Ai / ML assisted network slicing

Abstract

Methods and systems are described for employing AI / ML (artificial intelligence / machine learning) techniques to facilitate and further improve the process of slice SLA fulfillment to ensure more optimal outcomes in radio access networks. Certain embodiments can decentralize 5 the highly complex process of network wide decision making for actions to be taken to achieve network-wide slice SLA fulfillment. By pushing the decision-making process to the RAN nodes, the proposed solution enables each RAN node to take simpler actions for node-level or cluster-level slice SLA fulfillment based on the local context information. The outcome of these unitary actions taken by each node can sum into the result of network-wide slice SLA 0 fulfillment.

Description

AI / ML ASSISTED NETWORK SLICINGCROSS REFERENCE TO RELATED INFORMATION

[0001] This application claims the benefit of Greece priority application No. 20240100239 filed on April 03, 2024, titled “AIML assisted Network Slicing.”TECHNICAL FIELD

[0002] The present disclosure generally relates to systems and methods for performing SLA fulfillment.BACKGROUNDRAN Architecture

[0003] The current 5G RAN (NG-RAN) architecture is depicted in Figure 1 and described in TS 38.401 V18.0.0. The NG-RAN (Next Generation - Radio Access Network) consists of a set of gNBs (gNodeBs) connected to the 5GC (5thGeneration Core) through the NG interface. As specified in TS 38.300, the NG-RAN could also consist of a set of ng-eNBs (eLong Term Evolution eNodeBs). An ng-eNB may consist of an ng-eNB-CU (ng-eNB Central Unit) and one or more ng-eNB-DU (ng-eNB Distributed Unit). An ng-eNB-CU and an ng-eNB-DU are connected via a W1 interface. The general principle described here also applies to ng-eNB and W1 interface, if not explicitly specified otherwise.

[0004] An gNB can support FDD (frequency division duplex) mode, TDD (time division duplex) mode or dual mode operation. gNBs can be interconnected through the Xn interface. A gNB may consist of a gNB-CU and one or more gNB-DU(s). A gNB-CU and a gNB-DU are connected via a Fl interface. One gNB-DU is connected to only one gNB-CU. NG, Xn, and Fl are logical interfaces.

[0005] For NG-RAN, the NG and Xn-C interfaces for a gNB consist of a gNB-CU and gNB-DUs, and terminate in the gNB-CU. For EN-DC (E-UTRAN New Radio Dual Connectivity), the Sl-U and X2-C interfaces for a gNB consisting of a gNB-CU and gNB-DUs terminate in the gNB-CU. The gNB-CU and connected gNB-DUs are only visible to other gNBs and the 5GC as a gNB.

[0006] The overall architecture for separation of gNB-CU-CP (gNB-CU-Control Plane) and gNB-CU-UP (gNB-CU-User Plane) is depicted in Figure 2. A gNB may consist of a gNB- CU-CP, multiple gNB-CU-UPs and multiple gNB-DUs. The gNB-CU-CP is connected to the gNB-DU through the Fl-C (Fl Control Plane) interface. The gNB-CU-UP is connected to the gNB-DU through the Fl-U (Fl User Plane) interface. The gNB-CU-UP is connected to the gNB-CU-CP through the El interface. One gNB-DU is connected to only one gNB-CU-CP. One gNB-CU-UP is connected to only one gNB-CU-CP.

[0007] The architecture of Figure 2 is what 3GPP (3rdGeneration Partnership Project) has defined for 5G. Other standardization groups, such as the 0-RAN (Open RAN) Alliance, have further extended the architecture of Figure 2 and have, for example, split the gNB-DU into two further nodes connected by a fronthaul interface. The lower node of the split gNB-DU would contain the PHY (physical layer) protocol and the RF (radio frequency) parts, the upper node of the split gNB-DU would host the RLC (Radio Link Control) and MAC (Media Access Control). In 0-RAN the upper node is called O-DU, while the lower node is called O-RU.Network Slicing in 3GPP

[0008] A description of the basics of Network Slicing is provided in TS 38.300. A network slice always consists of a RAN part and a CN (core network) part. The support of network slicing relies on the principle that traffic for different slices is handled by different PDU sessions. A network can realize the different network slices by scheduling and also by providing different L1 / L2 configurations.

[0009] Each network slice is uniquely identified by a S-NSSAI, as defined in TS 23.501. NSSAI (Network Slice Selection Assistance Information) includes one or a list of S-NSSAIs (Single NS SAI), where a S-NSSAI is a combination of the following fields: (1) mandatory SST (Slice / Service Type) field, which identifies the slice type and consists of 8 bits (with range is 0-255), and (2) optional SD (Slice Differentiator) field, which differentiates among slices with same SST field and consist of 24 bits. A list of S-NSSAIs includes at most 8 S-NSSAI(s).

[0010] The UE provides NSSAI for network slice selection in RRCSetupComplete, if it has been provided by NAS (see clause 9.2.1.3 of TS 38.300). While the network can support a large number of slices (e.g., hundreds), the UE need not support more than 8 slices simultaneously. A BL UE or a NB-IoT UE supports a maximum of 8 slices simultaneously.

[0011] Network Slicing is a concept to allow differentiated treatment depending on each customer requirements. With slicing, it is possible for Mobile Network Operators (MNO) to consider customers as belonging to different tenant types with each having different servicerequirements that govern in terms of what slice types each tenant is eligible to use based on Service Level Agreement (SLA) and subscriptions.

[0012] The following key principles apply for support of Network Slicing in NG-RAN:

[0013] RAN awareness of slices: NG-RAN supports a differentiated handling of traffic for different network slices which have been pre-configured. How NG-RAN supports the slice enabling in terms of NG-RAN functions (the set of network functions that comprise each slice) is implementation dependent.

[0014] Selection of RAN part of the network slice: NG-RAN supports the selection of theRAN part of the network slice by NSSAI provided by the UE or the 5GC, which unambiguously identifies one or more of the pre-configured network slices in the PLMN.

[0015] Resource management between slices: NG-RAN supports policy enforcement between slices as per service level agreements. It should be possible for a single NG-RAN node to support multiple slices. The NG-RAN should be free to apply the best RRM policy for the SLA in place to each supported slice.

[0016] Support of QoS: NG-RAN supports QoS differentiation within a slice, and a per Slice-Maximum Bit Rate may be enforced per UE, if feasible. How NG-RAN enables UE- Slice-MBR enforcement and rate limitation (see TS 23.501 [3]) is up to network implementation.

[0017] RAN selection of CN entity: For initial attach, the UE may provide NSSAI to support the selection of an AMF. If available, NG-RAN uses this information for routing the initial NAS to an AMF. If the NG-RAN is unable to select an AMF using this information or the UE does not provide any such information, the NG-RAN sends the NAS signaling to one of the default AMFs. For subsequent accesses, the UE provides a Temp ID, which is assigned to the UE by the 5GC, to enable the NG-RAN to route the NAS message to the appropriate AMF as long as the Temp ID is valid (NG-RAN is aware of and can reach the AMF which is associated with the Temp ID). Otherwise, the methods for initial attach applies.

[0018] Resource isolation between slices: The NG-RAN supports resource isolation between slices. NG-RAN resource isolation may be achieved by means of RRM policies and protection mechanisms that should avoid the shortage of shared resources if one slice breaks the service level agreement for another slice. It should be possible to fully dedicate NG-RAN resources to a certain slice. Some RACH resources can be associated to specific NSAG(s). Other aspects of how NG-RAN supports resource isolation is implementation dependent.

[0019] Access control: By means of the unified access control (see clause 7.4 of TS 38.300), operator-defined access categories can be used to enable differentiated handling fordifferent slices. NG-RAN may broadcast barring control information (a list of barring parameters associated with operator-defined access categories) to minimize the impact of congested slices.

[0020] Slice Availability: Some slices may be available only in part of the network. A slice is considered available in a cell if it is supported by the TA comprising the cell and the slice is not configured with zero resources, as specified in TS 23.501. A slice is supported within a TA if it is included in the slice support list for the TA signaled from the NG-RAN to the AMF. The NG-RAN supported S-NSSAI(s), NSAG(s) and NSAG related information such as NSAG associated Cell Reselection Priority and / or NSAG associated RACH resources are configured by 0AM. Awareness in the NG-RAN of the slices supported in the cells of its neighbors may be beneficial for inter-frequency mobility in connected mode. In order to support the NSAG, the NG-RAN provides the AMF with the NSAG information per TA in the appropriate NG interface management procedures, as specified in TS 38.413. Awareness in the NG-RAN of the NSAG information supported in the list(s) of neighbor cells may be configured by 0 AM, or exchanged with neighbor NG-RAN nodes. The NG-RAN and the 5GC are responsible to handle a service request for a slice that may or may not be available in a given area. Admission or rejection of access to a slice may depend on factors such as support for the slice, availability of resources, support of the requested service by NG-RAN. The NG-RAN may be signaled with the Partially Allowed NSSAI from the AMF as specified in TS 23.501. The NG-RAN may decide to use the Partially Allowed NSSAI for mobility decision. Support for Network Slices with Network Slice Area of Service not matching deployed Tracking Areas is specified in TS 23.501. NG-RAN cells that are outside the Area of Service may be configured with zero resources for the concerned slice(s). The concerned slice(s) cannot use any dedicated, prioritized nor any shared resources of that cell. Awareness of zero resources configured for a slice in one or more cells may be exchanged with neighbor NG-RAN nodes for mobility reasons.

[0021] Support for UE associating with multiple network slices simultaneously: In case a UE is associated with multiple slices simultaneously, only one signaling connection is maintained and for intra-frequency cell reselection, the UE always tries to camp on the best cell. For inter-frequency cell reselection, dedicated priorities can be used to control the frequency on which the UE camps.

[0022] Granularity of slice awareness: Slice awareness in NG-RAN is introduced at PDU session level, by indicating the S-NSSAI corresponding to the PDU Session, in all signaling containing PDU session resource information.

[0023] Validation of the UE rights to access a network slice: It is the responsibility of the 5GC to validate that the UE has the rights to access a network slice. Prior to receiving the Initial Context Setup Request message, the NG-RAN may be allowed to apply some provisional / local policies, based on awareness of which slice the UE is requesting access to. During the initial context setup, the NG-RAN is informed of the slice for which resources are being requested.

[0024] Network slice replacement: NG-RAN may support network slice replacement for a PDU session as defined in TS 23.501.AI / ML Based Use Case for Network Slicing

[0025] As detailed in RP-234054 agreed at RAN Plenary meeting # 102, it has been agreed that new AI / ML based used cases will be studied as part of a Rel-19 Study Item (SI). Among the objectives of the SI, the study will focus on AI / ML based Network Slicing, as reported below:The aim of this study item is to further investigate new AI / ML based use cases and identify enhancements to support AI / ML functionality, and further discussions on the Rel-18 leftovers.The detailed objectives of the SI are listed as follows:Study two new AI / ML based use cases, i.e., Network Slicing and CCO, with existing NG-RAN interfaces and architecture (including non-split architecture and split architecture).Rel-18 leftovers as candidates for normative work, based on the Rel-18 principles, as follows:- Mobility optimization for NR-DC- Split architecture support for Rel-18 use cases based on the conclusions from Rel-18 WI- Energy Saving enhancements, e.g., Energy Cost Prediction- Continuous MDT collection targeting the same UE across RRC states- Multi-hop UE trajectory across gNBsNote: RAN3 should take the Rel-18 discussions into account.

[0026] Some elements have been proposed to be part of the study, as indicated in various contributions to the same RAN Plenary meeting.

[0027] A ZTE contribution in RP-233622 mentioned the following examples on AI / ML based network slicing to be studied:Slice-level Resource status prediction: Accurate predictions of resource status per slice level are crucial for efficient network slicing. AI / ML algorithms can analyze historical data and make predictions about future Slice-level resource status. This information helps in determining the appropriate allocation of network resources and the placement of network slices to meet anticipated demand.Feedback information for each slice: After resource allocation of each slice based on the prediction, nodes should know the performance of these decision. Firstly, resource status per slice information, as one type of information, can be collected through the existing resource status procedure. Another form of feedback information is UE performance feedback for each slice, including UE performance feedback and user traffic, which explicitly reflects the performance.

[0028] A CATT contribution in RP-232989 mentions:For the use case of slicing, we think AI / ML based resource allocation among slices could be considered which could support the adjustment of resource partitions beforehand and thereby improve resource usage and user experience. We consider the major enhancement may be exchanging perslice resource status predictions or performances.

[0029] A Nokia contribution in RP-233084 mentions:An important feature of 5G architecture is network slicing, which allows different slices of the network to provide different network characteristics (including resource isolation) according to the needs of specific tenants, applications, use cases, or users. Even though, our preference with respect to use cases is to study CCO, if a second new use case is introduced in Rel- 19, we see benefits in AI / ML slicing optimizations for mobility enhancements to enable optimal per-slice resource allocation to a handover. Additionally, predicted UE trajectory over a network slice could be considered to enable AI / ML slice-based mobility optimization.

