Multi-stage machine learning operation execution

Abstract

Various aspects of the present disclosure relate to a network entity comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the network entity to: receive information indicating a trigger event caused by energy usage of a user equipment (UE); determine, based on the information, that a module on the UE involved in execution of a stage of a multi-stage machine learning operation in co-ordination with one or more further entities, is to be replaced; and determine one or more entities to be selected or considered for replacement of the module on the UE for execution of the stage of the multi-stage machine learning operation, using energy status information of the one or more entities.

Description

MULTI-STAGE MACHINE LEARNING OPERATION EXECUTIONTECHNICAL FIELD

[0001] The present disclosure relates to wireless communications, and more specifically to the execution of multi-stage machine learning operations.BACKGROUND

[0002] A wireless communications system may include one or multiple network communication devices, such as base stations, which may support wireless communications for one or multiple user communication devices, which may be otherwise known as user equipment (UE), or other suitable terminology. The wireless communications system may support wireless communications with one or multiple user communication devices by utilizing resources of the wireless communication system (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers, or the like). Additionally, the wireless communications system may support wireless communications across various radio access technologies including third generation (3G) radio access technology, fourth generation (4G) radio access technology, fifth generation (5G) radio access technology, among other suitable radio access technologies beyond 5G (e.g., sixth generation (6G)).SUMMARY

[0003] An article “a” before an element is unrestricted and understood to refer to “at least one” of those elements or “one or more” of those elements. The terms “a,” “at least one,” “one or more,” and “at least one of one or more” may be interchangeable. As used herein, including in the claims, “or” as used in a list of items (e.g., a list of items prefaced by a phrase such as “at least one of’ or “one or more of’ or “one or both of’) indicates an inclusive list such that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C). Also, as used herein, the phrase “based on” shall not be construed as a reference to a closed set of conditions. For example, an example step that is described as “based on condition A” may be based on both a condition A and a condition B without departing from the scope of the present disclosure. In other words, as used herein,the phrase “based on” shall be construed in the same manner as the phrase “based at least in part on. Further, as used herein, including in the claims, a “set” may include one or more elements.

[0004] Some implementations of the method and apparatuses described herein may include a network entity for wireless communication, comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the network entity to: receive information indicating a trigger event caused by energy usage of a user equipment (UE); determine, based on the information, that a module on the UE involved in execution of a stage of a multi-stage machine learning operation in co-ordination with one or more further entities, is to be replaced; and determine one or more entities to be selected or considered for replacement of the module on the UE for execution of the stage of the multi-stage machine learning operation, using energy status information of the one or more entities.

[0005] The information may be received from the UE.

[0006] The trigger event may indicate that an energy usage indicator has satisfied, is expected to satisfy, or is predicted to satisfy, a predetermined threshold during execution of the multi-stage machine learning operation.

[0007] The at least one processor may be further configured to cause the network entity to: identify a profile defining the multi-stage machine learning operation; and perform the determination that the module on the UE involved in execution of a stage of the multi-stage machine learning operation is to be replaced based on the trigger event and the profile.

[0008] The information may request an update to the entities involved in execution of the multi-stage machine learning operation and comprise a profile defining the multi-stage machine learning operation.

[0009] The at least one processor may be further configured to cause the network entity to determine the one or more entities to be selected or considered for replacement of the module on the UE from a plurality of candidate entities using the energy status information of the plurality of candidate entities.

[0010] The energy status information of the plurality of candidate entities may comprise an energy usage indicator and / or an energy usage threshold.

[0011] The at least one processor may be further configured to cause the network entity to retrieve the energy status information of at least one of the plurality of candidate entities from a repository.

[0012] The at least one processor may be further configured to cause the network entity to receive the energy status information of at least one of the plurality of candidate entities from the at least one of the plurality of candidate entities.

[0013] The at least one processor may be further configured to cause the network entity to receive the energy status information of at least one of the plurality of candidate entities from an energy monitoring function.

[0014] The at least one processor may be further configured to cause the network entity to assign a rating and / or ranking to each of the plurality of candidate entities using the energy status information of the plurality of candidate entities and a profile defining the multi-stage machine learning operation.

[0015] The at least one processor may be further configured to cause the network entity, in response to the determination of the one or more entities to be selected for replacement of the module on the UE, to transmit a notification to the module on the UE, the notification including an identifier of the one or more entities.

[0016] The at least one processor may be further configured to cause the network entity, in response to the determination of the one or more entities to be considered for replacement of the module on the UE, to transmit a notification to the module on the UE, the notification including an identifier of the one or more entities.

[0017] The notification may further include a rating and / or ranking assigned to each of the one or more entities using the energy status information.

[0018] The at least one processor may be further configured to cause the network entity to determine one or more entities selected for replacement of the module on the UE based on a message received from the module.

[0019] The at least one processor may be further configured to cause the network entity to transmit identifiers, of entities for execution of the multi-stage machine learning operation after replacement of the module on the UE, to a repository.

[0020] The at least one processor may be further configured to cause the network entity to transmit energy status information, of the entities for execution of the multi-stage machine learning operation after replacement of the module on the UE, to the repository.

[0021] Some implementations of the method and apparatuses described herein may further include a method performed by a network entity, the method comprising: receiving information indicating a trigger event caused by energy usage of a UE; determining, based on the information, that a module on the UE involved in execution of a stage of a multi-stage machine learning operation in co-ordination with one or more further entities, is to be replaced; and determining one or more entities to be selected or considered for replacement of the module on the UE for execution of the stage of the multi-stage machine learning operation, using energy status information of the one or more entities.

[0022] Some implementations of the method and apparatuses described herein may further include a processor for wireless communication, comprising: at least one controller coupled with at least one memory and configured to cause the processor to: obtain information indicating an trigger event caused by energy usage of a UE; determine, based on the information, that an entity on the UE involved in execution of a stage of a multi-stage machine learning operation in co-ordination with one or more further entities, is to be replaced; and determine one or more entities to be selected or considered for replacement of the module on the UE for execution of the stage of the multi-stage machine learning operation, using energy status information of the one or more entities.

[0023] Some implementations of the method and apparatuses described herein may further include a UE for wireless communication, comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the UE to: commence execution of a stage of a multi-stage machine learning operation in co-ordination with one or more further entities; detect a trigger event caused by energy usage of the UE; transmit information indicating the trigger event; and receive a notification, the notification including an identifier of one or more entities selected or to be considered for replacement of a module on the UE for execution of the stage of the multi-stage machine learning operation.

[0024] The trigger event may indicate that an energy usage indicator has satisfied, is expected to satisfy, or is predicted to satisfy a predetermined threshold during execution of the multi-stage machine learning operation.

[0025] The at least one processor may be further configured to detect the trigger event based on an energy usage report.

[0026] The at least one processor may be further configured to cause the UE to monitor an energy usage indicator at the UE.

[0027] The at least one processor may be further configured to cause the UE to monitor the energy usage based on monitoring one or more of: a battery status, an application traffic schedule, or an application traffic pattern from an application.BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 illustrates an example of a wireless communications system in accordance with aspects of the present disclosure.

[0029] Figure 2 illustrates an on-network AIMLE functional model of AIML enablement.

[0030] Figure 3 illustrates an example execution of a multi-stage ML operation.

[0031] Figure 4 illustrates a process for updating participants involved in a multi-stage ML operation in accordance with aspects of the present disclosure.

[0032] Figure 5 illustrates a further process for updating participants involved in a multistage ML operation in accordance with aspects of the present disclosure.

[0033] Figure 6 illustrates an example of a user equipment (UE) 600 in accordance with aspects of the present disclosure.

[0034] Figure 7 illustrates an example of a processor 700 in accordance with aspects of the present disclosure.

[0035] Figure 8 illustrates an example of a network equipment (NE) 800 in accordance with aspects of the present disclosure.

[0036] Figure 9 illustrate a flowchart of a method performed by a UE in accordance with aspects of the present disclosure.

[0037] Figure 10 illustrate a flowchart of a method performed by a NE in accordance with aspects of the present disclosure.DETAILED DESCRIPTION

[0038] A wireless communications system, including one or more communication devices may be enabled (e.g. configured) to support machine learning (ML), and more generally artificial intelligence (Al) (referred to collectively as AIML) for various applications or services associated with the wireless communications system.

[0039] One use case for AIML is an AI / ML operation that is split between AI / ML endpoints, and in-time transfer of AI / ML models (for example as described in 3GPP TS 22.261). A multi-stage ML operation (otherwise referred to as a split AI / ML operation, a split ML operation, or a split operation pipeline), which may be or include a ML model training operation or a ML model inference operation, involves the performance of the ML operation being distributed (i.e. split) into multiple parts in accordance with a current task and environment (such as communications data rate, device resource, and server workload). The intention for a multi-stage ML operation is to offload the computationintensive, energy-intensive parts to one or more network endpoints (e.g. a cloud or edge server), whereas leave the privacy-sensitive and delay- sensitive parts at the end device (e.g. a UE). For example, in case of a multi-stage ML model inference operation, a device (e.g., the end device) executes a partial model inference and sends the intermediate data to a network endpoint, where the remaining model inference (or further partial model inference) is executed, and the inference results are fed back to the device.

