Authorization to retrieve a machine learning model in a communication network

Abstract

A method performed by network repository equipment (16) in a communication network (10). The network repository equipment (16) receives, from first model training equipment (12-1), a request (18) for an access token (20) indicating the first model training equipment (12-1) is authorized to retrieve a machine learning, ML, model from second model training equipment (12-2). The network repository equipment (16) makes a determination as to whether the first model training equipment (12-1) is authorized to retrieve the ML model from the second model training equipment (12-2), based on a first interoperability indicator list (24-1 ) for the first model training equipment (12-1) which identifies one or more equipment vendors (26-1, 26-2) nominally authorized to retrieve ML models from the first model training equipment (12-1). The network repository equipment (16) responds to the request (18) based on the determination.

Description

[0001] AUTHORIZATION TO RETRIEVE A MACHINE LEARNING MODEL IN A COMMUNICATION NETWORK

[0002] TECHNICAL FIELD

[0003] The present application relates generally to a communication network, and relates more particularly to authorization to retrieve a machine learning model in such a network.

[0004] BACKGROUND

[0005] A communication network can exploit machine learning to better support the communication services it provides. For example, machine learning can be used to learn and predict patterns in the demand for resources over time, so that the communication network can optimize resource allocation over time.

[0006] Distributed machine learning (DML) distributes machine learning training across different clients in the communication network. In some types of DML, such as federated learning (FL), different clients perform training locally using training data local to the respective client and a server aggregates the results of the clients’ local training. DML advantageously accelerates the speed of training so as to reduce training time, relieves congestion in the communication network by limiting the amount of data sent to a central node, and / or protects sensitive information so as to preserve data privacy.

[0007] In the context of a 5G communication network, the 5G system architecture allows any network function (NF) to obtain analytics from a Network Data Analytics Function (NWDAF). The NWDAF provides network analytics information (e.g., statistical information of past events and / or predictive information) to other NFs. The NWDAF can also store and retrieve analytics information from an Analytics Data Repository Function (ADRF). 3GPP TS 23.288 (v17.2.0) specifies that the NWDAF is the main NF for computing analytics reports, and classifies NWDAF into two sub-functions (or logical functions): Analytics Logical Function (AnLF) and Model Training Logical Function (MTLF). The AnLF is a logical function which performs inference, derives analytics information (i.e. derives statistics and / or predictions based on Analytics Consumer request) and exposes analytics service i.e. Nnwdaf_AnalyticsSubscription or Nnwdaf_Analyticslnfo. The MTLF is a logical function which trains Machine Learning (ML) models and exposes new training services (e.g. providing trained ML model). In order to retrieve the ML model from the MTLF, the AnLF may use trained ML model provisioning services from the MTLF to request the ML model. Note that, as used herein, then, when referring to NWDAF containing MTLF, only the word MTLF will be used, and when referring to NWDAF containing AnLF, only the word AnLF will be used.

[0008] When multiple NWDAFs exist, not all of them need to be able to provide the same type of analytics results, i.e. some of them can be specialized in providing certain types of analytics. An Analytics ID information element is used to identify the type of supported analytics that NWDAF can generate. Furthermore, an NWDAF MTLF can act as an NF service consumer and request a trained ML model from another NWDAF MTLF acting as an NF service producer, e.g., based on the ML model provided by the service consumer NWDAF. See 3rdGeneration Partnership Project (3GPP) Technical Specification (TS) 23.288 V18.2.0. The NWDAF MTLF (i.e., NF consumer) may determine to request a trained ML model from another NWDAF MTLF, either based on local configuration (i.e., without receiving any solicited request from AnLF) or when it receives the request from NWDAF containing AnLF. This ML model retrievla service may be used by an NWDAF containing MTLF service consumer to enable e.g., federated learning or to update an ML model.

[0009] Federated learning among multiple NWDAFs in this regard is a machine learning technique in the core network that trains an ML Model across multiple decentralized entities holding respective local data sets, without exchanging / sharing the underlying local data sets. This approach stands in contrast to traditional centralized machine learning techniques where all the local datasets are uploaded to one server, thus addressing critical issues such as data privacy, data security, data access rights. For Federated Learning supported by multiple NWDAFs containing MTLF, there is one NWDAF containing MTLF acting as FL server (called FL server NWDAF for short) and multiple NWDAFs containing MTLF acting as FL client (called FL client NWDAF for short). The FL Server NWDAF discovers and selects FL client NWDAFs to participant in an FL procedure, requests FL client NWDAFs to do local model training and to report local model information, generates a global ML model by aggregating local model information from FL client NWDAFs, and sends the global ML model back to FL client NWDAFs and repeats training iteration(s) if needed. Each FL client NWDAF locally trains the ML model tasked by the FL server NWDAF with the available local data set, which includes the data that is not allowed to be shared with others due to e.g. data privacy, data security, data access rights, reports the trained local ML model information to the FL server NWDAF, and receives the global ML model feedback from FL server NWDAF and repeats training iteration(s) if needed.

[0010] In scenarios where ML models are shared or stored in network equipment provided by different vendors, an ML model should be protected from access and use by consumer NFs that are provided by different vendors than the ML model. Indeed, ML models are generally considered important intellectual property of their owners (e.g., 5GC vendors) and, as such, need to have their confidentiality and integrity protected at all times.

[0011] Towards this end, TS 33.501 V18.2.0 and CR S3-233266 specify security aspects of FL and FL model sharing in a 5G network. In this approach, model sharing is authorized based on comparing the Vendor ID of an NF consumer to a so-called ML Model Interoperability indicator for the NF producer. The ML Model Interoperability Indicator comprises a list of NWDAF providers (vendors) that are allowed to retrieve ML models from this NWDAF containing MTLF. Accordingly, an NF consumer is allowed to retrieve an ML model from an NF producer if the Vendor ID of the NF consumer is included in the ML Model Interoperability indicator for the NF producer. The NF producer (NWDAF MTLF) therefore needs to be registered in the Network Repository Function (NRF), indicating the NF service producer information (including interoperability indicator per Analytics ID) that is used by the NRF to decide whether the consumer (e.g., NWDAF AnLF) is authorized. And the NF service consumer needs to be registered in the NRF, e.g., as OAuth 2.0 client, indicating the NF service consumer information (including Vendor ID) that is used by the NRF to decide whether the consumer is authorized.

[0012] SUMMARY

[0013] Some embodiments herein safeguard a machine learning (ML) model from secondhand distribution to an unauthorized vendor, e.g., by an authorized vendor retrieving the ML model firsthand but then further distributing the ML model secondhand to another vendor that would not itself have been authorized to retrieve the ML model firsthand. Some embodiments in this regard determine whether a first vendor is authorized to retrieve an ML model from a second vendor, on the basis of a first interoperability indicator list for the first vendor identifying vendor(s) nominally authorized to retrieve ML models from the first vendor. For example, even if the first vendor is on a second interoperability indicator list for the second vendor indicating vendor(s) nominally authorized to retrieve ML models from the second vendor, some embodiments nonetheless determine the first vendor is not actually authorized to retrieve an ML model from the second vendor because the first interoperability indicator list includes at least one vendor not on the second interoperability indicator list, i.e., because the first interoperability indicator list is not a subset of the second interoperability indicator list. Embodiments in this case deny the first vendor’s access to the ML model in order to prevent propagation of the ML model from the first vendor to a vendor that is on the first interoperability indicator list but not the second interoperability indicator list.

[0014] Accordingly, some embodiments advantageously improve the security of ML models in a context where ML models are shared or stored in network equipment provided by different vendors. This may in turn facilitate federated learning in a communication network, so as to reduce training time, relieve congestion in the communication network by limiting the amount of data sent to a central node, and / or protect sensitive information so as to preserve data privacy.

[0015] More particularly, embodiments herein include a method performed by network repository equipment in a communication network. The method comprises receiving, from first model training equipment, a request for an access token indicating the first model training equipment is authorized to retrieve a machine learning, ML, model from second model training equipment. The method also comprises making a determination as to whether the first model training equipment is authorized to retrieve the ML model from the second model training equipment, based on a first interoperability indicator list for the first model training equipment which identifies one or more equipment vendors nominally authorized to retrieve ML models from the first model training equipment. The method also comprises responding to the request based on the determination. In some embodiments, making the determination comprises making the determination based on whether the first interoperability indicator list is a subset of a second interoperability indicator list for the second model training equipment which identifies one or more equipment vendors nominally authorized to retrieve ML models from the second model training equipment. In some embodiments, the determination is made that the first model training equipment is authorized to retrieve the ML model if the first interoperability indicator list is a subset of the second interoperability indicator list and the second interoperability indicator list indicates a vendor of the first model training equipment is nominally authorized to retrieve ML models from the second model training equipment. In some embodiments, the determination is made that the first model training equipment is not authorized to retrieve the ML model if the first interoperability indicator list is not a subset of the second interoperability indicator list or the second interoperability indicator list indicates a vendor of the first model training equipment is not nominally authorized to retrieve ML models from the second model training equipment.

[0016] In some embodiments, making the determination comprises making the determination based on whether the first interoperability indicator list is included in a set of one or more authorized interoperability lists for the second model training equipment.

[0017] In some embodiments, the determination is made also based on whether the first model training equipment acts as a federated learning (FL) server in an FL process in which the second model training equipment locally trains the ML model. In some embodiments, the determination is made that the first model training equipment is authorized to retrieve the ML model if the first interoperability indicator list is not a subset of the second interoperability indicator list. In some embodiments, the determination is made that the first model training equipment is authorized to retrieve the ML model if the second interoperability indicator list indicates a vendor of the first model training equipment is nominally authorized to retrieve ML models from the second model training equipment. In some embodiments, the determination is made that the first model training equipment is authorized to retrieve the ML model if the first model training equipment acts as an FL server in an FL process in which the second model training equipment locally trains the ML model. In some embodiments, the determination is made that the first model training equipment is authorized to retrieve the ML model if the first interoperability indicator list is not a subset of the second interoperability indicator list. In some embodiments, the determination is made that the first model training equipment is authorized to retrieve the ML model if the second interoperability indicator list is a subset of the first interoperability indicator list. In some embodiments, the determination is made that the first model training equipment is authorized to retrieve the ML model if the second interoperability indicator list indicates a vendor of the first model training equipment is nominally authorized to retrieve ML models from the second model training equipment. In some embodiments, the determination is made that the first model training equipment is authorized to retrieve the ML model if the first model training equipment acts as an FL server in an FL process in which the second model training equipment locally trains the ML model. In some embodiments, the determination is made that the first model training equipment is authorized to retrieve the ML model if the first interoperability indicator list is not a subset of the second interoperability indicator list. In some embodiments, the determination is made that the first model training equipment is authorized to retrieve the ML model if the second interoperability indicator list indicates a vendor of the first model training equipment is nominally authorized to retrieve ML models from the second model training equipment. In some embodiments, the determination is made that the first model training equipment is authorized to retrieve the ML model if the first model training equipment acts as an FL server in an FL process in which the second model training equipment locally trains the ML model. In some embodiments, the determination is made that the first model training equipment is authorized to retrieve the ML model if, for each of multiple FL clients in the FL process for which the first model training equipment acts as an FL server, an interoperability indicator list for the FL client is not a superset of the second interoperability indicator list. In some embodiments, the determination is made that the first model training equipment is authorized to retrieve the ML model if the first interoperability indicator list is not a subset of the second interoperability indicator list. In some embodiments, the determination is made that the first model training equipment is authorized to retrieve the ML model if the second interoperability indicator list indicates a vendor of the first model training equipment is nominally authorized to retrieve ML models from the second model training equipment. In some embodiments, the determination is made that the first model training equipment is authorized to retrieve the ML model if the first model training equipment acts as an FL server in an FL process in which the second model training equipment locally trains the ML model. In some embodiments, the determination is made that the first model training equipment is authorized to retrieve the ML model if, for each of multiple FL clients in the FL process for which the first model training equipment acts as an FL server, an interoperability indicator list for the FL client is not a superset of the first interoperability indicator list.

[0018] In some embodiments, making the determination comprises making the determination based on an authorization policy specific to the second model training equipment. In some embodiments, according to the authorization policy, authorization of the first model training equipment to retrieve the ML model depends on the first interoperability indicator list for the first model training equipment. In some embodiments, the method further comprises receiving the authorization policy from the second model training equipment during a registration procedure for registering the second model training equipment with the network repository equipment. In some embodiments, the authorization policy specifies what requirements must be met in order for the network repository equipment to authorize any model training equipment to retrieve the ML model. In some embodiments, the requirements are specified as a function of an interoperability indicator list of any model training equipment requesting the ML model.

[0019] In some embodiments, the request includes the first interoperability indicator list. In some embodiments, the method further comprises receiving the first interoperability indicator list from the first model training equipment during a procedure for registering the first model training equipment with the network repository equipment. In some embodiments, the method further comprises storing the first interoperability indicator list in a profile for the first model training equipment. In some embodiments, the method further comprises, after receiving the request, retrieving the first interoperability indicator list from the profile for the first model training equipment.