[0030] A Samsung contribution in RP-233024 mentions:Slicing: network uncertainty and delayed reconfiguration may deteriorate the performance.Resource allocation: proper remapping policy to improve efficiency and satisfy QoS of UEs

[0031] A NEC contribution in RP-232889 mentions:Optimize the network slicing policy and resources by reinforcement learning, using for selecting / allocating appropriate resources to serve the UE in a sliceReduce the high computational complexity of manually policy based methods for network slicing resource management.

[0032] A China Telecom contribution in RP-233577 mentions:AI / ML can be used for generating slicing resource allocation strategies to improve performance of system and users, such as Resource allocation ratio among different slices or slice groups.Derive the strategies for resources allocation usage, e.g., dedicated, shared and exclusive, for RAN slices in same slice group.

[0033] A CMCC contribution in RP-233428 mentions:AI / ML based slice resource allocationSlice related parameter predictionEnhance the feedback procedure to include the slice related metrics

[0034] The mentioned published technology generically discusses aspects of interest for an AI / ML based (or AI / ML assisted) use case forNetwork Slicing, mainly focusing on resource allocation per slice.

[0035] There currently exist certain challenges. The published technology does not address many aspects of Network Slicing, especially in the area of fulfilment of RAN level requirements for a network slice, which may map to a Service Level Agreement (SLA) the network operator has signed with the customer or a service provider for which slice services are provided.SUMMARY

[0036] One embodiment under the present disclosure comprises a method performed by a first network node for performing SLA fulfillment of a network slice. The method comprises: receiving one or more SLA requirements for the network slice; generating first SLA fulfillment data related to the one or more SLA requirements; receiving, from a second network node, an SLA fulfillment status message comprising second SLA fulfillment data; obtaining one or more SLA output data from an AI / ML model that has been trained on a third SLA fulfillment data;comparing the first SLA fulfillment data and the second SLA fulfillment data to the one or more SLA output data; and taking an operation decision based on the comparison.

[0037] Another embodiment comprises a method performed by a first network node for performing SLA fulfillment of a network slice. The method comprises: receiving one or more SLA requirements for the network slice; generating first SLA fulfillment data related to the one or more SLA requirements; receiving, from a second network node, an SLA fulfillment status message comprising second SLA fulfillment data; requesting, from the second network node, updated second SLA fulfillment data; receiving, from the second network node, the updated second SLA fulfillment data; obtaining one or more SLA output data from an AI / ML model that has been trained on a third SLA fulfillment data; comparing the first SLA fulfillment data and the updated second SLA fulfillment data to the one or more SLA output data; and taking an operation decision based on the comparison.

[0038] Another embodiment comprises a method performed by a first network node for performing SLA, fulfillment of a network slice. The method comprises: receiving one or more SLA requirements for the network slice; generating first SLA fulfillment data related to the one or more SLA requirements; sending, to a second network node, a HANDOVER REQUEST message, wherein the HANDOVER REQUEST message comprises the first SLA fulfillment data; receiving, from the second network node, at least one of: a HANDOVER REQUEST ACK / NACK message; a second SLA fulfillment data.

[0039] Another embodiment comprises a method performed by a second network node for performing service level agreement, SLA, fulfillment of a network slice. The method comprises: receiving, from a first network node, a HANDOVER REQUEST message, wherein the HANDOVER REQUEST message comprises first SLA fulfillment data; and transmitting to the first network node, at least one of: a HANDOVER REQUEST ACK / NACK message; a second SLA fulfillment data.

[0040] Another embodiment comprises a network node for performing SLA, fulfillment of a network slice. The network node comprises: processing circuitry; and a memory. The memory stores instructions whereby the processing circuitry is operative to perform the steps of: receiving one or more SLA requirements for the network slice; generating first SLA fulfillment data related to the one or more SLA requirements; receiving, from a second network node, an SLA fulfillment status message comprising second SLA fulfillment data; obtaining one or more SLA output data from an AI / ML, model that has been trained on a third SLA fulfillment data; comparing the first SLA fulfillment data and the second SLA fulfillment data to the one or more SLA output data; and taking an operation decision based on the comparison.

[0041] Another embodiment comprises a network node for performing SLA fulfillment of a network slice. The network node comprises: processing circuitry; and a memory. The memory stores instructions whereby the processing circuitry is operative to perform the steps of: receiving one or more SLA requirements for the network slice; generating first SLA fulfillment data related to the one or more SLA requirements; receiving, from a second network node, an SLA fulfillment status message comprising second SLA fulfillment data; requesting, from the second network node, updated second SLA fulfillment data; receiving, from the second network node, the updated second SLA fulfillment data; obtaining one or more SLA output data from an AI / ML, model that has been trained on a third SLA fulfillment data; comparing the first SLA fulfillment data and the updated second SLA fulfillment data to the one or more SLA output data; and taking an operation decision based on the comparison.

[0042] Another embodiment comprises a network node for performing SLA fulfillment of a network slice. The network node comprises: processing circuitry; and a memory. The memory stores instructions whereby the processing circuitry is operative to perform the steps of: receiving one or more SLA requirements for the network slice; generating first SLA fulfillment data related to the one or more SLA requirements; sending, to a second network node, a HANDOVER REQUEST message, wherein the HANDOVER REQUEST message comprises the first SLA fulfillment data; receiving, from the second network node, at least one of: a HANDOVER REQUEST ACK / NACK message; a second SLA fulfillment data.

[0043] Another embodiment comprises a network node for performing SLA fulfillment of a network slice. The network node comprises: processing circuitry; and a memory. The memory stores instructions whereby the processing circuitry is operative to perform the steps of: receiving, from a first network node, a HANDOVER REQUEST message, wherein the HANDOVER REQUEST message comprises first SLA fulfillment data; transmitting, to the first network node, at least one of: a HANDOVER REQUEST ACK / NACK message; a second SLA fulfillment data.

[0044] This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an indication of the scope of the claimed subject matter.BRIEF DESCRIPTION OF THE DRAWINGS

[0045] For a more complete understanding of the present disclosure, reference is now made to the following descriptions taken in conjunction with the accompanying drawings, in which:

[0046] Fig. 1 illustrates an example of NG-RAN architecture;

[0047] Fig. 2 illustrates an architecture of separation of gNB-CU-CP and gNB-CU-UP;

[0048] Fig. 3 illustrates a flow-chart of a method embodiment under the present disclosure;

[0049] Fig. 4 illustrates a flow-chart of a method embodiment under the present disclosure;

[0050] Fig. 5 illustrates a flow-chart of a method embodiment under the present disclosure;

[0051] Fig. 6 illustrates a flow-chart of a method embodiment under the present disclosure;

[0052] Fig. 7 illustrates a flow-chart of a method embodiment under the present disclosure;

[0053] Fig. 8 illustrates a flow-chart of a method embodiment under the present disclosure;

[0054] Fig. 9 illustrates a flow-chart of a method embodiment under the present disclosure;

[0055] Fig. 10 illustrates a flow-chart of a method embodiment under the present disclosure;

[0056] Fig. 11 illustrates a flow-chart of a method embodiment under the present disclosure;

[0057]

[0058] Fig. 12 shows a schematic of a communication system embodiment under the present disclosure;

[0059] Fig. 13 shows a schematic of a user equipment embodiment under the present disclosure;

[0060] Fig. 14 shows a schematic of a network node embodiment under the present disclosure; and

[0061] Fig. 15 shows a schematic of a virtualization environment embodiment under the present disclosure.DETAILED DESCRIPTION

[0062] Before describing various embodiments of the present disclosure in detail, it is to be understood that this disclosure is not limited to the parameters of the particularly exemplified systems, methods, apparatus, products, processes, and / or kits, which may, of course, vary. Thus, while certain embodiments of the present disclosure will be described in detail, with reference to specific configurations, parameters, components, elements, etc., thedescriptions are illustrative and are not to be construed as limiting the scope of the claimed embodiments. In addition, the terminology used herein is for the purpose of describing the embodiments and is not necessarily intended to limit the scope of the claimed embodiments. Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art.

[0063] As described above, there currently exist certain challenges. The published technology does not address many aspects of Network Slicing, especially in the area of fulfilment of RAN level requirements for a network slice, which may map to a SLA the network operator has signed with the customer or a service provider for which slice services are provided.

[0064] Certain aspects of the disclosure and their embodiments may provide solutions to these or other challenges. For a cluster of RAN nodes supporting a network slice, that were pre-configured with, or which have obtained from an external system (e.g., 0AM (operations and management), SMO (Service Management and Orchestration)) a set of RAN level requirements and / or UE level requirements that can be mapped to the slice’s SLA, certain embodiments can enable the RAN nodes to coordinate their actions in order to reach the common goal of node-level and / or cluster-level slice SLA fulfillment. A cluster is a set of RAN nodes. There can be different criteria based on which cluster is defined. As non-limiting examples, a cluster can be defined on the basis of coverage area (e.g., it can be a set of RAN nodes providing wireless coverage for UEs in a certain geographical area), or on the basis of the ability for UEs to access a certain service (or a certain slice). In the second example, a cluster can be a set of RAN nodes capable of providing certain services (mapped to certain network slices) to the UEs (user equipments). A cluster can, in one example, comprise an entire radio access network.

[0065] In certain embodiments, fulfillment of the slice SLA is equivalent to fulfillment of the RAN-level requirements which map to the slice SLA.

[0066] Coordination of the actions among the nodes of a cluster implies exchanging, over an interface between the nodes, information regarding the node-level or cluster-level measured and / or predicted SLA fulfilment and, based on this information, infer actions and commonly agree on taking actions which lead toward reaching the common goal of cluster-level or network-level slice SLA fulfillment.

[0067] In order to infer the predicted level of SLA fulfilment and / or the actions to be taken for improving the SLA fulfillment level, certain embodiments can assume that the RAN nodes are enabled with trained AI / ML models for this purpose.

[0068] For a RAN node belonging to a cluster (such as described above), in certain embodiments there can be exchanging with its neighboring nodes AI / ML-empowered predicted and / or measured levels of slice SLA fulfillment, and to use the such obtained information in the process of inferring actions to be taken in order to improve the node-level or cluster-level slice SLA fulfillment.

[0069] Certain embodiments may provide one or more of the following technical advantages. Certain embodiments can employ AI / ML (artificial intelligence / machine learning) techniques to facilitate and further improve the process of slice SLA fulfillment to ensure a more optimal outcome. Also, certain embodiments can decentralize the highly complex process of network wide decision making for actions to be taken to achieve network-wide slice SLA fulfillment. Indeed, by pushing the decision-making process to the RAN nodes, the proposed solution enables each RAN node to take simpler actions for node-level or cluster-level slice SLA fulfillment based on the local context information. The outcome of these unitary actions taken by each node will sum into the result of network-wide slice SLA fulfillment.

[0070] The teachings of certain embodiments may improve the power consumption of various network-wide components by simplifying the actions required for slice SLA fulfillment.

[0071] For simplicity, the methods are described for a new radio (NR), and this should not be regarded as limiting. The methods comprise signaling between two functional entities of the same RAN node (i.e., intra-RAN node signaling) and signaling between two RAN nodes (i.e., inter-RAN node signaling). An example of intra-RAN node signaling is between a gNB-CU and a gNB-DU served by the gNB-CU, while an example of inter-RAN node signaling is between two gNBs. The methods herein are applicable to any network and Radio Access Technology where network slicing is supported.

[0072] In the provided non-limiting description of an embodiment, NR (New Radio) is used as an example radio access technology and the gNB-CU is the logical function in the radio access network, RAN, making use of an AI / ML inference function. However, the case where the AI / ML inference function is deployed at different nodes such as the gNB-DU (instead of a gNB-CU) is also possible and should be regarded as covered by one or more embodiments. Moreover, the methods disclosed herein can apply as well to other radio access technologies, such as 4G (4thGeneration) and 6G (6thGeneration) and the logical entities hosting the AI / MLalgorithms deriving the predictions described can consist of any of such radio access technology nodes.

[0073] In this disclosure the term Service Level Agreement (SLA) refers to a set of requirements applicable to the Radio Access Network, that are specific for the service of a given network slice. An “SLA fulfilment level” or “SLA fulfilment” provides an indication of whether there is an alignment with, or how close or far a RAN node is to reaching the per slice requirements received. A predicted SLA Fulfilment is a prediction of whether there will be an alignment with the per slice requirements, or how close or far the RAN node inferring the prediction will be to fulfilling the per slice requirements.

[0074] As non-limiting examples, the metrics mentioned herein can be measured by means of collecting samples for individual events pertaining to a UE (e.g., setup or release of a bearer / PDU session, sending / receiving a certain amount of data). The collected samples can then be aggregated and exposed / signaled as performance counters, providing statistics over different time intervals (e.g., per minutes, per hours), and / or at different granularities (e.g. per UE, per cell, per node, per PDU Session, per QoS flow).

