Positioning using a machine learning model

Abstract

A communication equipment (10) obtains different input datasets (22-1...22-N) that are respectively formed from results (21-1...21-N) of measurements on positioning signals (18) received by the communication equipment on different sets (20-1...20-N) of positioning signal resources (19). The communication equipment determines, from inputting each of the different input datasets into a machine learning model (12) deployed at the communication equipment, a respective estimate (24-1...24-N) that is output from the machine learning model. In some embodiments, each respective estimate comprises an estimation of a location of target equipment or an estimation of a result of a measurement from which the location of the target equipment is determinable. The target equipment may be the same as or different than the communication equipment. The communication equipment evaluates a performance of the machine learning model based on comparing the estimates that are output from the machine learning model for the different input datasets.

Description

[0001] POSITIONING USING A MACHINE LEARNING MODEL

[0002] TECHNICAL FIELD

[0003] The present application relates generally to positioning and relates more particularly to the use of a machine learning model for such positioning.

[0004] BACKGROUND

[0005] Machine learning (ML) -based positioning leverages the power of ML to improve the accuracy with which a target device’s position can be determined. For example, ML can be used to more accurately obtain signal measurements from which the target device’s position is estimated, and / or to more accurately estimate the target device’s position from those signal measurements.

[0006] The performance gains of ML-based positioning may however vary depending on a number of factors. For example, the performance gains realizable in any given scenario may depend on whether the underlying ML model was trained forthat scenario, e.g., an ML model trained to improve positioning of a target device in an outdoor environment may not provide the same performance gains when the target device is in an indoor environment. Monitoring the performance of an ML model in these and other situations thereby helps ensure the ML model remains effective and reliable for achieving its intended performance gains. For instance, if monitoring reveals an ML model’s performance has degraded, actions can be taken to remediate the degraded performance or fallback to traditional positioning approaches that do not leverage ML.

[0007] Monitoring ML model performance proves challenging, though. In the case where a communication device deploys an ML model for positioning, a communication network to which the communication device reports its location or measurements could remotely monitor the ML model’s performance. But this sort of remote ML model monitoring introduces inefficiencies in terms of latency, signaling overhead, and the like. A need therefore exists for self-monitoring of ML model performance local to the same node at which the ML model is deployed, without meaningfully compromising the efficiencies that such local monitoring would yield, e.g., without requiring external information or assistance from another node.

[0008] SUMMARY

[0009] Some embodiments herein enable communication equipment that deploys a machine learning (ML) model for positioning to itself evaluate the performance of that ML model. According to one or more embodiments in this regard, the communication equipment leverages signal measurements on different sets of positioning signal resourcesto form different input datasets into the ML model. The different sets of positioning signal resources may for example be associated with different transmission points and / or different positioning frequency layers. Regardless, equipped with these different input datasets, the communication equipment may input the input datasets into the ML model to obtain respective estimates that are output by the ML model and then evaluate the ML model’s performance based on how those estimates compare to one another, e.g., with performance being better the closer the estimates are to one another. Notably, by leveraging different sets of positioning signal resources in this way to form different input datasets, the communication equipment herein may advantageously self-monitor its ML model’s performance in an efficient way, e.g., without requiring external information or assistance from another node other than perhaps an indication of the positioning signal resources. Some embodiments may thereby advantageously improve ML-based positioning performance, while minimizing or reducing positioning latency and / or signaling overhead.

[0010] Moreover, in some embodiments, the communication equipment may indicate whether or not an estimate that it reports was determined from an ML model deployed at the communication equipment. In one or more such embodiments, this indication may effectively or implicitly indicate a performance of its ML model, e.g., as evaluated by the communication equipment based on comparison of different candidate estimates that are output by the ML model. For example, if the communication equipment was requested to report an estimate determined from the ML model, but the communication equipment instead reports an estimate that it indicates was not determined from its ML model, this may implicitly indicate that the communication equipment’s ML model has insufficient performance to meet the request.

[0011] More particularly, embodiments herein include a method performed by communication equipment. The method comprises obtaining different input datasets that are respectively formed from results of measurements on positioning signals received by the communication equipment on different sets of positioning signal resources. The method also comprises determining, from inputting each of the different input datasets into a machine learning model deployed at the communication equipment, a respective estimate that is output from the machine learning model. In some embodiments, each respective estimate comprises an estimation of a location of target equipment or an estimation of a result of a measurement from which the location of the target equipment is determinable. In some embodiments, the target equipment is the same as or different than the communication equipment. The method also comprises evaluating a performance of the machine learning model based on comparing the estimates that are output from the machine learning model for the different input datasets.Other embodiments herein include a communication equipment. The communication equipment is configured to obtain different input datasets that are respectively formed from results of measurements on positioning signals received by the communication equipment on different sets of positioning signal resources. The communication equipment is also configured to determine, from inputting each of the different input datasets into a machine learning model deployed at the communication equipment, a respective estimate that is output from the machine learning model. In some embodiments, each respective estimate comprises an estimation of a location of target equipment or an estimation of a result of a measurement from which the location of the target equipment is determinable. In some embodiments, the target equipment is the same as or different than the communication equipment. The communication equipment is also configured to evaluate a performance of the machine learning model based on comparing the estimates that are output by the machine learning model for the different input datasets.