[0040] Whilst an end device is performing its part of the multi-stage ML operation, it may be detected that the end device will not be able to complete its part of the multi-stage ML operation due to energy usage at the end device.

[0041] Embodiments of the present disclosure relate to the detection of a trigger event caused by energy usage of a UE that is involved in execution of a stage of a multi-stage MLoperation, and the subsequent identification of one or more entities to offload the execution of this stage to.

[0042] Aspects of the present disclosure are described in the context of a wireless communications system.

[0043] Figure 1 illustrates an example of a wireless communications system 100 in accordance with aspects of the present disclosure. The wireless communications system 100 may include one or more NE 102, one or more UE 104, and a core network (CN) 106. The wireless communications system 100 may support various radio access technologies. In some implementations, the wireless communications system 100 may be a 4G network, such as an LTE network or an LTE -Advanced (LTE-A) network. In some other implementations, the wireless communications system 100 may be a NR network, such as a 5G network, a 5G- Advanced (5G-A) network, or a 5G ultrawideband (5G-UWB) network. In other implementations, the wireless communications system 100 may be a combination of a 4G network and a 5G network, or other suitable radio access technology including Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20. The wireless communications system 100 may support radio access technologies beyond 5G, for example, 6G. Additionally, the wireless communications system 100 may support technologies, such as time division multiple access (TDMA), frequency division multiple access (FDMA), or code division multiple access (CDMA), etc.

[0044] The one or more NE 102 may be dispersed throughout a geographic region to form the wireless communications system 100. One or more of the NE 102 described herein may be or include or may be referred to as a network node, a base station, a network element, a network function, a network entity, a radio access network (RAN), a NodeB, an eNodeB (eNB), a next-generation NodeB (gNB), or other suitable terminology. An NE 102 and a UE 104 may communicate via a communication link, which may be a wireless or wired connection. For example, an NE 102 and a UE 104 may perform wireless communication (e.g., receive signaling, transmit signaling) over a Uu interface.

[0045] An NE 102 may provide a geographic coverage area for which the NE 102 may support services for one or more UEs 104 within the geographic coverage area. For example, an NE 102 and a UE 104 may support wireless communication of signals related to services(e.g., voice, video, packet data, messaging, broadcast, etc.) according to one or multiple radio access technologies. In some implementations, an NE 102 may be moveable, for example, a satellite associated with a non-terrestrial network (NTN). In some implementations, different geographic coverage areas associated with the same or different radio access technologies may overlap, but the different geographic coverage areas may be associated with different NE 102.

[0046] The one or more UE 104 may be dispersed throughout a geographic region of the wireless communications system 100. A UE 104 may include or may be referred to as a remote unit, a mobile device, a wireless device, a remote device, a subscriber device, a transmitter device, a receiver device, or some other suitable terminology. In some implementations, the UE 104 may be referred to as a unit, a station, a terminal, or a client, among other examples. Additionally, or alternatively, the UE 104 may be referred to as an Internet-of- Things (loT) device, an Internet-of-Everything (loE) device, or machine-type communication (MTC) device, among other examples.

[0047] A UE 104 may be able to support wireless communication directly with other UEs 104 over a communication link. For example, a UE 104 may support wireless communication directly with another UE 104 over a device-to-device (D2D) communication link. In some implementations, such as vehicle-to-vehicle (V2V) deployments, vehicle-to-everything (V2X) deployments, or cellular-V2X deployments, the communication link may be referred to as a sidelink. For example, a UE 104 may support wireless communication directly with another UE 104 over a PC5 interface.

[0048] An NE 102 may support communications with the CN 106, or with another NE 102, or both. For example, an NE 102 may interface with other NE 102 or the CN 106 through one or more backhaul links (e.g., SI, N2, N2, or network interface). In some implementations, the NE 102 may communicate with each other directly. In some other implementations, the NE 102 may communicate with each other or indirectly (e.g., via the CN 106. In some implementations, one or more NE 102 may include subcomponents, such as an access network entity, which may be an example of an access node controller (ANC). An ANC may communicate with the one or more UEs 104 through one or more other access networktransmission entities, which may be referred to as a radio heads, smart radio heads, or transmission-reception points (TRPs).

[0049] The CN 106 may support user authentication, access authorization, tracking, connectivity, and other access, routing, or mobility functions. The CN 106 may be an evolved packet core (EPC), or a 5G core (5GC), which may include a control plane entity that manages access and mobility (e.g., a mobility management entity (MME), an access and mobility management functions (AMF)) and a user plane entity that routes packets or interconnects to external networks (e.g., a serving gateway (S-GW), a Packet Data Network (PDN) gateway (P-GW), or a user plane function (UPF)). In some implementations, the control plane entity may manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management (e.g., data bearers, signal bearers, etc.) for the one or more UEs 104 served by the one or more NE 102 associated with the CN 106.

[0050] The CN 106 may communicate with a packet data network over one or more backhaul links (e.g., via an SI, N2, N2, or another network interface). The packet data network may include an application server. In some implementations, one or more UEs 104 may communicate with the application server. A UE 104 may establish a session (e.g., a protocol data unit (PDU) session, or the like) with the CN 106 via an NE 102. The CN 106 may route traffic (e.g., control information, data, and the like) between the UE 104 and the application server using the established session (e.g., the established PDU session). The PDU session may be an example of a logical connection between the UE 104 and the CN 106 (e.g., one or more network functions of the CN 106).

[0051] In the wireless communications system 100, the NEs 102 and the UEs 104 may use resources of the wireless communications system 100 (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers)) to perform various operations (e.g., wireless communications). In some implementations, the NEs 102 and the UEs 104 may support different resource structures. For example, the NEs 102 and the UEs 104 may support different frame structures. In some implementations, such as in 4G, the NEs 102 and the UEs 104 may support a single frame structure. In some other implementations, such as in 5G and among other suitable radio access technologies, the NEs 102 and the UEs 104 may support various frame structures (i.e., multiple frame structures).The NEs 102 and the UEs 104 may support various frame structures based on one or more numerologies.

[0052] One or more numerologies may be supported in the wireless communications system 100, and a numerology may include a subcarrier spacing and a cyclic prefix. A first numerology (e.g., / r=0) may be associated with a first subcarrier spacing (e.g., 15 kHz) and a normal cyclic prefix. In some implementations, the first numerology (e.g., / r=0) associated with the first subcarrier spacing (e.g., 15 kHz) may utilize one slot per subframe. A second numerology (e.g., / r=l) may be associated with a second subcarrier spacing (e.g., 30 kHz) and a normal cyclic prefix. A third numerology (e.g., / r=2) may be associated with a third subcarrier spacing (e.g., 60 kHz) and a normal cyclic prefix or an extended cyclic prefix. A fourth numerology (e.g., / r=3) may be associated with a fourth subcarrier spacing (e.g., 120 kHz) and a normal cyclic prefix. A fifth numerology (e.g., / r=4) may be associated with a fifth subcarrier spacing (e.g., 240 kHz) and a normal cyclic prefix.

[0053] A time interval of a resource (e.g., a communication resource) may be organized according to frames (also referred to as radio frames). Each frame may have a duration, for example, a 10 millisecond (ms) duration. In some implementations, each frame may include multiple subframes. For example, each frame may include 10 subframes, and each subframe may have a duration, for example, a 1 ms duration. In some implementations, each frame may have the same duration. In some implementations, each subframe of a frame may have the same duration.

[0054] Additionally, or alternatively, a time interval of a resource (e.g., a communication resource) may be organized according to slots. For example, a subframe may include a number (e.g., quantity) of slots. The number of slots in each subframe may also depend on the one or more numerologies supported in the wireless communications system 100. For instance, the first, second, third, fourth, and fifth numerologies (i.e., / r=0, jU=l, / r=2, jU=3, / r=4) associated with respective subcarrier spacings of 15 kHz, 30 kHz, 60 kHz, 120 kHz, and 240 kHz may utilize a single slot per subframe, two slots per subframe, four slots per subframe, eight slots per subframe, and 16 slots per subframe, respectively. Each slot may include a number (e.g., quantity) of symbols (e.g., OFDM symbols). In some implementations, the number (e.g., quantity) of slots for a subframe may depend on anumerology. For a normal cyclic prefix, a slot may include 14 symbols. For an extended cyclic prefix (e.g., applicable for 60 kHz subcarrier spacing), a slot may include 12 symbols. The relationship between the number of symbols per slot, the number of slots per subframe, and the number of slots per frame for a normal cyclic prefix and an extended cyclic prefix may depend on a numerology. It should be understood that reference to a first numerology (e.g., / i =0) associated with a first subcarrier spacing (e.g., 15 kHz) may be used interchangeably between subframes and slots.