[0020] In some embodiments, responding to the request comprises, if the determination is made that the first model training equipment is authorized to retrieve the ML model, transmitting the requested access token to the first model training equipment.

[0021] In some embodiments, the first model training equipment implements a first Network Data Analytics Function, NWDAF, Model Training Logic Function, MTLF, as a Network Function (NF) service consumer, and wherein the second model training equipment implements a second NWDAF MTLF as an NF service producer.

[0022] In some embodiments, the ML model is associated with an analytics identifier, ID, and wherein the first interoperability indicator list is specific to the analytics ID so as to identify one or more equipment vendors nominally authorized to retrieve from the first model training equipment ML models associated with the analytics ID.

[0023] In some embodiments, the method further comprises providing user data, and forwarding the user data to a host computer via the transmission to a base station.

[0024] Other embodiments herein include a method performed by first model training equipment in a communication network. The method comprises transmitting, to network repository equipment in the communication network, a request for an access token indicating the first model training equipment is authorized to retrieve a machine learning, ML, model from second model training equipment. In some embodiments, the request includes a first interoperability indicator list for the first model training equipment which identifies one or more equipment vendors nominally authorized to retrieve ML models from the first model training equipment. The method also comprises receiving a response to the request from the network repository equipment.

[0025] In some embodiments, the response includes the requested access token. In some embodiments, the method further comprises transmitting an ML model request to the second model training equipment or to analytical data repository equipment associated with the second model training equipment. In some embodiments, the ML model request includes the access token. In some embodiments, the method further comprises receiving the ML model in response to the ML model request.

[0026] In some embodiments, the first model training equipment implements a first Network Data Analytics Function, NWDAF, Model Training Logic Function, MTLF, as a Network Function (NF) service consumer, and wherein the second model training equipment implements a second NWDAF MTLF as an NF service producer.

[0027] In some embodiments, the ML model is associated with an analytics identifier, ID, and wherein the first interoperability indicator list is specific to the analytics ID so as to identify one or more equipment vendors nominally authorized to retrieve from the first model training equipment ML models associated with the analytics ID.

[0028] Other embodiments herein include a method performed by second model training equipment in a communication network. The method comprises transmitting, to network repository equipment in the communication network, an authorization policy for authorizing other model training equipment to retrieve a machine learning, ML, model from the second model training equipment. In some embodiments, the authorization policy specifies whether or not other model training equipment is nominally authorized to retrieve the ML model as a function of an interoperability indicator list for the other model training equipment.

[0029] In some embodiments, the authorization policy specifies whether or not first model training equipment is authorized to retrieve the ML model depending on whether or not a first interoperability indicator list for the first model training equipment is a subset of a second interoperability indicator list for the second model training equipment. In some embodiments, the first interoperability indicator list identifies one or more equipment vendors nominally authorized to retrieve ML models from the first model training equipment, and the second interoperability indicator list identifies one or more equipment vendors nominally authorized to retrieve ML models from the second model training equipment. In some embodiments, the authorization policy specifies that the first model training equipment is authorized to retrieve the ML model if the first interoperability indicator list is a subset of the second interoperability indicator list and the second interoperability indicator list indicates a vendor of the first model training equipment nominally authorized to retrieve ML models from the second model training equipment. In some embodiments, the authorization policy specifies that the first model training equipment is not authorized to retrieve the ML model if the first interoperability indicator list is not a subset of the second interoperability indicator list or the second interoperability indicator list indicates a vendor of the first model training equipment is not nominally authorized to retrieve ML models from the second model training equipment.

[0030] In some embodiments, the authorization policy indicates a set of one or more authorized interoperability lists for the second model training equipment. In some embodiments, the authorization policy specifies whether or not first model training equipment is authorized to retrieve the ML model depending on whether or not whether a first interoperability indicator list for the first model training equipment is included in the set of one or more authorized interoperability lists. In some embodiments, the first interoperability indicator list identifies one or more equipment vendors nominally authorized to retrieve ML models from the first model training equipment. In some embodiments, the authorization policy specifies whether or not other model training equipment is authorized to retrieve the ML model as a function whether the other model training equipment acts as a federated learning (FL) server in an FL process in which the second model training equipment locally trains the ML model. In some embodiments, the authorization policy specifies first model training equipment is authorized to retrieve the ML model if a second interoperability indicator list for the second model training equipment indicates a vendor of the first model training equipment is authorized to retrieve ML models from the second model training equipment. In some embodiments, the second interoperability indicator list identifies one or more equipment vendors nominally authorized to retrieve ML models from the second model training equipment. In some embodiments, the authorization policy specifies first model training equipment is authorized to retrieve the ML model if the first model training equipment acts as an FL server in an FL process in which the second model training equipment locally trains the ML model. In some embodiments, the authorization policy specifies first model training equipment is authorized to retrieve the ML model if a second interoperability indicator list for the second model training equipment is a subset of a first interoperability indicator list for the first model training equipment. In some embodiments, the first interoperability indicator list identifies one or more equipment vendors authorized to retrieve ML models from the first model training equipment, and the second interoperability indicator list identifies one or more equipment vendors nominally authorized to retrieve ML models from the second model training equipment. In some embodiments, the authorization policy specifies first model training equipment is authorized to retrieve the ML model if the second interoperability indicator list indicates a vendor of the first model training equipment is nominally authorized to retrieve ML models from the second model training equipment. In some embodiments, the authorization policy specifies first model training equipment is authorized to retrieve the ML model if the first model training equipment acts as an FL server in an FL process in which the second model training equipment locally trains the ML model. In some embodiments, the authorization policy specifies first model training equipment is authorized to retrieve the ML model if a second interoperability indicator list for the second model training equipment indicates a vendor of the first model training equipment is nominally authorized to retrieve ML models from the second model training equipment. In some embodiments, the authorization policy specifies first model training equipment is authorized to retrieve the ML model if the first model training equipment acts as an FL server in an FL process in which the second model training equipment locally trains the ML model. In some embodiments, the authorization policy specifies first model training equipment is authorized to retrieve the ML model if, for each of multiple FL clients in the FL process for which the first model training equipment acts as an FL server, an interoperability indicator list for the FL client is not a superset of the second interoperability indicator list. In some embodiments, the authorization policy specifies first model training equipment is authorized to retrieve the ML model if a second interoperability indicator list for the second model training equipment indicates a vendor of the first model training equipment is nominally authorized to retrieve ML models from the second model training equipment. In some embodiments, the authorization policy specifies first model training equipment is authorized to retrieve the ML model if the first model training equipment acts as an FL server in an FL process in which the second model training equipment locally trains the ML model. In some embodiments, the authorization policy specifies first model training equipment is authorized to retrieve the ML model if, for each of multiple FL clients in the FL process for which the first model training equipment acts as an FL server, an interoperability indicator list for the FL client is not a superset of the first interoperability indicator list.

[0031] In some embodiments, the authorization policy is specific to the second model training equipment.

[0032] In some embodiments, transmitting the authorization policy comprises transmitting the authorization policy during a registration procedure for registering the second model training equipment with the network repository equipment.

[0033] In some embodiments, the authorization policy specifies what requirements must be met in order for the network repository equipment to authorize any model training equipment to retrieve the ML model, wherein the requirements are specified as a function of an interoperability indicator list of any model training equipment requesting the ML model.

[0034] In some embodiments, the second model training equipment implements a second NWDAF MTLF.

[0035] In some embodiments, the ML model is associated with an analytics identifier, ID, and wherein the authorization policy is specific to the analytics ID.

[0036] In some embodiments, the authorization policy governs issuance of access tokens by the network repository equipment to other model training equipment authorized to retrieve the ML model. In some embodiments, the method further comprises receiving, from first model training equipment, a request to retrieve the ML model. In some embodiments, the request includes an access token. In some embodiments, the method further comprises transmitting the ML model to the first model training equipment in response to the request.

[0037] Other embodiments herein include corresponding apparatus, computer programs, and carriers of those computer programs.

[0038] Of course, the present disclosure is not limited to the above features and advantages. Indeed, those skilled in the art will recognize additional features and advantages upon reading the following detailed description, and upon viewing the accompanying drawings.

[0039] BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 illustrates a block diagram of a communication network including multiple instances of model training equipment according to certain embodiments.

[0041] Figure 2A illustrates a block diagram of an example authorization determination according to certain embodiments. Figure 2B illustrates a block diagram of an example authorization determination according to certain other embodiments.

[0042] Figure 2C illustrates a block diagram of an example authorization determination according to yet other embodiments.

[0043] Figure 3 illustrates a block diagram of model training equipment retrieving a machine learning, ML, model according to certain embodiments.

[0044] Figure 4A illustrates a block diagram of an example authorization determination based on a set of allowed interoperability indicator lists according to certain embodiments.

[0045] Figure 4B illustrates a block diagram of an example authorization determination based on a set of allowed interoperability indicator lists according to certain other embodiments.

[0046] Figure 5 shows an example procedure for authorization to retrieve an ML model according to some embodiments.

[0047] Figure 6 illustrates a logic flow diagram of a method performed by network repository equipment in a communication network in accordance with particular embodiments.

[0048] Figure 7A illustrates a logic flow diagram of a method performed by first model training equipment in a communication network in accordance with particular embodiments.

[0049] Figure 7B illustrates a logic flow diagram of a method performed by second model training equipment in a communication network in accordance with particular embodiments.

[0050] Figure 8 is a block diagram of network repository equipment according to some embodiments.

[0051] Figure 9 is a block diagram of model training equipment according to some embodiments.

[0052] Figure 10 is a block diagram of a communication system in accordance with some embodiments.

[0053] Figure 11 is a block diagram of a user equipment according to some embodiments.

[0054] Figure 12 is a block diagram of a network node according to some embodiments.

[0055] Figure 13 is a block diagram of a host according to some embodiments.

[0056] Figure 14 is a block diagram of a virtualization environment according to some embodiments.

[0057] DETAILED DESCRIPTION

[0058] Figure 1 shows a communication network 10 that exploits machine learning to support the communication services it provides, e.g., to learn and predict patterns in the demand for resources over time, so that the communication network 10 can optimize resource allocation over time. The communication network 10 in this regard includes equipment for training machine learning (ML) models, referred to generally as model training equipment 12. In embodiments where the communication network 10 is a 5G network, for example, model training equipment 12 may implement a Model Training Logic Function (MTLF), e.g., as part of a Network Data Analytics Function (NWDAF). io Regardless, the communication network 10 as shown includes multiple instances of model training equipment 12. Figure 1 shows two such instances of model training equipment 12 as model training equipment 12-1 and model training equipment 12-2, with model training equipment 12-1 training ML model 14-1 and model training equipment 12-2 training MNL model 14-2. Each model training equipment 12 thereby trains a respective ML model, e.g., as part of producing or maintaining that ML model.

[0059] For example, different model training equipment 12 may train different ML models associated with different types of analytics, different geographic parts of the communication network’s coverage area, different purposes, etc. Or, different model training equipment 12 may train the same ML model but using different training data, e.g., as part of a distributing ML approach such as federated learning (FL). For instance, each model training equipment 12 may locally train the same global ML model using local training data local to that model training equipment 12 in order to obtain a respective locally-trained ML model, with the different locally- trained ML models then being combined by a server into an updated global ML model.

[0060] No matter the particular use case for having multiple model training equipment 12, different model training equipment 12 may be owned or controlled by different vendors. A vendor of model training equipment 12 refers to a company or other party that owns, provides, or controls the model training equipment 12. At least some vendors may cooperate with one another (e.g., by agreement), so as to share ML models with one another or otherwise provide for the interoperability of their respective model training equipment 12 with one another. A vendor that interoperates with another vendor in this way may thereby authorize the other vendor to retrieve ML models from the vendor’s model training equipment 12.

[0061] Figure 1 shows the authorization framework according to some embodiments that account for vendor interoperability. In this framework, access to an ML model is restricted to those entities that present an access token demonstrating authorization to retrieve the ML model. Retrieval of the ML model therefore must be preceded by acquisition of an access token that demonstrates authorization to retrieve the ML model. In the framework of Figure 1 , network repository equipment 16 governs access to the ML model by governing issuance of access tokens, e.g., where network repository equipment 16 may implement a Network Repository Function (NRF) in embodiments where the communication network 10 is a 5G network.