[0012] Other embodiments herein include a method performed by communication equipment. The method comprises receiving assistance data indicating different sets of positioning signal resources on which the communication equipment is to perform measurements for locating target equipment. In some embodiments, the target equipment is the same as or different than the communication equipment. The method also comprises receiving a request for an estimate comprising an estimation of a location of the target equipment or an estimation of a result of a measurement from which the location of the target equipment is determinable. In some embodiments, the request requests that the estimate be determined from a machine learning model deployed at the communication equipment and from results of measurements on positioning signals received by the communication equipment on the different sets of positioning signal resources. The method also comprises transmitting a response to the request. In some embodiments, the response includes the estimate and an indication of whether or not the estimate included in the response was determined from the machine learning model deployed at the communication equipment.

[0013] Other embodiments herein include a communication equipment. The communication equipment is configured to receive assistance data indicating different sets of positioning signal resources on which the communication equipment is to perform measurements for locating target equipment. In some embodiments, the target equipment is the same as or different than the communication equipment. The communication equipment is also configured to receive a request for an estimate comprising an estimation of a location of the target equipment or an estimation of a result of a measurement from which the location of the target equipment is determinable. In some embodiments, the request requests that the estimate be determined from a machine learning model deployed at the communicationequipment and from results of measurements on positioning signals received by the communication equipment on the different sets of positioning signal resources. The communication equipment is also configured to transmit a response to the request. In some embodiments, the response includes the estimate and an indication of whether or not the estimate included in the response was determined from the machine learning model deployed at the communication equipment.

[0014] Embodiments herein also include corresponding computer programs and carriers of those computer programs.

[0015] BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a block diagram of communication equipment according to certain embodiments.

[0017] Figures 2A-2D illustrate block diagrams of transmission reception points (TRPs) and positioning frequency layers (PFLs) according to some embodiments.

[0018] Figures 3A-3C illustrate block diagrams of how estimates that are output from an ML model may compare according to various embodiments.

[0019] Figures 4A-4C illustrate block diagrams of how estimates that are output from an ML model may compare according to other embodiments.

[0020] Figure 5 is a block diagram of communication equipment according to other embodiments.

[0021] Figure 6 is a block diagram of communication equipment in the form of a communication device configured to receive service from a communication network according to certain embodiments.

[0022] Figure 7 is a block diagram of a relationship between PFLs and TRPs according to certain embodiments.

[0023] Figure 8 is a block diagram of model inputs used to produce a set of estimates that are output by a machine learning, ML, model according to some embodiments.

[0024] Figures 9A-9B depict a method performed by communication equipment in accordance with particular embodiments.

[0025] Figure 10 depicts a method performed by communication equipment in accordance with other particular embodiments.

[0026] Figure 11 is a block diagram of communication equipment according to some embodiments.

[0027] Figure 12 is a block diagram of a communication system according to some embodiments.

[0028] Figure 13 is a block diagram of a communication system according to other embodiments.Figure 14 is a block diagram of a wireless device according to some embodiments. Figure 15 is a block diagram of a network node according to other embodiments. Figure 16 is a block diagram of a virtualization environment according to other embodiments.

[0029] DETAILED DESCRIPTION

[0030] Figure 1 shows communication equipment 10 according to some embodiments herein. The communication equipment 10 may take the form of a communication device, e.g., configured to receive service from a communication network. Or, the communication equipment 10 may be a network node of such a communication network that is configured to provide service to communication device(s). Either way, a machine learning (ML) model 12 is deployed at the communication equipment 10 for positioning of target equipment 14, which may be the same as or different than communication equipment 10. The communication equipment 10 in some embodiments leverages the ML model 12 for estimating a location 14L of the target equipment 14 directly. In other embodiments, the communication equipment 10 leverages the ML model for estimating results of measurement(s) from which the location 14L of the target equipment 14 is determinable, e.g., by another node (not shown) to which the communication equipment 10 reports the measurement result(s) as part of assisting the other node to position the target equipment 14.

[0031] According to some embodiments herein, the communication equipment 10 itself evaluates the performance 28 of its ML model 12, i.e., locally at the communication equipment 10. The communication equipment 10 may for instance evaluate the ML model’s performance 28 in terms of whether, or to what extent, estimate(s) output from the ML model 12 are precise and / or accurate. The communication equipment 10 may evaluate the ML model’s performance 28 in this or other respects occasionally, periodically, or otherwise on an ongoing basis overtime, e.g., as part of performing self-monitoring of and / or self-validation of the ML model’s performance 28. This way, an action controller 30 of the communication equipment 10 can decide whether or not to perform remedial action(s) to address any problem(s) with the ML model’s performance 28. For example, based on the communication equipment’s own evaluation revealing a problem with the ML model’s performance, the action controller 30 may decide to update or retrain the ML model 12, switch to using a different ML model, or switch to a different positioning method that does not use any ML model.

