to create monitoring tasks for each network slice (NS), thereby enabling the NSP to interact with the slice management and orchestration system to monitor the data of each network slice (NS).
[0050] Secondly, it requires interaction with Network Slicing Customs (NSCs) to collect information on external events. For example, sudden events such as emergency large-scale meetings or large-scale live broadcasts collected from external public opinion monitoring systems, or information on temporary service guarantees from customers, will lead to a sudden increase in resource demand.
[0051] Network slicing service providers (NSPs) assess the resource usage of each NS based on its service level indicators (SLE) and external event information, analyzing and determining whether there are potential resource conflicts, i.e., more than one NS needs to be expanded.
[0052] The target network slice with external event identifier to be expanded: the current slice resource utilization rate is r1%, the slice traffic has suddenly increased several times, and it is estimated that the current slice capacity is insufficient and more resources need to be configured.
[0053] Other target network slices to be expanded: If the current slice resource utilization rate is r2%...rn%, and the expected slice traffic growth rate is t2%...tn%, at least one of r2%*t2%...rn%*tn% is greater than 100%, more resources need to be configured.
[0054] It should be noted that a resource adjustment request is only generated when at least two target network slices are determined to have resource conflicts. This is because if a network slice needs to be expanded, the expansion is requested directly from the shared resource pool, and no adjustment of the shared resources is required.
[0055] The target network slice where resource conflicts are identified can be a network slice that needs to execute sudden external events, or a network slice that needs to be expanded when there are traffic spikes based on normal business operations.
[0056] After generating resource adjustment requests, the Network Slicing Service Provider (NSP) sends these resource adjustment requests for the target network slices to be expanded to the slice management and orchestration system.
[0057] Based on the above methods, a method is proposed for Network Slice Service Providers (NSPs) to combine multi-source information such as service level index data and external event information for comprehensive analysis, thereby quickly determining potential conflicts in slice resource demand, thus broadening the functionality of NSPs.
[0058] In step S102, the resource adjustment request is parsed to obtain resource conflict information, and the priority information and shared resource requirements of each target network slice are determined based on the resource conflict information.
[0059] In one embodiment of this disclosure, upon receiving a resource adjustment request, the slice management and orchestration system initiates network slice (NS) resource adaptive adjustment analysis and determines the priority information and shared resource requirements of each target network slice to be expanded based on the resource conflict information corresponding to the resource adjustment request.
[0060] Specifically, Figure 2 This illustration schematically depicts a flowchart of a method for determining priority information and shared resource requirements in an exemplary embodiment of this disclosure. Figure 2 As shown, the method for determining priority information and shared resource requirements in step S102 includes steps S201 to S203:
[0061] Step S201: Based on the resource conflict information, determine the special target network slices with external event identifiers and the ordinary target network slices in the target network slices;
[0062] Step S202: Calculate the traffic volume prediction index values for each of the special target network slices and each of the ordinary target network slices, and determine the shared resource demand based on the traffic volume prediction index values; and
[0063] Step S203: Determine the first sequence of the special target network slice and the second sequence of the ordinary target network slice respectively, and concatenate the first sequence and the second sequence to obtain the priority information.
[0064] Specifically, in step S201, special target network slices that need to process external events and ordinary target network slices that do not process external events need to be processed differently. Therefore, the two types of target network slices are first classified.
[0065] It should be noted that, depending on the actual situation, there may be one or more special target network slices, and similarly, there may be one or more ordinary target network slices.
[0066] In step S202, it is necessary to determine the shared resource requirements of each target network slice. The calculation methods for the traffic forecasting index values of special target network slices and ordinary target network slices differ.
[0067] Specifically, for the specific target network slice, the event type is identified based on the external event identifier, and the traffic volume prediction index value is obtained by predicting the traffic volume based on the historical traffic volume data corresponding to the event type.
[0068] In other words, when a sudden external event occurs, it is first necessary to identify the type of the event, then determine its application pattern, and then combine it with historical traffic data (such as historical traffic, number of slice users, number of PDU sessions) of sudden events with the same application pattern in historical data to perform machine learning, and then output the predicted index value of network slice traffic within the target time period.
[0069] For the ordinary target network slice, the traffic volume prediction index value is obtained by predicting based on the historical traffic volume data of the ordinary target network slice.