[0075] In one embodiment under the present disclosure, RAN nodes are grouped into clusters, where the RAN nodes in the cluster are tasked to achieve common requirements for a specific network slice. A cluster could consist of the entire network or of a subset of it. Each RAN node in the cluster receives a representation of the requirements the RAN node needs to fulfil for a specific slice. Such set of requirements are herein also referred as slice SLA, SLA fulfilment, SLA fulfilment level for the RAN, or RAN specific expression of SLA.

[0076] Any RAN node in the cluster that is interconnected via a direct or indirect interface with other nodes exchanges information related to the current level of SLA fulfilment and the predicted level of SLA fulfillment. From a functional point of view, in one variant - assuming NR as radio access technology being used - in a scenario where two or more RAN nodes are involved (e.g., a first gNB and a second gNB), the information related to current and predicted SLA fulfillment and / or the corresponding information related to the resolution of the predicted SLA fulfillment failure and / or associated feedback are signaled via inter-RAN node signaling protocols (e.g., XnAP).

[0077] Also, in the case of a split architecture, in one embodiment, the gNB-CU is the logical entity in a RAN node being responsible to infer a predicted SLA fulfillment issue, and the gNB-DU is the logical entity in a RAN node being responsible to provide performance management information, namely information that the gNB-CU can use to determine if and to which level, the SLA for the slice was fulfilled. In another embodiment, the gNB-DU inferswhether at least a subset of the requirements applicable to the RAN are fulfilled and / or a predicted SLA fulfillment issue, and informs the gNB-CU.

[0078] Another aspect of certain embodiments disclosed herein concerns the reception at the RAN nodes in the cluster of a level of SLA fulfilment for the set of RAN nodes in the cluster.

[0079] Each RAN node in the cluster can attempt to achieve the per slice requirements, or SLA, provided to it by the 0AM system or any other equivalent system. Each RAN node in the cluster can also know if the cluster as a whole is fulfilling or not fulfilling the set of requirements for the network slice. By exchanging their own measured SLA fulfillment level and predicted SLA fulfillment level, each node in the cluster can know how its neighbor nodes are performing towards fulfilment of the requirements for the network slice. In options where the gNB-DU participates (or is the only function) in providing information concerning measurements and / or predictions on SLA fulfillment, the knowledge at each RAN node on whether the cluster as a whole is fulfilling or not fulfilling the set of requirements for the network slice can be acquired by sending such measurements and / or predictions on SLA fulfillment from a gNB-DU to the controlling gNB-CU, and further sending this information (or a processed version of it) to other RAN nodes via Xn / NG. An algorithm based on Al and / or ML may be able to infer how the actions of a RAN node may have an effect on the cluster level fulfilment of the SLA. Such algorithm could make use of inputs such as the measured and predicted SLA fulfilment of RAN nodes in the cluster, the cluster level SLA fulfilment, the per slice SLA requirements, and in addition other metrics that may be exchanged over Xn over different procedures, and it may derive inference outputs such as radio resource management strategies on how to serve UEs to reach SLA fulfilment, or mobility actions leading to better traffic load distribution and therefore leading to a better cluster level fulfilment of the SLA.

[0080] When a RAN cluster is mentioned, all the cells served by the nodes in the cluster may be implied. However, in one embodiment, the cells served by the nodes are intended as limited to the cells of such RAN nodes able to provide services (e.g., being activated and enabled). In another embodiment, a RAN cluster could comprise a specific subset of cells, tracking areas, and in general, coverage areas served by specific RAN nodes in the network. Non-limiting examples of definitions of a coverage area can be: a list of cells, a list of tracking areas, a list of PLMNs, polygons.

[0081] The following aspects may be considered:• Exchange of measured SLA fulfillment status between the nodes (e.g., between RAN nodes or within functions of RAN nodes [e.g., between two gNB-CUs or between a gNB-CU and a gNB-D])• Exchange of predicted SLA fulfillment status between the nodes (e.g., between RAN nodes or within functions of RAN nodes [e.g., between two gNB-CUs or between a gNB-CU and a gNB-DU[)• Based on received SLA fulfilment information (measured and / or predicted) and other metrics, inference of node level predicted SLA fulfillment status• Based on received SLA fulfilment information (measured and / or predicted) and other metrics, inference of joint level predicted SLA fulfillment status• Based on received SLA fulfilment information (measured and / or predicted) and other metrics, inference of cluster level predicted SLA fulfillment status• Associated feedback to validate the inference of predicted SLA fulfilment and correspondingly making effort to improve it with the support of neighboring nodes• Centralized or distributed inferenceEmbodiment 1

[0082] This embodiment provides a method for a first network node, such as a gNB or a gNB-CU in one slice, to handle fulfillment of requirements for a slice mapping to an SLA. In this embodiment, a set of RAN-specific requirements for a specific network slice may be received from an external system (e.g. 0AM), which constitutes an expression of the slice SLA for the RAN. The requirements may be used to derive if the performance for the services in the slice is in-line with the required network-level SLA receiving an indication from an external system (e.g., 0AM) of whether the RAN specific requirements and / or the SLA for the slice is fulfilled / not fulfilled across a cluster of nodes and / or across the whole network.

[0083] The set of requirements signaled to the RAN from the external system (e.g., 0AM) or the SMO may include, as an example, targets for one or more of the following metrics for a specific network slice identified, for example, by means of the S-NSSAI together with the requirements. Possible metrics (such as defined in TS 28.552 and TS 28.554) can include:• DRB Accessibility for UE services (average per cell or per beam)• DRB Retainability (average per cell or per beam)• Downlink latency in gNB-DU (average per cell or per beam)• Downlink latency (average per cell or per beam)• Uplink latency (average per cell or per beam)• Downlink latency variation or jitter (average per cell or per beam)• Uplink latency variation or jitter (average per cell or per beam)• Integrated downlink delay in RAN (sum of average DL (downlink) delay in gNB- CU-UP and average DL delay in gNB-DU)• Integrated uplink delay in RAN (sum of average UL (uplink) delay in gNB-DU and average UL delay in gNB-CU-UP)• DL RAN UE throughput (average per cell or per beam)• UL RAN UE throughput (average per cell or per beam)• Energy efficiency of MIoT (massive internet of things) network slice, based on the average number of active UEs in the network slice• UL PDCP (Packet Data Convergence Protocol) SDU (Service Data Unit) Loss Rate (average per CUUPFunction)• UL Fl-U Packet Loss Rate (average per CUUPFunction)• DL Fl-U Packet Loss Rate (average per CUUPFunction)• DL PDCP SDU Drop rate in gNB-CU-UP (average per CU UPF (user plane function))• DL Packet Drop Rate in gNB-DU (average per cell or per beam)• Downlink packet error rate (average per cell or per beam)• Uplink packet error rate (average per cell or per beam)• Downlink packet loss rate (average per cell or per beam)• Uplink packet loss rate (average per cell or per beam)• Distribution of delay DL in CU-UP• Distribution of delay DL on Fl-U• Distribution of delay DL in gNB-DU• Distribution of delay DL air-interface• Distribution of DL delay between NG-RAN and UE• Distribution of UL delay between NG-RAN and UE• Distribution of DL GTP packet delay between PSA UPF and NG-RAN• Distribution of IP Latency DL in gNB-DU• Distribution of DL UE throughput in gNB• Distribution of UL UE throughput in gNB• Percentage of unrestricted DL UE data volume in gNB• Percentage of unrestricted UL UE data volume in gNB• DL PRB used for data traffic (average per cell or per beam)• UL PRB used for data traffic (average per cell or per beam)• An expression specified by a combination of two or more of the above parameters• An expression that may be specified as a function of different parameters above.• Number of PDU Sessions requested to setup• Number of PDU Sessions successfully setup• Mean Time of requested handover executions• Max Time of requested handover executions• Max number of Active UEs in the DL per cell• Max number of Active UEs in the UL per cell• DL PDCP PDU Data Volume (average per CUUPFunction and link)• UL PDCP PDU Data Volume (average per CUUPFunction and link)• DL PDCP SDU Data Volume (average per CUUPFunction and link)• UL PDCP SDU Data Volume (average per CUUPFunction and link)• Counters for accessibility and retainability for QoSFlow• Counters for QoSFlow modification• Higher layer packet loss rate in uplink and / or downlink (e.g., TCP)• Higher layer average download rate in uplink and / or downlink (e.g., TCP)• Higher layer QoE values (e.g., RVQoE metrics). The RAN in this case may use preset rules to map the RVQoE metrics to metrics that the RAN may have control over

[0084] The preceding requirements, namely per metric targets, may be signaled to the RAN together with one or more additional information such as:• Percentage of time the RAN should fulfill the target• Percentage of cluster coverage area in which RAN should fulfill the target• Indication of whether a certain neighboring RAN node is fulfilling the target• Percentage of data for which the targets are to be fulfilled• Priority of each target, such as providing for each target an index representing the importance of the target. If the RAN has to choose which target to fulfill (in case not all the targets can be fulfilled), the targets with highest priority are those that the RANshould try to fulfill first. As an alternative to the priority, the RAN may also be sent an associated cost, or a representation that corresponds to the cost, when a certain target is not satisfied. The RAN node, based on implementation may choose a policy that may minimize the total cost when two or more specified targets cannot be met.• Allowed deviation from the target, in absolute scale, or in percentage. Namely, for each target, a maximum positive and / or negative deviation from the target. The target is considered fulfilled if the metric is equal or above / below the target plus its deviation. As an example, a target for a DL RAN UE throughput may be IGbps with a tolerance of + / -lkbps. In this example, if the throughput is equal to or above IGbps-lkbps the target is considered fulfilled. Allowed percentage of deviation from the target (in excess or in defect), expressed in terms of time in relation to a reference time interval (e.g., it is allowed to be off-target for up to 5% of the time, and the 5% is calculated with a reference of 1 hour, or 1 day, or 1 minute)• Optionally per network slice, or for any slice• Allowed percentage of deviation from the target (in excess or in defect), expressed in terms of served users, in relation to a reference number of users (e.g., it is allowed to be off target for up to 1% of the users being served) - Optionally per network slice, or for any slice• Allowed percentage of deviation from the target (in excess or in defect), expressed in terms of both time and served users, in relation to a reference time interval and number of users (e.g., it is allowed to be off-target for up to 2% of the time in 1 hour, and this should not affect more than to 5% of the users served) - Optionally per network slice, or for any slice• For a group of packets transmitted together, which may be determined by their generation time, the maximum deviation allowed across the entire group of packets, specified in terms of bandwidth, jitter, queuing delay, etc.,• For a group of packets transmitted together, which may be determined by their generation time, the expected distribution of different performance metrics (e.g., delay, latency, jitter)

[0085] Upon receiving from the external system a RAN specific set of per slice requirements, the first network node signals to a second network node, such as a gNB or a gNB-CU, the level of fulfilment for the requirements and / or a prediction of the level of fulfilment for the requirements. An example of the signal being whether it is (or it foresees tobe) on target of the per slice requirements or not and of how much it is “out of target.” The signal is sent in a message over an inter node interface, e.g. the Xn interface, as a response to a previously received request. In one example the request may be performed by extensions to the Data Collection Request message, or a new message, while the response carrying the requested information may be performed by extensions of the Data Collection Update message or a new message. In one dependent embodiment, the reporting node may include additional information in the response message. If the measurements / predictions of SLA fulfillment are done at gNB-DU, the first network node is a gNB-DU, the second network node is a gNB-CU and the signaling occurs over Fl interface.

[0086] The request to provide the above-mentioned fulfillment status may be requested as one off, periodic, or based on an event, or a combination of the above. For example, the event can be that the SLA fulfillment status in the first network node is below the desired level. In another example the first network node may request the second network node to provide the aforementioned information when the level of the SLA fulfillment in the second network node is below and / or above a certain threshold.

[0087] Consequently, the first network node receives, from the second network node, a response message over Xn accepting or rejecting to provide the requested information. In one example the response may be sent by extensions to the Data Collection Response message, or a new message.

[0088] Following that, the first network node may receive the requested data from the second network node, either immediately or after a delay determined by a condition to be fulfilled, or periodically, according to a reporting period requested by the first network node. In one example the message may be a part of the Data Collection Update message, or a new message.