[0062] In Figure 1 , then, in order for model training equipment 12-1 to retrieve ML model 14-2 from model training equipment 12-2, model training equipment 12-1 first transmits a request 18 to network repository equipment 16. The request 18 requests an access token 20 (e.g., an OAuth 2.0 token) indicating model training equipment 12-1 is authorized to retrieve ML model 14-2 from model training equipment 12-2. Network repository equipment 16 makes a determination as to whether model training equipment 12-1 is authorized to retrieve ML model 14-2 from model training equipment 12-2. If this authorization determination is that model training equipment 12-1 is indeed authorized to retrieve ML model 14-2, network repository equipment 16 transmits a response 22 to the request 18, with the response 22 including the requested access token 20. Model training equipment 12-1 may then use the access token 20 to retrieve ML model 14-2 from model training equipment 12-2, either directly or indirectly via other equipment. Model training equipment 12-1 may for example use the access token 20 to retrieve the ML model 14-2 directly from model training equipment 12-2 (e.g., via Nnwdaf_MLModelProvisioning service or an Nnwdaf_MLModelTrainingService in a 5G network service-based architecture), or indirectly via analytics data repository equipment (e.g., via an Nadrf MLModelManagement service provided by an Analytics Data Repository Function, ADRF).

[0063] The network repository equipment 16 in some embodiments may base its authorization determination at least in part on an interoperability indicator list 24-2 for model training equipment 12-2. This list 24-2 indicates which equipment vendor(s) 26-2 are nominally authorized to retrieve ML models from model training equipment 12-2, e.g., on the basis that the vendor of model training equipment 12-2 has agreed to cooperate with and / or trusts those equipment vendor(s) 26-2. In fact, in some embodiments, an equipment vendor on interoperability indicator list 24-2 is nominally authorized to retrieve any ML model from model training equipment 12-2. In some embodiments, though, the interoperability indicator list 24-2 is specific to a certain analytics identifier (ID), with different analytics IDs identifying different types of analytics. In this case, then, the interoperability indicator list 24-2 identifies equipment vendor(s) nominally authorized to retrieve ML models associated with the certain analytics ID. Model training equipment 12-2 may provision the network repository equipment 16 with its interoperability indicator list 24-2 as part of registering its profile with the network repository equipment 16. Regardless, the network repository equipment 16 checks the list 24-2 for whether or not the vendor of model training equipment 12-1 is included in the list 24-2 of equipment vendors 26-2 nominally authorized to retrieve ML models from model training equipment 12-2, e.g., either generally or with respect to a certain analytics ID. This check of the interoperability indicator list 24-2 therefore safeguards the ML model 14-2 from being distributed firsthand by model training equipment 12-2 to an unauthorized vendor.

[0064] Notably, the network repository equipment 16 in some embodiments herein further safeguards the ML model 14-2 from being distributed secondhand by model training equipment 12-1 to an unauthorized vendor. The network repository equipment 16 in this regard makes its determination of whether model training equipment 12-1 is authorized based on an interoperability indicator list 24-1 for model training equipment 12-1 , e.g., in addition to basing the authorization determination on the interoperability indicator list 24-2 for model training equipment 12-2.

[0065] The interoperability indicator list 24-1 for model training equipment 12-1 indicates which equipment vendor(s) 26-1 are nominally authorized to retrieve ML models from model training equipment 12-1 , e.g., either generally or with respect to a certain analytics ID. The network repository equipment 16 may obtain interoperability indicator list 24-1 by receiving it from model training equipment 12-1 in the request 18 for the access token 20. Or, the network repository function 16 may obtain interoperability indicator list 24-1 by receiving it from model training equipment 12-1 during a procedure for registering with the network repository equipment 16, e.g., whereupon the network repository function 16 may store the list 24-1 in a profile for model training equipment 12-1 , for later retrieval from the profile upon receipt of the request 18 for the access token 20.

[0066] In some embodiments, the network repository equipment 16 makes its determination of whether model training equipment 12-1 is authorized to retrieve the ML model 14-2, based on whether interoperability indicator list 24-1 is a subset of interoperability indicator list 24-2. Here, a set A is a subset of another set B if every element of the set A is also an element of the set B, i.e., A c B, such that the set A is a subset of the set B if either A = B or if the set A is a proper subset of the set B in a mathematical sense. In one such embodiment, for instance, the network repository equipment 16 makes the determination that model training equipment 12-1 is not authorized to retrieve the ML model 14-2 if interoperability indicator list 24-1 is not a subset of interoperability indicator list 24-2. The network repository equipment 16 may make this determination that model training equipment 12-1 is not authorized to retrieve the ML model 14- 2 even if the vendor of model training equipment 12-1 is included in interoperability indicator list 24-2, i.e., even if the vendor of model training equipment 12-1 is nominally authorized to retrieve ML models from model training equipment 12-2. Indeed, interoperability indicator list 24-1 not being a subset of interoperability indicator list 24-2 means that interoperability indicator list 24-1 includes at least one equipment vendor that is not on interoperability indicator list 24-2, such that there is at least one equipment vendor that is nominally authorized to retrieve ML models from model training equipment 12-1 but that is not nominally authorized to retrieve ML models from model training equipment 12-2. Embodiments in this case deny model training equipment 12-1 ’s request 18 in order to prevent propagation of the ML model 14-2 from model training equipment 12-1 to a vendor that is on interoperability indicator list 24-1 but not interoperability indicator list 24-2.

[0067] Figure 2A-2C illustrate various examples. In these examples, the vendor of model training equipment 12-1 is exemplified as being Vendor A. In each of the examples, the interoperability indicator list 24-2 for model training equipment 12-2 includes Vendor A. Since the vendor of model training equipment 12-1 (Vendor A) is on interoperability indicator list 24-2, model training equipment 12-1 is nominally authorized to retrieve ML model 14-2 from model training equipment 12-2. However, these examples demonstrate how the network repository equipment’s determination of whether model training equipment 12-1 is actually authorized to retrieve the ML model 14-2 varies depending on how interoperability indicator list 24-1 compares to interoperability indicator list 24-2.

[0068] In the example of Figure 2A, interoperability indicator list 24-1 indicates Vendors A and B are nominally authorized to retrieve ML models from model training equipment 12-1 , and interoperability indicator list 24-2 likewise indicates Vendors A and B are nominally authorized to retrieve ML models from model training equipment 12-2. Accordingly, interoperability indicator list 24-1 is equal to interoperability indicator list 24-2, meaning that the same Vendors are nominally authorized to retrieve ML models from both model training equipment 12-1 , 12-2. Based on the vendor of model training equipment 12-1 (Vendor A) being included in interoperability indicator list 24-2, and based on interoperability indicator list 24-1 being equal to interoperability indicator list 24-2, the network repository equipment 16 determines that model training equipment 12-1 is authorized to retrieve the ML model 14-2 from model training equipment 12-2. This determination accounts for the possibility that model training equipment 12-1 might later propagate the retrieved ML model 14-2 to other equipment whose vendor is nominally authorized to retrieve ML models from model training equipment 12-1 , as reflected in interoperability indicator list 24-1. As shown in Figure 2A in this regard, model training equipment 12-1 might later propagate the retrieved ML model 14-2 to equipment of Vendor A and to equipment of Vendor B, given that both Vendors A and B are included in model training equipment 12-1 ’s interoperability indicator list 24-1 . Since both Vendor A and Vendor B would have been nominally authorized to have retrieved the ML model 14-2 firsthand from model training equipment 12-2 anyway, model training equipment 12-1’s secondhand propagation of the ML model 14-2 to Vendors A and B does not divulge the ML model 14-2 to an unauthorized vendor. Because interoperability indicator list 24-1 suggests that distributing the ML model 14-2 to model training equipment 12-1 will not result in secondhand distribution of the ML model 14-2 to unauthorized vendors, the network repository equipment 16 determines that model training equipment 12-1 is authorized to retrieve the ML model 14-2 and grants its request for access token 20.

[0069] The same determination is made in Figure 2B’s example. Indeed, in this example, interoperability indicator list 24-1 is a proper subset of interoperability indicator list 24-2, i.e., every vendor in interoperability indicator list 24-1 is also in interoperability indicator list 24-2 but interoperability indicator list 24-1 includes fewer vendors than interoperability indicator list 24-2. Indeed, as shown, interoperability indicator list 24-1 includes only Vendor A, whereas interoperability indicator list 24-2 includes Vendors A and B. Model training equipment 12-1 might later propagate the retrieved ML model 14-2 to equipment of Vendor A, given that Vendor A is included in model training equipment 12-1’s interoperability indicator list 24-1 . Since Vendor A would have been nominally authorized to have retrieved the ML model 14-2 firsthand from model training equipment 12-2 anyway, model training equipment 12-1’s secondhand propagation of the ML model 14-2 to Vendor A does not divulge the ML model 14-2 to an unauthorized vendor. Just as in Figure 2A’s example, then, because interoperability indicator list 24-1 suggests that distributing the ML model 14-2 to model training equipment 12-1 will not result in secondhand distribution of the ML model 14-2 to unauthorized vendors, the network repository equipment 16 determines that model training equipment 12-1 is authorized to retrieve the ML model 14-2 and grants its request for access token 20.

[0070] In Figure 2C’s example, by contrast, interoperability indicator list 24-1 is not a subset of interoperability indicator list 24-2. Indeed, as shown, interoperability indicator list 24-1 includes Vendor A Vendor B, but interoperability indicator list 24-2 only includes Vendor A and does not include Vendor B. Model training equipment 12-1 might later propagate the retrieved ML model 14-2 to equipment of Vendor A and to equipment of Vendor B, given that Vendors A and B are included in model training equipment 12-1’s interoperability indicator list 24-1 . Since Vendor A would have been nominally authorized to have retrieved the ML model 14-2 firsthand from model training equipment 12-2 anyway, model training equipment 12-1’s secondhand propagation of the ML model 14-2 to Vendor A does not divulge the ML model 14-2 to an unauthorized vendor. However, since Vendor B would not have been nominally authorized to have retrieved the ML model 14-2 firsthand from model training equipment 12-2, model training equipment 12-1’s secondhand propagation of the ML model 14-2 to Vendor B does divulge the ML model 14-2 to an unauthorized vendor. Accordingly, because interoperability indicator list 24-1 suggests that distributing the ML model 14-2 to model training equipment 12-1 creates the risk of secondhand distribution of the ML model 14-2 to an unauthorized vendor, the network repository equipment 16 determines that model training equipment 12-1 is not authorized to retrieve the ML model 14-2 and denies its request for access token 20.

[0071] Accordingly, some embodiments advantageously improve the security of ML models in a context where ML models are shared or stored in network equipment provided by different vendors. Indeed, some embodiments enable full authorization based on interoperability indicator lists. This may in turn facilitate federated learning in a communication network, so as to reduce training time, relieve congestion in the communication network by limiting the amount of data sent to a central node, and / or protect sensitive information so as to preserve data privacy.

[0072] Rather than or in addition to comparing interoperability indicator list 24-1 to interoperability indicator list 24-2, the network repository equipment 16 in other embodiments may compare interoperability indicator list 24-1 to a set of allowed interoperability indicator lists, e.g., as may be explicitly configured by model training equipment 12-2 or its vendor. Figure 3 for example shows that a set 28-2 of allowed interoperability indicator list(s) may also govern the network repository equipment’s determination of whether model training equipment 12-1 is authorized to retrieve the ML model 14-2 from model training equipment 12-2. This set 28-2 of allowed interoperability indicator list(s) may be specifically established for restricting secondhand distribution of ML models and may therefore provide more configurable and / or flexible control over authorization decisions than embodiments that re-use interoperability indicator list 24-2 for that purpose.

[0073] In one embodiment, as an example, the network repository equipment 16 determines that model training equipment 12-1 is authorized to retrieve the ML model 14-2 if (i) the vendor of model training equipment 12-1 is included in interoperability indicator list 24-2 (so as to be nominally authorized for firsthand retrieval) and (ii) interoperability indicator list 24-1 is included in the set 28-2 of allowed interoperability indicator list(s) (such that any secondhand distribution of ML model 14-2 would be to an authorized vendor). Conversely, the network repository equipment 16 determines that model training equipment 12-1 is not authorized to retrieve the ML model 14-2 if (i) the vendor of model training equipment 12-1 is not included in interoperability indicator list 24-2; or (ii) interoperability indicator list 24-1 is not included in the set 28-2 of allowed interoperability indicator list(s). In these or other embodiments, then, inclusion of interoperability indicator list 24-1 in the set 28-2 of allowed interoperability indicator list(s) may replace the requirement for interoperability indicator list 24-1 to be a subset of interoperability indicator list 24-2.

[0074] Figures 4A-4B show some examples. In Figure 4A’s example, interoperability indicator list 24-1 is not a subset of interoperability indicator list 24-2, since interoperability indicator list 24-1 includes Vendor B but interoperability indicator list 24-2 does not. However, interoperability indicator list 24-1 is included in the set 28-2 of allowed interoperability indicator list(s), since allowed interoperability indicator lists include a list of Vendors A and B and a list of Vendors A and C. Accordingly, because interoperability indicator list 24-1’s inclusion in the set 28-2 of allowed interoperability indicator list(s) suggests that distributing the ML model 14-2 to model training equipment 12-1 does not create the risk of secondhand distribution of the ML model 14- 2 to an unauthorized vendor, the network repository equipment 16 determines that model training equipment 12-1 is authorized to retrieve the ML model 14-2 and grants its request for access token 20.