[0070] That is, select an appropriate AI algorithm model, make predictions based on the historical traffic data of the network slice, and then output the traffic prediction index value of the network slice within the target time period.
[0071] Based on the above methods, two prediction methods for traffic volume indicators are proposed for special target network slices and ordinary target network slices, which can better reflect the actual situation and have higher prediction accuracy.
[0072] In one embodiment of this disclosure, after obtaining the traffic volume forecast index value of each network slice NS, the shared resource demand of each NS is determined.
[0073] Specifically, determining the shared resource demand based on the traffic volume prediction index value includes: traversing all the target network slices, determining the total resource demand corresponding to the traffic volume prediction index value based on the mapping relationship between traffic volume and resource volume; determining the existing resource volume of the target network slice according to the service level agreement of the target network slice, and calculating the current remaining resource volume of the target network slice based on the existing resource volume and resource utilization rate; and calculating the difference between the total resource demand and the current remaining resource volume as the shared resource demand of the target network slice.
[0074] First, determine the total resource requirement. The mapping relationship between traffic volume and resource volume is pre-configured, for example, through pre-set templates in network resource planning or machine learning algorithm models that have already determined the correspondence between traffic volume and resource volume. Therefore, the corresponding total resource requirement R can be obtained based on the traffic volume prediction index value. The resource requirement includes at least one type of resource such as computing, storage, and bandwidth from any one of the core network (CN), transmission network (TN), and access network (AN). The required resources can be obtained from the current remaining resources of the NS and the shared resource pool.
[0075] Next, calculate the current remaining resource amount. The Service Level Agreement (SLA) describes an agreement between two parties and is a metric for service availability. It represents the pre-configured existing resource amount *c* of the network slice (NS); the resource utilization rate *r%* represents the current resource utilization rate of the NS; based on the existing resource amount *c* and the resource utilization rate *r%*, the current remaining resource amount can be calculated as *c*(1-r%).
[0076] Finally, calculate the shared resource requirement. Given the total resource requirement R of the target network slice and the current remaining resource quantity c*(1-r%), the difference between the two yields the shared resource requirement Rc*(1-r%) that the target network slice needs to extract from the shared resource pool.
[0077] In one embodiment of this disclosure, before determining the existing resource quantity of the target network slice according to the service level agreement of the target network slice, the method further includes: traversing all the target network slices, determining whether the traffic prediction index value of the target network slice exceeds the target extreme value of the service level agreement of the target network slice; and adjusting the service level agreement of the target network slice when the traffic prediction index value exceeds the target extreme value.
[0078] Specifically, after predicting the traffic volume forecast values for each target network slice, it can be determined whether the traffic volume forecast value exceeds the maximum value of the target indicators agreed upon in the Service Level Agreement (SLA). If it exceeds this target extreme value, the SLA needs to be renegotiated, and the existing resource volume corresponding to the Service Level Agreement needs to be changed.
[0079] In step S203, it is necessary to determine the priority information of each target network slice.
[0080] Specifically, the first step is to determine the first sequence of special target network slices. When there are multiple special target network slices, their order can be determined according to event priority; the higher the event priority, the earlier the corresponding target network slice appears. If there is only one special target network slice, the first sequence can be obtained directly without sorting.
[0081] Then, the second sequence of ordinary target network slices is determined. That is, when each target network slice has a priority identifier, the second sequence of ordinary target network slices is determined based on the original priority identifier, that is, the order remains unchanged; when each target network slice does not have a priority identifier, it is sorted from high to low based on the shared resource requirements of each ordinary target network slice. This method minimizes the number of network slices that perceive resource scarcity.
[0082] Finally, the first and second sequences are concatenated. Special target network slices have a higher priority than ordinary target network slices as a whole. Therefore, concatenating the second sequence after the first sequence yields the target network slice sequence. The priority of each target network slice is then set according to the target network slice sequence.
[0083] Based on the above method, the priority of each target network slice and the amount of shared resources required can be obtained, as shown in Table 1.
[0084] Table 1. Priority of target network slices and their shared resource requirements
[0085]
[0086] Wherein, R1-c1(1-r1%)+R2-c2(1-r2%)+...+Rn-c3(1-rn%)>s.
[0087] Based on the above method, it is possible to analyze the shared resource requirements of each target network slice to be expanded, and dynamically determine and update the network slice priority in combination with the service type of the network slice.