[0089] The message including the requested data may include one or more of the following information, which may be per-slice or for any slice:• Measured and / or predicted values for one or more of the metrics specified as part of the requirements• Indication of whether the requirement targets are fulfilled / not fulfilled for one or more of the required metrics• Indication of the deviation from the requirement target for one or more of the required metrics. As an example, if the requirement on the DL RAN UE throughput isIGbps and the reporting node is able to achieve 0.9Gbps, the reporting node reports a deviation of -0. IGbps• Indication of the percentage of time during which the requirement targets are fulfilled and / or are not fulfilled for one or more of the required metrics• An indication of the deviation or conformance for a group of packets transmitted together, which may be determined by their generation time, the maximum deviation allowed across the entire group of packets, specified in terms of bandwidth, jitter, or queuing delay, for example• An indication of the deviation or conformance for a group of packets transmitted together, which may be determined by their generation time, sequence number range, the expected distribution of different performance metrics (e.g., delay, latency jitter)• Percentage of deviation from the target (in excess or in defect), expressed in terms of time in relation to a reference time interval• Percentage of deviation from the target (in excess or in defect), expressed in terms of served users, in relation to a reference number of users• Percentage of deviation from the target (in excess or in defect), expressed in terms of both time and served users, in relation to a reference time interval and number of users

[0090] A non-limiting list of requirement metrics is provided below. The metrics are defined in TS 28.552 and TS 28.554:• DRB Accessibility for UE services (average per cell or per beam),• DRB Retainability (average per cell or per beam)• Downlink latency in gNB-DU (average per cell or per beam)• Downlink latency (average per cell or per beam)• Uplink latency (average per cell or per beam)• Downlink latency variation (average per cell or per beam)• Uplink latency variation (average per cell or per beam)• Integrated downlink delay in RAN (sum of average DL delay in gNB-CU-UP and average DL delay in gNB-DU)• Integrated uplink delay in RAN (sum of average UL delay in gNB-DU and average UL delay in gNB-CU-UP)• DL RAN UE throughput (average per cell or per beam)• UL RAN UE throughput (average per cell or per beam)• Energy efficiency of MIoT network slice, based on the average number of active UEs in the network sliceUL PDCP SDU Loss Rate (average per CUUPFunction)UL Fl-U Packet Loss Rate (average per CUUPFunction)DL Fl-U Packet Loss Rate (average per CUUPFunction)DL PDCP SDU Drop rate in gNB-CU-UP (average per CUUPFunction)DL Packet Drop Rate in gNB-DU (average per cell or per beam)Downlink packet error rate (average per cell or per beam)Uplink packet error rate (average per cell or per beam)Downlink packet loss rate (average per cell or per beam)Uplink packet loss rate (average per cell or per beam)Distribution of delay DL in CU-UPDistribution of delay DL on Fl-UDistribution of delay DL in gNB-DUDistribution of delay DL air-interfaceDistribution of DL delay between NG-RAN and UEDistribution of UL delay between NG-RAN and UEDistribution of DL GTP packet delay between PSA UPF and NG-RANDistribution of IP Latency DL in gNB-DUDistribution of DL UE throughput in gNBDistribution of UL UE throughput in gNBPercentage of unrestricted DL UE data volume in gNBPercentage of unrestricted UL UE data volume in gNBDL PRB used for data traffic (average per cell or per beam)UL PRB used for data traffic (average per cell or per beam)An expression specified by a combination of two or more of the above parametersAn expression that may be specified as a function of different parameters aboveNumber of PDU Sessions requested to setupNumber of PDU Sessions successfully setupMean Time of requested handover executionsMax Time of requested handover executionsMax number of Active UEs in the DL per cell• Max number of Active UEs in the UL per cell• DL PDCP PDU Data Volume (average per CUUPFunction and link)• UL PDCP PDU Data Volume (average per CUUPFunction and link)• DL PDCP SDU Data Volume (average per CUUPFunction and link)• UL PDCP SDU Data Volume (average per CUUPFunction and link)• Counters for accessibility and retainability for QoSFlow• Counters for QoSFlow modification

[0091] As non-limiting examples, the metrics listed above can be measured by means of collecting samples for individual events pertaining to a UE (e.g., setup or release of a bearer / PDU session, sending / receiving a certain amount of data). The collected samples can then be aggregated and exposed / signaled as performance counters, providing statistics over different time intervals (e.g., per minutes, per hours), and / or at different granularities (e.g. per UE, per cell, per node, per PDU Session, per QoS flow).

[0092] Based on the received data and other information, the first network node can infer actions to facilitate the fulfilment of the per slice requirements for the whole cluster of RAN nodes and correspondingly acts on how to get or provide support from one or more of the second network nodes in order to achieve SLA fulfilment within the cluster. In one embodiment the inference will provide predicted SLA fulfilment status or predicted fulfilment for SLA expression for the RAN after the proposed action is performed.

[0093] As part of the actions to facilitate fulfilment of the per slice requirements at the first RAN node, and therefore help achieve the per slice requirements within the RAN cluster, the first network node may send a message to the second network node to offload some of its load. In one embodiment the message can be a Handover Request. This message may include the node-level (for the first network node) or cluster-level predicted SLA fulfillment in case the request is accepted by the second network node. By offloading traffic, the first network node may be able to serve the remaining traffic with better performance and therefore to fulfil the per slice requirements. In an embodiment, the message may contain the predicted SLA fulfilment level or the predicted requirement fulfilment level for the first RAN node corresponding to when the proposed action will be performed. In yet another embodiment, the first RAN node may be aware that a neighboring RAN node is not fulfilling the per slice requirements. The first RAN node may therefore extend its cell coverage to absorb traffic from the second RAN node. This may enable the second RAN node to fulfil the per slice requirements.

[0094] Subsequently, the first network node may receive, from the second network node, a message indicating that it accepts the request. In one embodiment the message can be a Handover Request Acknowledge message. The second network node may reject the proposed action and may propose instead a different action (e.g., a resource partition for cells of the two nodes). The message sent by the second network node may, for example, contain the predicted node-level (at the second network node) and / or predicted joint=level (common between first and second network nodes) and / or the predicted cluster-level SLA fulfillment status.

[0095] In another embodiment, the first network node may trigger a procedure similar to the CCO procedure where an indication of the cells and beams that are not satisfying the per slice requirements may be signaled as the affected beams, followed by a cell / beam coverage state modification initiated by the second node.

[0096] In case the action is accepted, the second network node may later send feedback to the first network node in the form of new instances of the requested data described above. Based on the feedback and the updated SLA fulfillment status, the first network node can propose an updated action.Embodiment 2

[0097] This embodiment provides a method for a first and a second network node, such as gNB or gNB-CU both serving both slices A and B, to handle SLA fulfillment for each slice. In this embodiment, a RAN-specific expression of SLA for slices A and B is received from 0AM that may be used to derive if the performance delivered by the RAN for the services in the slices are in-line with the required network-level SLA. An indication from 0AM may also be received, of whether the SLA for the slices is fulfilled / not fulfilled across the whole network.

[0098] Next, the first network node may signal, to the second network node, the SLA fulfillment status, or the fulfillment status of the expression of SLA received from the 0AM. The fulfillment status may be, for example, whether it is on target of the expression of SLA for the RAN or not and of how much it is “out of target.” The signal is sent in a message over an Xn interface and requests relevant information from the second network node. In one example the request message can be Data Collection Request, or a new message.

[0099] The request to provide the above-mentioned fulfillment status maybe requested as one off, periodic or based on an event. For example, the event can be that the SLA fulfillment status in the second network node is below the desired level.

[0100] The first network node may receive, from the second network node, a response message over Xn accepting or rejecting to provide the requested information. In one example the response message can be Data Collection Response, or a new message.

[0101] Subsequently, the second network node may provide the requested data in the first network node, either immediately or after a delay determined by a condition to be fulfilled, or on the period of reporting requested by the first network node. In one example the message can be Data Collection Update, or a new message. The message providing the requested data can contain the following metrics that are defined in TS 28.552 and TS 28.554.:DRB Accessibility for UE services (average per cell or per beam)DRB Retainability (average per cell or per beam)Downlink latency in gNB-DU (average per cell or per beam)Downlink latency (average per cell or per beam) Uplink latency (average per cell or per beam) Downlink latency variation (average per cell or per beam) Uplink latency variation (average per cell or per beam) Integrated downlink delay in RAN (sum of average DL delay in gNB-CU-UP and average DL delay in gNB-DU)Integrated uplink delay in RAN (sum of average UL delay in gNB-DU and average UL delay in gNB-CU-UP)DL RAN UE throughput (average per cell or per beam) UL RAN UE throughput (average per cell or per beam) Energy efficiency of MIoT network slice, based on the average number of active UEs in the network sliceUL PDCP SDU Loss Rate (average per CUUPFunction) UL Fl-U Packet Loss Rate (average per CUUPFunction) DL Fl-U Packet Loss Rate (average per CUUPFunction) DL PDCP SDU Drop rate in gNB-CU-UP (average per CUUPFunction) DL Packet Drop Rate in gNB-DU (average per cell or per beam) Downlink packet error rate (average per cell or per beam) Uplink packet error rate (average per cell or per beam)Downlink packet loss rate (average per cell or per beam) Uplink packet loss rate (average per cell or per beam) Distribution of delay DL in CU-UPDistribution of delay DL on Fl-UDistribution of delay DL in gNB-DUDistribution of delay DL air-interfaceDistribution of DL delay between NG-RAN and UEDistribution of UL delay between NG-RAN and UEDistribution of DL GTP packet delay between PSA UPF and NG-RANDistribution of IP Latency DL in gNB-DUDistribution of DL UE throughput in gNB Distribution of UL UE throughput in gNB Percentage of unrestricted DL UE data volume in gNB Percentage of unrestricted UL UE data volume in gNB DL PRB used for data traffic (average per cell or per beam) UL PRB used for data traffic (average per cell or per beam) An expression specified by a combination of two or more of the above parameters An expression that may be specified as a function of different parameters above- Number of PDU Sessions requested to setup- Number of PDU Sessions successfully setupMean Time of requested handover executions Max Time of requested handover executions Max number of Active UEs in the DL per cell Max number of Active UEs in the UL per cell DL PDCP PDU Data Volume (average per CUUPFunction and link) UL PDCP PDU Data Volume (average per CUUPFunction and link) DL PDCP SDU Data Volume (average per CUUPFunction and link) UL PDCP SDU Data Volume (average per CUUPFunction and link) Counters for accessibility and retainability for QoSFlow Counters for QoSFlow modification

[0102] Based on the received data and other information, the first network node may infer actions to facilitate network wide SLA fulfilment for the slices A and B and correspondingly act on how to get support from one or more of the second network nodes in order to achieve SLA fulfilment across the network or SLA expression for the RAN. In case the requirements on Slice A and Slice B cannot be both fulfilled due to conflicting conditions fortheir fulfilment, the first network node may take into consideration the priority / weight of the slices A and B andalso the non-slice related requirements. The latter information may be received by the first network node from an external system such as the OAM. In one option, such information comes together with the per slice requirement targets. In one example the inference will provide predicted SLA fulfilment status or the predicted SLA expression for the RAN corresponding to when the proposed action may be performed

[0103] The proposed actions may include actions mentioned above, such as traffic offloading to achieve the per slice requirement targets. Alternatively, or additionally, the proposed action may concern the resource partition for the slices A and B in the first and the second network node. The first network node may send a message to the second network node to propose radio resource partitioning for slices A and B. The second network node may respond either accepting or rejecting the proposed action. In one example the second network node can propose instead a different resource partition for the two nodes.

[0104] In the case that the action is accepted, the second network node may later send feedback to the first network node. Based on the feedback and the updated SLA fulfillment status, the first network node can propose an updated action.Embodiment 3

[0105] This embodiment is similar to embodiment 2, in that it provides a method for a first and a second network node, such as gNB or gNB-CU both serving both slices A and B, to handle SLA fulfillment for each slice. In this embodiment, a RAN-specific expression of SLA for slices A and B is received from OAM that may be used to derive if the performance delivered by the RAN for the services in the slices are in-line with the required network-level SLA. An indication from OAM may also be received, of whether the SLA for the slices is fulfilled / not fulfilled across the whole network.

[0106] Another embodiment provides a method for a first and a second network node, such as gNB or gNB-CU where the first network node is serving slices A and B while the second network node is serving only slice A, to handle SLA fulfillment for each slice. In this embodiment, a RAN-specific expression of the SLA for slices A and B is received from OAM, along with an indication from OAM of whether the SLA for the slices is fulfilled / not fulfilled across the whole network.

[0107] A depending embodiment of Embodiment 1 provides a method for a first and a second network node, such as gNB or gNB-CU where the first network node is serving slices A and B while the second network node is serving only slice A. At issue for the first network node is that the RAN-specific requirements for the slice A and the slice B are in conflict. Byway of one example for addressing the issue, the first network node may infer that the best action is to offload a major part of the traffic for slice A to the second network node, assuming that the second network node is able to fulfill the RAN-specific requirements for slice A after it receives the relevant load from the first network node. A similar process as in embodiment 2 follows and the first network node proposes to handover UEs served in slice A to the second network node. In one example the first network node may infer a predicted level of SLA fulfilment after the proposed action will be performed and it signals it to the second network node.

