Intent violation reasoning in a cloud-based computing environment

The system employs machine learning models to analyze monitoring data and differentiate between infrastructure and service composition issues in cloud environments, facilitating automated and efficient intent violation resolution in cloud-based computing systems.

WO2025012686A1PCT designated stage expired Publication Date: 2025-01-16TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)

Patent Information

Application Number
PCT/IB2023/057167
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-07-12
Publication Date
2025-01-16

AI Technical Summary

Technical Problem

Existing systems lack suitable configurations for supporting intent violation reasoning in cloud-based computing environments, where intent violations can be caused by either infrastructure or service composition problems, and current solutions often fail to distinguish between the two, leading to inadequate recovery actions.

Method used

A method and system that utilize machine learning models, such as Bayesian networks, to analyze monitoring data and determine the probability of intent violations being caused by infrastructure or service composition issues, enabling automated reasoning and timely resource-efficient solutions.

Benefits of technology

Enables automated intent violation reasoning, reducing human intervention in service performance management and allowing for timely and resource-efficient resolution of intent violations by distinguishing between infrastructure and service composition problems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure IB2023057167_16012025_PF_FP_ABST
    Figure IB2023057167_16012025_PF_FP_ABST
Patent Text Reader

Abstract

A method implemented in an intent management node for detecting and managing intent violations for a network service in a network is provided, where the network service is associated with a service composition and a network infrastructure. The method includes detecting an intent violation event associated with the network service, analyzing monitoring data associated with the intent violation event, and determining, based on the analyzed monitoring data, whether the intent violation event was caused by at least one of a first problem in the network infrastructure, and a second problem in the service composition.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] INTENT VIOLATION REASONING IN A CLOUD-BASED COMPUTING ENVIRONMENT

[0002] TECHNICAL FIELD

[0003] The present disclosure relates to wireless communications, and in particular, to configurations for supporting intent violation reasoning in a system, such as a cloudbased computing system.

[0004] BACKGROUND

[0005] The Third Generation Partnership Project (3 GPP) has developed and is developing standards for Fourth Generation (4G) (also referred to as Long Term Evolution (LTE)) and Fifth Generation (5G) (also referred to as New Radio (NR)) wireless communication systems. Such systems provide, among other features, broadband communication between network nodes, such as base stations, and mobile wireless devices (WD), as well as communication between network nodes and between WDs. The 3GPP is also developing standards for Sixth Generation (6G) wireless communication networks.

[0006] Intent-based networking in the Software-Defined Network (SDN) domain offers network administrators a streamlined way to express their business goals, such as providing the expected Quality of Experience (QoE), without focusing on the technical details of the network. European Telecommunications Standards Institute (ETSI) Experiential Networked Intelligence (ENI) defines an intent policy as a set of operational goals that a network should meet and outcomes that a network is supposed to deliver, defined in a declarative manner without specifying how to achieve or implement them. For example, it converts a set of intents into detailed data plane configurations such as forwarding and access control rules. Recently, such a concept has been further studied in telecom management areas, such as radio access network (RAN) and cloud end-to-end service provisioning, in which the purpose is to "translate" the user's intent expressed as a set of service requirements into a composition of network functions and resource requirements, known as “service orchestration.”

[0007] When a service is deployed in a cloud environment, the cloud management system may keep provisioning reliable services by providing enough resources to support the service functionality and the performance of the service. The performance of a service may be measured via monitoring relative service metrics, i.e., Key Performance Indicators (KPIs). With the help of, e.g., threshold-based methods or AI / ML technologies, potential intent violations may be detected or predicted, which may eventually trigger a service violation event / alarm. In the presence of a violation, the cloud management system may execute proper actions to recover the service.

[0008] For example, when an intent is translated and deployed, an intent violation may be triggered by cloud system problems, such as infrastructure hardware issues, cloud management software issues, shortages of resources, and security attacks. However, in a dynamic and distributed cloud environment, there are often changes in cloud infrastructures and traffic patterns. A service graph that fulfills the user’s intent in one environment at one time period may suffer from an intent violation in another environment or at a different time period, for example.

[0009] In such a case, an intent violation may be caused by an inappropriate or outdated service composition, e.g., a wrong database was used in a web application, which worked in a lower throughput than expected for a specific edge cloud site. Before a cloud management system may make appropriate decisions for recovery, it may be necessary to understand whether the violation is caused by an infrastructure problem and / or by a service composition issue, which may trigger different actions to solve the intent violation problem.

[0010] Some existing systems utilize an intent-based application QoE management method, used in SDN, for example. Such systems may use a reinforcement learning model for QoE / QoS mapping. For example, an SDN controller judges whether the current network configuration continuously meets the intention request, if so, it maintains the current network configuration to finish the management of the QoE intention, otherwise, it reconfigures the intention path.

[0011] In some existing systems, reinforcement learning is used to calculate QoE and resource correlation for 5G network slicing. For example, a slice agent that calculates QoE / Resource correlation and determines the QoS parameters for a particular QoE may be used in some systems.

[0012] In some other existing systems, a RAN QoS / QoE management method is provided, including an adaptive quality controller, based on classification & a policy of the application. It determines QoE target, maps QoE to QoS, and enforces QoS with an application scheduler and a packet scheduler. It also defines a feedback loop to the QoE and QoS target reconfiguration from the QoE / QoS / Context monitoring results. In some existing systems, an automatic intent provisioning and management for computer networks is provided. Given a policy with high-level configuration data, a service is defined to be deployed within a network and which determines the resource(s) to support the service, translates the high-level configuration data to low- level configuration data.

[0013] In some existing systems, a runtime monitoring and visualization of intentbased network policies is provided. It determines a number of monitoring spots, the resource capacity, and bandwidth demand for runtime flow monitoring, based on a network topology and network configurations.

[0014] In some existing systems, techniques for correlating policy violation incidents are provided, where each policy violation incident is characterized by a set of attributes. It analyzes the policy violation incidents by correlating the attributes of each detected violation incident to find possible relationships between them and present the obtained results to the user.

[0015] In some existing systems, an intent-based service configuration and service conformance is provided, to check whether the assigned resources can support the service from a plurality of potential resources. This may include analyzing meta-data regarding resource attributes and characteristics of unassigned network resources.

[0016] In some existing systems, a logical model of the software-defined network in a hierarchical management information tree that defines manageable objects and object properties for the software-defined network is provided. Using such management information tree, the system may perform a policy analysis of configurations in the logical model and determines, based on the policy analysis, whether the configurations in the logical model contain one or more errors.

[0017] Existing systems, however, may lack suitable configurations for supporting intent violation reasoning in a system, such as a cloud system.

[0018] SUMMARY

[0019] Some embodiments advantageously provide methods, systems, and apparatuses for supporting intent violation reasoning in a system, such as a cloud-based computing system.

[0020] For example, some embodiments may provide a system or a method which may be configured for automatically (1) analyzing and reasoning intent violation events detected in the system and / or cloud, and (2) identifying the type of this violation, e.g., whether it is due to a service composition problem, an infrastructure problem, or a combination of the two, such as by using a machine learning model. For example, some embodiments provide a system and / or method for analyzing data collected from the system and / or cloud environment, such as service performance profiles, monitoring data, and system events, etc., which may be used to build an intelligent network to capture, on the fly, the different variations and / or changes on the monitored system and measure their impacts on the intent violation.