[0088] In step S103, a resource adjustment strategy for each target network slice is formulated based on the priority information and shared resource requirements of each target network slice, and the resource adjustment strategy is executed.
[0089] In one embodiment of this disclosure, the step of formulating a resource adjustment strategy for each target network slice based on the shared resource requirements and priority information of each target network slice includes: determining a target network slice sequence according to the priority information; and formulating a resource expansion strategy and / or flow control strategy for each target network slice in each single domain as the resource adjustment strategy according to the target network slice sequence based on the shared resource requirements of each target network slice; wherein, the single domain includes one or more of the core network (CN), the transmission network (TN), and the access network (AN).
[0090] Specifically, based on the shared resource requirements and priority information of each target network slice, the resource adjustment strategy for each target network slice in each single domain is determined sequentially according to the target network slice sequence. A single domain refers to one of the core network (CN), transport network (TN), and access network (AN) included in the target network slice. When formulating resource adjustment strategies, for higher-priority NSs, the strategy will be resource expansion, i.e., a resource capacity expansion strategy, where the expansion capacity is the shared resource requirement; for lower-priority NSs, the strategy will be flow control, access control, etc., i.e., a flow control strategy.
[0091] It should be noted that this strategy can be formulated using an AI (Artificial Intelligence) algorithm model. This model can be retrieved and saved from the AI analysis function module of the slice management and orchestration system. It is a supervised learning model trained by labeling the resource allocation strategy with historical resource demand and resource allocation data, combined with human experience. It can be optimized based on the feedback from strategy execution.
[0092] After determining the resource adjustment strategy for each target network slice, the slice management and orchestration system executes the resource adjustment strategy and then sends the response after execution back to the network slice service provider (NSP).
[0093] Subsequently, once the traffic peak period corresponding to the predicted business volume metric value for external events or other information has passed, the resource configuration strategy for network slices will be updated as before.
[0094] In one embodiment of this disclosure, before executing the resource adjustment strategy, the method further includes: traversing all the target network slices, evaluating the resource adjustment strategy of the target network slices through network digital twin simulation to obtain an evaluation result; and executing the resource adjustment strategy when the evaluation result meets the evaluation pass condition.
[0095] Specifically, to verify the effectiveness of the resource adjustment strategy, the NS resource adjustment strategy can be analyzed through network digital twin simulation before the strategy is executed.
[0096] Digital twins fully utilize data such as physical models, sensor updates, and operational history to integrate multi-disciplinary, multi-physical, multi-scale, and multi-probability simulation processes, completing mapping in virtual space to reflect the entire lifecycle of the corresponding physical equipment.
[0097] The evaluation of the resource adjustment strategy of the target network slice using network digital twins to obtain the evaluation result includes: collecting actual network data of the target network slice; wherein the actual network data includes physical data and operational data; performing digital modeling of the target network slice based on the actual network data to obtain virtual network data; using the virtual network data to determine the future state information of each single domain in the target network slice when executing the resource adjustment strategy; and obtaining the evaluation result based on the future state information of each single domain in the target network slice.
[0098] Figure 3 This schematic diagram illustrates the composition of a network digital twin system according to an exemplary embodiment of this disclosure. (Reference) Figure 3 As shown, the network digital twin system 300 includes a data interaction layer 301, a modeling and management function module 302, and a simulation and analysis function module 303.
[0099] The data interaction layer 301 primarily implements data acquisition, data fusion, and data governance functions. Data acquisition is used to collect intrinsic data from the physical environment, as well as multi-mode, multi-type operational data collected in real time by various sensors. Data fusion is used to capture large amounts of heterogeneous data. Finally, data governance is performed. The data interaction layer sends the governed data to the modeling management module for model optimization.
[0100] The modeling management module 302 primarily handles the digital modeling and representation of the network, its synchronization with the actual network, and its operational management. Modeling management provides digital modeling and model optimization (e.g., self-learning and self-adjustment).
[0101] The simulation analysis module 303 primarily provides model simulation analysis services. Based on the strategy topology and current state, it calculates and simulates the future state of the strategy deployment to evaluate and analyze the strategy.