[0075] In Figure 4B’s example, by contrast, interoperability indicator list 24-1 is not included in the set 28-2 of allowed interoperability indicator list(s), since allowed interoperability indicator lists include a list of Vendors A and B and a list of Vendors A and C, but do not include a list of Venders A and D. Because interoperability indicator list 24-1’s exclusion from the set 28-2 of allowed interoperability indicator list(s) suggests that distributing the ML model 14-2 to model training equipment 12-1 creates the risk of secondhand distribution of the ML model 14-2 to an unauthorized vendor, the network repository equipment 16 determines that model training equipment 12-1 is not authorized to retrieve the ML model 14-2 and denies its request for access token 20.

[0076] As these examples demonstrate, then, the network repository equipment 16 may safeguard against unauthorized secondhand distribution of the ML Model 14-2 by re-using interoperability indicator list 24-2 for comparison to interoperability indicator list 24-1 (as in Figures 2A-2C) and / or by exploiting a set of allowed interoperability indicator list(s) 28-2, e.g., specifically established for restricting secondhand distribution of ML models.

[0077] The network repository equipment 16 in still other embodiments may also base its authorization determination on whether model training equipment 12-1 acts as a federated learning (FL) server in an FL process in which model training equipment 12-2 locally trains the ML model 14-2. In fact, the network repository equipment 16 may even consider this FL scenario as a sort of exception that justifies allowing model training equipment 12-1 to retrieve the ML model 14-2 even if interoperability indicator list 24-1 is not a subset of interoperability indicator list 28-2 or is not included in a set 28-2 of allowed interoperability indicator list(s) as described above. The authorization determination in this regard may enforce an expectation that locally trained ML models shall only reside with an FL group and are not to be shared further by the FL server, e.g., as specified by a service-level agreement (SLA).

[0078] More particularly in this regard, the network repository equipment 16 may determine model training equipment 12-1 is authorized to retrieve the ML model 14-2 if the vendor of model training equipment 12-1 is included in interoperability indicator list 24-2 and model training equipment 12-1 acts as an FL server in an FL process in which model training equipment 12-2 locally trains the ML model 14-2. The network repository equipment 16 may make this determination even if interoperability indicator list 24-1 is not a subset of interoperability indicator list 28-2 or is not included in a set 28-2 of allowed interoperability indicator list(s) as described above, e.g., as an exception to this requirement.

[0079] In some embodiments, though, the network repository equipment 16 may require one or more other conditions on top of model training equipment 12-1 acting as such an FL server before allowing this exception. The network repository equipment 16 may for instance also require that interoperability indicator list 24-2 be a subset of interoperability indicator list 24-1 . This may enable a FL client to effectively perform a check on the interoperability indicator list of a FL server, to check the possible extent that its locally trained ML model may be shared (by the FL server) within the FL group, i.e. towards other FL clients. This may be especially appropriate in a layered deployment where the FL server is deployed in a central place, e.g., a central datacenter (DC) and FL clients are deployed in multiple local sites, e.g., regional DCs. In such deployment, it may be normally assumed the FL server in the central DC has wider interoperability indicator list capability than any FL client, e.g., the interoperability indicator list of the FL server is a superset of the interoperability indicator list of any FL client.

[0080] Or, in other embodiments, the network repository equipment 16 may also require that, for each of multiple FL clients in the FL process for which model training equipment 12-1 acts as an FL server, an interoperability indicator list for the FL client is not a superset of interoperability indicator list 24-1 . This may be appropriate in a non-layered deployment where FL Nodes are distributed in multiple sites, e.g. regional DCs, and the FL server is elected among these nodes, while the rest act as a FL client. In such deployment, it is not assumed the elected FL node (as FL server) could always have its interoperability indicator list be a superset of the interoperability indicator list of the rest of the FL clients.

[0081] In view of the various options above, some embodiments herein allow the vendor of model training equipment 12-2 to establish an authorization policy at the network repository equipment 16. Such authorization policy may specify what requirements must be met in order for the network repository equipment 16 to authorize any model training equipment to retrieve the ML model 14-2 and / or otherwise govern issuance of access tokens by the network repository equipment 16. In one such embodiment, this authorization policy may be dynamically configurable and / or specific to model training equipment 12-2 or its vendor. The network repository equipment 16 may for instance be provisioned with the authorization policy during a registration procedure for registering model training equipment with the network repository equipment 16, e.g., and be updatable thereafter. Regardless, the authorization policy may specify whether authorization of model training equipment to retrieve the ML model 14-2 depends on or is a function of the interoperability indicator list for that model training equipment. Alternatively or additionally, the authorization policy may specify whether authorization of model training equipment to retrieve the ML model 14-2 requires the interoperability indicator list for that model training equipment to be a subset of interoperability indicator list 24-2 or requires the interoperability indicator list for that model training equipment to be included in a set of allowed interoperability indicator list(s) 28-2. In still other embodiments, the authorization policy may specify whether and / or which of the above mentioned exceptions to these requirements are applicable or active for model training equipment acting as an FL server.

[0082] Consider now an example of some embodiments herein where model training equipment 14-1 is an NWDAF MTLF (referred to as MTLF1) acting as an NF service consumer in a service-based architecture, model training equipment 12-2 is an NWDAF MTLF (referred to as MTLF2) acting as an NF service producer, and network repository equipment 16 is represented as a Network Repository Function (NRF) 16 in a 5G network. For direct retrieval of an ML model from MTLF to MTLF, the services Nnwdaf_MLModelProvisioning and Nnwdaf_MLModelTrainingService may be used. For indirect retrieval of ML Model via ADRF, the Nadrf MLModelManagement service may be used. Furthermore, interoperability indicator list 24-1 is referred to as an Interoperability Indicator (ID) list InterOPI and interoperability indicator list 24-2 is referred to as Interoperability ID list lnterOP2, as defined by 3GPP TS 23.288 V18.2.0.

[0083] In this context, this example addresses a problem with both model sharing and federated learning, namely, if MTLF1 receives ML model 14-2 from MTLF2, MTLF1 could then in turn use this model when responding to a ML model provisioning subscription or request from a third consumer NFc (e.g., NWDAF AnLF). And this third NFc may not be included in MTLF2’s lnterOP2, meaning the third NFc may not be allowed to receive the ML model 14-2 according to MTLF2.

[0084] Some embodiments address this problem as follows. When an MTLF requests an ML model 14-2 (e.g., an FL trained model), the NRF 16 authorizes the request by comparing the Interoperability ID list (InterOPI) of MTLF1 to MTLF2’s Interoperability ID list (lnterOP2). For example, in some embodiments, the NRF 16 verifies that MTLF1 is authorized to receive the ML model 14-2 from MTLF2 based on an authorization policy related to the Interoperability ID list of MTLF1 (InterOPI ), in addition to comparing the Vendor ID of MTLF1 (as NF consumer) and the Interoperability ID list of MTLF2 (as NF service provider) as described in PCT Application No. PCT / CN2022 / 130285. Such authorization policy may be locally configured in the NRF 16 or provided by MTLF2 during NF profile registration procedure to NRF 16.

[0085] According to the authorization policy in some embodiments, the NRF 16 is to compare the Interoperability ID list of the requesting MTLF1 (InterOPI) with the Interoperability ID list of MTLF2 (lnterOP2). If InterOPI is a subset of lnterOP2, then NRF 16 can authorize the request, since all the vendors in InterOPI are also in lnterOP2, i.e., vendors authorized by MTLF1 (via InterOPI ) are also implicitly authorized by MTLF2. The NRF 16 then decides that the MTLF1 is authorized to receive ML models from MTLF2.

[0086] In other embodiments, the NRF 16 according to the authorization policy can check whether the Interoperability ID list of MTLF1 (InterOPI ) belongs to a set of allowed Interoperability ID list(s) provided by MTLF2. Vendors authorized by MTLF1 (via InterOPI) are explicitly authorized by MTLF2. NRF 16 then decides that the MTLF1 is authorized to receive the ML model 14-2 from MTLF2 if this is the case. Note that, in some embodiments, the set of allowed Interoperability ID list(s) can be set as “ANY”, in which case any NFc as MTLF1 is granted for service.

[0087] In yet other embodiments, the NRF 16 according to the authorization policy can compare the Interoperability ID list of the requesting MTLF1 (InterOPI) with the Interoperability ID list of MTLF2 (lnterOP2) and the FL capability of the two MTLFs, e.g., when MTLF1 is a FL server and would like to retrieve model or weights or other meta data. If InterOPI is not a subset of lnterOP2 then NRF 16 checks that MTLF1 is a FL server and optionally MTLF2 is FL client. There are then various alternatives for whether to authorize the request in this case.

[0088] In a first alternative, the NRF 16 can authorize the request independently of the relation between InterOPI and lnterOP2. This alternative covers a non-layered deployment.

[0089] In a second alternative, the NRF 16 can authorize the request only if the lnterOP2 is a subset of InterOPI . This alternative covers a layered deployment.

[0090] In a third alternative, the NRF 16 checks Interoperability ID lists of all MTLFs with the same FL group ID as the FL server and FL client and authorizes the request only if no Interoperability ID list of any FL client is a superset of the lnterOP2.

[0091] Figure 5 shows an example procedure according to some embodiments, as implemented on top of 3GPP TS 33.501 V18.2.0 Annex X.10 Security for AI / ML model storage and sharing (cf. S3-233266 living CR for eNA). Here, NF_1 exemplifies model training equipment 12-1 , NF_2 exemplifies model training equipment 12-2, and NRF exemplifies network repository equipment 16. Step 0a. NF_1 12-1 as NF Service consumer (NFc), e.g., NWDAF containing MTLF, registers its NF profile in the NRF 16 with ML Model Interoperability indicator list(s) per Analytics ID and its Vendor ID. The ML Model Interoperability indicator list is a list of NWDAF providers (vendors) that are allowed to retrieve ML models from this NWDAF containing MTLF. NF_1 12- 1 may also add its FL capability (server or client).

[0092] Step Ob. NF_2 12-2 as NF Service Producer (NFp), e.g., another NWDAF containing MTLF, registers at the NRF 16 its ML Model Interoperability indicator list(s) per Analytics ID. It may also add its FL capability (server or client).

[0093] In some embodiments, the NFp also provides authorization information of consumer NF (e.g., authorization policy on Interoperability ID list(s) or a set of allowed Interoperability ID list(s) of NFc).

[0094] Step Oc. Another NF, e.g., NWDAF containing MTLF acting as FL client registers its NF profile in the NRF 16 with its FL related information, including supported FL capability (e.g., FL client), Analytics ID(s) and Interoperability Indicator list per Analytics ID.

[0095] Step 1 : The NWDAF containing MTLF (i.e., NF_1 12-1 ) determines to request a trained ML model 14-2 from another NWDAF MTLF (i.e., NF_2 12-2) and requests an access token 20 from the NRF 16 using Nnrf AccessToken Get request. Note that NF_1 12-1 may determine to request the ML model 14-2 either based on local configuration (i.e., without receiving any solicited request from a third NF, e.g., AnLF) or when it receives the request from a NWDAF containing AnLF. Notably, as shown, the token request message contains , among other parameers, the Interoperability ID list (InterOPI) of NF_1 12-1. Note, though, that if NF_1 12-1 does not provide InterOPI of NF1 in the token request, the NRF 16 in some embodiments may obtain such information from NFTs NF profile (as provided in stepOa).

[0096] Step 2. NRF 16 authenticates NF_1 12-1 based on a service-based architecture (SBA) method described in clause 13.3.1 .2 of 3GPP TS 33.501 V18.2.0, e.g., based on Common Cryptographic Architecture (CCA) or direct Transport Layer Security (TLS) connection.

[0097] NRF checks whether the NF_1 12-1 is authorized to retrieve the ML model 14-2 for the analytics ID from NF_2 12-2. It does so by verifying the Interoperability ID list (InterOPI ) of NF_1 according to the authorization information provided by NF_2 12-2 in step Ob.

[0098] Note that, if NF2 12-2 does provide authorization information, NRF 16 may obtain such information from local configuration.

[0099] For example (also refer to clause 2.5 of 3GPP TS 33.501 V18.2.0), in some embodiments, NRF 16 checks NFTs interoperability ID list (InterOPI) is subset of NF_2's interoperability ID list (lnterOP2) for the Analytics ID.

[0100] If InterOPI is a subset of lnterOP2, the NRF 16 grants the token (token2).\l

[0101] If InterOPI is not a subset of lnterOP2, the NRF 16 checks the FL capability of NF1 . If NF1 is an FL server, the following options are possible depending on the NRF’s configuration, e.g., from the authorization policy: a) NRF 16 grants the token (token2) independently of anything else; b) NRF 16 authorizes the request only if lnterOP2 is a subset of InterOPI ; c) NRF 16 checks Interoperability ID list(s) of all MTLFs with the same FL group ID as server and client and grants the token (token2), only if no Interoperability ID list of any client is a superset of lnterOP2.