[0021] Some embodiments provide a system and / or method configured for supporting reasoning with different data variations, and building a model, such as a machine learning model, Bayesian network model, etc., to classify the type of each violation. Some embodiments may support, for example, a determination of which is the most possible / probable type of the intent violation, e.g., whether it is a service composition problem, an infrastructure problem, or some combination of the two.

[0022] For example, some embodiments provide an intent violation reasoning method and system that: receives an intent violation event for a specific service; triggers an intent violation reasoning, for which it: obtains data corresponding to the violated intent including cloud system events and alarms from a Cloud Management System, application and infrastructure monitoring data from a Monitoring System, and the service graph and service component resource profiles from an Intent Management System; and analyses all the information received using a model, such as a machine learning model, a reasoning framework, a Bayesian Network, etc.; outputs the potential reason behind the intent violation by calculating the probability of each reason, where the reasons may include, e.g., the infrastructure problem and the service composition problem; and calls a Cloud Management System and / or an Intent Management System to solve the problem accordingly.

[0023] Embodiments of the present disclosure may advantageously support service reconfiguration decision during a service execution phase, such that a service intent may be fulfilled in dynamic and distributed cloud environments.

[0024] Embodiments of the present disclosure may advantageously support automating intent violation reasoning, which may aid in reducing the human intervention required in service performance management. Embodiments of the present disclosure may advantageously support differentiating service composition problems and infrastructure problems, which may aid in solving an intent violation in a more timely and / or more resource-efficient manner.

[0025] According to a first aspect of the present disclosure, a method implemented in an intent management node for detecting and managing intent violations for a network service in a network is provided, where the network service is associated with a service composition and a network infrastructure. The method includes detecting an intent violation event associated with the network service, analyzing monitoring data associated with the intent violation event, and determining, based on the analyzed monitoring data, whether the intent violation event was caused by at least one of a first problem in the network infrastructure, and a second problem in the service composition.

[0026] According to one or more embodiments of this aspect, the first problem corresponds to at least one of a memory problem in at least one node in the network infrastructure, a processor problem in at least one node in the network infrastructure, a hard disk drive (HDD) problem in at least one node in the network infrastructure, an antenna problem in at least one node in the network infrastructure, an energy supply problem in at least one node in the network infrastructure, and a security problem in at least one node in the network infrastructure.

[0027] According to one or more embodiments of this aspect, the second problem corresponds to at least one of a failure to achieve a throughput value defined for the network service, a failure to achieve a latency value defined for the network service, a failure to achieve a capacity value defined for the network service and a use of a database not suitable for the network service.

[0028] According to one or more embodiments of this aspect, the monitoring data includes at least one of hardware fault data associated with the network infrastructure, performance metrics data associated with the service composition, performance profile data associated with the service composition, system event data associated with the network, alarm data associated with the network, and cloud configuration change data associated with the network.

[0029] According to one or more embodiments of this aspect, the analysis of the monitoring data includes determining a first probability that the intent violation event was caused by the first problem in the network infrastructure, and a second probability that the intent violation event was caused by the second problem in the service composition.

[0030] According to one or more embodiments of this aspect, the method further includes adjusting the network infrastructure for the network service based on the first probability exceeding a first threshold.

[0031] According to one or more embodiments of this aspect, the method further includes adjusting the service composition for the network service based on the second probability exceeding a second threshold.

[0032] According to one or more embodiments of this aspect, the method further includes adjusting both the network infrastructure for the network service and the service composition for the network service based on the first probability exceeding a third threshold, and the second probability exceeding a fourth threshold.

[0033] According to one or more embodiments of this aspect, at least one of the first probability and the second probability is determined based on at least one of a probabilistic method and a machine learning model.

[0034] According to one or more embodiments of this aspect, at least one of the first probability and the second probability is determined based on a Bayesian network.

[0035] According to another aspect of the present disclosure, an intent management node for detecting and managing intent violations for a network service in a network is provided, where the network service is associated with a service composition and a network infrastructure. The intent management node is configured to detect an intent violation event associated with the network service, analyze monitoring data associated with the intent violation event, and determine, based on the analyzed monitoring data, whether the intent violation event was caused by at least one of a first problem in the network infrastructure, and a second problem in the service composition.

[0036] According to one or more embodiments of this aspect, the first problem corresponds to at least one of a memory problem in at least one node in the network infrastructure, a processor problem in at least one node in the network infrastructure, a hard disk drive (HDD) problem in at least one node in the network infrastructure, an antenna problem in at least one node in the network infrastructure, an energy supply problem in at least one node in the network infrastructure, and a security problem in at least one node in the network infrastructure.

[0037] According to one or more embodiments of this aspect, the second problem corresponds to at least one of a failure to achieve a throughput value defined for the network service, a failure to achieve a latency value defined for the network service, a failure to achieve a capacity value defined for the network service, and a use of a database not suitable for the network service.

[0038] According to one or more embodiments of this aspect, the monitoring data includes at least one of hardware fault data associated with the network infrastructure, performance metrics data associated with the service composition, performance profile data associated with the service composition, system event data associated with the network, alarm data associated with the network, and cloud configuration change data associated with the network.

[0039] According to one or more embodiments of this aspect, the analysis of the monitoring data includes determining a first probability that the intent violation event was caused by the first problem in the network infrastructure, and a second probability that the intent violation event was caused by the second problem in the service composition.

[0040] According to one or more embodiments of this aspect, the intent management node is further configured to adjust the network infrastructure for the network service based on the first probability exceeding a first threshold.

[0041] According to one or more embodiments of this aspect, the intent management node is further configured to adjust the service composition for the network service based on the second probability exceeding a second threshold.

[0042] According to one or more embodiments of this aspect, the intent management node is further configured to adjust both the network infrastructure for the network service and the service composition for the network service based on the first probability exceeding a third threshold, and the second probability exceeding a fourth threshold.

[0043] According to one or more embodiments of this aspect, at least one of the first probability and the second probability is determined based on at least one of a probabilistic method and a machine learning model.

[0044] According to one or more embodiments of this aspect, at least one of the first probability and the second probability is determined based on a Bayesian network. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] A more complete understanding of the present embodiments, and the attendant advantages and features thereof, will be more readily understood by reference to the following detailed description when considered in conjunction with the accompanying drawings wherein:

[0046] FIG. 1 is a schematic diagram of an example network architecture illustrating a communication system according to principles disclosed herein;

[0047] FIG. 2 is a block diagram of a network node in communication with a wireless device over a wireless connection and in communication with a management node and core node over a wireless and / or wired connection, according to some embodiments of the present disclosure;

[0048] FIG. 3 is a flowchart of an example process in an intent management node for supporting intent violation reasoning in a system, such as a cloud system according to some embodiments of the present disclosure;

[0049] FIG. 4 is a flowchart of an example process according to some embodiments of the present disclosure;

[0050] FIG. 5 is a flowchart of another example process according to some embodiments of the present disclosure;

[0051] FIG. 6 is a signaling diagram illustrating another example process according to some embodiments of the present disclosure;

[0052] FIG. 7 is a flowchart of another example process according to some embodiments of the present disclosure;

[0053] FIG. 8 is a flowchart of another example process according to some embodiments of the present disclosure;

[0054] FIG. 9 is a flowchart of another example process according to some embodiments of the present disclosure; and

[0055] FIG. 10 is a flowchart of another example process according to some embodiments of the present disclosure.