[0108] The second network node may respond by either accepting or rejecting the proposed action. Acceptance / rej ection may be due to an analysis of the measured / predicted level of fulfilment of the slice requirements at the first RAN node, measured / predicted level of fulfilment of the slice requirements at the second RAN node, concluding that by accepting / rejecting the action the overall level of requirement fulfilment has improved or it has not changed. In the case that the action is accepted, the second network node may later send feedback to the first network node. Based on the feedback and the updated SLA fulfillment status, the first network node can propose an updated action.Embodiment 4

[0109] In an alternative embodiment to embodiment 1, the network nodes involved in the method do not explicitly receive information from an external system such as the 0AM concerning per slice requirements, but they are a priori configured with them. In this embodiment, the external system does not need to signal a fulfilment status of the per slice requirements for the whole cluster of nodes. The method is simply based on the exchange of the fulfilment level of the per slice requirements between network nodes, assuming that each network node is aware of the per slice requirements. Alternatively, per slice requirements may be implicitly signaled with the fulfilment status reporting from one network node to the other. For example, the status of a per slice requirement on DL throughput could be signaled by including the following information:• The target DL throughput in Mbps• The percentage of time the target is fulfilled• The percentage of space (coverage area) the target is fulfilled• The average deviation from target when this is not fulfilled

[0110] With this information, the target itself would be implicitly signaled.Embodiment 5

[0111] In this embodiment, the network node tasked to fulfill per slice requirements, and requested to report the status of such requirement fulfilment, configures UEs to take measurements allowing to determine the requirement fulfilment status.

[0112] In another embodiment, the UE may be configured to report raw measured information, which the network node may take into account to deduce the per slice requirement level of fulfilment. An example of this could be to configure the UE to report UL Packet Error Rate measurements. With this information the network node receiving the measurements is able to deduce if the target is fulfilled or not.

[0113] Alternatively, the RAN may configure the UE with the per slice requirements for which the UE itself could deduce whether the requirement is fulfilled. In the same example above, the network node may configure the UE with the UL packet error rate requirement for a specific network slice. The requirement may consist of the following:• Target UL Packet Error Rate• Percentage of time the target should be fulfilled

[0114] Together with this information the UE may be configured to report whether the target is fulfilled or not. Additionally, the UE may be provided with a time window within which the UE should measure whether the target is fulfilled or not.

[0115] The UE may report to the network node serving it the information concerning whether the target has been fulfilled or not. This enables the network node to avoid performing the analysis of raw measurements provided by the UE.Additional Embodiments and Variations

[0116] The methods described between two RAN nodes are also applicable between different functions of the same RAN node. This means that if the measurements and / or prediction concerning SLA fulfillment are performed / inferred by a gNB-DU within a gNB, the methods described between two network nodes are applicable also to the signaling via Fl between gNB-DU and gNB-CU.

[0117] In another embodiment, specific indications concerning the fulfillment of SLA requirement at RAN node level (or at cluster level) are exchanged between RAN nodes (or between a gNB-DU and a gNB-CU), to indicate that a level beyond target has been reached.This information can be used, e.g., by RAN node(s) where the SLA requirement(s) are not fulfilled, and receiving this information, to determine that the RAN node where fulfillment of SLA requirement is over-achieved, is a good candidate target to offload some users towards, so that the overall cluster level target is(are) fulfilled.

[0118] Embodiments can provide an implementation sequence for SLA fulfillment. One possible method embodiment 300 is shown in Figure 3, per node SLA fulfillment. In this embodiment, three RAN nodes 310, 315, 320 are used to facilitate explanation, but the number of nodes along with which nodes are communicated at a certain step may vary with other embodiments. Step 325: Each RAN node serving a slice (here, gNBl 310) receives an expression of the SLA for the slice, per slice requirements, where the SLA could be represented as, for example, target throughput and percentage of on target time, target drop rate and percentage of on target time, target packet delay and percentage of on target time. Step 330: Each RAN node (here, gNBl 310) tries to fulfill the per-slice targets for served DRBs associated to the slice. Step 335: Each RAN node (here, gNBl) may receive an indication from 0AM 305 of whether the SLA for the slice is fulfilled / not fulfilled across the whole network. The cluster-wide SLA fulfillment status may include: on target, not on target, details on KPIs (e.g., on target time, out of target time, deviation from target). In some embodiments, each RAN node 310, 315, 320 may signal to neighboring RAN nodes its SLA fulfilment status, such as whether it is on target of the SLA or not and of how much it is “out of target.” Step 340: gNBl 310 and gNB2 315 exchange node level per slice requirement fulfillment status: on target, not on target, details on KPIs (e.g., on target time, out of target time, deviation from target) and similarly prediction of node level per slice requirement. Step 345: gNBl 310 and gNB3 320 exchange node level per slice requirement fulfillment status: on target, not on target, details on KPIs (e.g., on target time, out of target time, deviation from target) and similarly prediction of node level per slice requirement fulfillment.

[0119] An AI / ML algorithm at the RAN (shown in Figure 3 with respect to gNBl 310 by way of example) may take as input the: network wide per slice level of SLA fulfillment, the per slice SLA fulfillment levels of its neighboring RAN nodes, its own per slice SLA level of fulfillment, predictions of its own per slice SLA level of fulfillment, and predictions of neighbor node’s per slice SLA level of fulfillment. The algorithm may then derive the following outputs: how to serve UEs for the slice based on predictions of how the RAN node behavior would affect the overall SLA, how to serve slice A so to facilitate network wide per slice requirement fulfillment, and how to support neighbor nodes to achieve pre slice requirement fulfillment.

[0120] Another possible method embodiment 400 is shown in Figure 4, per gNB-DU periodic SLA fulfillment. In this embodiment, the SLA fulfillment is reported per DU on a periodic basis. Step 420: gNBl-CU 410 receives an expression of the SLA for the slice, per slice requirements, where the SLA could be represented as, for example, target throughput and percentage of on target time, target drop rate and percentage of on target time, target packet delay and percentage of on target time. Step 425: gNBl-CU 410 tries to fulfill the per-slice targets for served DRBs associated to the slice. Step 430: gNBl-CU 410 may receive an indication from 0AM 405 of whether the SLA for the slice is fulfilled / not fulfilled across the whole network. The cluster-wide SLA fulfillment status may include: on target, not on target, details on KPIs (e.g., on target time, out of target time, deviation from target). Step 435: gNB- CU 410 requests to gNB-DU 415 to provide periodic updates on node level per slice requirement fulfillment status: (on target, not on target) for KPIs XI, X2, ... Xn and similarly prediction of node level per slice requirement fulfillment status. Step 440: gNB-DU 415 provides to gNB-CU 410 periodic updates on node level per slice requirement fulfillment status: (on target, not on target) for KPIs XI, X2, . . . Xn and similarly prediction of node level per slice requirement fulfillment status.

[0121] Possible method embodiment 500 is shown in Figure 5, per gNB-DU event SLA fulfillment. In this embodiment, the SLA fulfillment is reported per DU on an event basis. Step 520: gNBl-CU 510 receives an expression of the SLA for the slice, per slice requirements, where the SLA could be represented as, for example, target throughput and percentage of on target time, target drop rate and percentage of on target time, target packet delay and percentage of on target time. Step 525: gNBl-CU 510 tries to fulfill the per-slice targets for served DRBs associated to the slice. Step 530: gNBl-CU 510 may receive an indication from 0AM 505 of whether the SLA for the slice is fulfilled / not fulfilled across the whole network. The clusterwide SLA fulfillment status may include: on target, not on target, details on KPIs (e.g., on target time, out of target time, deviation from target). Step 535 gNB-CU 510 requests to gNB- DU 515 to provide event-based reporting for node level per slice requirement fulfillment status when “off target” for KPIs XI, X2, ... Xn and similarly prediction of node level per slice requirement fulfillment status. Step 540: gNB-DU 515 provides to gNB-CU 510 updates on node level per slice requirement fulfillment status: (on target, not on target) for KPIs XI, X2, . . . Xn and similarly prediction of node level per slice requirement fulfillment status.

[0122] Possible method embodiment 600 is shown in Figure 6. In this embodiment, the network node, based on the inference outcome, performs an action to reach the SLA fulfillment target. Additionally, in this embodiment, three RAN nodes are used to facilitate explanation,but the number of nodes along with which nodes are communicated at a certain step may vary with other embodiments. Step 625: gNBl 610, gNB2615, and gNB3620 receive an expression of the SLA for the slice, per slice requirements, where the SLA could be represented as, for example, target throughput and percentage of on target time, target drop rate and percentage of on target time, target packet delay and percentage of on target time. Step 630: gNBl 610 tries to fulfill the per-slice targets for served DRBs associated to the slice. Step 635: gNB2 615 receives a HANDOVER REQUEST that may include: per slice requirements fulfillment ratio, predicted per slice requirements fulfillment ratio after the requested action will be performed. Step 640: gNB2 615 uses the received prediction to predict the jointly (gNBl, gNB2) per slice requirements fulfillment ratio. Step 645: gNBl 610 receives a HANDOVER REQUEST ACK / NACK.

[0123] Possible method embodiment 700 is shown in Figure 7. In this embodiment, the network node based on the inference outcome performs an action to reach the SLA fulfillment target. Additionally, in this embodiment, three RAN nodes are used to facilitate explanation, but the number of nodes along with which nodes are communicated at a certain step may vary with other embodiments. Step 725: gNBl 710, gNB2715, and gNB3720 receive an expression of the SLA for the slice, per slice requirements, where the SLA could be represented as, for example, target throughput and percentage of on target time, target drop rate and percentage of on target time, target packet delay and percentage of on target time. Step 730: gNBl 710 tries to fulfill the per-slice targets for served DRBs associated to the slice. Step 735: gNB2 715 receives a HANDOVER REQUEST that may include a request for “node level per slice requirement fulfillment status.” Step 740: gNB2715 collects “feedback” on node level per slice requirement fulfillment ratio. Step 745: gNBl 745 receives a DATA COLLECTION UPDATE (per slice requirement fulfillment).

[0124] Another possible method embodiment is shown in Figure 8. Method 900 comprises a method performed by a first network node for performing SLA fulfillment of a network slice. Step 910 is receiving one or more SLA requirements for the network slice. Step 920 is generating first SLA fulfillment data related to the one or more SLA requirements. Step 930 is receiving, from a second network node, an SLA fulfillment status message comprising second SLA fulfillment data. Step 940 is obtaining one or more SLA output data from an AI / ML model that has been trained on a third SLA fulfillment data. Step 950 is comparing the first SLA fulfillment data and the second SLA fulfillment data to the one or more SLA output data. Step 960 is taking an operation decision based on the comparison. Method 900 can comprise various additional, alternative, and / or optional steps.

[0125] Another possible method embodiment is shown in Figure 9. Method 1100 comprises a method performed by a first network node for performing SLA fulfillment of a network slice. Step 1110 is receiving one or more SLA requirements for the network slice. Step 1120 is generating first SLA fulfillment data related to the one or more SLA requirements. Step 1130 is receiving, from a second network node, an SLA fulfillment status message comprising second SLA fulfillment data. Step 1140 is requesting, from the second network node, updated second SLA fulfillment data. Step 1150 is receiving, from the second network node, the updated second SLA fulfillment data. Step 1160 is obtaining one or more SLA output data from an AI / ML model that has been trained on a third SLA fulfillment data. Step 1170 is comparing the first SLA fulfillment data and the updated second SLA fulfillment data to the one or more SLA output data. Step 1180 is taking an operation decision based on the comparison. Method 1100 can comprise various additional, alternative, and / or optional steps.

[0126] Another possible method embodiment is shown in Figure 10. Method 1300 comprises a method performed by a first network node for performing SLA fulfillment of a network slice. Step 1310 is receiving one or more SLA requirements for the network slice. Step 1320 is generating first SLA fulfillment data related to the one or more SLA requirements. Step 1330 is sending, to a second network node, a HANDOVER REQUEST message, wherein the HANDOVER REQUEST message comprises the first SLA fulfillment data. Step 1340 is receiving, from the second network node, at least one of: a HANDOVER REQUEST ACK / NACK message; a second SLA fulfillment data. Method 1300 can comprise various additional, alternative, and / or optional steps.

[0127] Another possible method embodiment is shown in Figure 11. Method 1500 comprises a method performed by a second network node for performing SLA fulfillment of a network slice. Step 1510 is receiving, from a first network node, a HANDOVER REQUEST message, wherein the HANDOVER REQUEST message comprises first SLA fulfillment data. Step 1520 is transmitting, to the first network node, at least one of: a HANDOVER REQUEST ACK / NACK message; a second SLA fulfillment data. Method 1500 can comprise various additional, alternative, and / or optional steps.

[0128] Figure 12 shows an example of a communication system 3100 in accordance with some embodiments. In the example, the communication system 3100 includes a telecommunication network 3102 that includes an access network 3104, such as a radio access network (RAN), and a core network 3106, which includes one or more core network nodes 3108. The access network 3104 includes one or more access network nodes, such as network nodes 3110a and 3110b (one or more of which may be generally referred to as network nodes3110), or any other similar 3rd Generation Partnership Project (3GPP) access nodes or non- 3GPP access points. Moreover, as will be appreciated by those of skill in the art, a network node is not necessarily limited to an implementation in which a radio portion and a baseband portion are supplied and integrated by a single vendor. Thus, it will be understood that network nodes include disaggregated implementations or portions thereof. For example, in some embodiments, the telecommunication network 3102 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a node in the telecommunication network 3102 that supports an ORAN specification (e.g., a specification published by the O-RAN Alliance, or any similar organization) and may operate alone or together with other nodes to implement one or more functionalities of any node in the telecommunication network 3102, including one or more network nodes 3110 and / or core network nodes 3108.