[0055] In the wireless communications system 100, an electromagnetic (EM) spectrum may be split, based on frequency or wavelength, into various classes, frequency bands, frequency channels, etc. By way of example, the wireless communications system 100 may support one or multiple operating frequency bands, such as frequency range designations FR1 (410 MHz - 7.125 GHz), FR2 (24.25 GHz - 52.6 GHz), FR3 (7.125 GHz - 24.25 GHz), FR4 (52.6 GHz - 114.25 GHz), FR4a or FR4-1 (52.6 GHz - 71 GHz), and FR5 (114.25 GHz - 300 GHz). In some implementations, the NEs 102 and the UEs 104 may perform wireless communications over one or more of the operating frequency bands. In some implementations, FR1 may be used by the NEs 102 and the UEs 104, among other equipment or devices for cellular communications traffic (e.g., control information, data). In some implementations, FR2 may be used by the NEs 102 and the UEs 104, among other equipment or devices for short-range, high data rate capabilities.

[0056] FR1 may be associated with one or multiple numerologies (e.g., at least three numerologies). For example, FR1 may be associated with a first numerology (e.g., / r=0), which includes 15 kHz subcarrier spacing; a second numerology (e.g., / r=l), which includes 30 kHz subcarrier spacing; and a third numerology (e.g., / r=2), which includes 60 kHz subcarrier spacing. FR2 may be associated with one or multiple numerologies (e.g., at least 2 numerologies). For example, FR2 may be associated with a third numerology (e.g., / r=2), which includes 60 kHz subcarrier spacing; and a fourth numerology (e.g., / r=3), which includes 120 kHz subcarrier spacing.

[0057] 3 GPP SA6 is the application enablement and critical communications applications group for vertical markets. The main objective of SA6 is to provide application layer architecture specifications for 3 GPP verticals, including architecture requirements andfunctional architecture for supporting the integration of verticals to 3 GPP systems. With respect to application enablement, the main focus is on enablers for vertical applications (e.g., automotive) and service frameworks (e.g. Common API Framework, Service Enabler Architecture Layer (SEAL), Edge Application enablement).

[0058] AD AES (Application Data Analytics Enablement Service), e.g. as described in3 GPP TR 23.700-36, is an enablement service (which can be part of SEAL) and discusses new potential application data analytics services (stats / predictions) to optimize the application service operation by notifying the application specific layer, and potentially 5GS, for expected / predicted application service parameters changes considering both on-network and off-network deployments (e.g., related to application QoS parameters)

[0059] One SEAL service which was defined in Rel-19 is AIML Enablement (AIMLE) service as described in 3GPP TS 23.482 and TS 23.434 is illustrated in Figure 2. Figure 2 illustrates an on-network AIMLE functional model of AIML enablement.

[0060] The devices shown in Figure 2 may be implemented by aspects of the wireless communications system 100 described herein with reference to Figure 1. For example, the UE 104 shown in Figure 2, may be an example of a UE 104 as described herein with reference to Figure 1. Furthermore, the 3 GPP system shown in Figure 2 may include one or more NE 102 and / or the CN 106 described herein with reference to Figure 1.

[0061] A UE 104 may comprise a UE modem and one or more of the following functionalities: an application client (e.g. a VAL client), an application enablement client, an edge enablement client, a SEAL client (e.g. an AIMLE client), a vertical application.

[0062] The UE 104 shown in Figure 2 comprises a vertical application layer (VAL) client 202, a SEAL client in the form of an AIMLE client 204, and a UE modem (not shown in Figure 2), and therefore may be termed a VAL UE. The VAL client 202 is a vertical application client, for example an loT application or a V2X application. In the VAL, the VAL client 202 communicates with the VAL server 206 over VAL-UU reference point. VAL-UU supports both unicast and multicast delivery modes. The AIMLE functional entities on the UE 104 and the server are grouped into AIMLE client(s) 204 and AIMLE server(s) 208 respectively.

[0063] The AIMLE server 208 is a type of SEAL server which includes a common set of services for comprehensive enablement of AIML functionality. The AIMLE server 208 defines or otherwise supports the following group of capabilities:Support for application-layer ML model related aspects, including model retrieval, model training, model monitoring, model selection, model update and model storage or discovery.Assistance in AI / ML task transfer and split AI / ML operations.Support HFL / VFL operations, including FL member registration, FL grouping and FL-related events notification, VFL feature alignment, HFL training.Support for AIMLE client registration, discovery, participation, and selection.

[0064] The AIMLE client 204 communicates with the AIMLE server(s) 208 over one or more AIML-UU reference points. The AIMLE client 204 provides functionality to the VAL client(s) 202 over AIML-C reference point. The VAL server(s) 206 communicate with the AIMLE server(s) 208 over AIML-S reference points. The AIMLE server(s) 208 communicate with the underlying 3 GPP network systems using the respective 3 GPP interfaces specified by the 3 GPP network system. The AIML-E reference point enables interactions between two AIMLE servers (e.g. central and edge AIMLE servers).

[0065] The AIMLE client 204 is a functional entity which acts as an application client supporting AIMLE services.

[0066] The AIMLE server 208 interacts with a ML repository 210 which serves as (i) a registry for ML / FL members (e.g. application layer entities participating in an AI / ML operation) and (ii) as a repository for application layer ML model related information.

[0067] The following functionality at AIMLE server is provided to support split AI / ML operation:An application consuming services from the AI / ML application enablement layer can discover or manage (e.g., create, update, delete) a split operation profile with the AIMLE server for the purpose of consuming results from corresponding instance of a split AI / ML operation pipeline.A VAL server can register with the AIMLE server to indicate its capabilities for acting as a processing node of an instance of a split AI / ML operation pipeline.An application consuming services from the AI / ML application enablement layer can subscribe with the AIMLE server to receive event notifications related to an instance of a split AI / ML operation pipeline.

[0068] Figure 3 illustrates an example execution of a multi-stage ML operation involving an end device and two network endpoints. In the example of Figure 3, the end device is performing a first stage of the multi-stage ML operation (e.g. a ML model training operation or a ML model inference operation) on input data, and the network endpoints are performing respective stages of the multi-stage ML operation based on the output of a previous stage such that a ML model is processed in sequential stages. It will be appreciated that a multistage ML operation can have two or more stages, and embodiments of the present disclosure are not limited to a multi-stage ML operation having three stages as shown in Figure 3.

[0069] In some embodiments of the present disclosure, a UE monitors an energy usage indicator and based on this monitoring detects a trigger event which indicates that an energy usage indicator has satisfied (e.g. reached), is expected to satisfy, or is predicted to satisfy a predetermined threshold (e.g. an energy usage limit) during execution of the multi-stage ML operation by a module on the UE. One example of an energy usage indicator is an energy credit level, and an example of an energy usage limit is an energy credit limit.

[0070] Energy related issues are considered in 5G core as a part of TR 23.700-66, which identifies enhancements including network energy related information exposure, subscription, and policy control to enable energy as service criteria to improve energy efficiency and to support energy saving in the network. Energy enhancements are also considering the use of renewable energy and control of carbon dioxide emissions. Energy as serving criteria can be applied considering different granularities including UE level, PDU session, QoS flow or application, slice, service, and network function (NF).

[0071] The energy credit level may be, or may be representative of, a quantity of credit associated with a subscriber that can be used for credit control by the 5 G system. In particular, energy credit can be associated to the following five concepts related to new energy events and energy event monitoring: a) the ability for the network operator to create a 'maximum energy credit' policy, after which services are gated,b) the ability for the network operator to inform an AS of the 'maximum energy credit expired' event, c) the ability for the 5G system to calculate 'energy credit' use, d) the ability to monitor and provide to the AS the use of 'energy credits' (or other energy 'quantum'), e) the support a new policy that establishes the energy consequence for charging control - either charging for use of energy or establishing an 'energy credit limit' for enforcement by the 5G system.

[0072] Energy credit control relates to comparing a first energy credit level (indicating energy usage) against a second energy credit limit (e.g., a threshold). The result of energy credit control may include, e.g., gating, increased charging rates, data throttling, or change of QoS class, etc.

[0073] The energy credit limit may be associated with a UE by the means of subscription, i.e., as a maximum energy credit limit. Energy credit can also be introduced in the context of a network slice, i.e., per UE per DNN for S-NSSAI level.

[0074] An energy credit limit can be calculated either by: (i) a new dedicated 5G core network function (NF) or (ii) a charging function (CHF) that is provided to the 5G core, where needed, e.g., Policy Control Function (PCF) or Session Management Function (SMF). The energy credit limit can be communicated to / from the 5G core to the respective Application Function (AF). Alternatively, the energy credit limit can be communicated to the UE by an SMS. For each UE an energy credit profile can be provisioned as a subscription information.

[0075] If a UE’s energy credit level has a reached zero or dropped to a predetermined level the PCF can take the policy decision e.g. to reject establishing a PDU Session for that UE, i.e., the PDU Session response shall include, e.g., rejection cause 'no energy credit'.

[0076] The energy credit limit (e.g. for an application or per UE) referred to herein may be defined in a similar manner as the term “energy credit” in the 5G core (e.g. as per TR 22.882 and TS 22.261); however embodiments of the present disclosure are not limited to this definition and the energy credit limit may be any form of energy usage allowance or budget for an application or aggregately for an application service provider for providing anapplication service for one or group of UEs or for a given service area (e.g. a multiplayer VR game).