[0056] DETAILED DESCRIPTION

[0057] Many existing solutions related to intent translation and deployment analyze the intent and map it into the required QoE / QoS. When testing intent deployment and seeing an intent violation, such solutions only assume that there is a service composition problem, but do not consider that an infrastructure problem could be the reason.

[0058] For example, some existing solutions are limited to finding QoE / QoS related reasons behind the intent violation. However, many reasons could be behind the violation of the intent including functional and non-functional requirements.

[0059] Some existing systems using RL / feedback loop to solve the intent translation and mapping intent to service configurations typically only consider intent violation as infrastructure faults once an intent is deployed. In dynamic and distributed cloud environments, however, a run-time intent violation may be caused by both reasons: infrastructure problems and / or service composition problems.

[0060] Considering the above-mentioned problems, there is a need for a solution that can automatically analyze intent violation events and determine whether it is due to an infrastructure problem and / or a service composition problem.

[0061] Before describing in detail example embodiments, it is noted that the embodiments reside primarily in combinations of apparatus components and processing steps related to supporting intent violation reasoning in a system, such as a cloud-based computing system. Accordingly, components have been represented where appropriate by conventional symbols in the drawings, showing only those specific details that are pertinent to understanding the embodiments so as not to obscure the disclosure with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.

[0062] As used herein, relational terms, such as “first” and “second,” “top” and “bottom,” and the like, may be used solely to distinguish one entity or element from another entity or element without necessarily requiring or implying any physical or logical relationship or order between such entities or elements. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the concepts described herein. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and / or “including” when used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. In embodiments described herein, the joining term, “in communication with” and the like, may be used to indicate electrical or data communication, which may be accomplished by physical contact, induction, electromagnetic radiation, radio signaling, infrared signaling or optical signaling, for example. One having ordinary skill in the art will appreciate that multiple components may interoperate and modifications and variations are possible of achieving the electrical and data communication.

[0063] In some embodiments described herein, the term “coupled,” “connected,” and the like, may be used herein to indicate a connection, although not necessarily directly, and may include wired and / or wireless connections.

[0064] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the concepts described herein. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and / or “including” when used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0065] The term “network node” used herein can be any kind of network node comprised in a radio network which may further comprise any of base station (BS), radio base station, base transceiver station (BTS), base station controller (BSC), radio network controller (RNC), g Node B (gNB), evolved Node B (eNB or eNodeB), Node B, multi- standard radio (MSR) radio node such as MSR BS, multi-cell / multicast coordination entity (MCE), relay node, donor node controlling relay, radio access point (AP), transmission points, transmission nodes, Remote Radio Unit (RRU) Remote Radio Head (RRH), a core network node (e.g., mobile management entity (MME), selforganizing network (SON) node, a coordinating node, positioning node, MDT node, etc.), an external node (e.g., 3rd party node, a node external to the current network), nodes in distributed antenna system (DAS), a spectrum access system (SAS) node, an element management system (EMS), etc. The network node may also comprise test equipment. The term “radio node” used herein may be used to also denote a wireless device (WD) such as a wireless device (WD) or a radio network node.

[0066] In some embodiments, the non-limiting terms wireless device (WD) or a user equipment (UE) are used interchangeably. The WD herein can be any type of wireless device capable of communicating with a network node or another WD over radio signals, such as wireless device (WD). The WD may also be a radio communication device, target device, device to device (D2D) WD, machine type WD or WD capable of machine to machine communication (M2M), low-cost and / or low-complexity WD, a sensor equipped with WD, Tablet, mobile terminals, smart phone, laptop embedded equipped (LEE), laptop mounted equipment (LME), USB dongles, Customer Premises Equipment (CPE), an Internet of Things (loT) device, or a Narrowband loT (NB-IOT) device etc.

[0067] Also, in some embodiments the generic term “radio network node” is used. It can be any kind of a radio network node which may comprise any of base station, radio base station, base transceiver station, base station controller, network controller, RNC, evolved Node B (eNB), Node B, gNB, Multi-cell / multicast Coordination Entity (MCE), relay node, access point, radio access point, Remote Radio Unit (RRU) Remote Radio Head (RRH).

[0068] Note that although terminology from one particular wireless system, such as, for example, 3GPP LTE and / or New Radio (NR), may be used in this disclosure, this should not be seen as limiting the scope of the disclosure to only the aforementioned system. Other wireless systems, including without limitation Wide Band Code Division Multiple Access (WCDMA), Worldwide Interoperability for Microwave Access (WiMax), Ultra Mobile Broadband (UMB) and Global System for Mobile Communications (GSM), may also benefit from exploiting the ideas covered within this disclosure.

[0069] An intent, as used herein, may refer to a high-level description of QoE in a SDN, or it may be a policy / rule definition in a service orchestration environment. As used herein, the term intent may be generalized as a business goal definition without necessarily including technical details. For example, intent may be defined according to a natural human language or some rule specifications following a certain format. An intent may be defined so as to comply with a Service Level Agreement (SLA). For example, an intent may refer to “what” requirements need to be met, rather than “how” to meet such requirements. Such requirements may, for example, be grouped into: (a) functional and (b) non- functional requirements:

[0070] Functional requirements may define what a software environment must do and how the system must respond to inputs and generate the output (e.g., calculations, technical details, data manipulation and processing, etc.) Non-functional requirements may define the system’s non- fundamental behaviors, such as performance requirements, security requirements, and reliability requirements.

[0071] Examples of an intent could include:

[0072] Example 1: “A web service to handle 1000 transactions per minute and provide the highest levels of security and reliability, with latency no longer than 3 seconds”.

[0073] Example 2: “Service to provide two Slices. One with minimum throughput of 10 MB / s and the other with 20 MB / s. The second slice shall be able to serve at least 1000 users.”

[0074] As used herein, Quality of Experience (QoE) may refer to a measure of the overall level of customer satisfaction with a vendor. QoE is related to but differs from Quality of Service (QoS), which embodies the notion that hardware and software characteristics can be measured, improved and perhaps guaranteed. In contrast, QoE expresses user satisfaction both objectively and subjectively.

[0075] As used herein, QoS may refer to the description or measurement of the overall performance of a service, particularly the performance seen by the users of the network. To quantitatively measure quality of service, several related KPIs of the network service are typically considered, such as response time, throughput, transmission delay, availability, jitter, etc.

[0076] As used herein, a Service Level Agreement (SLA) may refer to a commitment between a service provider and a client / service user. Aspects of the service, such as quality, availability, and responsibilities, may be agreed between the service provider and the service user. SLA may include, for example, QoS KPIs

[0077] Note further, that functions described herein as being performed by a wireless device, core node, management node, or a network node may be distributed over a plurality of wireless devices, core nodes, management nodes, and / or network nodes. In other words, it is contemplated that the functions of the network node, core node, management node, and wireless device described herein are not limited to performance by a single physical device and, in fact, can be distributed among several physical devices.

[0078] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It will be further understood that terms used herein should be interpreted as having a meaning that is consistent with their meaning in the context of this specification and the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0079] Some embodiments are directed to systems and methods for supporting intent violation reasoning in a system, such as a cloud-based computing system.