[0102] Step 3. The NRF 16 after successful verification then generates and provides token2 to the NF_1 12-1.

[0103] Dependent on the service requested and type of deployment (e.g., ADRF is available) following options are possible:

[0104] OPTION 1 (model sharing with direct retrieval from MTLF)

[0105] Step 4a. The NF_1 12-1 sends ML model request to the NF_2 12-2, NWDAF containing MTLF, by performing Nnwdaf_MLModelProvision or Nnwdaf_MLModelTraining service operation to retrieve ML models (e.g., ML or FL model) for the Analytics ID.

[0106] OPTION 2 (FL, i.e., NF1 and NF2 are within the same FL group):

[0107] Step 4b. The NF_1 12-1 sends ML model request to the NF_2 12-2, NWDAF containing MTLF, by performing Nnwdaf_MLModelTraining to retrieve ML models (e.g., FL global or FL local model) for the Analytics ID.

[0108] OPTION 3 (indirect retrieval from ADRF):

[0109] Either Step 4a or 4b is performed by NF_1 12-1 ; (Observe only step 4a is possible in this release of the specification).

[0110] Steo 5. The NF_2 12-2 updates the NFc allowed list in ADRF adding NF_1 , NWDAF containing MTLF, by performing Nadrf MLModelStorageRequest Update for the Analytics ID.

[0111] Step 6. NF2 12-2 provides Model information (e.g. Model URL in ADRF) to NF1 . NF1 retrieves Model either directly from NF2 or from ADRF accordingly.

[0112] In view of the modifications and variations herein, Figure 6 depicts a method performed by network repository equipment 16 in a communication network 10 in accordance with particular embodiments. The method includes receiving, from first model training equipment 12-1 , a request 18 for an access token 20 indicating the first model training equipment 12-1 is authorized to retrieve a machine learning, ML, model 14-2 from second model training equipment 12-2 (Block 600). The method also includes making a determination as to whether the first model training equipment 12-1 is authorized to retrieve the ML model 14-2 from the second model training equipment 12-2, based on a first interoperability indicator list 24-1 for the first model training equipment 12-1 which identifies one or more equipment vendors 26-1 , 26-2 nominally authorized to retrieve ML models from the first model training equipment 12-1 (Block 610). The method also includes responding to the request 18 based on the determination (Block 620).

[0113] In some embodiments, the method further comprises receiving an authorization policy from the second model training equipment 12-2, e.g., during a registration procedure for registering the second model training equipment 12-2 with the network repository equipment 16 (Block 630). In some embodiments, according to the authorization policy, authorization of the first model training equipment 12-1 to retrieve the ML model 14-2 depends on the first interoperability indicator list 24-1 for the first model training equipment.

[0114] In some embodiments, the method further comprises receiving the first interoperability indicator list 24-1 from the first model training equipment 12-1 , e.g., during a procedure for registering the first model training equipment 12-1 with the network repository equipment 16 (Block 640). In one or more such embodiments, the method further comprises storing the first interoperability indicator list 24-1 in a profile for the first model training equipment 12-1 (Block 650). The method may further comprise, after receiving the request 18, retrieving the first interoperability indicator list 24-1 from the profile for the first model training equipment 12-1 (Block 660).

[0115] In some embodiments, making the determination comprises making the determination based on whether the first interoperability indicator list 24-1 is a subset of a second interoperability indicator list 24-2 for the second model training equipment 12-2 which identifies one or more equipment vendors 26-1 , 26-2 nominally authorized to retrieve ML models 14-2 from the second model training equipment 12-2. In some embodiments, the determination is made that the first model training equipment 12-1 is authorized to retrieve the ML model 14-2 if the first interoperability indicator list 24-1 is a subset of the second interoperability indicator list 24-2 and the second interoperability indicator list 24-2 indicates a vendor of the first model training equipment 12-1 is nominally authorized to retrieve ML models 14-2 from the second model training equipment 12-2. In some embodiments, the determination is made that the first model training equipment 12-1 is not authorized to retrieve the ML model 14-2 if the first interoperability indicator list 24-1 is not a subset of the second interoperability indicator list 24-2 or the second interoperability indicator list 24-2 indicates a vendor of the first model training equipment 12-1 is not nominally authorized to retrieve ML models 14-2 from the second model training equipment 12-2.

[0116] In some embodiments, making the determination comprises making the determination based on whether the first interoperability indicator list 24-1 is included in a set of one or more authorized interoperability lists 28-2 for the second model training equipment 12-2.

[0117] In some embodiments, the determination is made also based on whether the first model training equipment 12-1 acts as a federated learning (FL) server in an FL process in which the second model training equipment 12-2 locally trains the ML model 14-2. In some embodiments, the determination is made that the first model training equipment 12-1 is authorized to retrieve the ML model 14-2 if the first interoperability indicator list 24-1 is not a subset of the second interoperability indicator list 24-2. In some embodiments, the determination is made that the first model training equipment 12-1 is authorized to retrieve the ML model 14-2 if the second interoperability indicator list 24-2 indicates a vendor of the first model training equipment 12-1 is nominally authorized to retrieve ML models 14-2 from the second model training equipment 12- 2. In some embodiments, the determination is made that the first model training equipment 12-1 is authorized to retrieve the ML model 14-2 if the first model training equipment 12-1 acts as an FL server in an FL process in which the second model training equipment 12-2 locally trains the ML model 14-2. In some embodiments, the determination is made that the first model training equipment 12-1 is authorized to retrieve the ML model 14-2 if the first interoperability indicator list 24-1 is not a subset of the second interoperability indicator list 24-2. In some embodiments, the determination is made that the first model training equipment 12-1 is authorized to retrieve the ML model 14-2 if the second interoperability indicator list 24-2 is a subset of the first interoperability indicator list 24-1 . In some embodiments, the determination is made that the first model training equipment 12-1 is authorized to retrieve the ML model 14-2 if the second interoperability indicator list 24-2 indicates a vendor of the first model training equipment 12-1 is nominally authorized to retrieve ML models 14-2 from the second model training equipment 12- 2. In some embodiments, the determination is made that the first model training equipment 12-1 is authorized to retrieve the ML model 14-2 if the first model training equipment 12-1 acts as an FL server in an FL process in which the second model training equipment 12-2 locally trains the ML model 14-2. In some embodiments, the determination is made that the first model training equipment 12-1 is authorized to retrieve the ML model 14-2 if the first interoperability indicator list 24-1 is not a subset of the second interoperability indicator list 24-2. In some embodiments, the determination is made that the first model training equipment 12-1 is authorized to retrieve the ML model 14-2 if the second interoperability indicator list 24-2 indicates a vendor of the first model training equipment 12-1 is nominally authorized to retrieve ML models 14-2 from the second model training equipment 12-2. In some embodiments, the determination is made that the first model training equipment 12-1 is authorized to retrieve the ML model 14-2 if the first model training equipment 12-1 acts as an FL server in an FL process in which the second model training equipment 12-2 locally trains the ML model 14-2. In some embodiments, the determination is made that the first model training equipment 12-1 is authorized to retrieve the ML model 14-2 if, for each of multiple FL clients in the FL process for which the first model training equipment 12-1 acts as an FL server, an interoperability indicator list for the FL client is not a superset of the second interoperability indicator list 24-2. In some embodiments, the determination is made that the first model training equipment 12-1 is authorized to retrieve the ML model 14-2 if the first interoperability indicator list 24-1 is not a subset of the second interoperability indicator list 24-2. In some embodiments, the determination is made that the first model training equipment 12-1 is authorized to retrieve the ML model 14-2 if the second interoperability indicator list 24-2 indicates a vendor of the first model training equipment 12-1 is nominally authorized to retrieve ML models 14-2 from the second model training equipment 12- 2. In some embodiments, the determination is made that the first model training equipment 12-1 is authorized to retrieve the ML model 14-2 if the first model training equipment 12-1 acts as an FL server in an FL process in which the second model training equipment 12-2 locally trains the ML model 14-2. In some embodiments, the determination is made that the first model training equipment 12-1 is authorized to retrieve the ML model 14-2 if, for each of multiple FL clients in the FL process for which the first model training equipment 12-1 acts as an FL server, an interoperability indicator list for the FL client is not a superset of the first interoperability indicator list 24-1.

[0118] In some embodiments, making the determination comprises making the determination based on an authorization policy specific to the second model training equipment 12-2. In some embodiments, according to the authorization policy, authorization of the first model training equipment 12-1 to retrieve the ML model 14-2 depends on the first interoperability indicator list 24-1 for the first model training equipment 12-1 . In some embodiments, the authorization policy specifies what requirements must be met in order for the network repository equipment 16 to authorize any model training equipment to retrieve the ML model. In some embodiments, the requirements are specified as a function of an interoperability indicator list of any model training equipment requesting the ML model.

[0119] In some embodiments, the request 18 includes the first interoperability indicator list 24-1.

[0120] In some embodiments, responding to the request 18 comprises, if the determination is made that the first model training equipment 12-1 is authorized to retrieve the ML model 14-2, transmitting the requested access token 20 to the first model training equipment 12-1 .

[0121] In some embodiments, the first model training equipment 12-1 implements a first Network Data Analytics Function, NWDAF, Model Training Logic Function, MTLF, as a Network Function (NF) service consumer, and wherein the second model training equipment 12-2 implements a second NWDAF MTLF as an NF service producer.

[0122] Figure 7A depicts a method performed by first model training equipment 12-1 in a communication network 10 in accordance with particular embodiments. The method includes transmitting, to network repository equipment 16 in the communication network 10, a request 18 for an access token 20 indicating the first model training equipment 12-1 is authorized to retrieve a machine learning, ML, model from second model training equipment 12-2 (Block 700). In some embodiments, the request 18 includes a first interoperability indicator list 24-1 for the first model training equipment 12-1 which identifies one or more equipment vendors 26-1 , 26-2 nominally authorized to retrieve ML models from the first model training equipment 12-1. The method also comprises receiving a response 22 to the request 18 from the network repository equipment 16 (710).

[0123] In some embodiments, the response 22 includes the requested access token 20. In some embodiments, the method further comprises transmitting an ML model request to the second model training equipment 12-2 or to analytical data repository equipment associated with the second model training equipment 12-2. In some embodiments, the ML model request includes the access token 20. In some embodiments, the method further comprises receiving the ML model in response to the ML model request.

[0124] In some embodiments, the first model training equipment 12-1 implements a first Network Data Analytics Function, NWDAF, Model Training Logic Function, MTLF, as a Network Function (NF) service consumer, and wherein the second model training equipment 12-2 implements a second NWDAF MTLF as an NF service producer.

[0125] In some embodiments, the ML model is associated with an analytics identifier, ID, and wherein the first interoperability indicator list 24-1 is specific to the analytics ID so as to identify one or more equipment vendors 26-1 , 26-2 nominally authorized to retrieve from the first model training equipment 12-1 ML models associated with the analytics ID.

[0126] Figure 7B depicts a method performed by second model training equipment 12-2 in a communication network 10 in accordance with particular embodiments. The method includes transmitting, to network repository equipment 16 in the communication network 10, an authorization policy for authorizing other model training equipment to retrieve a machine learning, ML, model from the second model training equipment 12-2, wherein the authorization policy specifies whether or not other model training equipment is nominally authorized to retrieve the ML model as a function of an interoperability indicator list for the other model training equipment (Block 720).

[0127] In some embodiments, the authorization policy specifies whether or not first model training equipment 12-1 is authorized to retrieve the ML model depending on whether or not a first interoperability indicator list 24-1 for the first model training equipment 12-1 is a subset of a second interoperability indicator list 24-2 for the second model training equipment 12-2. In some embodiments, the first interoperability indicator list 24-1 identifies one or more equipment vendors 26-1 , 26-2 nominally authorized to retrieve ML models from the first model training equipment 12-1 , and the second interoperability indicator list 24-2 identifies one or more equipment vendors 26-1 , 26-2 nominally authorized to retrieve ML models from the second model training equipment 12-2. In some embodiments, the authorization policy specifies that the first model training equipment 12-1 is authorized to retrieve the ML model if the first interoperability indicator list 24-1 is a subset of the second interoperability indicator list 24-2 and the second interoperability indicator list 24-2 indicates a vendor of the first model training equipment 12-1 nominally authorized to retrieve ML models from the second model training equipment 12-2. In some embodiments, the authorization policy specifies that the first model training equipment 12-1 is not authorized to retrieve the ML model if the first interoperability indicator list 24-1 is not a subset of the second interoperability indicator list 24-2 or the second interoperability indicator list 24-2 indicates a vendor of the first model training equipment 12-1 is not nominally authorized to retrieve ML models from the second model training equipment 12-2.