[0032] To evaluate the performance of its ML model 12, the communication equipment 10 receives positioning signals 18. A positioning signal 18 as used herein may be any type of signal that supports positioning. For example, a positioning signal 18 may be a PositioningReference Signal (PRS), where a PRS is a reference signal dedicated for supporting positioning, e.g., as specified in 3GPP TS 36.211 V18.0.1 orTS 38.211 v18.3.0. As another example, a positioning signal 18 may be a Sounding Reference Signal (SRS), which is a reference signal usable for channel estimation as well as for supporting positioning, e.g., as also specified in 3GPP TS 36.211 V18.0.1 or TS 38.211 v18.3.0.

[0033] The communication equipment 10 receives these positioning signals 18 on different sets 20-1...20-N of positioning signal resources 19, e.g., as indicated by assistance data that the communication equipment 10 receives. The different sets 20-1...20-N of positioning signal resources 19 may for example be different sets of PRS resources or different SRS resources, e.g., depending on whether the positioning signals 18 are PRS or SRS. In some embodiments, the positioning signals 18 received on different sets 20-1 ...20-N of positioning signal resources 19 are received from different transmission points (e.g., different transmission reception points, TRPs), are received on different frequency carriers, and / or belong to different positioning frequency layers (PFLs), e.g., such that the different sets 20-1...20-N of positioning signal resources 19 are associated with different respective transmission points, different respective frequency carriers, and / or different respective PFLs. Figures 2A-2D illustrate various embodiments in this regard as examples.

[0034] As shown in Figure 2A, one or more TRPs 15-1 ...15-X may transmit positioning signals 18, for X > 1. Each TRP 15-x may transmit those positioning signals 18 on one or more PFLs 17-1 ...17-Y, for Y > 1. A positioning frequency layer 17-y herein refers to one or more sets of positioning signal resources 19 (e.g., PRS resources) on a carrier frequency whereby each set within the positioning frequency layer 17-y shares common configuration parameters, e.g., according to 3GPP TS 38.214 v18.5.0. A single carrier frequency may support multiple different positioning frequency layers, each with different configuration parameters. Different positioning frequency layers 17-1 ...17-Y may for example have different time-frequency resource allocations, e.g., which may enable flexibility and / or target positioning in varied deployment scenarios.

[0035] In this context, the example of Figure 2B shows some embodiments where at least some positioning signals 18 received on different sets 20-1...20-Y of positioning signal resources 19 are received from the same (single) TRP but belong to different PFLs 17-1 ...17-Y, e.g., where N=Y in this example. More particularly in this example, at least some of the positioning signals 18 received on different sets 20-1...20-Y of positioning signal resources 19 are received from the same transmission point 15-x, but those different sets 20-1 ...20-Y of positioning signal resources 19 belong to different positioning frequency layers 17-1...17-Y. That is, set 20-1 belongs to PFL 17-1 , set 20-2 belongs to PFL 17-2, set 20-3 belongs to PFL 17-3, and so on, even though the positioning signals 18 received across those sets 20-1...20-Y are received from the same TRP 15-x.The example of Figure 2C by contrast shows an example of other embodiments where at least some positioning signals 18 received on different sets 20-1...20-Y of positioning signal resources 19 are received from the same set 15S of multiple TRPs 15-1 ...15-X but belong to different PFLs 17-1...17-Y, e.g., where N=Y in this example. More particularly in this example, at least some of the positioning signals 18 received on different sets 20-1...20-Y of positioning signal resources 19 are received from the same set 15S of TRPs 15-1 ...15-X. Indeed, as shown, positioning signals 18 received on set 20-1 are received from a set 15S of TRPs that includes TRPs 15-1 ...15-X, positioning signals 18 received on set 20-2 are received from that same set 15S of TRPs 15-1...15-X, and so on. But, those different sets 20-1 ...20-Y of positioning signal resources 19 belong to different respective positioning frequency layers 17-1...17-Y, i.e., set 20-1 belongs to PFL 17-1, set 20-2 belongs to PFL 17-2, etc.

[0036] The example of Figure 2D shows an example of still other embodiments where at least some positioning signals 18 received on different sets 20-1...20-Y of positioning signal resources 19 are received from different sets of TRPs 15-1...15-X and belong to different PFLs 17-1...17-Y. More particularly in this example, positioning signals 18 received on positioning signal resources 20-1 , 20-2 are received from different sets 15S-1 , 15S-2 of TRPs 15-1 ...15-X and belong to different positioning frequency layers 17-1 and 17-2.

[0037] Indeed, positioning signals 18 received on set 20-1 of positioning signal resource 19 are received from a set 15S-1 of TRPs that includes TRPs 15-1 and 15-2 and the that set 20-1 of positioning signal resources 19 belongs to positioning frequency layer 17-1. By contrast, positioning signals 18 received on set 20-2 of positioning signal resources 19 are received from a set 15S-2 of TRPs that includes TRPs 15-3 to 15-X and that set 20-2 of positioning signal resources 19 belongs to positioning frequency layer 17-2.