[0080] Referring to the drawing figures, in which like elements are referred to by like reference numerals, there is shown in FIG. 1 a schematic diagram of a communication system 10, according to an embodiment, such as a 3GPP-type cellular network that may support standards such as LTE and / or NR (5G), which comprises an access network 12, such as a radio access network, and a core network 13 comprising one or more core nodes 14 for performing core node functions. The core network may also comprise a management node 15 for performing one or more network management functions, which may be a type of core node 14 or a different type of node from core node 14. The access network 12 comprises a plurality of network nodes 16a, 16b, 16c (referred to collectively as network nodes 16), such as NBs, eNBs, gNBs or other types of wireless access points, each defining a corresponding coverage area 18a, 18b, 18c (referred to collectively as coverage areas 18). Each network node 16a, 16b, 16c is connectable to the core network 13 over a wired or wireless connection 20. A first wireless device (WD) 22a located in coverage area 18a is configured to wirelessly connect to, or be paged by, the corresponding network node 16a. A second WD 22b in coverage area 18b is wirelessly connectable to the corresponding network node 16b. While a plurality of WDs 22a, 22b (collectively referred to as wireless devices 22) are illustrated in this example, the disclosed embodiments are equally applicable to a situation where a sole WD is in the coverage area or where a sole WD is connecting to the corresponding network node 16. Note that although only two WDs 22, one core node 14, one management node 15, and three network nodes 16 are shown for convenience, the communication system may include many more WDs 22, core nodes 14, management nodes 15, and network nodes 16.

[0081] Also, it is contemplated that a WD 22 can be in simultaneous communication and / or configured to separately communicate with more than one network node 16 and more than one type of network node 16. For example, a WD 22 can have dual connectivity with a network node 16 that supports LTE and the same or a different network node 16 that supports NR. As an example, WD 22 can be in communication with an eNB for LTE / E-UTRAN and a gNB for NR / NG-RAN. A management node 15, which in some embodiments may be referred to as an intent management node 15 and / or a cloud management node 15, may include an intent violation detector unit 23, an intent reasoning unit 24, and / or a monitoring unit 25. In some embodiments, one or more of these units may be implemented in one or more core nodes 14. In some implementations, violation detector unit 23 and intent reasoning unit 24 may be combined.

[0082] Example implementations, in accordance with an embodiment, of the WD 22, core node 14, management node 15, and network node 16 discussed in the preceding paragraphs will now be described with reference to FIG. 2.

[0083] The communication system 10 includes a network node 16 provided in a communication system 10 and including hardware 28 enabling it to communicate with the WD 22. The hardware 28 may include a radio interface 30 for setting up and maintaining at least a wireless connection 32 with a WD 22 located in a coverage area 18 served by the network node 16. The radio interface 30 may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers, and / or one or more RF transceivers. The radio interface 30 includes an array of antennas 34 to radiate and receive signal(s) carrying electromagnetic waves.

[0084] In the embodiment shown, the hardware 28 of the network node 16 further includes processing circuitry 36. The processing circuitry 36 may include a processor 38 and a memory 40. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 36 may comprise integrated circuitry for processing and / or control, e.g., one or more processors and / or processor cores and / or FPGAs (Field Programmable Gate Array) and / or ASICs (Application Specific Integrated Circuitry) adapted to execute instructions. The processor 38 may be configured to access (e.g., write to and / or read from) the memory 40, which may comprise any kind of volatile and / or nonvolatile memory, e.g., cache and / or buffer memory and / or RAM (Random Access Memory) and / or ROM (Read- Only Memory) and / or optical memory and / or EPROM (Erasable Programmable Read- Only Memory).

[0085] Thus, the network node 16 further has software 42 stored internally in, for example, memory 40, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the network node 16 via an external connection. The software 42 may be executable by the processing circuitry 36. The processing circuitry 36 may be configured to control and execute any of the methods and / or processes described herein and / or to cause such methods, and / or processes to be performed, e.g., by network node 16. Processor 38 corresponds to one or more processors 38 for performing network node 16 functions described herein. The memory 40 is configured to store data, programmatic software code and / or other information described herein. In some embodiments, the software 42 may include instructions that, when executed by the processor 38 and / or processing circuitry 36, causes the processor 38 and / or processing circuitry 36 to perform the processes described herein with respect to network node 16.

[0086] The communication system 10 further includes the WD 22 already referred to. The WD 22 may have hardware 44 that may include a radio interface 46 configured to set up and maintain a wireless connection 32 with a network node 16 serving a coverage area 18 in which the WD 22 is currently located. The radio interface 46 may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers, and / or one or more RF transceivers. The radio interface 46 includes an array of antennas 48 to radiate and receive signal(s) carrying electromagnetic waves.

[0087] The hardware 44 of the WD 22 further includes processing circuitry 50. The processing circuitry 50 may include a processor 52 and memory 54. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 50 may comprise integrated circuitry for processing and / or control, e.g., one or more processors and / or processor cores and / or FPGAs (Field Programmable Gate Array) and / or ASICs (Application Specific Integrated Circuitry) adapted to execute instructions. The processor 52 may be configured to access (e.g., write to and / or read from) memory 54, which may comprise any kind of volatile and / or nonvolatile memory, e.g., cache and / or buffer memory and / or RAM (Random Access Memory) and / or ROM (Read-Only Memory) and / or optical memory and / or EPROM (Erasable Programmable Read-Only Memory).

[0088] Thus, the WD 22 may further comprise software 56, which is stored in, for example, memory 54 at the WD 22, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the WD 22. The software 56 may be executable by the processing circuitry 50.

[0089] The processing circuitry 50 may be configured to control any of the methods and / or processes described herein and / or to cause such methods, and / or processes to be performed, e.g., by WD 22. The processor 52 corresponds to one or more processors 52 for performing WD 22 functions described herein. The WD 22 includes memory 54 that is configured to store data, programmatic software code and / or other information described herein. In some embodiments, the software 56 may include instructions that, when executed by the processor 52 and / or processing circuitry 50, causes the processor 52 and / or processing circuitry 50 to perform the processes described herein with respect to WD 22.

[0090] The communication system 10 further includes the management node 15 already referred to. The management node 15 may have hardware 58 that may include a communication interface 60 configured to set up and maintain a wired and / or wireless connection 62 with one or more core nodes 14 and / or with a network node 16 serving a coverage area 18.

[0091] The hardware 58 of the management node 15 further includes processing circuitry 64. The processing circuitry 64 may include a processor 66 and memory 68. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 64 may comprise integrated circuitry for processing and / or control, e.g., one or more processors and / or processor cores and / or FPGAs and / or ASICs adapted to execute instructions. The processor 66 may be configured to access (e.g., write to and / or read from) memory 68, which may comprise any kind of volatile and / or nonvolatile memory, e.g., cache and / or buffer memory and / or RAM and / or ROM and / or optical memory and / or EPROM.

[0092] Thus, the management node 15 may further comprise software 70, which is stored in, for example, memory 68 at the management node 15, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the management node 15. The software 70 may be executable by the processing circuitry 76.

[0093] The processing circuitry 64 may be configured to control any of the methods and / or processes described herein and / or to cause such methods, and / or processes to be performed, e.g., by management node 15. The processor 66 corresponds to one or more processors 66 for performing management node 15 functions described herein. The management node 15 includes memory 68 that is configured to store data, programmatic software code and / or other information described herein. In some embodiments, the software 70 may include instructions that, when executed by the processor 66 and / or processing circuitry 64, causes the processor 66 and / or processing circuitry 64 to perform the processes described herein with respect to management node 15, such as with respect to intent violation detector unit 23, intent reasoning unit 24, and / or monitoring unit 25.

[0094] The communication system 10 further includes the core node 14 already referred to. The core node 14 may have hardware 72 that may include a communication interface 74 configured to set up and maintain a wired and / or wireless connection 62 with one or more core nodes 14, management nodes 15, and / or with a network node 16 serving a coverage area 18.