[0128] In some embodiments, the authorization policy indicates a set of one or more authorized interoperability lists for the second model training equipment 12-2. In some embodiments, the authorization policy specifies whether or not first model training equipment 12-1 is authorized to retrieve the ML model depending on whether or not whether a first interoperability indicator list 24-1 for the first model training equipment 12-1 is included in the set of one or more authorized interoperability lists 28-1 , 28-2. In some embodiments, the first interoperability indicator list 24-1 identifies one or more equipment vendors 26-1 , 26-2 nominally authorized to retrieve ML models from the first model training equipment 12-1 .

[0129] In some embodiments, the authorization policy specifies whether or not other model training equipment is authorized to retrieve the ML model as a function whether the other model training equipment acts as a federated learning (FL) server in an FL process in which the second model training equipment 12-2 locally trains the ML model. In some embodiments, the authorization policy specifies first model training equipment 12-1 is authorized to retrieve the ML model if a second interoperability indicator list 24-2 for the second model training equipment 12- 2 indicates a vendor of the first model training equipment 12-1 is authorized to retrieve ML models from the second model training equipment 12-2. In some embodiments, the second interoperability indicator list 24-2 identifies one or more equipment vendors 26-1 , 26-2 nominally authorized to retrieve ML models from the second model training equipment 12-2. In some embodiments, the authorization policy specifies first model training equipment 12-1 is authorized to retrieve the ML model if the first model training equipment 12-1 acts as an FL server in an FL process in which the second model training equipment 12-2 locally trains the ML model. In some embodiments, the authorization policy specifies first model training equipment 12-1 is authorized to retrieve the ML model if a second interoperability indicator list 24-2 for the second model training equipment 12-2 is a subset of a first interoperability indicator list 24-1 for the first model training equipment 12-1 . In some embodiments, the first interoperability indicator list 24-1 identifies one or more equipment vendors 26-1 , 26-2 authorized to retrieve ML models from the first model training equipment 12-1 , and the second interoperability indicator list 24-2 identifies one or more equipment vendors 26-1 , 26-2 nominally authorized to retrieve ML models from the second model training equipment 12-2. In some embodiments, the authorization policy specifies first model training equipment 12-1 is authorized to retrieve the ML model if the second interoperability indicator list 24-2 indicates a vendor of the first model training equipment 12-1 is nominally authorized to retrieve ML models from the second model training equipment 12-2. In some embodiments, the authorization policy specifies first model training equipment 12-1 is authorized to retrieve the ML model if the first model training equipment 12-1 acts as an FL server in an FL process in which the second model training equipment 12-2 locally trains the ML model. In some embodiments, the authorization policy specifies first model training equipment 12-1 is authorized to retrieve the ML model if a second interoperability indicator list 24-2 for the second model training equipment 12-2 indicates a vendor of the first model training equipment 12-1 is nominally authorized to retrieve ML models from the second model training equipment 12-2. In some embodiments, the authorization policy specifies first model training equipment 12-1 is authorized to retrieve the ML model if the first model training equipment 12-1 acts as an FL server in an FL process in which the second model training equipment 12-2 locally trains the ML model. In some embodiments, the authorization policy specifies first model training equipment 12-1 is authorized to retrieve the ML model if, for each of multiple FL clients in the FL process for which the first model training equipment 12-1 acts as an FL server, an interoperability indicator list for the FL client is not a superset of the second interoperability indicator list 24-2. In some embodiments, the authorization policy specifies first model training equipment 12-1 is authorized to retrieve the ML model if a second interoperability indicator list 24-2 for the second model training equipment 12- 2 indicates a vendor of the first model training equipment 12-1 is nominally authorized to retrieve ML models from the second model training equipment 12-2. In some embodiments, the authorization policy specifies first model training equipment 12-1 is authorized to retrieve the ML model if the first model training equipment 12-1 acts as an FL server in an FL process in which the second model training equipment 12-2 locally trains the ML model. In some embodiments, the authorization policy specifies first model training equipment 12-1 is authorized to retrieve the ML model if, for each of multiple FL clients in the FL process for which the first model training equipment 12-1 acts as an FL server, an interoperability indicator list for the FL client is not a superset of the first interoperability indicator list 24-1 .

[0130] In some embodiments, the authorization policy is specific to the second model training equipment 12-2.

[0131] In some embodiments, transmitting the authorization policy comprises transmitting the authorization policy during a registration procedure for registering the second model training equipment 12-2 with the network repository equipment 16.

[0132] In some embodiments, the authorization policy specifies what requirements must be met in order for the network repository equipment 16 to authorize any model training equipment to retrieve the ML model, wherein the requirements are specified as a function of an interoperability indicator list of any model training equipment requesting the ML model.

[0133] In some embodiments, the second model training equipment 12-2 implements a second NWDAF MTLF.

[0134] In some embodiments, the ML model is associated with an analytics identifier, ID, and wherein the authorization policy is specific to the analytics ID.

[0135] In some embodiments, the authorization policy governs issuance of access tokens by the network repository equipment 16 to other model training equipment authorized to retrieve the ML model. In some embodiments, the method further comprises receiving, from first model training equipment 12-1 , a request to retrieve the ML model. In some embodiments, the request 18 includes an access token 20. In some embodiments, the method further comprises transmitting the ML model to the first model training equipment 12-1 in response 22 to the request 18. Embodiments herein also include corresponding apparatuses. Embodiments herein for instance include a communication device configured to perform any of the steps of any of the embodiments described above for the communication device.

[0136] Embodiments also include network repository equipment 16 comprising processing circuitry and power supply circuitry. The processing circuitry is configured to perform any of the steps of any of the embodiments described above for the network repository equipment 16. The power supply circuitry is configured to supply power to the network repository equipment 16.

[0137] Embodiments further include network repository equipment 16 comprising processing circuitry. The processing circuitry is configured to perform any of the steps of any of the embodiments described above for the network repository equipment 16. In some embodiments, the network repository equipment 16 further comprises communication circuitry.

[0138] Embodiments further include network repository equipment 16 comprising processing circuitry and memory. The memory contains instructions executable by the processing circuitry whereby the network repository equipment 16 is configured to perform any of the steps of any of the embodiments described above for the network repository equipment 16.

[0139] Embodiments herein also include model training equipment 12-1 , 12-2 configured to perform any of the steps of any of the embodiments described above for the model training equipment 12-1 , 12-2.

[0140] Embodiments also include model training equipment 12-1 , 12-2 comprising processing circuitry and power supply circuitry. The processing circuitry is configured to perform any of the steps of any of the embodiments described above for the model training equipment 12-1 , 12-2. The power supply circuitry is configured to supply power to the model training equipment 12-1 , 12-2.

[0141] Embodiments further include model training equipment 12-1 , 12-2comprising processing circuitry. The processing circuitry is configured to perform any of the steps of any of the embodiments described above for the model training equipment 12-1 , 12-2. In some embodiments, the model training equipment 12-1 , 12-2 further comprises communication circuitry.

[0142] Embodiments further include model training equipment 12-1 , 12-2comprising processing circuitry and memory. The memory contains instructions executable by the processing circuitry whereby the model training equipment 12-1 , 12-2 is configured to perform any of the steps of any of the embodiments described above for the model training equipment 12-1 , 12-2.

[0143] More particularly, the apparatuses described above may perform the methods herein and any other processing by implementing any functional means, modules, units, or circuitry. In one embodiment, for example, the apparatuses comprise respective circuits or circuitry configured to perform the steps shown in the method figures. The circuits or circuitry in this regard may comprise circuits dedicated to performing certain functional processing and / or one or more microprocessors in conjunction with memory. For instance, the circuitry may include one or more microprocessor or microcontrollers, as well as other digital hardware, which may include digital signal processors (DSPs), special-purpose digital logic, and the like. The processing circuitry may be configured to execute program code stored in memory, which may include one or several types of memory such as read-only memory (ROM), random-access memory, cache memory, flash memory devices, optical storage devices, etc. Program code stored in memory may include program instructions for executing one or more telecommunications and / or data communications protocols as well as instructions for carrying out one or more of the techniques described herein, in several embodiments. In embodiments that employ memory, the memory stores program code that, when executed by the one or more processors, carries out the techniques described herein.

[0144] Figure 8 for example illustrates network repository equipment 16 as implemented in accordance with one or more embodiments. As shown, the network repository equipment 16 includes processing circuitry 810 and communication circuitry 820. The communication circuitry 820 is configured to transmit and / or receive information to and / or from one or more other nodes, e.g., via any communication technology. The processing circuitry 810 is configured to perform processing described above, e.g., in Figure 6, such as by executing instructions stored in memory 830. The processing circuitry 810 in this regard may implement certain functional means, units, or modules.

[0145] Figure 9 illustrates model training equipment 12-1 , 12-2 as implemented in accordance with one or more embodiments. As shown, the model training equipment 12-1 , 12-2 includes processing circuitry 910 and communication circuitry 920. The communication circuitry 920 is configured to transmit and / or receive information to and / or from one or more other nodes, e.g., via any communication technology. The processing circuitry 910 is configured to perform processing described above, e.g., in Figure 7, such as by executing instructions stored in memory 930. The processing circuitry 910 in this regard may implement certain functional means, units, or modules.

[0146] Those skilled in the art will also appreciate that embodiments herein further include corresponding computer programs.

[0147] A computer program comprises instructions which, when executed on at least one processor of an apparatus, cause the apparatus to carry out any of the respective processing described above. A computer program in this regard may comprise one or more code modules corresponding to the means or units described above.

[0148] Embodiments further include a carrier containing such a computer program. This carrier may comprise one of an electronic signal, optical signal, radio signal, or computer readable storage medium.

[0149] In this regard, embodiments herein also include a computer program product stored on a non-transitory computer readable (storage or recording) medium and comprising instructions that, when executed by a processor of an apparatus, cause the apparatus to perform as described above.

[0150] Embodiments further include a computer program product comprising program code portions for performing the steps of any of the embodiments herein when the computer program product is executed by a computing device. This computer program product may be stored on a computer readable recording medium.

[0151] Figure 10 shows an example of a communication system 1000 in accordance with some embodiments.

[0152] In the example, the communication system 1000 includes a telecommunication network 1002 that includes an access network 1004, such as a radio access network (RAN), and a core network 1006, which includes one or more core network nodes 1008. The access network 1004 includes one or more access network nodes, such as network nodes 1010a and 1010b (one or more of which may be generally referred to as network nodes 1010), or any other similar 3rdGeneration 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 1002 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a node in the telecommunication network 1002 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 1002, including one or more network nodes 1010 and / or core network nodes 1008.

[0153] Examples of an ORAN network node include an open radio unit (0-Rll), 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 A1 , F1 , W1 , E1 , 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 1010 facilitate direct or indirect connection of user equipment (UE), such as by connecting UEs 1012a, 1012b, 1012c, and 1012d (one or more of which may be generally referred to as UEs 1012) to the core network 1006 over one or more wireless connections.

[0154] 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 1000 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 communication of data and / or signals whether via wired or wireless connections. The communication system 1000 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0155] The UEs 1012 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 1010 and other communication devices. Similarly, the network nodes 1010 are arranged, capable, configured, and / or operable to communicate directly or indirectly with the UEs 1012 and / or with other network nodes or equipment in the telecommunication network 1002 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 1002.

[0156] In the depicted example, the core network 1006 connects the network nodes 1010 to one or more hosts, such as host 1016. 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 1006 includes one more core network nodes (e.g., core network node 1008) 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 1008. 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).

[0157] The host 1016 may be under the ownership or control of a service provider other than an operator or provider of the access network 1004 and / or the telecommunication network 1002, and may be operated by the service provider or on behalf of the service provider. The host 1016 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.

[0158] As a whole, the communication system 1000 of Figure 10 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication system may be configured 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.

[0159] In some examples, the telecommunication network 1002 is a cellular network that implements 3GPP standardized features. Accordingly, the telecommunications network 1002 may support network slicing to provide different logical networks to different devices that are connected to the telecommunication network 1002. For example, the telecommunications network 1002 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)ZMassive loT services to yet further UEs.

[0160] In some examples, the UEs 1012 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 1004 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 1004. 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).

[0161] In the example, the hub 1014 communicates with the access network 1004 to facilitate indirect communication between one or more UEs (e.g., UE 1012c and / or 1012d) and network nodes (e.g., network node 1010b). In some examples, the hub 1014 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 1014 may be a broadband router enabling access to the core network 1006 for the UEs. As another example, the hub 1014 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 1010, or by executable code, script, process, or other instructions in the hub 1014. As another example, the hub 1014 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 1014 may be a content source. For example, for a UE that is a VR headset, display, loudspeaker or other media delivery device, the hub 1014 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub 1014 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 1014 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy loT devices.