[0038] In these and other embodiments, the positioning signals 18 received on different sets 20-1...20-N of positioning signal resources 19 may be received in parallel (e.g., at substantially the same time) or successively in series (e.g., at different times). Either way, the communication equipment 10 notably leverages receipt of positioning signals 18 on these different sets 20-1...20-N of positioning signal resources 19 (e.g., associated with different transmission points and / or PFLs) as an opportunity to itself evaluate the ML model’s performance. Notably, by leveraging different sets 20-1...20-N of positioning signal resources 19 in this way, the communication equipment 10 herein may advantageously self-monitor its ML model’s performance 28 in an efficient way, e.g., without requiring external information or assistance from another node other than perhaps an indication of the positioning signal resources 19. Some embodiments may thereby advantageously improve ML-based positioning performance, while minimizing or reducing positioning latency and / or signaling overhead.More specifically, the communication equipment 10 performs measurements on the positioning signals 18 that are received on the different sets 20-1...20-N of positioning signal resources 19. A measurement herein may directly measure the location 14L of the target equipment 14, or may measure some other metric that is usable for determining the location 14L of the target equipment 14. With the target equipment’s location 14L being directly or indirectly determinable from a measurement, a measurement herein may also generally be referred to as a positioning measurement.

[0039] From the results 21-1 ...21-N of these measurements, the communication equipment 10 forms different respective input datasets 22-1...22-N. As shown in Figure 1 , for example, the communication equipment 10 forms input dataset 22-n from the results 21 -n of measurements on positioning signals 18 received on set 20-n of positioning signal resource(s) 19, for 1 < n < N. The communication equipment 10 may thereby separate the results 21-1 ...21-N of the measurements into different input datasets 22-1 ...22-N, based on which of the sets 20-1 ...20-N of positioning signal resources 19 those measurements were performed on.

[0040] The communication equipment 10 inputs each of these input datasets 22-1...22-N into the ML model 12. The ML model 12 in turn outputs estimates 24-1...24-N that respectively correspond to (e.g., are a function of) the input datasets 22-1 ...2-N. That is, the ML model 12 outputs estimate 24-n corresponding to input dataset 22-n, for 1 < n < N. In some embodiments, for example, the communication equipment 10 inputs each of the input datasets 22-1 ...22-N into the ML model 12 separately and / or successively, so that the ML model 12 correspondingly outputs the respective estimates 24-1 ...24-N separately and / or successively. In other embodiments, by contrast, the communication equipment 10 inputs each of the input datasets 22-1...22-N into a respective mirror image of the ML model 12 in parallel, so that the mirror images of the ML model 12 correspondingly output the respective estimates 24-1 ...24-N in parallel. In these and other embodiments, the estimate 24-n output for input dataset 22-n may be a function of that input dataset 22-n but not a function of any other input dataset 22-m, for m n. Either way, the communication equipment 10 effectively determines, from inputting each of the different input datasets 22-1 ...22-N into the ML model 12, a respective estimate 24-1...24-N that is output from the ML model 12.

[0041] In some embodiments, each respective estimate 24-1 ...24-N is an estimation of the location 14L of the target equipment 14. In other embodiments, each respective estimate 24-1 ...24-N is an estimation of a result of a measurement from which the location 14L of the target equipment 14 is determinable, e.g., by the communication equipment 10 itself or by other equipment not shown. Either way, in some embodiments, each estimate

[0042] 24-1 ...24-N output from the ML model 12 may be or reflect an inference that the ML model12 makes from a respective input dataset 22-1 ...22-N, e.g., an inference about the target equipment’s location 14L or about a measurement from which that location 14L is determinable, in view of underlying patterns or characteristics of data within each input dataset 22-1 ...22-N. In other embodiments, each estimate 24-1...24-N output from the ML model 12 may be or reflect a prediction that the ML model 12 makes from a respective input dataset 22-1 ...22-N, e.g., a prediction forecasting the target equipment’s location 14L or forecasting a measurement from which that location 14L is determinable.

[0043] Regardless, the communication equipment 10 notably implements performance evaluation 26 using the estimates 24-1 ...24-N output from the ML model 12. In some embodiments in this regard, performance evaluation 26 evaluates the performance of the ML model 12 based on comparing the estimates 24-1 ...24-N that are output from the ML model 12 for the different input datasets 22-1...22-N. For example, performance evaluation 26 may evaluate the performance of the ML model 12 based on how close the estimates 24-1 ...24-N output forthe different input datasets 22-1 ...22-N are to one another. In one such embodiment, the closer the estimates 24-1...24-N are to one another, the better the performance of the ML model 12. For instance, the communication equipment 10 may determine that the ML model 12 has a first level of performance if any pair of estimates 24-1 ...24-N output for different input datasets 22-1...22-N differ from one another by at least a threshold amount, but determine that the ML model 12 has a second level of performance if each pair of estimates 24-1 ...24-N output for different input datasets 22-1 ...22-N differ from one another by less than the threshold amount. Although exemplified for two levels of performance, though, two or more different levels of performance may be defined by one or more threshold amounts, e.g., as indicated by signaling that the communication equipment 10 receives from another node.