[0129] Examples of an ORAN network node include an open radio unit (O-RU), an open distributed unit (O-DU), an open central unit (O-CU), including an O-CU control plane (O- CU-CP) or an O-CU user plane (O-CU-UP), a RAN intelligent controller (near-real time or non-real time) hosting software or software plug-ins, such as a near-real time control application (e.g., xApp) or a non-real time control application (e.g., rApp), or any combination thereof (the adjective “open” designating support of an ORAN specification). The network node may support a specification by, for example, supporting an interface defined by the ORAN specification, such as an Al, Fl, Wl, El, E2, X2, Xn interface, an open fronthaul user plane interface, or an open fronthaul management plane interface. Moreover, an ORAN access node may be a logical node in a physical node. Furthermore, an ORAN network node may be implemented in a virtualization environment (described further below) in which one or more network functions are virtualized. For example, the virtualization environment may include an O-Cloud computing platform orchestrated by a Service Management and Orchestration Framework via an O-2 interface defined by the O-RAN Alliance or comparable technologies. The network nodes 3110 facilitate direct or indirect connection of user equipment (UE), such as by connecting UEs 3112a, 3112b, 3112c, and 3112d (one or more of which may be generally referred to as UEs 3112) to the core network 3106 over one or more wireless connections.

[0130] Example wireless communications over a wireless connection include transmitting and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information without the use of wires, cables, or other material conductors. Moreover, in different embodiments, the communication system 3100 may include any number of wired or wireless networks, network nodes, UEs, and / or any other components or systems that may facilitate or participate in the communicationof data and / or signals whether via wired or wireless connections. The communication system 3100 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0131] The UEs 3112 may be any of a wide variety of communication devices, including wireless devices arranged, configured, and / or operable to communicate wirelessly with the network nodes 3110 and other communication devices. Similarly, the network nodes 3110 are arranged, capable, configured, and / or operable to communicate directly or indirectly with the UEs 3112 and / or with other network nodes or equipment in the telecommunication network 3102 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in the telecommunication network 3102.

[0132] In the depicted example, the core network 3106 connects the network nodes 3110 to one or more host computing systems, such as host 3116. These connections may be direct or indirect via one or more intermediary networks or devices. In other examples, network nodes may be directly coupled to hosts. The core network 3106 includes one more core network nodes (e.g., core network node 3108) that are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the UEs, network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node 3108. Example core network nodes include functions of one or more of a Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (AUSF), Subscription Identifier De-concealing function (SIDF), Unified Data Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).

[0133] The host 3116 may be under the ownership or control of a service provider other than an operator or provider of the access network 3104 and / or the telecommunication network 3102. The host 3116 may host a variety of applications to provide one or more service. Examples of such applications include live and pre-recorded audio / video content, data collection services such as retrieving and compiling data on various ambient conditions detected by a plurality of UEs, analytics functionality, social media, functions for controlling or otherwise interacting with remote devices, functions for an alarm and surveillance center, or any other such function performed by a server.

[0134] As a whole, the communication system 3100 of Figure 12 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication system may beconfigured to operate according to predefined rules or procedures, such as specific standards that include, but are not limited to: Global System for Mobile Communications (GSM); Universal Mobile Telecommunications System (UMTS); Long Term Evolution (LTE), and / or other suitable 2G, 3G, 4G, 5G standards, or any applicable future generation standard (e.g., 6G); wireless local area network (WLAN) standards, such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards (WiFi); and / or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (WiMax), Bluetooth, Z-Wave, Near Field Communication (NFC) ZigBee, LiFi, and / or any low-power wide-area network (LPWAN) standards such as LoRa and Sigfox.

[0135] In some examples, the telecommunication network 3102 is a cellular network that implements 3GPP standardized features. Accordingly, the telecommunications network 3102 may support network slicing to provide different logical networks to different devices that are connected to the telecommunication network 3102. For example, the telecommunications network 3102 may provide Ultra Reliable Low Latency Communication (URLLC) services to some UEs, while providing Enhanced Mobile Broadband (eMBB) services to other UEs, and / or Massive Machine Type Communication (mMTC) / Massive loT services to yet further UEs.

[0136] In some examples, the UEs 3112 are configured to transmit and / or receive information without direct human interaction. For instance, a UE may be designed to transmit information to the access network 3104 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 3104. Additionally, a UE may be configured for operating in single- or multi-RAT or multi -standard mode. For example, a UE may operate with any one or combination of Wi-Fi, NR (New Radio) and LTE, i.e. being configured for multi -radio dual connectivity (MR-DC), such as E-UTRAN (Evolved-UMTS Terrestrial Radio Access Network) New Radio - Dual Connectivity (EN- DC).

[0137] In the example, the hub 3114 communicates with the access network 3104 to facilitate indirect communication between one or more UEs (e.g., UE 3112c and / or 3112d) and network nodes (e.g., network node 3110b). In some examples, the hub 3114 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 3114 may be a broadband router enabling access to the core network 3106 for the UEs. As another example, the hub 3114 may be a controller that sends commands or instructions to one or more actuators in the UEs. Commands or instructions may be received from the UEs, network nodes 3110, or by executable code, script, process, or other instructions in the hub 3114. As another example, thehub 3114 may be a data collector that acts as temporary storage for UE data and, in some embodiments, may perform analysis or other processing of the data. As another example, the hub 3114 may be a content source. For example, for a UE that is a VR device, display, loudspeaker, or other media delivery device, the hub 3114 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub 3114 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 3114 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy loT devices.

[0138] The hub 3114 may have a constant / persistent or intermittent connection to the network node 3110b. The hub 3114 may also allow for a different communication scheme and / or schedule between the hub 3114 and UEs (e.g., UE 3112c and / or 3112d), and between the hub 3114 and the core network 3106. In other examples, the hub 3114 is connected to the core network 3106 and / or one or more UEs via a wired connection. Moreover, the hub 3114 may be configured to connect to an M2M service provider over the access network 3104 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 3110 while still connected via the hub 3114 via a wired or wireless connection. In some embodiments, the hub 3114 may be a dedicated hub - that is, a hub whose primary function is to route communications to / from the UEs from / to the network node 3110b. In other embodiments, the hub 3114 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node 3110b, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0139] Figure 13 shows a UE 3200 in accordance with some embodiments. The UE 3200 presents additional details of some embodiments of the UE 3112 of Figure 12. As used herein, a UE refers to a device capable, configured, arranged and / or operable to communicate wirelessly with network nodes and / or other UEs. Examples of a UE include, but are not limited to, a smart phone, mobile phone, cell phone, voice over IP (VoIP) phone, wireless local loop phone, desktop computer, personal digital assistant (PDA), wireless cameras, gaming console or device, music storage / playback device, wearable terminal device, wireless endpoint, mobile station, tablet, laptop, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), an Augmented Reality (AR) or Virtual Reality (VR) device, wireless customer-premise equipment (CPE), vehicle, vehicle-mounted or vehicle embedded / integrated wireless device, etc. Other examples include any UE identified by the 3rd Generation Partnership Project(3GPP), including a narrow band internet of things (NB-IoT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0140] A UE may support device-to-device (D2D) communication, for example by implementing a 3 GPP standard for sidelink communication, Dedicated Short-Range Communication (DSRC), vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), or vehicle- to-everything (V2X). In other examples, a UE may not necessarily have a user in the sense of a human user who owns and / or operates the relevant device. Instead, a UE may represent a device that is intended for sale to, or operation by, a human user but which may not, or which may not initially, be associated with a specific human user (e.g., a smart sprinkler controller). Alternatively, a UE may represent a device that is not intended for sale to, or operation by, an end user but which may be associated with or operated for the benefit of a user (e.g., a smart power meter).

[0141] The UE 3200 includes processing circuitry 3202 that is operatively coupled via a bus 3204 to an input / output interface 3206, a power source 3208, a memory 3210, a communication interface 3212, and / or any other component, or any combination thereof. Certain UEs may utilize all or a subset of the components shown in Figure 13. The level of integration between the components may vary from one UE to another UE. Further, certain UEs may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.

[0142] The processing circuitry 3202 is configured to process instructions and data and may be configured to implement any sequential state machine operative to execute instructions stored as machine-readable computer programs in the memory 3210. The processing circuitry 3202 may be implemented as one or more hardware-implemented state machines (e.g., in discrete logic, field-programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), etc.); programmable logic together with appropriate firmware; one or more stored computer programs, general -purpose processors, such as a microprocessor or digital signal processor (DSP), together with appropriate software; or any combination of the above. For example, the processing circuitry 3202 may include multiple central processing units (CPUs).

[0143] In the example, the input / output interface 3206 may be configured to provide an interface or interfaces to an input device, output device, or one or more input and / or output devices. Examples of an output device include a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smartcard, another output device, or any combination thereof. An input device may allow a user to capture information into the UE 3200. Examples of an input device include a touch-sensitive or presence-sensitive display, acamera (e.g., a digital camera, a digital video camera, a web camera, etc.), a microphone, a sensor, a mouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smartcard, and the like. The presence-sensitive display may include a capacitive or resistive touch sensor to sense input from a user. A sensor may be, for instance, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, a biometric sensor, etc., or any combination thereof. An output device may use the same type of interface port as an input device. For example, a Universal Serial Bus (USB) port may be used to provide an input device and an output device.

[0144] In some embodiments, the power source 3208 is structured as a battery or battery pack. Other types of power sources, such as an external power source (e.g., an electricity outlet), photovoltaic device, or power cell, may be used. The power source 3208 may further include power circuitry for delivering power from the power source 3208 itself, and / or an external power source, to the various parts of the UE 3200 via input circuitry or an interface such as an electrical power cable. Delivering power may be, for example, for charging of the power source 3208. Power circuitry may perform any formatting, converting, or other modification to the power from the power source 3208 to make the power suitable for the respective components of the UE 3200 to which power is supplied.

[0145] The memory 3210 may be or be configured to include memory such as random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, and so forth. In one example, the memory 3210 includes one or more application programs 3214, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 3216. The memory 3210 may store, for use by the UE 3200, any of a variety of various operating systems or combinations of operating systems.

[0146] The memory 3210 may be configured to include a number of physical drive units, such as redundant array of independent disks (RAID), flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, high-density digital versatile disc (HD- DVD) optical disc drive, internal hard disk drive, Blu-Ray optical disc drive, holographic digital data storage (HDDS) optical disc drive, external mini-dual in-line memory module (DIMM), synchronous dynamic random access memory (SDRAM), external micro-DIMM SDRAM, smartcard memory such as tamper resistant module in the form of a universal integrated circuit card (UICC) including one or more subscriber identity modules (SIMs), suchas a USIM and / or ISIM, other memory, or any combination thereof. The UICC may for example be an embedded UICC (eUICC), integrated UICC (iUICC) or a removable UICC commonly known as ‘SIM card.’ The memory 3210 may allow the UE 3200 to access instructions, application programs and the like, stored on transitory or non-transitory memory media, to off-load data, or to upload data. An article of manufacture, such as one utilizing a communication system may be tangibly embodied as or in the memory 3210, which may be or comprise a device-readable storage medium.

[0147] The processing circuitry 3202 may be configured to communicate with an access network or other network using the communication interface 3212. The communication interface 3212 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 3222. The communication interface 3212 may include one or more transceivers used to communicate, such as by communicating with one or more remote transceivers of another device capable of wireless communication (e.g., another UE or a network node in an access network). Each transceiver may include a transmitter 3218 and / or a receiver 3220 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter 3218 and receiver 3220 may be coupled to one or more antennas (e.g., antenna 3222) and may share circuit components, software or firmware, or alternatively be implemented separately.

[0148] In the illustrated embodiment, communication functions of the communication interface 3212 may include cellular communication, Wi-Fi communication, LPWAN communication, data communication, voice communication, multimedia communication, short-range communications such as Bluetooth, near-field communication, location-based communication such as the use of the global positioning system (GPS) to determine a location, another like communication function, or any combination thereof. Communications may be implemented in according to one or more communication protocols and / or standards, such as IEEE 802.11, Code Division Multiplexing Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMax, Ethernet, transmission control protocol / intemet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0149] Regardless of the type of sensor, a UE may provide an output of data captured by its sensors, through its communication interface 3212, via a wireless connection to a network node. Data captured by sensors of a UE can be communicated through a wireless connection to a network node via another UE. The output may be periodic (e.g., once every 15 minutes ifit reports the sensed temperature), random (e.g., to even out the load from reporting from several sensors), in response to a triggering event (e.g., when moisture is detected an alert is sent), in response to a request (e.g., a user initiated request), or a continuous stream (e.g., a live video feed of a patient).