[0095] The hardware 72 of the core node 14 further includes processing circuitry 76. The processing circuitry 76 may include a processor 78 and memory 80. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 76 may comprise integrated circuitry for processing and / or control, e.g., one or more processors and / or processor cores and / or FPGAs and / or ASICs adapted to execute instructions. The processor 78 may be configured to access (e.g., write to and / or read from) memory 80, which may comprise any kind of volatile and / or nonvolatile memory, e.g., cache and / or buffer memory and / or RAM and / or ROM and / or optical memory and / or EPROM.

[0096] Thus, the core node 14 may further comprise software 82, which is stored in, for example, memory 80 at the core node 14, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the core node 14. The software 82 may be executable by the processing circuitry 76.

[0097] The processing circuitry 76 may be configured to control any of the methods and / or processes described herein and / or to cause such methods, and / or processes to be performed, e.g., by core node 14. The processor 78 corresponds to one or more processors 78 for performing core node 14 functions described herein. The core node 14 includes memory 80 that is configured to store data, programmatic software code and / or other information described herein. In some embodiments, the software 82 may include instructions that, when executed by the processor 78 and / or processing circuitry 76, causes the processor 78 and / or processing circuitry 76 to perform the processes described herein with respect to core node 14. In some embodiments, a management node 15 may be implemented in and / or identical to a core node 14. In some embodiments, one or more of the intent violation detector unit 23, intent reasoning unit 24, and / or monitoring unit 25 may be implemented in the processing circuitry 76, processor 78, memory 80, and / or software 82 of the core node 14. In some embodiments, the inner workings of the core node 14, management node 15, network node 16, and WD 22 may be as shown in FIG. 2 and independently, the surrounding network topology may be that of FIG. 1.

[0098] The wireless connection 32 between the WD 22 and the network node 16 is in accordance with the teachings of the embodiments described throughout this disclosure. More precisely, the teachings of some of these embodiments may improve the data rate, latency, and / or power consumption and thereby provide benefits such as reduced user waiting time, relaxed restriction on file size, better responsiveness, extended battery lifetime, etc. In some embodiments, a measurement procedure may be provided for the purpose of monitoring data rate, latency and other factors on which the one or more embodiments improve.

[0099] Although FIGS. 1 and 2 show various “units” such as intent violation detector unit 23, intent reasoning unit 24, and monitoring unit 25 as being within a respective processor, it is contemplated that these units may be implemented such that a portion of the unit is stored in a corresponding memory within the processing circuitry. In other words, the units may be implemented in hardware or in a combination of hardware and software within the processing circuitry. Further, these units may be implemented in a single node and / or in separate nodes (e.g., virtual nodes, physical nodes, etc.).

[0100] FIG. 3 is a flowchart of an example process in a management node 15, referred to in some embodiments as an intent management node 15, for supporting intent violation reasoning in a system, such as a cloud system. One or more blocks described herein may be performed by one or more elements of management node 15 such as by one or more of processing circuitry 64 (including the intent violation detector unit 23, intent reasoning unit 24, and monitoring unit 25), processor 66, and / or communication interface 60. Management node 15 is configured to detect (Block S100) an intent violation event associated with the network service. Management node 15 is configured to analyze (Block S102) monitoring data associated with the intent violation event. Management node 15 is further configured to determine (Block S104), based on the analyzed monitoring data, whether the intent violation event was caused by at least one of a first problem in the network infrastructure, or a second problem in the service composition. As used herein, “network infrastructure” may refer to one or more physical and / or virtual nodes, devices, servers, cloud nodes, etc., such as WDs 22, network nodes 16, core nodes 14, management nodes 15, etc. For example, a “service composition” may correspond to one or more services, functions, steps, etc., associated with an intent. For example, “network infrastructure” may correspond to one or more hardware devices, logical devices, software devices, virtual devices, platforms, physical nodes, logical nodes, virtual nodes, etc. For example, “problem” may correspond to one or more of faults, performance degradations, security threats, etc.

[0101] In some embodiments, the first problem corresponds to at least one of a memory problem in at least one node in the network infrastructure, a processor problem in at least one node in the network infrastructure, a hard disk drive (HDD) problem in at least one node in the network infrastructure, an antenna problem in at least one node in the network infrastructure, an energy supply problem in at least one node in the network infrastructure, and a security problem in at least one node in the network infrastructure.

[0102] In some embodiments, the second problem corresponds to at least one of a failure to achieve a throughput value defined for the network service, a failure to achieve a latency value defined for the network service, a failure to achieve a capacity value defined for the network service and a use of a database not suitable for the network service. Thus, while the second problem here may be related to not achieving the non- functional requirements defined in an intent, the second problem can also be related to the functional ones, e.g., the selected services in the service graph, how those services are connected, the mapping of the intent to the services, etc. Further, the problem such as the failure to achieve a value may be the cause of a fault that results from a symptom. For example, a non-proper database usage (fault) may cause a failure to achieve a throughput value defined for the network service (symptom), a non-proper microservice may have been selected that failed to achieve a capacity value defined for the network service, of a wrong network function may have been selected that failed to achieve a latency requirement defined for the network service.

[0103] In some embodiments, the monitoring data includes at least one of hardware fault data associated with the network infrastructure, performance metrics data associated with the service composition, performance profile data associated with the service composition, system event data associated with the network, alarm data associated with the network, and cloud configuration change data associated with the network.

[0104] In some embodiments, the analysis of the monitoring data includes determining a first probability that the intent violation event was caused by the first problem in the network infrastructure, and a second probability that the intent violation event was caused by the second problem in the service composition.

[0105] In some embodiments, the intent management node 15 is further configured to adjust the network infrastructure for the network service based on the first probability exceeding a first threshold.

[0106] In some embodiments, the intent management node 15 is further configured to adjust the service composition for the network service based on the second probability exceeding a second threshold.

[0107] In some embodiments, the intent management node 15 is further configured to adjust both the network infrastructure for the network service and the service composition for the network service based on the first probability exceeding a third threshold, and the second probability exceeding a fourth threshold.

[0108] In some embodiments, at least one of the first probability and the second probability is determined based on at least one of a probabilistic method and a machine learning model.

[0109] In some embodiments, at least one of the first probability and the second probability is determined based on a Bayesian network.

[0110] Having described the general process flow of arrangements of the disclosure and having provided examples of hardware and software arrangements for implementing the processes and functions of the disclosure, the sections below provide details and examples of arrangements for supporting intent violation reasoning in a system 10, such as a system, such as a cloud-based computing system.

[0111] Embodiments of the present disclosure may provide intent violation reasoning systems and methods (e.g., implemented in a system 10 including one or more of a core node 14, management node 15, network node 16, etc.) that may automatically and dynamically analyze violated intents in a system, such as a cloud environment and / or cloud system, based on data collected (e.g., on the fly, during runtime) from such environment. This may enable reasoning as to which type of intent violation occurred and identifying the probability of the violation type, e.g., whether it is a composition problem, infrastructure problem, or a combination of the two.

[0112] FIG. 4 illustrates an example embodiment for intent violation reasoning.

[0113] In Step SI 10, the intent management node 15, including intent violation detector unit 23 and / or intent reasoning unit 24 (also referred to as an “intent reasoner system”) receives as inputs the user’s intent (e.g., with the service graph and a description of required services to fulfill the intent), one or more service performance profiles associated with the service graph and / or system, monitoring data, alarms, and / or system events, e.g., as provided by monitoring unit 25. In Step S 112, the intent violation detector unit 23 and / or intent reasoning unit 24 detects an intent violation and may send an indication of the detected intent violation.