[0077] The energy credit limit can be coupled with the charging of the application for utilizing the mobile communications system capabilities and in particular the energy demand for the user plane and control plane capabilities involved with the application. Such an energy credit limit may be configured by Service Level Agreement (SLA) or by the service agreement between the Mobile Network Operator (MNO) and the vertical / Application Service Provider (ASP).

[0078] As explained in more detail below, an energy credit level is merely an example of an energy usage indicator. In other implementations, the energy usage indicator may be an energy usage parameter (which may also be termed an energy consumption parameter), or an energy efficiency parameter, and the UE (or an application running on the UE) may be associated with a corresponding energy usage threshold, limit or target. The energy usage parameter may be expressed as the energy consumed for the application service(s) running at the UE in bit / J. Such usage or consumption can be calculated over a pre-defined time window, or from the time that the application started its operation, or from the instantiation of the application at the UE. The energy efficiency parameter may be expressed as a ratio of a performance metric (e.g. of an application service or UE application(s)) over the energy consumption or usage. The performance metric may be a traffic volume over a given time for the application.

[0079] In embodiments of the present disclosure, during execution of a stage of a multistage ML operation by a module on a UE, responsibility for execution of the stage may be optimally offloaded from the UE to another application entity (at an edge server, cloud server or other UE) based on a trigger event caused by energy usage of the UE, while ensuring that the performance requirements of the multi-stage ML operation are met. The energy usage of a UE comprises the energy usage of the constituent functionalities of the UE (UE modem functionalities, application clients, etc.) as well as the communication with the network for supporting the operation of such functionalities.

[0080] Embodiments of the present disclosure relate to the detection of a trigger event caused by energy usage of a UE that is involved in execution of a stage of a multi-stage ML operation, and the subsequent identification of one or more entities to offload the executionof this stage to. The cause of the update to the participant entities involved in the multi-stage ML operation may be a trigger event comprising an energy usage indicator (of the UE, of an application running on the UE, or of the multi-stage ML operation of which the UE is participating) having reached, being expected to reach, or being predicted to reach, a predetermined threshold during execution of the multi-stage ML operation. Responsive to detection of the trigger event, a module (e.g. an AIMLE client) on the UE may detect the need to modify the participant entities involved in the execution multi-stage ML operation, and in particular to offload execution of a stage of the multi-stage ML operation to one or more entities (e.g. an edge AIMLE server and / or another AIMLE client).

[0081] Figure 4 shows a process 400 for updating participant entities involved in a multistage ML operation in accordance with aspects of the present disclosure. The process 400 may, for example, be implemented within the architecture shown in Figure 2.

[0082] In advance of the process 400 being performed, several pre-conditions may be satisfied. In particular, (i) the AIMLE client 204 may have received information related to the multi-stage ML operation (e.g. a split ML operation pipeline profile as specified in clause 8.14.2.3 of TS 23.482); (ii) the VAL client 202 is aware of an energy usage threshold (e.g. an energy credit limit) for the VAL UE 104; and / or (iii) the AIMLE server 208 has provided in advance to AIMLE clients (e.g. the AIMLE client 204) a policy or configuration information for reporting trigger events related to energy status changes.

[0083] At optional step S402, the VAL client 202 sends a UE energy usage report to the AIMLE client 204 (via AIMLE-C API). The energy usage report may include a value for an energy usage indicator and / or an energy usage threshold associated with the UE 104 or an application running on the UE. For example, at step S402 the VAL client 202 may send a UE energy credit report to indicate the current status of the energy credit (remaining) and / or the maximum credit limit for the UE / application. The UE energy usage report may additionally or alternatively include an energy efficiency value or target, or an energy usage / consumption target associated with the UE 104 or an application running on the UE.

[0084] At step S404, the AIMLE client 204 detects a trigger event caused by energy usage of the UE 104. The trigger event may indicate that an energy usage indicator has satisfied (e.g. reached), is expected to satisfy, or is predicted to satisfy a predetermined threshold (e.g. an energy usage limit) during execution of a stage of the multi-stage MLoperation by the AIMLE client 204. Step S404 may be performed in a number of different ways. An energy usage indicator is referred to as being expected to satisfy (e.g. expected to reach) a predetermined threshold to mean that energy usage indicator is anticipated to reach the predetermined threshold imminently e.g. within a predetermined time period. Additionally, or alternatively, an energy usage indicator is referred to as being predicted to satisfy (e.g. predicted to reach) a predetermined threshold to mean that there is a prediction with a certain confidence level as output of an analytics function.

[0085] In one example, the AIMLE client 204 may detect the trigger event based on information conveyed in the UE energy usage report received at step S402.

[0086] Alternatively, or additionally, the AIMLE client 204 may detect the trigger event at step S402 based on monitoring the energy status at the UE 104. This can be done by monitoring the battery status, the application traffic schedule or application traffic pattern from an application, e.g. a VAL application, (this can be also detected locally if the AIMLE client 204 is used for the distribution of the application messages) or based on energy-related monitoring from the UE modem (up to implementation).

[0087] Alternatively, or additionally, the detection of the trigger event by the AIMLE client 204 at step S402 may be based on application layer AI / ML member capability Analytics (e.g. as described in TS 23.436 clause 8.16). This step requires (i) the addition of energy criteria (e.g. an energy usage indicator and / or an energy usage threshold) per VAL UE or VAL / AIMLE client in AD AES analytics service; and (ii) AIMLE client (directly or via AIMLE server or via VAL client) to be a consumer of such analytics.

[0088] In response to the detection of the trigger event, at step S406 the AIMLE client transmits information indicating the trigger event. In particular, the AIMLE client 204 sends an event trigger message to the AIMLE server 208. The information transmitted to the AIMLE server 208 at step S406 may indicate: (i) that an energy usage threshold (e.g. an energy credit limit) is expected to be reached; (ii) a high predicted or actual or expected energy usage indicator for the VAL UE or application, wherein the predicted / actual / expected energy usage indicator is (or is predicted or expected to be) higher that an energy usage threshold or within a threshold range from an energy usage limit; (iii) a low predicted or actual or expected energy credit for a UE or application, wherein the predicted / actual / expected energy credit is (or is predicted or expected to be) within athreshold range from a zero credit balance or less than a predefined credit balance; and / or (iv) a low predicted or actual or expected energy efficiency parameter, wherein the energy efficiency parameter is (or is predicted or expected to be) lower than an energy efficiency threshold.

[0089] Upon receiving the event trigger message from the AIMLE client 204, at step S408 the AIMLE server 208 identifies the multi-stage ML operation (e.g. split operation pipeline) for which the VAL UE 104 is applicable and determines whether the multi-stage ML operation needs to be updated based on a profile of the multi-stage ML operation (e.g. a split operation profile) that is associated with a unique identifier (e.g. a split operation pipeline identifier), and the energy status trigger. Optionally, the event trigger message may comprise the unique identifier of the multi-stage ML operation. The multi-stage ML operation has already been established with the support of the AIMLE server 208, hence the AIMLE server has the mapping of the VAL UE 104 and / or AIMLE client 204 with one or more existing multi-stage ML operation in which the UE is participating.

[0090] If the AIMLE server 208 determines that the multi-stage ML operation is to be updated (e.g. that the stage of the multi-stage ML operation being performed by the AIMLE client 204 should be continued by one or more alternative entity), the AIMLE server 208 updates the profile of the multi-stage ML operation and notifies the appropriate processing nodes about their inclusion or exclusion in the multi-stage ML operation (this may be performed as described in clause 8.14.2.5 of TS 23.482). The AIMLE server also notifies the already existing nodes about modification of the existing multi-stage ML operation (this may be performed as described in clause 8.14.2.5 of TS 23.482).

[0091] At step S408 the AIMLE server 208 determines to check alternative entities (e.g. AIMLE clients or AIMLE servers) to undertake the task and discovers candidate entities (e.g. AIMLE client(s) and / or other AIMLE server(s)) that may replace the AIMLE client 204 in performing the stage of the multi-stage ML operation. This may be performed based on the AIMLE capability called “Support for AIMLE client discovery” as described in TS 23.482 clause 8.8.2.

[0092] The list of AIMLE clients and AIMLE servers which are mapped to a certain ML model or model profile or ML operation (e.g. training) are registered and stored in the ML repository 210. So, the ML repository can be used to fetch information on candidate entitiesfor performing the stage of the multi-stage ML operation in place of the AIMLE client 204. For AIMLE servers in particular such information may be known at the AIMLE server 208 since it is assumed that there is an existing interface among AIMLE servers of the same operator. For the AIMLE servers, in certain embodiments the discovery may be based on CAPIF (common API framework) which supports API discovery.

[0093] The AIMLE server 208 obtains energy status information, e.g. an energy usage indicator and / or an energy usage threshold (e.g. an energy usage limit), of one or more of the candidate entities. This may be performed using a number of different methods which may be performed alone or in combination.