[0102] Specifically, the data interaction layer 301 collects the physical and operational data of the target network slice, then the modeling and management function module 302 performs digital modeling to obtain virtual network data, and finally the simulation analysis function module 303 determines the future state information of each single domain to obtain the final evaluation result. When the evaluation is passed, it means that the resource adjustment strategy is feasible.
[0103] Based on the above method, the strategy can be verified through network digital twin simulation analysis before deployment, thus ensuring the reliability of the strategy.
[0104] Figure 4 This schematic diagram illustrates the composition of a network slice resource adaptive adjustment system according to an exemplary embodiment of this disclosure. (Reference) Figure 4 As shown, the network slice resource adaptive adjustment system includes a network slice consumer 401, a network service provider 402, and a slice management and orchestration system 403.
[0105] Among them, the network service provider 402 interacts with the network slice consumer 401 and can obtain external event information such as public opinion from the network slice consumer 401; at the same time, the network service provider 402 interacts with the slice management and orchestration system 403 and can realize the request and response to the data monitoring tasks of the slice management and orchestration system 403, as well as the request and response to the adjustment of network slice resources.
[0106] The slice management and orchestration system 403 includes four modules: cross-domain management and orchestration function module 4031, single-domain management and orchestration function module 4032, digital twin simulation verification module 4033, and AI analysis function module 4034.
[0107] Among them, the cross-domain management and orchestration function module 4031 interacts with the network service provider 402 to respond to relevant requests. The modules between the systems interact to complete their respective functions to realize the intelligent management and scheduling of network slices. For example, the AI analysis function module 4034 is responsible for determining the shared resource requirements and priority information of each NS and formulating resource adjustment strategies based on the resource conflict information corresponding to the resource adjustment request. The single-domain management and orchestration function module 4032 is responsible for sending the resource adjustment strategy to the digital twin simulation verification module 4033 to realize the mapping, verification and implementation of the strategy. The digital twin simulation verification module 4033 realizes strategy simulation verification and analysis, AI model verification, digital twin model iteration, etc.
[0108] It should be noted that the network digital twin simulation verification module 4033 can interact not only with the single-domain management and orchestration function module 4032, but also with the cross-domain management and orchestration function module 4031, thereby realizing cross-domain policy simulation verification and analysis.
[0109] Figure 5 This illustration schematically depicts a data interaction diagram of a network slice resource adaptive adjustment system according to an exemplary embodiment of this disclosure. (Reference) Figure 5 As shown, the steps of the network slice resource adaptive adjustment system in executing the network slice resource adaptive adjustment method are as follows:
[0110] Step S501: The network service provider NSP sends a monitoring task request to the cross-domain management and orchestration function module of the slice management and orchestration system.
[0111] Step S502: The cross-domain management and orchestration function module returns the Service Level Indicator (SLI) data for each network slice.
[0112] Step S503: The network slice consumer NSC sends an external message;
[0113] Step S504: The Network Service Provider (NSP) determines whether a resource conflict exists based on the Service Level Indicator (SLI) data and external event information.
[0114] In step S505, when the network service provider NSP determines that there is a resource conflict, it sends a resource adjustment request to the cross-domain management and orchestration function module of the slice management and orchestration system.
[0115] In step S506, the cross-domain management and orchestration function module forwards the resource adjustment request to the AI analysis function module;
[0116] Step S507: The AI analysis function module predicts the traffic volume prediction index value and redefines the shared resource requirements and priority information of the target network slice to be expanded.
[0117] In step S508, the AI analysis module forwards the shared resource demand and priority information to the cross-domain management and orchestration module.
[0118] Step S509: The cross-domain management and orchestration module formulates resource adjustment strategies for the target network slices in each domain based on the shared resource requirements and priority information of each target network slice.
[0119] Step S510: The cross-domain management and orchestration function module sends the resource adjustment strategy of the target network slice in each domain to the single-domain management and orchestration function module.
[0120] In step S511, the single-domain management and orchestration function module calls the network digital twin simulation verification module to perform policy mapping, verification and implementation deployment to execute the resource adjustment policy after the resource adjustment strategy evaluation is passed.
[0121] In step S512, after executing the resource adjustment policy, the completed response is sent to the network service provider NSP.