[0114] For example, intent management node 15 may be configured to collect a large amount of data from the managed cloud system (e.g., from one or more core nodes 14, management nodes 15, network nodes 16, etc.), including, for example, a status of infrastructure, events that the cloud system has experienced (including, e.g., hardware changes, alarms, changes on applications or workload, etc.) and profiles of the services composing the intent. Non-limiting examples of such services may include Virtual Network Functions (VNFs) and microservices. Management node 15 may be configured to build a network-based ML model to capture the different changes (and possible transitions) between the states of the cloud system. One example of a network-based model includes a Bayesian network, but other models, such as ML models, may be used in various embodiments (e.g., Random Forest and Graph Neural Network, for example).

[0115] In Step SI 14, once an intent violation is detected by intent violation detector unit 23, intent management node 15 may collect the required data to be fitted to the ML model, e.g., Bayesian network, and may identify the type of intent violation and its probability. In Step SI 16, the output of the intent validation reasoner step may include a probability of each violation type (e.g., a probability of a composition problem, a probability of an infrastructure problem, etc.). This information cloud may be used by an Intent-Based Framework (e.g., in the same intent management node 15, or in a different management node 15, such as a cloud management node 15) to find appropriate actions to be applied to avoid intent violations in the future.

[0116] FIG. 5 illustrates an example embodiment of an Intent Violation Reasoner step (Step S 112) described with respect to FIG. 4. This step may be implemented as a part of a cloud management system, e.g., in an intent management node 15, which may include the following components or steps:

[0117] Step S 120: An intent management node 15 and / or other management node 15 translates a user’s intent via compositing network functions or microservices into a service graph, and deploys the service graph in the cloud system (Step S 121). If a running service graph leads to an intent violation, as detected by intent violation detector unit 23, the intent management node 15 may need to perform a service recomposition and / or reconfiguration. The service graph generation may be based on profiling, e.g., as defined for VNFs or microservices, for example.

[0118] For example, a serverless application management framework including an intent management node 15 may be configured to automate the resource management of the functions of the serverless applications. This may be based on service performance profiles predictions for the functions in a serverless application using minimal number of performance data points, i.e., without the need to test all memory configurations supported by a function-as-a-service (FaaS) platform which minimizes the cost overhead incurred by generating the profiles.

[0119] Step S122: Service Performance Profile Predictions may provide intent management node 15 with information for predicting the performance KPI values of a specific service, e.g., given current workload and resource status information.

[0120] Step S 124: A monitoring unit 25 may be configured to collect the application KPIs and the infrastructure metric data, such as CPU, memory, HDD and network utilizations associated with one or more physical and / or virtual entities of system 10. This information (e.g., KPIs, infrastructure data, etc.) may be provided to the intent violation detector unit 23 and / or intent reasoning unit 24.

[0121] Step S 125: An intent violation detector unit 23 is configured to detect the application QoS violations via monitoring the application KPIs, for example. Once an intent violation is detected, the intent reasoning unit 24 receives a request to analyze whether the violation is caused by an infrastructure problem or a service composition problem, or some combination of the two.

[0122] Step S126: A management node 15, such as intent management node 15 or cloud management node 15, may provide alarm and / or event information to the intent reasoning unit 24 and / or monitoring unit 25.

[0123] Step S128: The intent reasoning unit 24 applies, e.g., a Bayesian network, to analyze the violation reasons, based on alarm information, event information performance KPIs, infrastructure data, intent (service graph) information, service performance profile information, and / or violation detection information. The intent reasoning unit 24 may determine a probability of each violation type (composition problem %, infrastructure problem %, etc.

[0124] Step S130: In some embodiments, the (cloud) management node 15 is configured to manage a system infrastructure, cloud infrastructure, etc. Once an infrastructure fault has been identified, it is configured for locating the fault and recovering the system.

[0125] Step S 132: In some embodiments, when a composition problem has been identified, a request for service re-composition may be sent to an intent management node 15, e.g., for adjusting, reconfiguring, updating, etc., an intent and / or service graph.

[0126] FIG. 6 is a sequence diagram illustrating an example intent violation reasoning process, e.g., in an intent reasoning unit 24, according to some embodiments.

[0127] In some embodiments, the reasoning process may be triggered by an intent violation detection event from intent violation detector unit 23, e.g., the response time for a web request is detected as being higher than a threshold. The intent reasoning unit 24 may then request to collect information for analyzing whether the violation is caused by an infrastructure problem, a composition problem, or a combination of both. The information may include, for example:

[0128] 1) System alarms / events generated by the cloud management node 15 (and / or other nodes, entities, units, etc.) between the last violation and the current violation time, e.g., a hard disk fault and a new CPU added to the cloud system (e.g., to virtual nodes of system 10, physical entities of system 10, etc.).

[0129] 2) The infrastructure and cloud management system data collected between the last violation and the current violation time, e.g., the CPU, Memory, HDD, Network utilization and the container / pod resource utilization. The data may be provided by a monitoring unit 25, for example.

[0130] 3) The service profile is generated by the intent management node 15 for each component (e.g., a VNF or a microservice) in the service graph, e.g., an expected performance profile, e.g., the database 1 is expected to process 100 reads and 50 writes per second with 500m of memory, and frontend service 1 is expected to handle 200 requests per second with 2 CPU cores, 1GB memory and 500mbps network speed.

[0131] Once all of the information has been collected, the intent reasoning unit 24 may analyze the cloud system events / alarms, the service performance profile and the monitoring data and determines the probabilities of the violation type, e.g., 80% service composition problem, 20% infrastructure problem. The intent reasoning unit 24, based on these probabilities, determines to request either the cloud management node 15 to solve the infrastructure problem or the intent management node 15 to redo the service composition, or both. Finally, the intent reasoning unit 24 may respond to the intent violation detector unit 23 that the current intent violation has been handled. A variety of implementations for the cloud management node 15 and intent management node 15 to respond to the violation may be used without deviating from the scope of the present disclosure.

[0132] Step S 140: An intent violation detector unit 23 informs the intent reasoning unit 24 of a service intent violation event.

[0133] Steps S142 and S144: The Intent Violation Reasoner (e.g., intent reasoning unit 24) collects the system alarms / events from the cloud management node 15, which may, in some cases, be provided without an additional request step (Step S142).

[0134] Steps S146 and S148: The intent reasoning unit 24 requests and receives the infrastructure and cloud system data from monitoring unit 25.

[0135] Steps S150 and S152: Intent reasoning unit 24 collects the service graph and service component performance profiles of the violated intent from the intent management node 15.

[0136] It is to be understood that in some cases, the various reasoners and the management systems may be in the same nodes and / or units or in different nodes and / or units, without deviating from the scope of the present disclosure. In cases where the systems are in the same node, one or more of these data requesting / collection steps (S 142, S 144, S 146, S 148, S 150, and / or S 152) may be unnecessary or optional, e.g., because the alarm / event information, monitoring data, infrastructure and cloud management system data, service graph, and / or service component performance profiles, are already available for processing.

[0137] Step S 154: The intent reasoning unit 24 analyzes the collected information and provides reasoning services.

[0138] Steps S156 and S158: The intent reasoning unit 24 informs the intent management node 15 of a request to fix a composition problem, and / or it informs the cloud management node 15 of a request to recover / address / fix the infrastructure problem.