[0094] At step S408, the AIMLE server 208 may retrieve the energy status information of one or more of the candidate entities from the ML repository 210.

[0095] Alternatively, or additionally, at step S408, the AIMLE server 208 may receive the energy status information of one or more of the candidate entities from the candidate entities themselves.

[0096] As shown in Figure 4, at step S410 the AIMLE server 208 may transmit a request for energy status information of one or more VAL UEs having the respective discovered AIMLE clients, to an energy monitoring function 212. The energy monitoring function 212 may be an Energy Information Function (EIF) or other energy monitoring function at Operations, Administration and Maintenance (0AM) or application enablement layer. If the AIMLE server 208 interacts with a network function (NF) e.g. as EIF, then this is performed via the Network Exposure Function (NEF) or directly if AIMLE server 208 is in trusted operator’s domain. In response, at step S412 the AIMLE server 208 receives the energy status information for the one or more VAL UEs.

[0097] The AIMLE server 208 may additionally or alternatively retrieve the energy status information of one or more of the candidate entities from a charging function (e.g. a charging function in the network operator’s charging domain). The interaction with the charging function may be implemented when the AIMLE server 208 is deployed by the network operator. Alternatively, the AIMLE server 208 may obtain the energy status information from a charging domain from the service provider (e.g. platform provider, vertical).

[0098] At step S414, for candidate AIMLE servers e.g. deployed at an edge data network (DN), the AIMLE server 208 may consume the DN energy analytics service from AD AES (using the corresponding analytics service as in TS 23.436). Additionally for candidate AIMLE clients the AIMLE server 208 may also collect analytics by extending application layer AI / ML Member Capability Analytics (e.g. as described in TS 23.436 clause 8.16). Thus it can be seen that step S414 is an additional or alternative way of obtaining the energy status information that is based on analytics e.g. predictions or statistics.

[0099] At step S416, the AIMLE server 208 evaluates the candidate entities for their suitability to replace the AIMLE client 204 for performing the stage of the multi-stage ML operation. The AIMLE server 208 performs step S416 using the energy status information of the plurality of candidate entities and a required performance of the multi-stage machine learning operation (which may be defined in a profile associated with the multi-stage machine learning operation). At step S416, the AIMLE server 208 may rate and / or rank the plurality of candidate entities as part of the evaluation.

[0100] At step S418, the AIMLE server 208 determines one or more entities (from the plurality of candidate entities) to be selected (by the AIMLE server 208) or considered as an alternative to the AIMLE client 204 for becoming part of an updated multi-stage ML operation, based on the evaluation performed at step S416. For example, the AIMLE server 208 may determine the one or more entities to be selected or considered as an alternative to the AIMLE client 204 based on the rating and / or ranking assigned to the plurality of candidate entities at step S416.

[0101] At step S420 the AIMLE server 208 transmits a notification to the AIMLE client 204, the notification including an identifier of the determined one or more entities.

[0102] In embodiments in which at step S418 the AIMLE server 208 selects one or more entities (from the plurality of candidate entities) to replace the AIMLE client 204 for performing the stage of the multi-stage ML operation, the AIMLE server 208 updates the profile of the multi-stage ML operation accordingly (to remove the AIMLE client 204 as the entity performing the stage of the multi-stage ML operation and to include the selected one or more entities as performing the stage of the multi-stage ML operation), and the notification transmitted at step S420 may comprise the updated profile of the multi-stage ML operation.In these embodiments, the identifier of the selected one or more entities may be included in the updated profile of the multi-stage ML operation, or as a separate information element (IE). The identifier of the selected one or more entities may comprise a VAL UE ID, an AIMLE client ID, and / or an AIMLE server ID. The selection may be based on the rating and / or ranking assigned to each of the plurality of candidate entities at step S416. The selection may be based on the time and area for validity for the availability of the candidate entities. The selection may be based on an energy sustainability factor associated with each of the plurality of candidate entities. The energy sustainability factor may provide supplementary information identifying whether given a predicted UE route and traffic, the candidate entity will meet the requirements of the multi-stage ML operation.

[0103] In embodiments in which at step S418 the AIMLE server 208 selects one or more entities (from the plurality of candidate entities) to be considered for replacing the AIMLE client 204 for performing the stage of the multi-stage ML operation, the notification transmitted at step S420 includes an identifier of the one or more entities that are to be considered for replacing the AIMLE client 204. The identifier of the one or more entities that are to be considered for replacing the AIMLE client 204 may comprise a VAL UE ID, an AIMLE client ID, and / or an AIMLE server ID. The notification may further include a rating and / or ranking assigned to the one or more entities that are to be considered for replacing the AIMLE client 204 at step S416. The notification may further include the time and area for validity for the availability of the one or more entities that are to be considered for replacing the AIMLE client 204 and optionally whether this is based on prediction / analytics. The notification may further include an energy sustainability factor associated with each of the one or more entities that are to be considered for replacing the AIMLE client 204. In response to receiving the notification, the AIMLE client 204 may select one or more entities (from those identified in the notification) to replace the AIMLE client 204 for performing the stage of the multi-stage ML operation, and transmit a message to the AIMLE server 208 identifying the selected one or more entities (e.g. by including an identifier of the selected one or more entities). In response to receiving the message, the AIMLE server 208 may update the profile of the multi-stage ML operation accordingly (to remove the AIMLE client 204 as the entity performing the stage of the multi-stage ML operation and to include the selected one or more entities as performing the stage of the multi-stage ML operation).

[0104] It will be appreciated that the VAL client 202 may have a role in the selection of the one or more entities (from those identified in the notification) to replace the AIMLE client 204 for performing the stage of the multi-stage ML operation. For example, the AIMLE client 204 may inform the VAL client 202 of the entities identified in the notification, and the selection of the one or more entities (from those identified in the notification) may be jointly performed by the AIMLE client 204 and the VAL client 202. In another example, the selection of the one or more entities (from those identified in the notification) to replace the AIMLE client 204 for performing the stage of the multi-stage ML operation may be performed by the AIMLE client 204 after it has received confirmation of the selection by the VAL client 202.

[0105] The one or more entities selected to replace the AIMLE client 204 for performing the stage of the multi-stage ML operation may comprise one or more alternative AIMLE client and / or one or more AIMLE server.

[0106] The energy sustainability factor referred to herein may be useful for cases when the alternative entity (e.g. alternative AIMLE client or an AIMLE server) has a good rating (e.g., a rating greater than a threshold value) for the current time, however due to mobility and overload or poor channel conditions in future time instances its energy usage may be high, and the same issue may arise regarding the replacement of the AIMLE client 204 on UE 104. The energy sustainability factor ensures that the entity is good candidate not only for the near future, but till the end of the expected operation (so to make sure that it will fulfil the requirement).

[0107] At step S422, the AIMLE server 208 transmits identifiers of the entities which will be involved in performing the updated multi-stage ML operation (e.g. after replacement of the AIMLE client 204 with one or more alternative entities) to the ML repository 210. The AIMLE server 208 may also transmit energy status information (e.g. an energy usage indicator and / or an energy usage threshold) associated with the entities which will be involved in performing the updated multi-stage ML operation, to the ML repository 210.

[0108] Figure 5 shows a further process 500 for updating participant entities involved in a multi-stage ML operation in accordance with aspects of the present disclosure. The process 500 may, for example, be implemented within the architecture shown in Figure 2.

[0109] In advance of the process 500 being performed several pre-conditions may be satisfied. In particular, (i) the AIMLE client 204 may have received information related to the multi-stage ML operation (e.g. a split ML operation pipeline profile as specified in clause 8.14.2.3 of TS 23.482); and (ii) the VAL client 202 is aware of an energy usage threshold (e.g. an energy credit limit) for the VAL UE 104.

[0110] Optional step S502 corresponds to step S402 described with reference to Eigure 4. Step S504 corresponds to S404 described above.

[0111] In response to the detection of the trigger event at step S504, at step S506 the AIMLE client 204, which has commenced execution of a stage of a multi-stage ML operation, determines that the multi-stage ML operation is to be updated (e.g. that the stage of the multi-stage ML operation being performed by the AIMLE client 204 should be continued by one or more alternative entity). Thus it can be seen that in the process 500 it is the AIMLE client 204 which determines that the multi-stage ML operation is to be updated, in contrast to the process 400 in which the AIMLE server 208 determines that the multi-stage ML operation is to be updated. The VAL client 202 may have a role in the determination that the multi-stage ML operation is to be updated. For example, the determination that the multistage ML operation is to be updated may instead be performed by the VAL client 202 (e.g. after being informed of the event trigger), or the determination may be jointly performed by the AIMLE client 204 and the VAL client 202, or the determination may be performed by the AIMLE client 204 after it has received confirmation of the determination by the VAL client 202.