[0044] Figures 3A-3C illustrate an example of this for one pair of estimates 24-1 , 24-2, where each estimate 24-1, 24-2 is an estimation of a location 14L of the target equipment 14. As shown, performance evaluation 26 reveals the ML model 12 experiences Performance Level 1 if the distance D between the estimates 24-1 , 24-2 is less than threshold TH1 (Figure 3A), Performance Level 2 if the distance D between the estimates 24-1 , 24-2 is more than threshold TH1 but less than threshold TH2 (Figure 3B), and Performance Level 3 if the distance D between the estimates 24-1 , 24-2 is more than threshold TH2 but less than threshold TH3 (Figure 3C).

[0045] Figures 4A-4C illustrate another example of this for another pair of estimates 24-1 , 24-2, where each estimate 24-1, 24-2 includes an estimation of a location 14L of the target equipment 14 along with an uncertainty area associated with that estimated location. As shown, performance evaluation 26 reveals the ML model 12 experiences Performance Level 1 if the uncertainty areas overlap by at least a threshold amount TH1 , e.g., implying that theML model 12 is performing well (Figure 4A). On the other hand, performance evaluation 26 may reveal the ML model 12 experiences Performance Level 2 if the uncertainty areas overlap by less than the threshold amount TH1 but more than threshold TH2 (Figure 4B). And performance evaluation 26 may reveal the ML model 12 experiences Performance Level 3 if the uncertainty areas overlap by less than threshold TH3 or not at all, e.g., implying that the ML model 12 is not performing well at all (Figure 4C).

[0046] In these and other embodiments, the action controller 30 may decide whether to perform one or more actions, and / or decide which one or more actions to perform, depending on what level of performance 28 the ML model 12 has or is experiencing. For example, if the ML model 12 is experiencing a first level of performance, the action controller 30 may decide not to perform any action and / or to continue to use the ML mode 12 in its current state for positioning. By contrast, if the ML mode 12 is experiencing a second level of performance lower than the first level, the action controller 30 may decide to update or retrain the ML model 12. Or, if the ML model 12 is experiencing a third level of performance lower than the first level and / or the second level, the action controller 30 may decide to switch to using a different ML model altogether. Or, if the ML model 12 is experiencing a fourth level of performance lower than the first, second, and / or third level, the action controller 30 may decide to fall back to using a different positioning method that does not rely on any ML model.

[0047] Generally in some embodiments, then, the communication equipment 10 may enforce a requirement that the ML model 12 have at least some minimum level of performance 28 in order forthe communication equipment 10 to use the ML model 12, e.g., where this minimum level of performance may be indicated by signaling received from another node. The minimum level of performance in this case may for instance be specified in terms of a maximum allowable amount by which respective estimates 24-1...24-N that are output by the ML model 12 forthe different sets 20-1...20-N of positioning signal resources 19 can differ from one another in order for the ML mode 12 to be used.

[0048] In these and other embodiments where use of the ML model 12 is conditioned on its performance, the communication equipment 10 may indicate whether or not it uses the ML model 12. Figure 5 illustrates one such embodiment which may be implemented separately from or in combination with the embodiment in Figure 1.

[0049] As shown in Figure 5, the communication equipment 10 receives a request 32 for an estimate 24, e.g., from another node not shown. The estimate 24 requested may be an estimate of the location 14L of the target equipment 14 or an estimate of a result of a measurement from which the location 14L of the target equipment 14 is determinable. In some embodiments, the request 32 requests that the estimate 24 be determined from the results of measurements on positioning signals 18 received by the communicationequipment 10 on one or more of the different sets 20-1...20-N of positioning signal resources 19. The request 32 may for instance include, be based on, or otherwise accompany assistance data 31 that indicates (e.g., via resource indication 33) the different sets 20-1...20-N of positioning signal resources 19 on which the communication device 10 is to perform measurements for locating the target equipment 14. Regardless, the request 32 requests that the estimate 24 be determined from the ML model 12 deployed at the communication equipment 10. The request 32 may for instance include an ML-based indication 34 that indicates the estimate 24 is to be an ML-based estimate determined from the ML model 12.

[0050] The communication equipment 10 in some embodiments returns a response 36 to the request 32 that includes not only the estimate 24 requested but also an indication 38 of whether or not the estimate 24 was determined from the ML model 12. That is, the indication 38 may effectively indicate whether or not the communication equipment 10 was able to accommodate the request that the estimate 24 be determined from the ML model 12. If the indication 38 indicates that the estimate 24 was not determined from the ML model 12, the response 36 in some embodiments may explicitly or implicitly indicate a reason why the estimate 24 was not determined from the ML model 12. The reason may for instance be a problem with the performance 28 of the ML model 12, e.g., as evaluated by the communication equipment 10 itself as described with respect to Figure 1. The problem may for example be that respective estimates 24-1...24-N that are output by the ML model 12 for the different sets 20-1 ...20-N of positioning signal resources 19 are not close enough together, e.g., to meet the minimum level of performance 28 required to use the ML model 12. In these and other embodiments, then, the indication 38 in the communication equipment’s response 36 may explicitly or implicitly indicate the performance 28 of the ML model 12 as evaluated by the communication equipment 10, e.g., based on a comparison of respective estimates 24-1 ...24-N that are output by the ML model 12 for different input datasets 22-1...22-N formed from the results of measurements on the different sets 20-1...20-N of positioning signal resources 19.