[0139] Step S 160: The intent reasoning unit 24 responds to the intent violation detector unit 23 that the intent violation has been handled.

[0140] FIG. 7 is a flowchart illustrating an example intent reasoning unit 24 logic, according to some embodiments of the present disclosure, for determining the problem type(s) causing a detected intent violation. Step S 170: The intent reasoning unit 24 and / or intent violation detector unit 23 identifies the presence of hardware and / or cloud management alarms.

[0141] Step S172: If alarms are detected, the flow proceeds to Step S176.

[0142] Step S 174: Infrastructure monitoring / cloud management data may be retrieved, provided, stored, etc., for use in Step S176. This may in some embodiments be provided by monitoring unit 25

[0143] Step S 176: In the presence of alarms, the intent reasoning unit 24 retrieves / receives / etc. the corresponding data associated with a time period when the intent was violated, and compares it to the distribution (e.g., historical distribution, current distribution etc.) of infrastructure monitoring data and / or cloud data.

[0144] Step S 178: When the difference between the retrieved data and the distribution is greater than a threshold X, which corresponds to the hardware or the cloud system experiencing issues related to the associated resources (e.g., faults, resource overloads, etc.), the intent reasoning unit 24 assigns a probability difference compared to the infrastructure monitoring and cloud data as the “infrastructure problem rate”. The threshold X may be provided by a cloud administrator as an input, for example, and / or may be preconfigured in the system.

[0145] When the difference is less than the threshold X, intent reasoning unit 24 retrieves performance profiles of the service components belonging to the intent. (Step SI 80), and identifies the service components in question and obtains their monitoring data (e.g., from monitoring unit 25) for those components and compare the data to the distribution of the performance profiles.

[0146] Step S 184: If the change is greater than a threshold Y, this condition may correspond to those components in question running on infrastructure elements that are experiencing poor and / or unexpected performance compared to a normal state of the system. It is to be understood that threshold Y may be provided by a cloud provider / administrator as an input and / or preconfigured in the system. Intent reasoning unit 24 assigns a difference probability, e.g., as an “infrastructure problem rate”.

[0147] Otherwise, the intent reasoning unit 24 assigns the difference probability as the “composition problem rate,” e.g., since the executed services are behaving as expected and the resources are behaving as expected.

[0148] When no alarms are detected (Step S172), the flow proceeds to Step S186, and the intent reasoning unit 24 checks whether there are hardware and cloud management changes. Step S 188: If the hardware and / or the cloud management changed between the last violation and the current violation time, the intent reasoning unit 24 requests to retrieve and update new performance profiles, since there is a new update on the hardware and / or the (cloud) management node 15 which requires obtaining new performance profiles for the services to be deployed for the input, and the flow proceeds to Step SI 82 to identify whether it is an infrastructure problem or composition problem.

[0149] Step S190: Otherwise, the intent reasoning unit 24 identifies the system events (e.g., new application deployed, unpredictable workload, peak hour, etc.).

[0150] Step S 192: If new events or updates are detected, this may imply that the intent was violated because of an update on the infrastructure, and intent reasoning unit 24 measures the distribution change of the new update on the system and assigns it as the infrastructure problem rate.

[0151] Otherwise, the flow proceeds to Step S176 to compare infrastructure data and identify whether the violation was caused by an infrastructure problem or composition problem, or both.

[0152] FIG. 8 illustrates an example of a Bayesian network that the intent reasoning unit 24 may utilize, which captures the different distributions of the collected data from the cloud system (e.g., alarms, infrastructure data, cloud changes, performance profiles of services, system events, etc.). When an intent violation is detected, the intent reasoning unit 24 collects those data from the cloud system and maps them to the different connections between the Bayesian Network variables. In Step S200, alarms are received / collected / stored / etc. In Step S202, the cloud infrastructure is analyzed, e.g., for cloud changes. In Step S204, system events are analyzed. In Step S206, infrastructure data is analyzed. In Step S208, the performance profiles are analyzed. In Step S210 a composition problem rate is determined, and in Step S212, an infrastructure problem rate is determined.

[0153] Thus, the tables shown in FIG. 8 are examples of probabilities that could be captured by the Bayesian network. For example, the first table (on the top of FIG, 8) shows the probabilities of whether or not there is an alarm. Then, the second table (left of S206) shows when there is infrastructure changes (system events) or not [Alarm = yes / no, Sys_events =yes / no] and checks the infrastructure data changes compared to a threshold X. Thus, two different expected outputs of such network may include, e.g., the “composition problem rate” and / or “infrastructure problem rate”. In one example, the “composition problem rate” is about 65%, which implies that the “infrastructure problem rate” is 35% (i.e., the complement of the composition problem rate of 65%). In another example, the “composition problem rate” is 50%, which implies that the “infrastructure problem rate” is 50%, and hence that the reason behind such intent violation is both composition and infrastructure problem.

[0154] FIG. 9 illustrates an example implementation according to some embodiments of the present disclosure. In this example, in Step S220, an intent is defined as “I want to have a holographic communication with high interaction, and latency less than 10ms, through a mobile 5G network.” In this case, the intent may include at least three elements: (1) holographic communication with high interaction; (2) latency less than 10ms; and (3) through a 5G mobile network.

[0155] A service graph may be determined / configured based on this intent. These services may be implemented in one or more network nodes 16, WDs 22, core nodes 14, management nodes 15, etc. Latency information, for example, may be measured for each service (e.g., by monitoring unit 25). A holo-generator service (Step S222 in the service graph) is determined to have a latency of 3ms. A holo-encoder service (Step S224) is determined to have a latency of 2ms. A holo-decoder service (Step S226) is determined to have a latency of 3ms . A holo-display service (Step S228) is determined to have a latency of 2ms. A raw-holo-write service (Step S230) is determined to have a latency of 3ms. A storage service (Step S232) is determined to have a latency of 4ms. Thus, an intent violation may be detected (e.g., by intent violation detector unit 23) where the total latency sums to at least 10ms. Intent reasoner unit 24 may then be configured to perform one or more responsive actions, as described herein.

[0156] FIG. 10 illustrates another example implementation according to some embodiments of the present disclosure. In this example, in Step S240, an intent is defined as “I need a 5G core to support 5,000 subscribers with a high QoE and latency less than 10ms, with a handover success rate greater than 95%. ” In this case, the intent may include: (1) a 5G core network; (2) support for 5,000 subscribers; (3) a high QoE; (4) a latency less than 10ms; and (5) a handover success rate greater than 95%. In Step S242, a service graph may be determined / configured (e.g., by intent management node 15) based on this intent. These services may be implemented in one or more network nodes 16, WDs 22, core nodes 14, management nodes 15, etc.

[0157] Here, the total latency for the service graph may be monitored, e.g., by monitoring unit 25, which determines a latency of 2ms and handover success rate of 70% for the 5G core with 5,000 users. Thus, an intent violation is detected (e.g., by intent violation detector unit 23) in this example. Intent reasoner unit 24 may then be configured to perform one or more responsive actions, as described herein.