[0112] At step S508, the AIMLE client 204 transmits a request (e.g. a split operation pipeline update request) to the AIMLE server 208. The split operation pipeline update request includes an energy cause of the update to the multi-stage ML operation which indicates the trigger event. For example the split operation pipeline update request may indicate: (i) that an energy usage threshold (e.g. an energy credit limit) is expected to be reached; (ii) a high predicted or actual or expected energy usage indicator for the VAL UE or application, wherein the predicted / actual / expected energy usage indicator is (or is predicted or expected to be) higher that an energy usage threshold or within a threshold range from an energy usage limit; (iii) a low predicted or actual or expected energy credit for a UE or application, wherein the predicted / actual / expected energy credit is (or is predicted or expected to be) within athreshold range from a zero credit balance or less than a predefined credit balance; and / or (iv) a low predicted or actual or expected energy efficiency parameter, wherein the energy efficiency parameter is (or is predicted or expected to be) lower than an energy efficiency threshold).

[0113] The information which may be included in a split operation pipeline update request is shown below in Table 1. In the example of Table 1 , the energy cause of the update to the multi-stage ML operation is included as an IE of the split operation pipeline update request. It will be appreciated that Table 1 is merely an example and one or more IES of the split operation pipeline update request shown in Table 1 may be omitted.Table 1

[0114] Table 2 shows data which may be included in a profile of a multi-stage ML operation (split operation profile). In particular, Table 2 shows data which may be included in the split operation pipeline information of the split operation pipeline update request. As an alternative to including the energy cause of the update to the multi-stage ML operation as an IE of the split operation pipeline update request, the energy cause of the update to the multi-stage ML operation may be included in the split operation pipeline information. It will be appreciated that Table 2 is merely an example and one or more IEs of the profile of a multi-stage ML operation shown in Table 2 may be omitted.Table 2

[0115] Upon receiving the request from the AIMLE client, at step S510 the AIMLE server 208 validates if the requestor is authorized for the request. If the requestor is authorized, the AIMLE server 208 validates if the requested multi-stage ML operation can be updated based on the split operation pipeline identifier included in the request. If the requestor is authorized and a profile of a multi-stage ML operation (split operation profile) is determined, the AIMLE server 208 updates the profile of the multi-stage ML operation and notifies the appropriate processing nodes indicated in the request about their inclusion or exclusion in themulti-stage ML operation (this may be performed as described in clause 8.14.2.5 of TS 23.482). The AIMLE server 208 also notifies the already existing nodes about modification of the existing multi-stage ML operation (this may be performed as described in clause 8.14.2.5 of TS 23.482).

[0116] At step S510 the AIMLE server 208 determines to check alternative entities (e.g. AIMLE clients or AIMLE servers) to undertake the task and discovers candidate entities (e.g. AIMLE client(s) and / or other AIMLE server(s)) that may replace the AIMLE client 204 in performing the stage of the multi-stage ML operation. This may be performed based on the AIMLE capability called “Support for AIMLE client discovery” as described in TS 23.482 clause 8.8.2.

[0117] The AIMLE server 208 obtains energy status information, e.g. an energy usage indicator and / or an energy usage threshold (e.g. an energy usage limit), of one or more of the candidate entities. This may be performed using a number of different methods which may be performed alone or in combination.

[0118] At step S510, the AIMLE server 208 may retrieve the energy status information of one or more of the candidate entities from the ML repository 210.

[0119] Alternatively, or additionally, at step S510, the AIMLE server 208 may receive the energy status information of one or more of the candidate entities from the candidate entities themselves.

[0120] As shown in Figure 5, at step S512 the AIMLE server 208 may transmit a request for energy status information of one or more VAL UEs having the respective discovered AIMLE clients, to the energy monitoring function 212. The energy monitoring function 212 may be implemented by a network entity. If the AIMLE server 208 interacts with a network function (NF) e.g. as EIF, then this is performed via NEF or directly if AIMLE server is in trusted operator’s domain. In response, at step S514 the AIMLE server 208 receives the energy status information for the one or more VAL UEs.

[0121] The AIMLE server 208 may additionally or alternatively retrieve the energy status information of one or more of the candidate entities from a charging function (e.g. a charging function in the network operator’s charging domain). The interaction with the charging function may be implemented when the AIMLE server 208 is deployed by the networkoperator. Alternatively, the AIMLE server 208 may obtain the energy status information from a charging domain from the service provider (e.g. platform provider, vertical).

[0122] At step S516, for candidate AIMLE servers e.g. deployed at an edge data network (DN), the AIMLE server 208 may consume the DN energy analytics service from AD AES (using the corresponding analytics service as in TS 23.436). Additionally for candidate AIMLE clients the AIMLE server 208 may also collect analytics by extending application layer AI / ML Member Capability Analytics (e.g. as described in TS 23.436 clause 8.16). Thus it can be seen that step S516 is an additional or alternative way of obtaining the energy status information that is based on analytics e.g. predictions or statistics.

[0123] At step S518, the AIMLE server 208 evaluates the candidate entities for their suitability to replace the AIMLE client 204 for performing the stage of the multi-stage ML operation. The AIMLE server 208 performs step S518 using the energy status information of the plurality of candidate entities and a required performance of the multi-stage machine learning operation (which may be defined in a profile associated with the multi-stage machine learning operation). At step S518, the AIMLE server 208 may rate and / or rank the plurality of candidate entities as part of the evaluation.

[0124] At step S518, the AIMLE server 208 determines one or more entities (from the plurality of candidate entities) to be selected (by the AIMLE server 208) or considered as an alternative to the AIMLE client 204 for becoming part of an updated multi-stage ML operation, based on the evaluation performed. For example, the AIMLE server 208 may determine the one or more entities to be selected or considered as an alternative to the AIMLE client 204 based on the rating and / or ranking assigned to the plurality of candidate entities.

[0125] At step S520 the AIMLE server 208 transmits a notification (e.g. a split operation pipeline update notification message) to the AIMLE client 204, the notification including an identifier of the determined one or more entities.

[0126] In embodiments in which at step S518 the AIMLE server 208 selects one or more entities (from the plurality of candidate entities) to replace the AIMLE client 204 for performing the stage of the multi-stage ML operation, the AIMLE server 208 updates the profile of the multi-stage ML operation accordingly (to remove the AIMLE client 204 as the entity performing the stage of the multi-stage ML operation and to include the selected one or more entities as performing the stage of the multi-stage ML operation), and the notificationtransmited at step S520 may comprise the updated profile of the multi-stage ML operation. In these embodiments, the identifier of the selected one or more entities may be included in the updated profile of the multi-stage ML operation, or as a separate information element (IE). The identifier of the selected one or more entities may comprise a VAL UE ID, an AIMLE client ID, and / or an AIMLE server ID. The selection may be based on the rating and / or ranking assigned to each of the plurality of candidate entities at step S518. The selection may be based on the time and area for validity for the availability of the candidate entities. The selection may be based on an energy sustainability factor associated with each of the plurality of candidate entities. The energy sustainability factor may provide supplementary information identifying whether given a predicted UE route and traffic, the candidate entity will meet the requirements of the multi-stage ML operation.

[0127] In embodiments in which at step S518 the AIMLE server 208 selects one or more entities (from the plurality of candidate entities) to be considered for replacing the AIMLE client 204 for performing the stage of the multi-stage ML operation, the notification transmited at step S520 includes an identifier of the one or more entities that are to be considered for replacing the AIMLE client 204. The identifier of the one or more entities that are to be considered for replacing the AIMLE client 204 may comprise a VAL UE ID, an AIMLE client ID, and / or an AIMLE server ID. The notification may further include a rating and / or ranking assigned to the one or more entities that are to be considered for replacing the AIMLE client 204 at step S518. The notification may further include the time and area for validity for the availability of the one or more entities that are to be considered for replacing the AIMLE client 204 and optionally whether this is based on prediction / analytics. The notification may further include an energy sustainability factor associated with each of the one or more entities that are to be considered for replacing the AIMLE client 204. In response to receiving the notification, the AIMLE client 204 may select one or more entities (from those identified in the notification) to replace the AIMLE client 204 for performing the stage of the multi-stage ML operation, and transmit a message to the AIMLE server 208 identifying the selected one or more entities (e.g. by including an identifier of the selected one or more entities). In response to receiving the message, the AIMLE server 208 may update the profile of the multi-stage ML operation accordingly (to remove the AIMLE client 204 as the entityperforming the stage of the multi-stage ML operation and to include the selected one or more entities as performing the stage of the multi-stage ML operation).

[0128] It will be appreciated that the VAL client 202 may have a role in the selection of the one or more entities (from those identified in the notification) to replace the AIMLE client 204 for performing the stage of the multi-stage ML operation. For example, the AIMLE client 204 may inform the VAL client 202 of the entities identified in the notification, and the selection of the one or more entities (from those identified in the notification) may be jointly performed by the AIMLE client 204 and the VAL client 202. In another example, the selection of the one or more entities (from those identified in the notification) to replace the AIMLE client 204 for performing the stage of the multi-stage ML operation may be performed by the AIMLE client 204 after it has received confirmation of the selection by the VAL client 202.

[0129] The one or more entities selected to replace the AIMLE client 204 for performing the stage of the multi-stage ML operation may comprise one or more alternative AIMLE client and / or one or more AIMLE server.