[0122] Based on the above methods, this disclosure provides a conflict-avoiding adaptive adjustment scheme for slice resources. It utilizes AI-assisted analysis to predict surges in traffic and resource demand, defines slice priorities and resource allocation strategies, verifies these strategies using digital twins, and then deploys the resource adjustment strategy. This scheme ensures network quality and SLA, and enables the identification of potential resource demand conflict scenarios and intelligent, flexible resource scheduling. It can solve the problems of predictive resource management and scheduling of multiple slices in resource-constrained scenarios, comprehensively reducing the impact on slice services; it addresses the resource scheduling problem when slice-borne services experience sudden surges in traffic demand, ensuring network quality and SLA; and it solves the problem of how to ensure slice resource allocation through slice service type identification when multiple slices have resource contention needs.
[0123] Figure 6 This schematic diagram illustrates the composition of a network slice resource adaptive adjustment device in an exemplary embodiment of the present disclosure, such as... Figure 6 As shown, the network slice resource adaptive adjustment device 600 may include a receiving module 601, a parsing module 602, and a strategy module 603. Wherein:
[0124] The receiving module 601 is configured to receive a resource adjustment request sent by the network slicing service provider when the network slicing service provider determines that at least two target network slices have resource conflicts.
[0125] The parsing module 602 is used to parse the resource adjustment request to obtain resource conflict information, and determine the priority information and shared resource requirements of each target network slice based on the resource conflict information;
[0126] The strategy module 603 is used to formulate resource adjustment strategies for each target network slice based on the priority information and shared resource requirements of each target network slice, and to execute the resource adjustment strategies.
[0127] According to an exemplary embodiment of this disclosure, the parsing module 602 includes a determination unit, a demand unit, and a priority unit. The determination unit is used to determine, based on the resource conflict information, special target network slices with external event identifiers and ordinary target network slices in the target network slices. The demand unit is used to calculate the traffic prediction index values for each special target network slice and each ordinary target network slice, and determine the shared resource demand based on the traffic prediction index values. The priority unit is used to determine a first sequence of special target network slices and a second sequence of ordinary target network slices, and concatenate the first sequence and the second sequence to obtain the priority information.
[0128] According to an exemplary embodiment of this disclosure, the demand unit is configured to, for the special target network slice, identify the event type based on the external event identifier and predict the traffic volume prediction index value based on the historical traffic volume data corresponding to the event type; and for the ordinary target network slice, predict the traffic volume prediction index value based on the historical traffic volume data of the ordinary target network slice.
[0129] According to an exemplary embodiment of this disclosure, the demand unit is further configured to traverse all the target network slices, determine the total resource demand corresponding to the predicted service volume index value based on the mapping relationship between service volume and resource volume; determine the existing resource volume of the target network slice according to the service level agreement of the target network slice, and calculate the current remaining resource volume of the target network slice based on the existing resource volume and resource utilization rate; and calculate the difference between the total resource demand and the current remaining resource volume as the shared resource demand of the target network slice.
[0130] According to an exemplary embodiment of this disclosure, the demand unit is further configured to traverse all the target network slices, determine whether the traffic prediction index value of the target network slice exceeds the target extreme value of the service level protocol of the target network slice; and adjust the service level protocol of the target network slice when the traffic prediction index value exceeds the target extreme value.
[0131] According to an exemplary embodiment of this disclosure, the priority unit is configured to determine a first sequence of the special target network slices according to event priority; and when each of the target network slices has a priority identifier, determine a second sequence of the ordinary target network slices based on the original priority identifier; and when each of the target network slices does not have a priority identifier, determine the second sequence based on the shared resource requirements of each of the ordinary target network slices.
[0132] According to an exemplary embodiment of this disclosure, the strategy module 603 is configured to determine a target network slice sequence based on the priority information; and formulate resource expansion strategies and / or traffic control strategies for each target network slice in each single domain as the resource adjustment strategy according to the target network slice sequence and based on the shared resource requirements of the target network slices; wherein, the single domain includes one or more of the core network CN, the transmission network TN, and the access network AN.
[0133] According to an exemplary embodiment of this disclosure, the network slice resource adaptive adjustment device 600 further includes a verification unit. The verification unit is configured to, after formulating a resource adjustment strategy for each target network slice based on the priority information and shared resource requirements of each target network slice, traverse all the target network slices, evaluate the resource adjustment strategy of the target network slices through network digital twins to obtain an evaluation result; and execute the resource adjustment strategy when the evaluation result meets the evaluation pass condition.