[0051] In some embodiments such as these where the communication equipment 10 needs to both determine an estimate 24 and evaluate the performance 28 of the ML model 12, the communication equipment 10 may effectively split or partition the positioning signal resources 19 as needed to do both. For example, from among the positioning signal resources 19 indicated by the assistance data 31 as being available for use by the communication equipment 10, the communication equipment 10 may select different subsets of those positioning signal resources 19 for use in different purposes. For example, the communication equipment 10 may select a first subset of the positioning signal resources 19 as positioning signal resources 19 on which to perform measurementsfor locating the target equipment 14 using the ML model 12, i.e., for determining the estimate 24 to report in its response 36 for such an estimate 24. By contrast the communication equipment 10 may select a second subset of the positioning signal resources 19 as positioning signal resources on which to evaluate the performance 28 of the ML model 12, e.g., as positioning signal resources 19 in the different sets 20-1...20-N of positioning signal resources 19. The communication equipment 10 in some embodiments may autonomously select such subsets on its own, whereas in other embodiments the communication equipment 10 may perform subset selection in accordance with configuration signaling (not shown) that governs how the communication equipment 10 is to perform the selection and / or that governs which subset is to be used for which purpose. In these latter embodiments, for instance, the communication equipment 10 may receive signaling indicating which of the positioning signal resources 19 are usable for determining the estimate 24 and / or which of the positioning signal resources 19 are usable for evaluating the performance 28 of its ML model 12.

[0052] Consider as an example a scenario where the communication equipment 10 is static, or the environment within which the communication equipment 10 is located does not change much. In this case, ML model performance monitoring may not need to be performed frequently. The communication equipment 10 can resort to periodic performance monitoring in some embodiments. Depending on the need, the gap between two performance checks can either be short or long.

[0053] When the communication equipment 10 is in a dynamic environment, by contrast, the communication equipment 10 may need to perform more frequent ML model performance monitoring. In this type of situation, the communication equipment 10 may split the positioning signal resources 19 into two sets, and use measurements from one set to infer its location and measurements from the other set to validate the performance of its ML model 12. This may advantageously allow the communication equipment 10 to infer its location and validate the performance of its ML model 12 in a single go.

[0054] In still other embodiments, though, the communication equipment 10 may partition the positioning signal resources 19 into multiple subsets, but use both subsets for each purpose. That is, the communication equipment 10 in some embodiments may use each subset both for determining the estimate 24 to report and for evaluating the performance 28 of the ML model 12.

[0055] Consider now some embodiments herein as exemplified in a context for positioning in a communication network. The communication network may be a 3GPP-based network such as a Long Term Evolution (LTE) network or a New Radio (NR) network.

[0056] In one or more such embodiments shown in Figure 6, the communication equipment 10 herein is a communication device 10D configured to receive service from acommunication network 50. The communication device 10D may for instance be a user equipment (UE). In these embodiments, the communication device 10D may receive positioning signals 18 in the form of downlink positioning signals, e.g., downlink PRS, and perform downlink positioning measurements on those positioning signals 18. Moreover, in some embodiments, the target equipment 14 is the communication device 10D itself, such that the communication device 10D uses its ML model 12 to obtain estimates 24-1...24-N that are estimates of downlink positioning measurements to be reported to a location server 52 (e.g., a Location Management Function, LMF) or that are estimates of its own location 14L.

[0057] In some embodiments where the communication network 50 is an NR network and the positioning signals 18 are PRS, configuration of the PRS follows a hierarchy that allows a network node such as LMF to provide assistance data in a structured format to enable the communication device 10D to unambiguously locate PRS resources 19 from different TRPs and / or different PFLs to perform positioning measurements on. PRS resources in this case can be configured to be transmitted in up to K positioning frequency layers from the same TRP, where PRS resources from the same PLF can be configured to up to L TRPs. Figure 7 shows one example where K=4 and L=64.

[0058] In some embodiments, the location server 52 may signal assistance data 31 to the communication device 10D to assist the communication device 10D with PRS reception. See, e.g., Chapter 6.4.3 of 3GPP TS 37.355 V18.4.0, which specifies the Information Element (IE) A / R-DL-PRS-AssistanceData for such purpose, as one example of the assistance data 31 in Figure 5. This assistance data may for instance include a field nr-DL-PRS-PositioningFrequencyLayer that specifies the Positioning Frequency Layer for the nr-DL-PRS-AssistanceDataPerFreq field and a nr-DL-PRS-AssistanceDataPerFreq field that specifies the DL-PRS Resources for the TRPs within the Positioning Frequency Layer. See also Chapter 6.6 of 3GPP TS 37.355 V18.4.0 which specifies the number of PFLs and the number of TRPs per frequency layer that can be configured with PRS resources according to some embodiments. For example, nrMaxFreqLayers-r16 may specify the maximum number of frequency layers as 4, and nrMaxTRPsPerFreq-r16 may specify the maximum number of TRPs per frequency layer as 64. Regardless, in some embodiments, the procedure for provisioning of PRS assistance data can be initiated by the communication device 10D, by the communication device 10D sending a request for PRS assistance data to the location server 52 and the location server 52 responding with the PRS assistance data as elaborated above. Or, the procedure for provisioning of PRS assistance data can be initiated by the location server 52 requesting the communication device 10D to perform measurements on the resources indicated in the PRS assistance data as elaborated above, whereupon the communication device 10D reports an estimate 24 either in terms ofmeasurement(s) that can be used for positioning or in terms of the location 14L of the communication device 10D as the target equipment 14.