[0130] At step S522, the AIMLE server 208 transmits identifiers of the entities which will be involved in performing the updated multi-stage ML operation (e.g. after replacement of the AIMLE client 204 with one or more alternative entities) to the ML repository 210. The AIMLE server 208 may also transmit energy status information (e.g. an energy usage indicator and / or an energy usage threshold) associated with the entities which will be involved in performing the updated multi-stage ML operation, to the ML repository 210.

[0131] Figure 6 illustrates an example of a UE 600 in accordance with aspects of the present disclosure. The UE 600 may include a processor 602, a memory 604, a controller 606, and a transceiver 608. The processor 602, the memory 604, the controller 606, or the transceiver 608, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.

[0132] The processor 602, the memory 604, the controller 606, or the transceiver 608, or various combinations or components thereof may be implemented in hardware (e.g., circuitry). The hardware may include a processor, a digital signal processor (DSP), anapplication-specific integrated circuit (ASIC), or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.

[0133] The processor 602 may include an intelligent hardware device (e.g., a general- purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof). In some implementations, the processor 602 may be configured to operate the memory 604. In some other implementations, the memory 604 may be integrated into the processor 602. The processor 602 may be configured to execute computer-readable instructions stored in the memory 604 to cause the UE 600 to perform various functions of the present disclosure.

[0134] The memory 604 may include volatile or non-volatile memory. The memory 604 may store computer-readable, computer-executable code including instructions when executed by the processor 602 cause the UE 600 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 604 or another type of memory. Computer-readable media includes both non- transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or specialpurpose computer.

[0135] In some implementations, the processor 602 and the memory 604 coupled with the processor 602 may be configured to cause the UE 600 to perform one or more of the functions described herein (e.g., executing, by the processor 602, instructions stored in the memory 604). For example, the processor 602 may support wireless communication at the UE 600 in accordance with examples as disclosed herein. The UE 600 may be configured to support a means for commencing execution of a stage of a multi-stage machine learning operation in co-ordination with one or more further entities; detecting a trigger event caused by energy usage of the UE; transmitting information indicating the trigger event; and receiving a notification, the notification including an identifier of one or more entities selected or to be considered for replacement of a module on the UE for execution of the stage of the multi-stage machine learning operation.

[0136] The controller 606 may manage input and output signals for the UE 600. The controller 606 may also manage peripherals not integrated into the UE 600. In some implementations, the controller 606 may utilize an operating system such as iOS®, ANDROID®, WINDOWS®, or other operating systems. In some implementations, the controller 606 may be implemented as part of the processor 602.

[0137] In some implementations, the UE 600 may include at least one transceiver 608. In some other implementations, the UE 600 may have more than one transceiver 608. The transceiver 608 may represent a wireless transceiver. The transceiver 608 may include one or more receiver chains 610, one or more transmitter chains 612, or a combination thereof.

[0138] A receiver chain 610 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 610 may include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 610 may include at least one amplifier (e.g., a low-noise amplifier (LNA)) configured to amplify the received signal. The receiver chain 610 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 610 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.

[0139] A transmitter chain 612 may be configured to generate and transmit signals (e.g., control information, data, packets). The transmitter chain 612 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM), frequency modulation (FM), or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM). The transmitter chain 612 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 612 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.

[0140] Figure 7 illustrates an example of a processor 700 in accordance with aspects of the present disclosure. The processor 700 may be an example of a processor configured toperform various operations in accordance with examples as described herein. The processor 700 may include a controller 702 configured to perform various operations in accordance with examples as described herein. The processor 700 may optionally include at least one memory 704, which may be, for example, an L1 / L2 / L3 cache. Additionally, or alternatively, the processor 700 may optionally include one or more arithmetic-logic units (ALUs) 706. One or more of these components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., buses).

[0141] The processor 700 may be a processor chipset and include a protocol stack (e.g., a software stack) executed by the processor chipset to perform various operations (e.g., receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) in accordance with examples as described herein. The processor chipset may include one or more cores, one or more caches (e.g., memory local to or included in the processor chipset (e.g., the processor 700) or other memory (e.g., random access memory (RAM), read-only memory (ROM), dynamic RAM (DRAM), synchronous dynamic RAM (SDRAM), static RAM (SRAM), ferroelectric RAM (FeRAM), magnetic RAM (MRAM), resistive RAM (RRAM), flash memory, phase change memory (PCM), and others).

[0142] The controller 702 may be configured to manage and coordinate various operations (e.g., signaling, receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) of the processor 700 to cause the processor 700 to support various operations in accordance with examples as described herein. For example, the controller 702 may operate as a control unit of the processor 700, generating control signals that manage the operation of various components of the processor 700. These control signals include enabling or disabling functional units, selecting data paths, initiating memory access, and coordinating timing of operations.

[0143] The controller 702 may be configured to fetch (e.g., obtain, retrieve, receive) instructions from the memory 704 and determine subsequent instruction(s) to be executed to cause the processor 700 to support various operations in accordance with examples as described herein. The controller 702 may be configured to track memory address ofinstructions associated with the memory 704. The controller 702 may be configured to decode instructions to determine the operation to be performed and the operands involved. For example, the controller 702 may be configured to interpret the instruction and determine control signals to be output to other components of the processor 700 to cause the processor 700 to support various operations in accordance with examples as described herein. Additionally, or alternatively, the controller 702 may be configured to manage flow of data within the processor 700. The controller 702 may be configured to control transfer of data between registers, arithmetic logic units (ALUs), and other functional units of the processor 700.

[0144] The memory 704 may include one or more caches (e.g., memory local to or included in the processor 700 or other memory, such RAM, ROM, DRAM, SDRAM, SRAM, MRAM, flash memory, etc. In some implementations, the memory 704 may reside within or on a processor chipset (e.g., local to the processor 700). In some other implementations, the memory 704 may reside external to the processor chipset (e.g., remote to the processor 700).

[0145] The memory 704 may store computer-readable, computer-executable code including instructions that, when executed by the processor 700, cause the processor 700 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. The controller 702 and / or the processor 700 may be configured to execute computer-readable instructions stored in the memory 704 to cause the processor 700 to perform various functions. For example, the processor 700 and / or the controller 702 may be coupled with or to the memory 704, the processor 700, the controller 702, and the memory 704 may be configured to perform various functions described herein. In some examples, the processor 700 may include multiple processors and the memory 704 may include multiple memories. One or more of the multiple processors may be coupled with one or more of the multiple memories, which may, individually or collectively, be configured to perform various functions herein.

[0146] The one or more ALUs 706 may be configured to support various operations in accordance with examples as described herein. In some implementations, the one or more ALUs 706 may reside within or on a processor chipset (e.g., the processor 700). In someother implementations, the one or more ALUs 706 may reside external to the processor chipset (e.g., the processor 700). One or more ALUs 706 may perform one or more computations such as addition, subtraction, multiplication, and division on data. For example, one or more ALUs 706 may receive input operands and an operation code, which determines an operation to be executed. One or more ALUs 706 be configured with a variety of logical and arithmetic circuits, including adders, subtractors, shifters, and logic gates, to process and manipulate the data according to the operation. Additionally, or alternatively, the one or more ALUs 706 may support logical operations such as AND, OR, exclusive-OR (XOR), not-OR (NOR), and not-AND (NAND), enabling the one or more ALUs 706 to handle conditional operations, comparisons, and bitwise operations.

[0147] The processor 700 may support wireless communication in accordance with examples as disclosed herein. The processor 700 may be configured to or operable to support a means for obtaining information indicating an trigger event caused by energy usage of a UE; determining, based on the information, that an entity on the UE involved in execution of a stage of a multi-stage machine learning operation in co-ordination with one or more further entities, is to be replaced; and determining one or more entities to be selected or considered for replacement of the module on the UE for execution of the stage of the multi-stage machine learning operation, using energy status information of the one or more entities.

[0148] In another example the processor 700 may be configured to or operable to support a means for commencing execution of a stage of a multi-stage machine learning operation in co-ordination with one or more further entities; detecting a trigger event caused by energy usage of the UE; outputting information indicating the trigger event; and obtaining a notification, the notification including an identifier of one or more entities selected or to be considered for replacement of a module on the UE for execution of the stage of the multistage machine learning operation.

[0149] Figure 8 illustrates an example of a NE 800 in accordance with aspects of the present disclosure. The NE 800 may include a processor 802, a memory 804, a controller 806, and a transceiver 808. The processor 802, the memory 804, the controller 806, or the transceiver 808, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as describedherein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.

[0150] The processor 802, the memory 804, the controller 806, or the transceiver 808, or various combinations or components thereof may be implemented in hardware (e.g., circuitry). The hardware may include a processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.

[0151] The processor 802 may include an intelligent hardware device (e.g., a general- purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof). In some implementations, the processor 802 may be configured to operate the memory 804. In some other implementations, the memory 804 may be integrated into the processor 802. The processor 802 may be configured to execute computer-readable instructions stored in the memory 804 to cause the NE 800 to perform various functions of the present disclosure.