[0162] The hub 1014 may have a constant / persistent or intermittent connection to the network node 1010b. The hub 1014 may also allow for a different communication scheme and / or schedule between the hub 1014 and UEs (e.g., UE 1012c and / or 1012d), and between the hub 1014 and the core network 1006. In other examples, the hub 1014 is connected to the core network 1006 and / or one or more UEs via a wired connection. Moreover, the hub 1014 may be configured to connect to an M2M service provider over the access network 1004 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 1010 while still connected via the hub 1014 via a wired or wireless connection. In some embodiments, the hub 1014 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 1010b. In other embodiments, the hub 1014 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node 1010b, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0163] Figure 11 shows a UE 1100 in accordance with some embodiments. 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 device, playback appliance, wearable terminal device, wireless endpoint, mobile station, tablet, laptop, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), smart device, wireless customer-premise equipment (CPE), vehicle, vehicle-mounted or vehicle embedded / integrated wireless device, etc. Other examples include any UE identified by the 3rdGeneration Partnership Project (3GPP), including a narrow band internet of things (NB- loT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0164] A UE may support device-to-device (D2D) communication, for example by implementing a 3GPP 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).

[0165] The UE 1100 includes processing circuitry 1102 that is operatively coupled via a bus 1104 to an input / output interface 1106, a power source 1108, a memory 1110, a communication interface 1112, and / or any other component, or any combination thereof. Certain UEs may utilize all or a subset of the components shown in Figure 11 . 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.

[0166] The processing circuitry 1102 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 1110. The processing circuitry 1102 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 1102 may include multiple central processing units (CPUs).

[0167] In the example, the input / output interface 1106 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 1100. Examples of an input device include a touch-sensitive or presence-sensitive display, a camera (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.

[0168] In some embodiments, the power source 1108 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 1108 may further include power circuitry for delivering power from the power source 1108 itself, and / or an external power source, to the various parts of the UE 1100 via input circuitry or an interface such as an electrical power cable. Delivering power may be, for example, for charging of the power source 1108. Power circuitry may perform any formatting, converting, or other modification to the power from the power source 1108 to make the power suitable for the respective components of the UE 1100 to which power is supplied.

[0169] The memory 1110 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 1110 includes one or more application programs 1114, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 1116. The memory 1110 may store, for use by the UE 1100, any of a variety of various operating systems or combinations of operating systems.

[0170] The memory 1110 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), such as a USIM and / or ISIM, other memory, or any combination thereof. The UICC may for example be an embedded UICC (eUlCC), integrated UICC (iUICC) or a removable UICC commonly known as ‘SIM card.’ The memory 1110 may allow the UE 1100 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 1110, which may be or comprise a device-readable storage medium.

[0171] The processing circuitry 1102 may be configured to communicate with an access network or other network using the communication interface 1112. The communication interface 1112 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 1122. The communication interface 1112 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 1118 and / or a receiver 1120 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter 1118 and receiver 1120 may be coupled to one or more antennas (e.g., antenna 1122) and may share circuit components, software or firmware, or alternatively be implemented separately.

[0172] In the illustrated embodiment, communication functions of the communication interface 1112 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 / internet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0173] Regardless of the type of sensor, a UE may provide an output of data captured by its sensors, through its communication interface 1112, 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 if it 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).

[0174] 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.

[0175] 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 head-mounted display for Augmented Reality (AR) or Virtual Reality (VR), 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 1100 shown in Figure 11 .

[0176] 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-loT 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.

[0177] 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.

[0178] Figure 12 shows a network node 1200 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).

[0179] 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). 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 / multicast 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).

[0180] The network node 1200 includes a processing circuitry 1202, a memory 1204, a communication interface 1206, and a power source 1208. The network node 1200 may be composed 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 1200 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 1200 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memory 1204 for different RATs) and some components may be reused (e.g., a same antenna 1210 may be shared by different RATs). The network node 1200 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 1200, 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 1200.

[0181] The processing circuitry 1202 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 1200 components, such as the memory 1204, to provide network node 1200 functionality.

[0182] In some embodiments, the processing circuitry 1202 includes a system on a chip (SOC). In some embodiments, the processing circuitry 1202 includes one or more of radio frequency (RF) transceiver circuitry 1212 and baseband processing circuitry 1214. In some embodiments, the radio frequency (RF) transceiver circuitry 1212 and the baseband processing circuitry 1214 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 1212 and baseband processing circuitry 1214 may be on the same chip or set of chips, boards, or units. The memory 1204 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 computer-executable memory devices that store information, data, and / or instructions that may be used by the processing circuitry 1202. The memory 1204 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 1202 and utilized by the network node 1200. The memory 1204 may be used to store any calculations made by the processing circuitry 1202 and / or any data received via the communication interface 1206. In some embodiments, the processing circuitry 1202 and memory 1204 is integrated.

[0183] The communication interface 1206 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 1206 comprises port(s) / terminal(s) 1216 to send and receive data, for example to and from a network over a wired connection. The communication interface 1206 also includes radio front-end circuitry 1218 that may be coupled to, or in certain embodiments a part of, the antenna 1210. Radio front-end circuitry 1218 comprises filters 1220 and amplifiers 1222. The radio front-end circuitry 1218 may be connected to an antenna 1210 and processing circuitry 1202. The radio front-end circuitry may be configured to condition signals communicated between antenna 1210 and processing circuitry 1202. The radio front-end circuitry 1218 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 1218 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of filters 1220 and / or amplifiers 1222. The radio signal may then be transmitted via the antenna 1210. Similarly, when receiving data, the antenna 1210 may collect radio signals which are then converted into digital data by the radio front-end circuitry 1218. The digital data may be passed to the processing circuitry 1202. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0184] In certain alternative embodiments, the network node 1200 does not include separate radio front-end circuitry 1218, instead, the processing circuitry 1202 includes radio front-end circuitry and is connected to the antenna 1210. Similarly, in some embodiments, all or some of the RF transceiver circuitry 1212 is part of the communication interface 1206. In still other embodiments, the communication interface 1206 includes one or more ports or terminals 1216, the radio front-end circuitry 1218, and the RF transceiver circuitry 1212, as part of a radio unit (not shown), and the communication interface 1206 communicates with the baseband processing circuitry 1214, which is part of a digital unit (not shown). The antenna 1210 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 1210 may be coupled to the radio front-end circuitry 1218 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 1210 is separate from the network node 1200 and connectable to the network node 1200 through an interface or port.

[0185] The antenna 1210, communication interface 1206, and / or the processing circuitry 1202 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 LIE, another network node and / or any other network equipment. Similarly, the antenna 1210, the communication interface 1206, and / or the processing circuitry 1202 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 LIE, another network node and / or any other network equipment.

[0186] The power source 1208 provides power to the various components of network node 1200 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source 1208 may further comprise, or be coupled to, power management circuitry to supply the components of the network node 1200 with power for performing the functionality described herein. For example, the network node 1200 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 1208. As a further example, the power source 1208 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.

[0187] Embodiments of the network node 1200 may include additional components beyond those shown in Figure 12 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 1200 may include user interface equipment to allow input of information into the network node 1200 and to allow output of information from the network node 1200. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node 1200.

[0188] Figure 13 is a block diagram of a host 1300, which may be an embodiment of the host 1016 of Figure 10, in accordance with various aspects described herein. As used herein, the host 1300 may be or comprise various combinations hardware and / or software, including a standalone server, a blade server, a cloud-implemented server, a distributed server, a virtual machine, container, or processing resources in a server farm. The host 1300 may provide one or more services to one or more UEs. The host 1300 includes processing circuitry 1302 that is operatively coupled via a bus 1304 to an input / output interface 1306, a network interface 1308, a power source 1310, and a memory 1312. Other components may be included in other embodiments. Features of these components may be substantially similar to those described with respect to the devices of previous figures, such as Figures 11 and 12, such that the descriptions thereof are generally applicable to the corresponding components of host 1300.

[0189] The memory 1312 may include one or more computer programs including one or more host application programs 1314 and data 1316, which may include user data, e.g., data generated by a UE for the host 1300 or data generated by the host 1300 for a UE. Embodiments of the host 1300 may utilize only a subset or all of the components shown. The host application programs 1314 may be implemented in a container-based architecture and may provide support for video codecs (e.g., Versatile Video Coding (VVC), High Efficiency Video Coding (HEVC), Advanced Video Coding (AVC), MPEG, VP9) and audio codecs (e.g., FLAC, Advanced Audio Coding (AAC), MPEG, G.711), including transcoding for multiple different classes, types, or implementations of UEs (e.g., handsets, desktop computers, wearable display systems, heads-up display systems). The host application programs 1314 may also provide for user authentication and licensing checks and may periodically report health, routes, and content availability to a central node, such as a device in or on the edge of a core network. Accordingly, the host 1300 may select and / or indicate a different host for over-the-top services for a UE. The host application programs 1314 may support various protocols, such as the HTTP Live Streaming (HLS) protocol, Real-Time Messaging Protocol (RTMP), Real-Time Streaming Protocol (RTSP), Dynamic Adaptive Streaming over HTTP (MPEG-DASH), etc.

[0190] Figure 14 is a block diagram illustrating a virtualization environment 1400 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 1400 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 1400 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. Applications 1402 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment 0400 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0191] Hardware 1404 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 1406 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VMs 1408a and 1408b (one or more of which may be generally referred to as VMs 1408), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. The virtualization layer 1406 may present a virtual operating platform that appears like networking hardware to the VMs 1408.

[0192] The VMs 1408 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by a corresponding virtualization layer 1406. Different embodiments of the instance of a virtual appliance 1402 may be implemented on one or more of VMs 1408, and the implementations may be made in different ways. Virtualization of the hardware is in some contexts referred to as network function virtualization (NFV). NFV may 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.

[0193] In the context of NFV, a VM 1408 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 1408, and that part of hardware 1404 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 1408 on top of the hardware 1404 and corresponds to the application 1402.

[0194] Hardware 1404 may be implemented in a standalone network node with generic or specific components. Hardware 1404 may implement some functions via virtualization. Alternatively, hardware 1404 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 1410, which, among others, oversees lifecycle management of applications 1402. In some embodiments, hardware 1404 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 1412 which may alternatively be used for communication between hardware nodes and radio units.

[0195] Although the computing devices described herein (e.g., UEs, network nodes, hosts) 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 comprise multiple 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.

[0196] 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.

[0197] Notably, modifications and other embodiments of the present disclosure will come to mind to one skilled in the art having the benefit of the teachings presented in the foregoing descriptions and the associated drawings. Therefore, it is to be understood that the present disclosure is not to be limited to the specific embodiments disclosed and that modifications and other embodiments are intended to be included within the scope of this disclosure. Although specific terms may be employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.

[0198] Example embodiments of the techniques and apparatus described herein include, but are not limited to, the following claims.

Claims

CLAIMS1 . A method performed by network repository equipment (16) in a communication network (10), the method comprising: receiving (600), from first model training equipment (12-1), a request (18) for an access token (20) indicating the first model training equipment (12-1 ) is authorized to retrieve a machine learning, ML, model from second model training equipment (12-2); making (610) a determination as to whether the first model training equipment (12-1 ) is authorized to retrieve the ML model from the second model training equipment (12-2), based on a first interoperability indicator list (24-1) for the first model training equipment (12-1) which identifies one or more equipment vendors (26-1 , 26-2) nominally authorized to retrieve ML models from the first model training equipment (12-1); and responding (620) to the request (18) based on the determination.

2. The method of claim 1 , wherein making the determination comprises making the determination based on whether the first interoperability indicator list (24-1) is a subset of a second interoperability indicator list (24-2) for the second model training equipment (12-2) which identifies one or more equipment vendors (26-1 , 26-2) nominally authorized to retrieve ML models from the second model training equipment (12-2).

3. The method of claim 2, wherein the determination is made that the first model training equipment (12-1) is authorized to retrieve the ML model if the first interoperability indicator list (24-1 ) is a subset of the second interoperability indicator list (24-2) and the second interoperability indicator list (24-2) indicates a vendor of the first model training equipment (12-1 ) is nominally authorized to retrieve ML models from the second model training equipment (12-2).

4. The method of claim 3, wherein the determination is made that the first model training equipment (12-1) is not authorized to retrieve the ML model if the first interoperability indicator list (24-1) is not a subset of the second interoperability indicator list (24-2) or the second interoperability indicator list (24-2) indicates a vendor of the first model training equipment (12-1 ) is not nominally authorized to retrieve ML models from the second model training equipment (12-2).

5. The method of any of claims 1 -4, wherein making the determination comprises making the determination based on whether the first interoperability indicator list (24-1 ) is included in aset of one or more authorized interoperability lists (28-2) for the second model training equipment (12-2).

6. The method of any of claims 1 -5, wherein the determination is made also based on whether the first model training equipment (12-1) acts as a federated learning (FL) server in an FL process in which the second model training equipment (12-2) locally trains the ML model.

7. The method of claim 6, wherein the determination is made that the first model training equipment (12-1) is authorized to retrieve the ML model if: the first interoperability indicator list (24-1) is not a subset of the second interoperability indicator list (24-2); the second interoperability indicator list (24-2) indicates a vendor of the first model training equipment (12-1) is nominally authorized to retrieve ML models from the second model training equipment (12-2); and the first model training equipment (12-1) acts as an FL server in an FL process in which the second model training equipment (12-2) locally trains the ML model.