[0134] According to an exemplary embodiment of this disclosure, the verification unit is used to collect actual network data of the target network slice; wherein, the actual network data includes physical data and operational data; digitally model the target network slice based on the actual network data to obtain virtual network data; use the virtual network data to determine the future state information of each single domain in the target network slice when executing the resource adjustment strategy; and obtain the evaluation result based on the future state information of each single domain in the target network slice.
[0135] According to an exemplary embodiment of this disclosure, the network slice resource adaptive adjustment device 600 further includes a monitoring unit, which is configured to send service level indicator data of each network slice to the network slice service provider in response to a monitoring task sent by the network slice service provider, so that the network slice service provider can determine whether the resource conflict exists based on the service level indicator data and external event information obtained from the network slice consumer.
[0136] The specific details of each module in the aforementioned network slice resource adaptive adjustment device 600 have been described in detail in the corresponding network slice resource adaptive adjustment method, so they will not be repeated here.
[0137] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.
[0138] In an exemplary embodiment of this disclosure, a storage medium capable of implementing the above-described method is also provided. Figure 7 This schematic diagram illustrates a computer-readable storage medium according to an exemplary embodiment of the present disclosure, such as... Figure 7 As shown, a program product 700 for implementing the above-described method according to an embodiment of the present disclosure is described. This product may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a mobile phone. However, the program product of the present disclosure is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.
[0139] In an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided. Figure 8 The schematic diagram illustrates the structure of a computer system of an electronic device according to an exemplary embodiment of the present disclosure.
[0140] It should be noted that, Figure 8 The computer system 800 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.
[0141] like Figure 8 As shown, the computer system 800 includes a Central Processing Unit (CPU) 801, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 802 or programs loaded from storage section 808 into Random Access Memory (RAM) 803. The RAM 803 also stores various programs and data required for system operation. The CPU 801, ROM 802, and RAM 803 are interconnected via a bus 804. An Input / Output (I / O) interface 805 is also connected to the bus 804.
[0142] The following components are connected to I / O interface 805: an input section 806 including a keyboard, mouse, etc.; an output section 807 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to I / O interface 805 as needed. A removable medium 811, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 810 as needed so that computer programs read from it can be installed into storage section 808 as needed.
[0143] In particular, according to embodiments of this disclosure, the processes described below with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 809, and / or installed from removable medium 811. When the computer program is executed by central processing unit (CPU) 801, it performs various functions defined in the system of this disclosure.
[0144] It should be noted that the computer-readable medium shown in the embodiments of this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such transmitted data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.
[0145] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0146] The units described in the embodiments of this disclosure can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the unit itself.
[0147] In another aspect, this disclosure also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to perform the methods described in the above embodiments.
[0148] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.
[0149] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the method according to the embodiments of this disclosure.
[0150] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein.
[0151] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.
Claims
1. A method for adaptive adjustment of network slice resources, characterized in that, include: When the network slicing service provider determines that at least two target network slices have resource conflicts, the resource adjustment request sent by the network slicing service provider is received. The resource adjustment request is parsed to obtain resource conflict information, and based on the resource conflict information, special target network slices with external event identifiers and ordinary target network slices are identified in the target network slice. Calculate the traffic volume prediction index values for each of the special target network slices and each of the ordinary target network slices, and determine the shared resource requirements of each target network slice based on the traffic volume prediction index values; and The first sequence of the special target network slice and the second sequence of the ordinary target network slice are determined respectively, and the first sequence and the second sequence are concatenated to obtain the priority information of each target network slice; Based on the shared resource requirements and priority information of each target network slice, a resource adjustment strategy is formulated for each target network slice, and the resource adjustment strategy is executed.
2. The network slice resource adaptive adjustment method according to claim 1, characterized in that, The calculation of traffic prediction index values for each of the special target network slices and each of the ordinary target network slices includes: For the specific target network slice, the event type is identified based on the external event identifier, and the traffic volume prediction index value is obtained by predicting the traffic volume based on the historical traffic volume data corresponding to the event type; and For the ordinary target network slice, the traffic volume prediction index value is obtained by predicting based on the historical traffic volume data of the ordinary target network slice.