[0150] As another example, a UE comprises an actuator, a motor, or a switch, related to a communication interface configured to receive wireless input from a network node via a wireless connection. In response to the received wireless input the states of the actuator, the motor, or the switch may change. For example, the UE may comprise a motor that adjusts the control surfaces or rotors of a drone in flight according to the received input or to a robotic arm performing a medical procedure according to the received input.

[0151] A UE, when in the form of an Internet of Things (loT) device, may be a device for use in one or more application domains, these domains comprising, but not limited to, city wearable technology, extended industrial application and healthcare. Non-limiting examples of such an loT device are a device which is or which is embedded in: a connected refrigerator or freezer, a TV, a connected lighting device, an electricity meter, a robot vacuum cleaner, a voice controlled smart speaker, a home security camera, a motion detector, a thermostat, a smoke detector, a door / window sensor, a flood / moisture sensor, an electrical door lock, a connected doorbell, an air conditioning system like a heat pump, an autonomous vehicle, a surveillance system, a weather monitoring device, a vehicle parking monitoring device, an electric vehicle charging station, a smart watch, a fitness tracker, a wearable for tactile augmentation or sensory enhancement, a water sprinkler, an animal- or item-tracking device, a sensor for monitoring a plant or animal, an industrial robot, an Unmanned Aerial Vehicle (UAV), and any kind of medical device, like a heart rate monitor or a remote controlled surgical robot. A UE in the form of an loT device comprises circuitry and / or software in dependence of the intended application of the loT device in addition to other components as described in relation to the UE 3200 shown in Figure 13.

[0152] As yet another specific example, in an loT scenario, a UE may represent a machine or other device that performs monitoring and / or measurements, and transmits the results of such monitoring and / or measurements to another UE and / or a network node. The UE may in this case be an M2M device, which may in a 3GPP context be referred to as an MTC device. As one particular example, the UE may implement the 3GPP NB-IoT standard. In other scenarios, a UE may represent a vehicle, such as a car, a bus, a truck, a ship and an airplane, or other equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation.

[0153] In practice, any number of UEs may be used together with respect to a single use case. For example, a first UE might be or be integrated in a drone and provide the drone’s speed information (obtained through a speed sensor) to a second UE that is a remote controller operating the drone. When the user makes changes from the remote controller, the first UE may adjust the throttle on the drone (e.g. by controlling an actuator) to increase or decrease the drone’s speed. The first and / or the second UE can also include more than one of the functionalities described above. For example, a UE might comprise the sensor and the actuator, and handle communication of data for both the speed sensor and the actuators.

[0154] Figure 14 shows a network node 3300 in accordance with some embodiments. As used herein, network node refers to equipment capable, configured, arranged and / or operable to communicate directly or indirectly with a UE and / or with other network nodes or equipment, in a telecommunication network. Examples of network nodes include, but are not limited to, access points (APs) (e.g., radio access points), base stations (BSs) (e.g., radio base stations, Node Bs, evolved Node Bs (eNBs) and NR NodeBs (gNBs)), O-RAN nodes or components of an O-RAN node (e g., O-RU, O-DU, O-CU).

[0155] Base stations may be categorized based on the amount of coverage they provide (or, stated differently, their transmit power level) and so, depending on the provided amount of coverage, may be referred to as femto base stations, pico base stations, micro base stations, or macro base stations. A base station may be a relay node or a relay donor node controlling a relay. A network node may also include one or more (or all) parts of a distributed radio base station such as centralized digital units, distributed units (e.g., in an O-RAN access node) and / or remote radio units (RRUs), sometimes referred to as Remote Radio Heads (RRHs). Such remote radio units may or may not be integrated with an antenna as an antenna integrated radio. Parts of a distributed radio base station may also be referred to as nodes in a distributed antenna system (DAS).

[0156] Other examples of network nodes include multiple transmission point (multi-TRP) 5G access nodes, multi -standard radio (MSR) equipment such as MSR BSs, network controllers such as radio network controllers (RNCs) or base station controllers (BSCs), base transceiver stations (BTSs), transmission points, transmission nodes, multi -cell / multi cast coordination entities (MCEs), Operation and Maintenance (O&M) nodes, Operations Support System (OSS) nodes, Self-Organizing Network (SON) nodes, positioning nodes (e.g., Evolved Serving Mobile Location Centers (E-SMLCs)), and / or Minimization of Drive Tests (MDTs).

[0157] The network node 3300 includes a processing circuitry 3302, a memory 3304, a communication interface 3306, and a power source 3308. The network node 3300 may becomposed of multiple physically separate components (e.g., a NodeB component and a RNC component, or a BTS component and a BSC component, etc.), which may each have their own respective components. In certain scenarios in which the network node 3300 comprises multiple separate components (e.g., BTS and BSC components), one or more of the separate components may be shared among several network nodes. For example, a single RNC may control multiple NodeBs. In such a scenario, each unique NodeB and RNC pair, may in some instances be considered a single separate network node. In some embodiments, the network node 3300 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memory 3304 for different RATs) and some components may be reused (e.g., a same antenna 3310 may be shared by different RATs). The network node 3300 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 3300, for example GSM, WCDMA, LTE, NR, WiFi, Zigbee, Z-wave, LoRaWAN, Radio Frequency Identification (RFID) or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within network node 3300.

[0158] The processing circuitry 3302 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and / or encoded logic operable to provide, either alone or in conjunction with other network node 3300 components, such as the memory 3304, to provide network node 3300 functionality.

[0159] In some embodiments, the processing circuitry 3302 includes a system on a chip (SOC). In some embodiments, the processing circuitry 3302 includes one or more of radio frequency (RF) transceiver circuitry 3312 and baseband processing circuitry 3314. In some embodiments, the radio frequency (RF) transceiver circuitry 3312 and the baseband processing circuitry 3314 may be on separate chips (or sets of chips), boards, or units, such as radio units and digital units. In alternative embodiments, part or all of RF transceiver circuitry 3312 and baseband processing circuitry 3314 may be on the same chip or set of chips, boards, or units.

[0160] The memory 3304 may comprise any form of volatile or non-volatile computer- readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD)),and / or any other volatile or non-volatile, non-transitory device-readable and / or computerexecutable memory devices that store information, data, and / or instructions that may be used by the processing circuitry 3302. The memory 3304 may store any suitable instructions, data, or information, including a computer program, software, an application including one or more of logic, rules, code, tables, and / or other instructions capable of being executed by the processing circuitry 3302 and utilized by the network node 3300. The memory 3304 may be used to store any calculations made by the processing circuitry 3302 and / or any data received via the communication interface 3306. In some embodiments, the processing circuitry 3302 and memory 3304 is integrated.

[0161] The communication interface 3306 is used in wired or wireless communication of signaling and / or data between a network node, access network, and / or UE. As illustrated, the communication interface 3306 comprises port(s) / terminal(s) 3316 to send and receive data, for example to and from a network over a wired connection. The communication interface 3306 also includes radio front-end circuitry 3318 that may be coupled to, or in certain embodiments a part of, the antenna 3310. Radio front-end circuitry 3318 comprises filters 3320 and amplifiers 3322. The radio front-end circuitry 3318 may be connected to an antenna 3310 and processing circuitry 3302. The radio front-end circuitry may be configured to condition signals communicated between antenna 3310 and processing circuitry 3302. The radio front-end circuitry 3318 may receive digital data that is to be sent out to other network nodes or UEs via a wireless connection. The radio front-end circuitry 3318 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of filters 3320 and / or amplifiers 3322. The radio signal may then be transmitted via the antenna 3310. Similarly, when receiving data, the antenna 3310 may collect radio signals which are then converted into digital data by the radio front-end circuitry 3318. The digital data may be passed to the processing circuitry 3302. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0162] In certain alternative embodiments, the network node 3300 does not include separate radio front-end circuitry 3318, instead, the processing circuitry 3302 includes radio front-end circuitry and is connected to the antenna 3310. Similarly, in some embodiments, all or some of the RF transceiver circuitry 3312 is part of the communication interface 3306. In still other embodiments, the communication interface 3306 includes one or more ports or terminals 3316, the radio front-end circuitry 3318, and the RF transceiver circuitry 3312, as part of a radio unit (not shown), and the communication interface 3306 communicates with the baseband processing circuitry 3314, which is part of a digital unit (not shown).

[0163] The antenna 3310 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 3310 may be coupled to the radio frontend circuitry 3318 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 3310 is separate from the network node 3300 and connectable to the network node 3300 through an interface or port.

[0164] The antenna 3310, communication interface 3306, and / or the processing circuitry 3302 may be configured to perform any receiving operations and / or certain obtaining operations described herein as being performed by the network node. Any information, data and / or signals may be received from a UE, another network node and / or any other network equipment. Similarly, the antenna 3310, the communication interface 3306, and / or the processing circuitry 3302 may be configured to perform any transmitting operations described herein as being performed by the network node. Any information, data and / or signals may be transmitted to a UE, another network node and / or any other network equipment.

[0165] The power source 3308 provides power to the various components of network node 3300 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source 3308 may further comprise, or be coupled to, power management circuitry to supply the components of the network node 3300 with power for performing the functionality described herein. For example, the network node 3300 may be connectable to an external power source (e.g., the power grid, an electricity outlet) via an input circuitry or interface such as an electrical cable, whereby the external power source supplies power to power circuitry of the power source 3308. As a further example, the power source 3308 may comprise a source of power in the form of a battery or battery pack which is connected to, or integrated in, power circuitry. The battery may provide backup power should the external power source fail.

[0166] Embodiments of the network node 3300 may include additional components beyond those shown in Figure 14 for providing certain aspects of the network node’s functionality, including any of the functionality described herein and / or any functionality necessary to support the subject matter described herein. For example, the network node 3300 may include user interface equipment to allow input of information into the network node 3300 and to allow output of information from the network node 3300. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node 3300. In some embodiments providing a core network no

[0167] de, such as core network node 108 of FIG. 31, some components, such as the radio front-end circuitry 3318 and the RF transceiver circuitry 3312 may be omitted.

[0168] Figure 15 is a block diagram illustrating a virtualization environment 3400 in which functions implemented by some embodiments may be virtualized. In the present context, virtualizing means creating virtual versions of apparatuses or devices which may include virtualizing hardware platforms, storage devices and networking resources. As used herein, virtualization can be applied to any device described herein, or components thereof, and relates to an implementation in which at least a portion of the functionality is implemented as one or more virtual components. Some or all of the functions described herein may be implemented as virtual components executed by one or more virtual machines (VMs) implemented in one or more virtual environments 3400 hosted by one or more of hardware nodes, such as a hardware computing device that operates as a network node, UE, core network node, or host. Further, in embodiments in which the virtual node does not require radio connectivity (e.g., a core network node or host), then the node may be entirely virtualized. In some embodiments, the virtualization environment 3400 includes components defined by the O-RAN Alliance, such as an O-Cloud environment orchestrated by a Service Management and Orchestration Framework via an O-2 interface. Virtualization may facilitate distributed implementations of a network node, UE, core network node, or host.

[0169] Applications 3402 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment 3400 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0170] Hardware 3404 includes processing circuitry, memory that stores software and / or instructions executable by hardware processing circuitry, and / or other hardware devices as described herein, such as a network interface, input / output interface, and so forth. Software may be executed by the processing circuitry to instantiate one or more virtualization layers 3406 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VMs 3408a and 3408b (one or more of which may be generally referred to as VMs 3408), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. The virtualization layer 3406 may present a virtual operating platform that appears like networking hardware to the VMs 3408.

[0171] The VMs 3408 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by a corresponding virtualization layer 3406. Different embodiments of the instance of a virtual appliance 3402 may be implemented on one or more of VMs 3408, and the implementations may be made in different ways. Virtualization of the hardware is in some contexts referred to as network function virtualization (NFV). NFVmay be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches, and physical storage, which can be located in data centers, and customer premise equipment.

[0172] In the context of NFV, a VM 3408 may be a software implementation of a physical machine that runs programs as if they were executing on a physical, non-virtualized machine. Each of the VMs 3408, and that part of hardware 3404 that executes that VM, be it hardware dedicated to that VM and / or hardware shared by that VM with others of the VMs, forms separate virtual network elements. Still in the context of NFV, a virtual network function is responsible for handling specific network functions that run in one or more VMs 3408 on top of the hardware 3404 and corresponds to the application 3402.

[0173] Hardware 3404 may be implemented in a standalone network node with generic or specific components. Hardware 3404 may implement some functions via virtualization. Alternatively, hardware 3404 may be part of a larger cluster of hardware (e.g. such as in a data center or CPE) where many hardware nodes work together and are managed via management and orchestration 3410, which, among others, oversees lifecycle management of applications 3402. In some embodiments, hardware 3404 is coupled to one or more radio units that each include one or more transmitters and one or more receivers that may be coupled to one or more antennas. Radio units may communicate directly with other hardware nodes via one or more appropriate network interfaces and may be used in combination with the virtual components to provide a virtual node with radio capabilities, such as a radio access node or a base station. In some embodiments, some signaling can be provided with the use of a control system 3412 which may alternatively be used for communication between hardware nodes and radio units.