[0059] According to embodiments herein, the communication device 10D is capable of estimating measurements that can be used for positioning or location of the communication device 10D as an output of its ML model 12 that is trained and deployed to support positioning functionality. Towards this end, the communication device 10D performs measurements on the indicated PRS resources to determine the input for its ML model 12. The estimate(s) 24 output by the ML model 12 are then reported to the location server 52 and / or used to monitor performance of its ML model 12.

[0060] For monitoring or self-validating the performance 28 of its ML model 12, the communication device 10D can perform measurement on PRS resources 19 in multiple PFLs as indicated in PRS assistance data 31 to produce a set of inputs 22-1 ...22-N to its ML model 12. This set of model inputs 22-1...22-N can then be used by the communication device 10D to produce a set of estimates 24-1 ...24-N that are output by the ML model 12, e.g., as shown in Figure 8 where the inputs or input datasets 22-1...22-N are exemplified as inputs 11-14 corresponding to PFL1-PFL4 and the outputs or estimates 24-1 ...24-N are exemplified as outputs 01-04 based on measurements on PFL1-PFL4. If the estimates 24-1...24-N that are output remain constant or unchanged, or are within a certain limit / threshold, the communication device 10D can validate that the performance 28 of its ML model 12 to support positioning functionality is working as expected.

[0061] Consider now a number of example implementations according to some embodiments.

[0062] A first implementation example illustrates an implementation of the scenario in Figure 2B where at least some of the positioning signals 18 are received from the same transmission point on different sets 20-1...20-N of positioning signal resources 19 that belong to different PFLs. In this first example, the ML model 12 at the communication device 10D can output an estimate in the form of a prediction of a time of arrival (ToA) measurement, e.g., which may be used as an inference for Reference Signal Time Difference (RSTD) or UE Receive-Transmit (Rx-Tx) measurements for determination of the communication device’s location 14L. To monitor the performance of the ML model 12 in this case, the communication device 10D generates inputs 11-14 by forming input datasets 22-1 to 22-4 from the results of measurements that the communication device 10D performs on positioning signals 18 received from the same TRP on sets 20-1...20-4 of PRS resources 19 that respectively belong to PLF1-PLF4. In this case, 11, I2, I3, I4 in Figure 8 are based on the PRS resources transmitted by the same TRP on PFL1, PFL2, PFL3, and PFL4. The outputs O1 , 02, 03, and 04 from the model in Figure 8 are the predictions of time of arrival measurements produced by the ML model 12 at the communication device 10D for the sameTRP transmitting PRS resources on PFL1, PFL2, PFL3, and PFL4. If the differences between model the outputs O1 , 02, 03, and 04 are within a certain threshold, then the communication device 10D determines its ML model 12 is operating as expected and is capable of supporting positioning functionality as intended. The threshold value for performance validation can either be determined by the communication device 10D depending on the use case for which it intends to support positioning functionality or is configured by a network node such as LMF for the purpose of performance monitoring.

[0063] A second implementation example illustrates an implementation of the scenario in Figure 2C where at least some of the positioning signals 18 are received from the same set 15S of TRPs on different sets 20-1 ...20-N of positioning signal resources 19 that belong to different PFLs. In this example, the ML model 12 at the communication device 10D can predict the location 14L of the communication device 10D with the ML model 12, i.e., the communication device 10D is the target equipment 14. To monitor the performance of such ML model 12 in this example, the communication device 10D generates model inputs 11-14 from signal measurements on indicated PRS resources. The communication device 10D does so by generating model input 11 from signal measurements on PRS resources transmitted by a set of TRPs on PFL1, generating model input I2 from signal measurements on PRS resources transmitted by the same set of TRPs on PFL2, generating model input I3 from signal measurements on PRS resources transmitted by the set of TRPs on PFL3, and generating model input I4 from signal measurements on PRS resources transmitted by the set of TRPs on PFL4. That is, different model input are generated from signal measurements on PRS resources transmitted by the same set of TRPs but on different PLFs. In this case, 11 , I2, I3, I4 in Figure 8 are based on the PRS resources transmitted by the same TRPs on PFL1, PFL2, PFL3, and PFL4. The communication device 10D provides these model inputs to the ML model 12 for location inference. The model inference indicated as O1, 02, 03, and 04 in Figure 8 are the predictions of the communication device’s location 14L in this example. If the differences between model output / inference O1, 02, 03, and 04 are within a certain threshold, then the communication device 10D determines its ML model 12 is operating as expected and is capable of supporting positioning functionality as intended. The threshold value for performance validation can either be determined by the communication device 10D depending on the use case it intends to support positioning functionality for or is configured by a network node such as LMF for the purpose of performance monitoring.