8. The method of claim 6, wherein the determination is made that the first model training equipment (12-1) is authorized to retrieve the ML model if: the first interoperability indicator list (24-1) is not a subset of the second interoperability indicator list (24-2); the second interoperability indicator list (24-2) is a subset of the first interoperability indicator list (24-1); the second interoperability indicator list (24-2) indicates a vendor of the first model training equipment (12-1) is nominally authorized to retrieve ML models from the second model training equipment (12-2); and the first model training equipment (12-1) acts as an FL server in an FL process in which the second model training equipment (12-2) locally trains the ML model.

9. The method of claim 6, wherein the determination is made that the first model training equipment (12-1) is authorized to retrieve the ML model if: the first interoperability indicator list (24-1) is not a subset of the second interoperability indicator list (24-2); the second interoperability indicator list (24-2) indicates a vendor of the first model training equipment (12-1) is nominally authorized to retrieve ML models from the second model training equipment (12-2); the first model training equipment (12-1) acts as an FL server in an FL process in which the second model training equipment (12-2) locally trains the ML model; andfor each of multiple FL clients in the FL process for which the first model training equipment (12-1) acts as an FL server, an interoperability indicator list for the FL client is not a superset of the second interoperability indicator list (24-2).

10. The method of claim 6, wherein the determination is made that the first model training equipment (12-1) is authorized to retrieve the ML model if: the first interoperability indicator list (24-1) is not a subset of the second interoperability indicator list (24-2); the second interoperability indicator list (24-2) indicates a vendor of the first model training equipment (12-1) is nominally authorized to retrieve ML models from the second model training equipment (12-2); the first model training equipment (12-1) acts as an FL server in an FL process in which the second model training equipment (12-2) locally trains the ML model; and for each of multiple FL clients in the FL process for which the first model training equipment (12-1) acts as an FL server, an interoperability indicator list for the FL client is not a superset of the first interoperability indicator list (24-1).11 . The method of any of claims 1 -10, wherein making the determination comprises making the determination based on an authorization policy specific to the second model training equipment (12-2).

12. The method of claim 11 , wherein, according to the authorization policy, authorization of the first model training equipment (12-1) to retrieve the ML model depends on the first interoperability indicator list (24-1 ) for the first model training equipment (12-1 ).

13. The method of any of claims 11-12, further comprising receiving (630) the authorization policy from the second model training equipment (12-2) during a registration procedure for registering the second model training equipment (12-2) with the network repository equipment (16).

14. The method of any of claims 11-13, wherein the authorization policy specifies what requirements must be met in order for the network repository equipment (16) to authorize any model training equipment to retrieve the ML model, wherein the requirements are specified as a function of an interoperability indicator list of any model training equipment requesting the ML model.

15. The method of any of claims 1 -14, wherein the request (18) includes the first interoperability indicator list (24-1).

16. The method of any of claims 1 -14, further comprising: receiving (640) the first interoperability indicator list (24-1) from the first model training equipment (12-1) during a procedure for registering the first model training equipment (12-1) with the network repository equipment (16); storing (650) the first interoperability indicator list (24-1) in a profile for the first model training equipment (12-1); and after receiving the request (18), retrieving (660) the first interoperability indicator list (24- 1 ) from the profile for the first model training equipment (12-1).

17. The method of any of claims 1 -16, wherein responding to the request (18) comprises, if the determination is made that the first model training equipment (12-1) is authorized to retrieve the ML model, transmitting the requested access token (20) to the first model training equipment (12-1).

18. The method of any of claims 1 -17, wherein the first model training equipment (12-1) implements a first Network Data Analytics Function, NWDAF, Model Training Logic Function, MTLF, as a Network Function (NF) service consumer, and wherein the second model training equipment (12-2) implements a second NWDAF MTLF as an NF service producer.

19. The method of any of claims 1 -18, wherein the ML model is associated with an analytics identifier, ID, and wherein the first interoperability indicator list (24-1) is specific to the analytics ID so as to identify one or more equipment vendors (26-1 , 26-2) nominally authorized to retrieve from the first model training equipment (12-1 ) ML models associated with the analytics ID.

20. A method performed by first model training equipment (12-1) in a communication network (10), the method comprising: transmitting (700), to network repository equipment (16) in the communication network (10), a request (18) for an access token (20) indicating the first model training equipment (12-1) is authorized to retrieve a machine learning, ML, model from second model training equipment (12-2), wherein the request (18) includes a first interoperability indicator list (24-1 ) for the first model training equipment (12-1 ) which identifies one or more equipment vendors (26-1 , 26-2) nominally authorized to retrieve ML models from the first model training equipment (12-1 ); and receiving (710) a response (22) to the request (18) from the network repository equipment (16).21 . The method of claim 20, wherein the response (22) includes the requested access token (20), and wherein the method further comprises: transmitting an ML model request to the second model training equipment (12-2) or to analytical data repository equipment associated with the second model training equipment (12-2), wherein the ML model request includes the access token (20); and receiving the ML model in response to the ML model request.

22. The method of any of claims 20-21 , wherein the first model training equipment (12-1 ) implements a first Network Data Analytics Function, NWDAF, Model Training Logic Function, MTLF, as a Network Function (NF) service consumer, and wherein the second model training equipment (12-2) implements a second NWDAF MTLF as an NF service producer.

23. The method of any of claims 20-22, wherein the ML model is associated with an analytics identifier, ID, and wherein the first interoperability indicator list (24-1) is specific to the analytics ID so as to identify one or more equipment vendors (26-1 , 26-2) nominally authorized to retrieve from the first model training equipment (12-1) ML models associated with the analytics ID.

24. A method performed by second model training equipment (12-2) in a communication network (10), the method comprising: transmitting (720), to network repository equipment (16) in the communication network (10), an authorization policy for authorizing other model training equipment to retrieve a machine learning, ML, model from the second model training equipment (12-2), wherein the authorization policy specifies whether or not other model training equipment is nominally authorized to retrieve the ML model as a function of an interoperability indicator list for the other model training equipment.

25. The method of claim 24, wherein the authorization policy specifies whether or not first model training equipment (12-1) is authorized to retrieve the ML model depending on whether or not a first interoperability indicator list (24-1 ) for the first model training equipment (12-1 ) is a subset of a second interoperability indicator list (24-2) for the second model training equipment (12-2), wherein the first interoperability indicator list (24-1) identifies one or more equipment vendors (26-1 , 26-2) nominally authorized to retrieve ML models from the first model training equipment (12-1), and wherein the second interoperability indicator list (24-2) identifies one or more equipment vendors (26-1 , 26-2) nominally authorized to retrieve ML models from the second model training equipment (12-2).

26. The method of claim 25, wherein the authorization policy specifies that the first model training equipment (12-1) is authorized to retrieve the ML model if the first interoperability indicator list (24-1) is a subset of the second interoperability indicator list (24-2) and the second interoperability indicator list (24-2) indicates a vendor of the first model training equipment (12-1 ) nominally authorized to retrieve ML models from the second model training equipment (12-2).

27. The method of claim 25, wherein the authorization policy specifies that the first model training equipment (12-1) is not authorized to retrieve the ML model if the first interoperability indicator list (24-1) is not a subset of the second interoperability indicator list (24-2) or the second interoperability indicator list (24-2) indicates a vendor of the first model training equipment (12-1) is not nominally authorized to retrieve ML models from the second model training equipment (12-2).

28. The method of claim 24, wherein the authorization policy indicates a set of one or more authorized interoperability lists for the second model training equipment (12-2), wherein the authorization policy specifies whether or not first model training equipment (12-1) is authorized to retrieve the ML model depending on whether or not whether a first interoperability indicator list (24-1 ) for the first model training equipment (12-1 ) is included in the set of one or more authorized interoperability lists, wherein the first interoperability indicator list (24-1) identifies one or more equipment vendors (26-1 , 26-2) nominally authorized to retrieve ML models from the first model training equipment (12-1 ).

29. The method of any of claims 24-28, wherein the authorization policy specifies whether or not other model training equipment is authorized to retrieve the ML model as a function whether the other model training equipment acts as a federated learning (FL) server in an FL process in which the second model training equipment (12-2) locally trains the ML model.

30. The method of claim 29, wherein the authorization policy specifies first model training equipment (12-1) is authorized to retrieve the ML model if: a second interoperability indicator list (24-2) for the second model training equipment (12-2) indicates a vendor of the first model training equipment (12-1 ) is authorized to retrieve ML models from the second model training equipment (12- 2), wherein the second interoperability indicator list (24-2) identifies one or more equipment vendors (26-1 , 26-2) nominally authorized to retrieve ML models from the second model training equipment (12-2); and the first model training equipment (12-1) acts as an FL server in an FL process in which the second model training equipment (12-2) locally trains the ML model.31 . The method of claim 29, wherein the authorization policy specifies first model training equipment (12-1) is authorized to retrieve the ML model if: a second interoperability indicator list (24-2) for the second model training equipment (12-2) is a subset of a first interoperability indicator list (24-1) for the first model training equipment (12-1), wherein the first interoperability indicator list (24-1 ) identifies one or more equipment vendors (26-1 , 26-2) authorized to retrieve ML models from the first model training equipment (12-1 ), and wherein the second interoperability indicator list (24-2) identifies one or more equipment vendors (26- 1 , 26-2) nominally authorized to retrieve ML models from the second model training equipment (12-2); the second interoperability indicator list (24-2) indicates a vendor of the first model training equipment (12-1) is nominally authorized to retrieve ML models from the second model training equipment (12-2); and the first model training equipment (12-1) acts as an FL server in an FL process in which the second model training equipment (12-2) locally trains the ML model.

32. The method of claim 29, wherein the authorization policy specifies first model training equipment (12-1) is authorized to retrieve the ML model if: a second interoperability indicator list (24-2) for the second model training equipment (12-2) indicates a vendor of the first model training equipment (12-1 ) is nominally authorized to retrieve ML models from the second model training equipment (12- 2); the first model training equipment (12-1) acts as an FL server in an FL process in which the second model training equipment (12-2) locally trains the ML model; and for each of multiple FL clients in the FL process for which the first model training equipment (12-1) acts as an FL server, an interoperability indicator list for the FL client is not a superset of the second interoperability indicator list (24-2).

33. The method of claim 29, wherein the authorization policy specifies first model training equipment (12-1) is authorized to retrieve the ML model if: a second interoperability indicator list (24-2) for the second model training equipment (12-2) indicates a vendor of the first model training equipment (12-1 ) is nominally authorized to retrieve ML models from the second model training equipment (12- 2); the first model training equipment (12-1) acts as an FL server in an FL process in which the second model training equipment (12-2) locally trains the ML model; andfor each of multiple FL clients in the FL process for which the first model training equipment (12-1) acts as an FL server, an interoperability indicator list for the FL client is not a superset of the first interoperability indicator list (24-1).

34. The method of any of claims 24-33, wherein the authorization policy is specific to the second model training equipment (12-2).

35. The method of any of claims 24-34, wherein transmitting the authorization policy comprises transmitting the authorization policy during a registration procedure for registering the second model training equipment (12-2) with the network repository equipment (16).

36. The method of any of claims 24-35, wherein the authorization policy specifies what requirements must be met in order for the network repository equipment (16) to authorize any model training equipment to retrieve the ML model, wherein the requirements are specified as a function of an interoperability indicator list of any model training equipment requesting the ML model.

37. The method of any of claims 24-36, wherein the second model training equipment (12-2) implements a second NWDAF MTLF.

38. The method of any of claims 24-37, wherein the ML model is associated with an analytics identifier, ID, and wherein the authorization policy is specific to the analytics ID.

39. The method of any of claims 24-38, wherein the authorization policy governs issuance of access tokens by the network repository equipment (16) to other model training equipment authorized to retrieve the ML model, and wherein the method further comprises: receiving, from first model training equipment (12-1 ), a request (18) to retrieve the ML model, wherein the request (18) includes an access token (20); and transmitting the ML model to the first model training equipment (12-1) in response (22) to the request (18).

40. Network repository equipment (16) configured to perform the method of any of claims 1 - 19.41 . A computer program comprising instructions which, when executed by at least one processor of a network repository equipment (16), causes the network repository equipment (16) to perform the method of any of claims 1-19.

42. A first model training equipment (12-1) configured to perform the method of any of claims 20-23.

43. A computer program comprising instructions which, when executed by at least one processor of a first model training equipment (12-1 ), causes the first model training equipment (12-1 ) to perform the method of any of claims 20-23.

44. A second model training equipment (12-2) configured to perform the method of any of claims 24-39.

45. A computer program comprising instructions which, when executed by at least one processor of a second model training equipment (12-2), causes the second model training equipment (12-2) to perform the method of any of claims 24-39.

Images