[0174] Although the computing devices described herein (e.g., UEs, network nodes) may include the illustrated combination of hardware components, other embodiments may comprise computing devices with different combinations of components. It is to be understood that these computing devices may comprise any suitable combination of hardware and / or software needed to perform the tasks, features, functions and methods disclosed herein. Determining, calculating, obtaining or similar operations described herein may be performed by processing circuitry, which may process information by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination. Moreover, while components are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, computing devices may comprisemultiple different physical components that make up a single illustrated component, and functionality may be partitioned between separate components. For example, a communication interface may be configured to include any of the components described herein, and / or the functionality of the components may be partitioned between the processing circuitry and the communication interface. In another example, non-computationally intensive functions of any of such components may be implemented in software or firmware and computationally intensive functions may be implemented in hardware.

[0175] In certain embodiments, some or all of the functionality described herein may be provided by processing circuitry executing instructions stored on in memory, which in certain embodiments may be a computer program product in the form of a non-transitory computer- readable storage medium. In alternative embodiments, some or all of the functionality may be provided by the processing circuitry without executing instructions stored on a separate or discrete device-readable storage medium, such as in a hard-wired manner. In any of those particular embodiments, whether executing instructions stored on a non-transitory computer- readable storage medium or not, the processing circuitry can be configured to perform the described functionality. The benefits provided by such functionality are not limited to the processing circuitry alone or to other components of the computing device, but are enjoyed by the computing device as a whole, and / or by end users and a wireless network generally.

Claims

ClaimsWhat is claimed is:

1. A method (900) performed by a first network node (3300) for performing service level agreement, SLA, fulfillment of a network slice, the method comprising: receiving (910) one or more SLA requirements for the network slice; generating (920) first SLA fulfillment data related to the one or more SLA requirements; receiving (930), from a second network node (3300), an SLA fulfillment status message comprising second SLA fulfillment data; obtaining (940) one or more SLA output data from an artificial intelligence / machine learning, AI / ML, model that has been trained on a third SLA fulfillment data; comparing (950) the first SLA fulfillment data and the second SLA fulfillment data to the one or more SLA output data; and taking (960) an operation decision based on the comparison.

2. The method of claim 1, wherein the first network node comprises at least one of: an Operation and Management, 0AM, node; a gNodeB, gNB; a Radio Access Network, RAN, node; a gNB-Central Unit, gNB-CU.

3. The method of claim 1 or 2, wherein the second network node comprises at least one of: an Operation and Management, 0AM, node; a gNodeB, gNB; a Radio Access Network, RAN, node; a gNB-Distributed Unit, gNB-DU.

4. The method of any of claims 1 to 3, wherein the SLA fulfillment status message comprises at least one of: a cluster-wide SLA fulfillment message; a node-level SLA fulfillment message.

5. The method of any of claims 1 to 4, wherein the first SLA fulfillment data, second SLA fulfillment data, one or more SLA output data, and / or third SLA fulfillment data comprise at least one of: cluster-wide SLA fulfillment data; node-level SLA fulfillment data.

6. The method of any of claims 1 to 5, further comprising:sending a second SLA fulfillment status message comprising fourth SLA fulfillment data to at least one of a plurality of network nodes.

7. The method of any of claims 1 to 4, wherein the first SLA fulfillment data, second SLA fulfillment data, one or more SLA output data, and / or third SLA fulfillment data comprise at least one of: one or more on-target data; one or more not-on-target data; one or more on-targettime data; one or more out-of-target-time data; one or more deviation-from-target data; one or more predictions of SLA fulfillment data.

8. The method of any of claims 1 to 7, further comprising: receiving, from a third network node, a third SLA fulfillment status message comprising fourth SLA fulfillment data; wherein the comparing further comprises comparing the first SLA fulfillment data and the second SLA fulfillment data to the fourth SLA fulfillment data.

9. The method of any of claims 1 to 8, wherein the one or more SLA requirements for the network slice are received from the second network node.

10. A method (1100) performed by a first network node (3300) for performing service level agreement, SLA, fulfillment of a network slice, the method comprising: receiving (1110) one or more SLA requirements for the network slice; generating (1120) first SLA fulfillment data related to the one or more SLA requirements; receiving (1130), from a second network node (3300), an SLA fulfillment status message comprising second SLA fulfillment data; requesting (1140), from the second network node, updated second SLA fulfillment data; receiving (1150), from the second network node, the updated second SLA fulfillment data; obtaining (1160) one or more SLA output data from an artificial intelligence / machine learning, AI / ML, model that has been trained on a third SLA fulfillment data; comparing (1170) the first SLA fulfillment data and the updated second SLA fulfillment data to the one or more SLA output data; and taking (1180) an operation decision based on the comparison.

11. The method of claim 10, wherein the first network node comprises at least one of: agNodeB, gNB; a Radio Access Network, RAN, node; a gNB-Central Unit, gNB-CU.

12. The method of claim 10 or 11, wherein the second network node comprises at least one of: an Operation and Management, 0AM, node; a gNodeB, gNB; a Radio Access Network, RAN, node; a gNB-Distributed Unit, gNB-DU.

13. The method of any of claims 10 to 12, wherein the requesting comprises requesting the updated second SLA fulfillment data to be send at a defined time period.

14. The method of any of claims 10 to 13, wherein the updated second SLA fulfillment data is received at the defined time period.

15. The method of any of claims 10 to 14, wherein the SLA fulfillment status message comprises at least one of: a cluster-wide SLA fulfillment message; a node-level SLA fulfillment message.

16. The method of any of claims 10 to 15, wherein the first SLA fulfillment data, second SLA fulfillment data, one or more SLA output data, updated second SLA fulfillment data, and / or third SLA fulfillment data comprise at least one of: cluster- wide SLA fulfillment data; node-level SLA fulfillment data.

17. The method of any of claims 10 to 16, further comprising: sending a second SLA fulfillment status message comprising fourth SLA fulfillment data to at least one of a plurality of network nodes.

18. The method of any of claims 10 to 17, wherein the first SLA fulfillment data, second SLA fulfillment data, one or more SLA output data, updated second SLA fulfillment data, and / or third SLA fulfillment data comprise at least one of: one or more on-target data; one or more not-on-target data; one or more on-target-time data; one or more out-of-target-time data; one or more deviation-from-target data; one or more predictions of SLA fulfillment data.

19. The method of any of claims 10 to 18, wherein the one or more SLA requirements are received from the second network node.

20. A method (1300) performed by a first network node (3300) for performing service level agreement, SLA, fulfillment of a network slice, the method comprising: receiving (1310) one or more SLA requirements for the network slice; generating (1320) first SLA fulfillment data related to the one or more SLA requirements; sending (1330), to a second network node (3300), a HANDOVER REQUEST message, wherein the HANDOVER REQUEST message comprises the first SLA fulfillment data; receiving (1340), from the second network node, at least one of: a HANDOVER REQUEST ACK / NACK message; a second SLA fulfillment data.

21. The method of claim 20, wherein the HANDOVER REQUEST message further comprises a prediction of second SLA fulfillment data after a handover to the second network node.

22. The method of claim 21 or 22, wherein the HANDOVER REQUEST ACK / NACK message and / or second SLA fulfillment data are based on the second network node performing the steps of: obtaining one or more SLA output data from an artificial intelligence / machine learning, AI / ML, model that has been trained on a third SLA fulfillment data; and comparing the first SLA fulfillment data and / or the second SLA fulfillment data to the one or more SLA output data;23. The method of any of claims 20 to 22, wherein the first network node comprises at least one of: an Operation and Management, 0AM, node; a gNodeB, gNB; a Radio Access Network, RAN, node; a gNB-Central Unit, gNB-CU.

24. The method of any of claims 20 to 23, wherein the second network node comprises at least one of: an Operation and Management, 0AM, node; a gNodeB, gNB; a Radio Access Network, RAN, node; a gNB-Distributed Unit, gNB-DU.

25. The method of any of claims 20 to 24, wherein the first SLA fulfillment data, second SLA fulfillment data, one or more SLA output data, and / or third SLA fulfillment data comprise at least one of: cluster-wide SLA fulfillment data; node-level SLA fulfillment data.

26. The method of any of claims 20 to 25, wherein the one or more SLA requirements arereceived from the second network node.

27. A method (1500) performed by a second network node (3300) for performing service level agreement, SLA, fulfillment of a network slice, the method comprising: receiving (1510), from a first network node, a HANDOVER REQUEST message, wherein the HANDOVER REQUEST message comprises first SLA fulfillment data; transmitting (1520), to the first network node, at least one of: a HANDOVER REQUEST ACK / NACK message; a second SLA fulfillment data.

28. The method of claim 27, further comprising: obtaining one or more SLA output data from an artificial intelligence / machine learning, AI / ML, model that has been trained on a third SLA fulfillment data; and comparing the first SLA fulfillment data and / or the second SLA fulfillment data to the one or more SLA output data; wherein the HANDOVER REQUEST ACK / NACK message and / or the second SLA fulfillment data are based on the comparison.

29. The method of claim 27 or 28, wherein the HANDOVER REQUEST message further comprises a prediction of second SLA fulfillment data after a handover to the second network node.

30. The method of any of claims 27 to 29, wherein the first network node comprises at least one of: a gNodeB, gNB; a Radio Access Network, RAN, node; a gNB-Central Unit, gNB-CU.

31. The method of any of claims 27 to 30, wherein the second network node comprises at least one of: an Operation and Management, 0AM, node; a gNodeB, gNB; a Radio Access Network, RAN, node; a gNB-Distributed Unit, gNB-DU.

32. The method of any of claims 27 to 31, wherein the first SLA fulfillment data, second SLA fulfillment data, one or more SLA output data, and / or third SLA fulfillment data comprise at least one of: cluster-wide SLA fulfillment data; node-level SLA fulfillment data.

33. The method of any of claims 27 to 32, further comprising transmitting, to the first network node, one or more SLA requirements for a network slice.

34. A network node for (3300) performing service level agreement, SLA, fulfillment of a network slice comprising: processing circuitry (3302) configured to perform any of the steps of any of claims 1 to 33; and power supply circuitry (3308) configured to supply power to the processing circuitry.

35. A network node (3300) for performing service level agreement, SLA, fulfillment of a network slice comprising: processing circuitry (3302) ; and a memory (3304) storing instructions whereby the processing circuitry is operative to perform the steps of: receiving one or more SLA requirements for the network slice; generating first SLA fulfillment data related to the one or more SLA requirements; receiving, from a second network node, an SLA fulfillment status message comprising second SLA fulfillment data; obtaining one or more SLA output data from an artificial intelligence / machine learning, AI / ML, model that has been trained on a third SLA fulfillment data; comparing the first SLA fulfillment data and the second SLA fulfillment data to the one or more SLA output data; and taking an operation decision based on the comparison.

36. A network node (3300) for performing service level agreement, SLA, fulfillment of a network slice comprising: processing circuitry (3302) ; and a memory (3304) storing instructions whereby the processing circuitry is operative to perform the steps of: receiving one or more SLA requirements for the network slice; generating first SLA fulfillment data related to the one or more SLA requirements; receiving, from a second network node, an SLA fulfillment status message comprising second SLA fulfillment data; requesting, from the second network node, updated second SLA fulfillment data; receiving, from the second network node, the updated second SLA fulfillment data;obtaining one or more SLA output data from an artificial intelligence / machine learning, AI / ML, model that has been trained on a third SLA fulfillment data; comparing the first SLA fulfillment data and the updated second SLA fulfillment data to the one or more SLA output data; and taking an operation decision based on the comparison.

37. A network node (3300) for performing service level agreement, SLA, fulfillment of a network slice comprising: processing circuitry (3302) ; and a memory (3304) storing instructions whereby the processing circuitry is operative to perform the steps of: receiving one or more SLA requirements for the network slice; generating first SLA fulfillment data related to the one or more SLA requirements; sending, to a second network node, a HANDOVER REQUEST message, wherein the HANDOVER REQUEST message comprises the first SLA fulfillment data; receiving, from the second network node, at least one of: a HANDOVER REQUEST ACK / NACK message; a second SLA fulfillment data.

38. A network node (3300) for performing service level agreement, SLA, fulfillment of a network slice comprising: processing circuitry (3302) ; and a memory (3304) storing instructions whereby the processing circuitry is operative to perform the steps of: receiving, from a first network node, a HANDOVER REQUEST message, wherein the HANDOVER REQUEST message comprises first SLA fulfillment data; transmitting, to the first network node, at least one of: a HANDOVER REQUEST ACK / NACK message; a second SLA fulfillment data.

39. The network node of any of claims 34 to 38, wherein the network node comprises at least one of: a gNodeB, gNB; a Radio Access Network, RAN, node; a gNB-Central Unit, gNB-CU; an Operation and Management, 0AM, node; a gNB-Distributed Unit, gNB-DU.

Images