3. The network slice resource adaptive adjustment method according to claim 1, characterized in that, Determining the shared resource demand based on the business volume forecast index value includes: Traverse all the target network slices and determine the total resource demand corresponding to the predicted service volume index value based on the mapping relationship between service volume and resource volume. The existing resource quantity of the target network slice is determined according to the service level agreement of the target network slice, and the current remaining resource quantity of the target network slice is calculated based on the existing resource quantity and resource utilization rate. The difference between the total resource demand and the current remaining resource amount is calculated as the shared resource demand of the target network slice.
4. The network slice resource adaptive adjustment method according to claim 3, characterized in that, Before determining the existing resource quantity of the target network slice according to the service level agreement of the target network slice, the method further includes: Traverse all the target network slices and determine whether the traffic volume prediction index value of the target network slice exceeds the target extreme value of the service level protocol of the target network slice. When the traffic volume prediction index value exceeds the target extreme value, the service level protocol of the target network slice is adjusted.
5. The network slice resource adaptive adjustment method according to claim 1, characterized in that, The step of determining the first sequence of the special target network slice and the second sequence of the ordinary target network slice includes: Determine the first sequence of the special target network slices according to event priority; and When each of the target network slices has a priority identifier, the second sequence of the ordinary target network slices is determined based on the original priority identifier; When none of the target network slices have a priority identifier, the second sequence is determined based on the shared resource requirements of each of the ordinary target network slices.
6. The network slice resource adaptive adjustment method according to claim 1, characterized in that, The process of formulating resource adjustment strategies for each target network slice based on the shared resource requirements and priority information of each target network slice includes: The target network slice sequence is determined based on the priority information; According to the target network slice sequence, resource expansion strategies and / or traffic control strategies for each target network slice in each single domain are formulated as the resource adjustment strategies based on the shared resource requirements of the target network slices; wherein, the single domain includes one or more of the core network (CN), transmission network (TN), and access network (AN).
7. The network slice resource adaptive adjustment method according to claim 1, characterized in that, Before executing the resource adjustment strategy, the method further includes: By traversing all the target network slices, the resource adjustment strategy of the target network slices is evaluated using network digital twins to obtain the evaluation results; When the evaluation results meet the evaluation pass criteria, the resource adjustment strategy is executed.
8. The network slice resource adaptive adjustment method according to claim 7, characterized in that, The evaluation results obtained by assessing the resource adjustment strategy of the target network slice through network digital twin include: Collect actual network data of the target network slice; wherein, the actual network data includes physical data and operational data; Virtual network data is obtained by digitally modeling the target network slice based on the actual network data. The virtual network data is used to determine the future state information of each single domain in the target network slice when the resource adjustment strategy is executed; The evaluation result is obtained based on the future state information of each single domain in the target network slice.
9. The network slice resource adaptive adjustment method according to claim 1, the method further includes: In response to the monitoring task sent by the network slice service provider, service level indicator data for each network slice is sent to the network slice service provider so that the network slice service provider can determine whether the resource conflict exists based on the service level indicator data and external event information obtained from the network slice consumer.
10. A network slice resource adaptive adjustment device, characterized in that, include: The receiving module is configured to receive a resource adjustment request sent by the network slicing service provider when the network slicing service provider determines that at least two target network slices have resource conflicts; The parsing module is used to parse the resource adjustment request to obtain resource conflict information, and based on the resource conflict information, determine the special target network slice with external event identifier and the ordinary target network slice in the target network slice; Calculate the traffic volume prediction index values for each of the special target network slices and each of the ordinary target network slices respectively, and determine the shared resource requirements of each target network slice based on the traffic volume prediction index values; And determine the first sequence of the special target network slice and the second sequence of the ordinary target network slice respectively, and concatenate the first sequence and the second sequence to obtain the priority information of each target network slice; The strategy module is used to formulate resource adjustment strategies for each target network slice based on the priority information and shared resource requirements of each target network slice, and to execute the resource adjustment strategies.
11. A computer-readable storage medium having a computer program stored thereon, the program, when executed by a processor, implementing the network slice resource adaptive adjustment method as described in any one of claims 1 to 9.
12. An electronic device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the network slice resource adaptive adjustment method as described in any one of claims 1 to 9.
Citation Information
Patent Citations
RAN side network slice resource allocation method and device and electronic equipment
CN112600695A
Overload control mechanism
US20220070737A1