[0152] The memory 804 may include volatile or non-volatile memory. The memory 804 may store computer-readable, computer-executable code including instructions when executed by the processor 802 cause the NE 800 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 804 or another type of memory. Computer-readable media includes both non- transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or specialpurpose computer.

[0153] In some implementations, the processor 802 and the memory 804 coupled with the processor 802 may be configured to cause the NE 800 to perform one or more of the functions described herein (e.g., executing, by the processor 802, instructions stored in the memory 804). For example, the processor 802 may support wireless communication at the NE 800 in accordance with examples as disclosed herein. The NE 800 may be configured to support a means for receiving information indicating a trigger event caused by energy usage of a UE; determining, based on the information, that a module on the UE involved inexecution of a stage of a multi-stage machine learning operation in co-ordination with one or more further entities, is to be replaced; and determining one or more entities to be selected or considered for replacement of the module on the UE for execution of the stage of the multistage machine learning operation, using energy status information of the one or more entities.

[0154] The controller 806 may manage input and output signals for the NE 800. The controller 806 may also manage peripherals not integrated into the NE 800. In some implementations, the controller 806 may utilize an operating system such as iOS®, ANDROID®, WINDOWS®, or other operating systems. In some implementations, the controller 806 may be implemented as part of the processor 802.

[0155] In some implementations, the NE 800 may include at least one transceiver 808. In some other implementations, the NE 800 may have more than one transceiver 808. The transceiver 808 may represent a wireless transceiver. The transceiver 808 may include one or more receiver chains 810, one or more transmitter chains 812, or a combination thereof.

[0156] A receiver chain 810 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 810 may include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 810 may include at least one amplifier (e.g., a low-noise amplifier (LNA)) configured to amplify the received signal. The receiver chain 810 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 810 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.

[0157] A transmitter chain 812 may be configured to generate and transmit signals (e.g., control information, data, packets). The transmitter chain 812 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM), frequency modulation (FM), or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM). The transmitter chain 812 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission overthe wireless medium. The transmitter chain 812 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.

[0158] Figure 9 illustrates a flowchart of a method in accordance with aspects of the present disclosure. The operations of the method may be implemented by a UE as described herein, in particular the AIMLE client 204 described herein. In some implementations, the UE may execute a set of instructions to control the function elements of the UE to perform the described functions.

[0159] At 902, the method may include commencing execution of a stage of a multistage machine learning operation in co-ordination with one or more further entities. The operations of 902 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 902 may be performed by a UE as described with reference to Figure 6.

[0160] At 904, the method may include detecting a trigger event caused by energy usage of the UE. The operations of 904 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 904 may be performed by a UE as described with reference to Figure 6.

[0161] At 906, the method may include transmitting information indicating the trigger event. The operations of 906 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 906 may be performed a UE as described with reference to Figure 6.

[0162] At 908, the method may include receiving a notification, the notification including an identifier of one or more entities selected or to be considered for replacement of a module on the UE for execution of the stage of the multi-stage machine learning operation. The operations of 908 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 908 may be performed a UE as described with reference to Figure 6.

[0163] It should be noted that the method described herein describes a possible implementation, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible.

[0164] Figure 10 illustrates a flowchart of a method in accordance with aspects of the present disclosure. The operations of the method may be implemented by a NE as described herein, in particular the AIMLE server 208 described herein. In some implementations, the NE may execute a set of instructions to control the function elements of the NE to perform the described functions.

[0165] At 1002, the method may include receiving information indicating a trigger event caused by energy usage of a UE. The operations of 1002 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1002 may be performed by a NE as described with reference to Figure 8.

[0166] At 1004, the method may include determining, based on the information, that a module on the UE involved in execution of a stage of a multi-stage machine learning operation in co-ordination with one or more further entities, is to be replaced. The operations of 1004 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1004 may be performed by a NE as described with reference to Figure 8.

[0167] At 1006, the method may include determining one or more entities to be selected or considered for replacement of the module on the UE for execution of the stage of the multistage machine learning operation, using energy status information of the one or more entities. The operations of 1006 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1006 may be performed a NE as described with reference to Figure 8.

[0168] It should be noted that the method described herein describes a possible implementation, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible.

[0169] The description herein is provided to enable a person having ordinary skill in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to a person having ordinary skill in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, thedisclosure is not limited to the examples and designs described herein but is to be accorded the broadest scope consistent with the principles and novel features disclosed herein.

Claims

CLAIMS1. A network entity for wireless communication, comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the network entity to: receive information indicating a trigger event caused by energy usage of a user equipment (UE); determine, based on the information, that a module on the UE involved in execution of a stage of a multi-stage machine learning operation in co-ordination with one or more further entities, is to be replaced; and determine one or more entities to be selected or considered for replacement of the module on the UE for execution of the stage of the multi-stage machine learning operation, using energy status information of the one or more entities.

2. The network entity of claim 1, wherein the trigger event indicates that an energy usage indicator has satisfied, is expected to satisfy, or is predicted to satisfy, a predetermined threshold during execution of the multi-stage machine learning operation.

3. The network entity of claim 2, wherein the at least one processor is further configured to cause the network entity to: identify a profile defining the multi-stage machine learning operation; and perform the determination that the module on the UE involved in execution of a stage of the multi-stage machine learning operation is to be replaced based on the trigger event and the profile.

4. The network entity of claim 2, wherein the information requests an update to the entities involved in execution of the multi-stage machine learning operation and comprises a profile defining the multi-stage machine learning operation.

5. The network entity of any preceding claim, wherein the at least one processor is further configured to cause the network entity to determine the one or more entities to be selected or considered for replacement of the module on the UE from a plurality of candidate entities using the energy status information of the plurality of candidate entities.

6. The network entity of claim 5, wherein the energy status information of the plurality of candidate entities comprises an energy usage indicator.

7. The network entity of claim 5 or 6, wherein the energy status information of the plurality of candidate entities comprises an energy usage threshold.

8. The network entity of any of claims 5 to 7, wherein the at least one processor is further configured to cause the network entity to retrieve the energy status information of at least one of the plurality of candidate entities from a repository.

9. The network entity of any of claims 5 to 8, wherein the at least one processor is further configured to cause the network entity to receive the energy status information of at least one of the plurality of candidate entities from the at least one of the plurality of candidate entities.

10. The network entity of any of claims 5 to 9, wherein the at least one processor is further configured to cause the network entity to receive the energy status information of at least one of the plurality of candidate entities from an energy monitoring function.

11. The network entity of any of claims 5 to 10, wherein the at least one processor is further configured to cause the network entity to assign a rating and / or ranking to each of the plurality of candidate entities using the energy status information of the plurality of candidate entities and a profile defining the multi-stage machine learning operation.

12. The network entity of any preceding claim, wherein the at least one processor is further configured to cause the network entity, in response to the determination of the one ormore entities to be selected for replacement of the module on the UE, to transmit a notification to the module on the UE, the notification including an identifier of the one or more entities.

13. The network entity of any of claims 1 to 11, wherein the at least one processor is further configured to cause the network entity, in response to the determination of the one or more entities to be considered for replacement of the module on the UE, to transmit a notification to the module on the UE, the notification including an identifier of the one or more entities.

14. The network entity of claim 13, wherein the notification further includes a rating and / or ranking assigned to each of the one or more entities using the energy status information.

15. The network entity of claim 13 or 14, wherein the at least one processor is further configured to cause the network entity to determine one or more entities selected for replacement of the module on the UE based on a message received from the module.

16. The network entity of any preceding claim, wherein the at least one processor is further configured to cause the network entity to transmit identifiers, of entities for execution of the multi-stage machine learning operation after replacement of the module on the UE, to a repository.

17. The network entity of claim 16, wherein the at least one processor is further configured to cause the network entity to transmit energy status information, of the entities for execution of the multi-stage machine learning operation after replacement of the module on the UE, to the repository.

18. A method performed by a network entity, the method comprising: receiving information indicating a trigger event caused by energy usage of a user equipment (UE);determining, based on the information, that a module on the UE involved in execution of a stage of a multi-stage machine learning operation in co-ordination with one or more further entities, is to be replaced; and determining one or more entities to be selected or considered for replacement of the module on the UE for execution of the stage of the multi-stage machine learning operation, using energy status information of the one or more entities.

19. A processor for wireless communication, comprising: at least one controller coupled with at least one memory and configured to cause the processor to: obtain information indicating an trigger event caused by energy usage of a user equipment (UE); determine, based on the information, that an entity on the UE involved in execution of a stage of a multi-stage machine learning operation in co-ordination with one or more further entities, is to be replaced; and determine one or more entities to be selected or considered for replacement of the module on the UE for execution of the stage of the multi-stage machine learning operation, using energy status information of the one or more entities.

20. A user equipment (UE) for wireless communication, comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the UE to: commence execution of a stage of a multi-stage machine learning operation in co-ordination with one or more further entities; detect a trigger event caused by energy usage of the UE; transmit information indicating the trigger event; andreceive a notification, the notification including an identifier of one or more entities selected or to be considered for replacement of a module on the UE for execution of the stage of the multi-stage machine learning operation.

Images