[0158] As will be appreciated by one of skill in the art, the concepts described herein may be embodied as a method, data processing system, computer program product and / or computer storage media storing an executable computer program. Accordingly, the concepts described herein may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects all generally referred to herein as a “circuit” or “module.” Any process, step, action and / or functionality described herein may be performed by, and / or associated to, a corresponding module, which may be implemented in software and / or firmware and / or hardware. Furthermore, the disclosure may take the form of a computer program product on a tangible computer usable storage medium having computer program code embodied in the medium that can be executed by a computer. Any suitable tangible computer readable medium may be utilized including hard disks, CD- ROMs, electronic storage devices, optical storage devices, or magnetic storage devices.

[0159] Some embodiments are described herein with reference to flowchart illustrations and / or block diagrams of methods, systems and computer program products. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer (to thereby create a special purpose computer), special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0160] These computer program instructions may also be stored in a computer readable memory or storage medium that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instruction means which implement the function / act specified in the flowchart and / or block diagram block or blocks.

[0161] The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0162] It is to be understood that the functions / acts noted in the blocks may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality / acts involved. Although some of the diagrams include arrows on communication paths to show a primary direction of communication, it is to be understood that communication may occur in the opposite direction to the depicted arrows.

[0163] Computer program code for carrying out operations of the concepts described herein may be written in an object oriented programming language such as Python, Java® or C++. However, the computer program code for carrying out operations of the disclosure may also be written in conventional procedural programming languages, such as the "C" programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer. In the latter scenario, the remote computer may be connected to the user's computer through a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0164] Many different embodiments have been disclosed herein, in connection with the above description and the drawings. It will be understood that it would be unduly repetitious and obfuscating to literally describe and illustrate every combination and subcombination of these embodiments. Accordingly, all embodiments can be combined in any way and / or combination, and the present specification, including the drawings, shall be construed to constitute a complete written description of all combinations and subcombinations of the embodiments described herein, and of the manner and process of making and using them, and shall support claims to any such combination or subcombination.

[0165] Abbreviations that may be used in the preceding description include:

[0166] A I / ML Artificial Intelligence / Machine Learning

[0167] FaaS Functions as a Service

[0168] KPI Key Performance Indicator

[0169] QoE Quality of Experience

[0170] QoS Quality of Service

[0171] RAN Radio Access Network

[0172] RL Reinforcement Learning

[0173] VNF Virtual Network Function

[0174] It will be appreciated by persons skilled in the art that the embodiments described herein are not limited to what has been particularly shown and described herein above. In addition, unless mention was made above to the contrary, it should be noted that all of the accompanying drawings are not to scale. A variety of modifications and variations are possible in light of the above teachings.

Claims

What is claimed is:

1. A method implemented in an intent management node (15) for detecting and managing intent violations for a network service in a network, the network service being associated with a service composition and a network infrastructure, the method comprising: detecting (S100) an intent violation event associated with the network service; analyzing (S102) monitoring data associated with the intent violation event; and determining (S104), based on the analyzed monitoring data, whether the intent violation event was caused by at least one of: a first problem in the network infrastructure; and a second problem in the service composition.

2. The method of Claim 1, wherein the first problem corresponds to at least one of: a memory problem in at least one node in the network infrastructure; a processor problem in at least one node in the network infrastructure; a hard disk drive (HDD) problem in at least one node in the network infrastructure; an antenna problem in at least one node in the network infrastructure; an energy supply problem in at least one node in the network infrastructure; and a security problem in at least one node in the network infrastructure.

3. The method of any one of Claims 1 and 2, wherein the second problem corresponds to at least one of: a failure to achieve a throughput value defined for the network service; a failure to achieve a latency value defined for the network service; a failure to achieve a capacity value defined for the network service; and a use of a database not suitable for the network service.

4. The method of any one of Claims 1-3, wherein the monitoring data comprises at least one of: hardware fault data associated with the network infrastructure;performance metrics data associated with the service composition; performance profile data associated with the service composition; system event data associated with the network; alarm data associated with the network; and cloud configuration change data associated with the network;5. The method of any one of Claims 1-4, wherein the analysis of the monitoring data includes determining: a first probability that the intent violation event was caused by the first problem in the network infrastructure; and a second probability that the intent violation event was caused by the second problem in the service composition.

6. The method of Claim 5, wherein the method further comprises: adjusting the network infrastructure for the network service based on the first probability exceeding a first threshold.

7. The method of any one of Claims 5 and 6, wherein the method further comprises: adjusting the service composition for the network service based on the second probability exceeding a second threshold.

8. The method of any one of Claims 5-7, wherein the method further comprises: adjusting both the network infrastructure for the network service and the service composition for the network service based on: the first probability exceeding a third threshold; and the second probability exceeding a fourth threshold.

9. The method of any one of Claims 5-8, wherein at least one of the first probability and the second probability is determined based on at least one of a probabilistic method and a machine learning model.

10. The method of any one of Claims 5-9, wherein at least one of the first probability and the second probability is determined based on a Bayesian network.

11. An intent management node (15) for detecting and managing intent violations for a network service in a network, the network service being associated with a service composition and a network infrastructure, the intent management node (15) comprising processing circuitry (64) configured to: detect an intent violation event associated with the network service; analyze monitoring data associated with the intent violation event; and determine, based on the analyzed monitoring data, whether the intent violation event was caused by at least one of: a first problem in the network infrastructure; and a second problem in the service composition.

12. The intent management node (15) of Claim 11, wherein the first problem corresponds to at least one of: a memory problem in at least one node in the network infrastructure; a processor problem in at least one node in the network infrastructure; a hard disk drive (HDD) problem in at least one node in the network infrastructure; an antenna problem in at least one node in the network infrastructure; an energy supply problem in at least one node in the network infrastructure; and a security problem in at least one node in the network infrastructure.

13. The intent management node (15) of any one of Claims 11 and 12, wherein the second problem corresponds to at least one of: a failure to achieve a throughput value defined for the network service; a failure to achieve a latency value defined for the network service; a failure to achieve a capacity value defined for the network service; and a use of a database not suitable for the network service.

14. The intent management node (15) of any one of Claims 11-13, wherein the monitoring data comprises at least one of: hardware fault data associated with the network infrastructure;performance metrics data associated with the service composition; performance profile data associated with the service composition; system event data associated with the network; alarm data associated with the network; and cloud configuration change data associated with the network;15. The intent management node (15) of any one of Claims 11-14, wherein the analysis of the monitoring data includes determining: a first probability that the intent violation event was caused by the first problem in the network infrastructure; and a second probability that the intent violation event was caused by the second problem in the service composition.

16. The intent management node (15) of Claim 15, wherein the processing circuitry (64) is further configured to: adjust the network infrastructure for the network service based on the first probability exceeding a first threshold.

17. The intent management node (15) of any one of Claims 15 and 16, wherein the processing circuitry (64) is further configured to: adjust the service composition for the network service based on the second probability exceeding a second threshold.

18. The intent management node (15) of any one of Claims 15-17, wherein the processing circuitry (64) is further configured to: adjust both the network infrastructure for the network service and the service composition for the network service based on: the first probability exceeding a third threshold; and the second probability exceeding a fourth threshold.

19. The intent management node (15) of any one of Claims 15-19, wherein at least one of the first probability and the second probability is determined based on at least one of a probabilistic method and a machine learning model.

20. The intent management node (15) of any one of Claims 15-19, wherein at least one of the first probability and the second probability is determined based on a Bayesian network.

Citation Information

Patent Citations

  • Intention-driven 6G network intelligent operation and maintenance method, system, device and application

    CN112631856A

  • Infrastructure processing unit

    CN116018795A

Cited By

  • Knowledge-driven service assurance information system for autonomous telecommunications networks

    WO2026171354A1