[0064] A third implementation example illustrates an implementation of the scenario in Figure 2D where at least some of the positioning signals 18 are received from the different sets 15S-1 , 15S-2 of TRPs on different sets 20-1 ...20-N of positioning signal resources 19 that belong to different PFLs. In this example, the ML model 12 at the communication device 10D can predict the location of the communication device 10D with the ML model 12, i.e.,the communication device 10D itself is the target equipment 14. To monitorthe performance of such ML model 12, the communication device 10D provides model inputs generated from the results of signal measurements performed on indicated PRS resources. The communication device 10D does so by generating model input 11 from signal measurements on PRS resources transmitted by a first set 15S-1 of TRPs on PFL1 , generating model input I2 from signal measurements on PRS resources transmitted by a second set 15S-2 of TRPs on PFL2, generating model input I3 from signal measurements on PRS resources transmitted by a third set 15S-3 of TRPs on PFL3, and generating model input I4 from signal measurements on PRS resources transmitted by a fourth set 15S-4 of TRPs on PFL4. Here, at least some of the sets 15S-1...15S-4 of TRPs may be different from one another.

[0065] Accordingly, different model inputs are generated from signal measurements on PRS resources transmitted by different sets of TRPs and on different PLFs. Note here though that the TRPs in any given set of TRPs may transmit PRS resources on the same PFL. In this case, 11 , I2, I3, I4 in Figure 8 are based on the PRS resources transmitted by the TRPs on PFL1 , PFL2, PFL3, and PFL4, and here the TRPs in one PFL may not necessarily be the same as the TRPs in another PFL. The model inference indicated as O1 , 02, 03, and 04 in Figure 8 are the predictions of the communication device’s location 14L. If the differences between model output / inference O1 , 02, 03, and 04 are within a certain threshold, then the communication device 10D determines its ML model 12 is operating as expected and is capable of supporting positioning functionality as intended. The threshold value for performance validation can either be determined by the communication device 10D depending on the use case it intends to support positioning functionality for or is configured by a network node such as LMF for the purpose of performance monitoring.

[0066] As these examples illustrate, then, communication equipment 10 herein may provides measurements or samples from PFLi and PFLj to the ML model 12 as a model inputs. The communication equipment 10 may compare inferences that are output by the ML model 12 for the respective model inputs. The respective inferences are comparable if they are within a certain threshold, e.g., so as to provide comparable accuracy / precision. When accuracy / precision is not comparable across the different PFLs, then the communication equipment 10 determines its ML model 12 is not performing as it is supposed to perform. When accuracy / precision is comparable, then the communication equipment 10 determines its ML model 12 is performing as it is supposed to perform.

[0067] Consider now a fourth implementation example in which the communication device 10D organizes signal measurements from different TRPs in a way that one set of measurements may be used for ML model inference and another set of measurements may be used to validate the ML model inference. In some embodiments, the communication device 10D splits the indicated PRS resources into two sets, where one set is used for MLmodel inference and the other set is used for evaluating ML model performance, or both sets are used for ML model inference and ML model performance monitoring. In other embodiments, the split may be signaled by a network node indicating which PRS resources are usable for ML model inference and which PRS resources are usable for ML model performance monitoring.

[0068] In one embodiment, apart from PFL, the split of PRS resources for positioning is done between ML model inference and ML model performance monitoring with respect to set of TRPs. The communication device 10D compares model inference by providing measurements or samples from one set of TRPs and another set of TRPs to the ML model 12 as model input. A first inference may be output from the ML model 12 when measurements or samples from one set of TRPs are input to the ML model 12, and a second inference may be output from the ML model 12 when measurements or samples from another set of TRPs are input to the ML model. The first and second inferences may be deemed comparable if they are within a certain threshold of one another. If the first and second inferences are not comparable, then the ML model 12 is deemed to not be performing as it is supposed to perform, e.g., in terms of its accuracy or precision. If the first and second inferences are comparable, then the ML model 12 is deemed to be performing as it is supposed to perform

[0069] These and other embodiments may thereby infer the communication device’s location 14S using two different sets of TRPs and compare the uncertainty area. If the uncertainty areas are overlapping (e.g., as in Figure 4A), this implies that the ML model 12 is performing well. If the overlap and / or distance between the two inferred locations is marginal (e.g., as in Figure 4B), then it can be considered that the ML model 12 is still performing well. However, if there is no overlapping uncertainty area and / or the distance between two inferred locations are beyond a certain threshold (e.g., as in Figure 4C), then there is an outlier which has been identified and the ML model 12 may be considered to not perform well.

[0070] Generally, then, in some embodiments, communication equipment 10 herein provides measurements or samples from one set of TRPs to the ML model 12 as a model input, and also provides measurements or samples from another set of TRPs to the ML model 12 as another model input. The communication equipment 10 compares inferences that are output by the ML model 12 for the respective model inputs. The respective inferences are comparable if they are within a certain threshold, e.g., so as to provide comparable accuracy / precision. When accuracy / precision is not comparable across the different sets of TRPs, then the communication equipment 10 determines its ML model 12 is not performing as it is supposed to perform. When accuracy / precision is comparable, then the communication equipment 10 determines its ML model 12 is performing as it issupposed to perform.

[0071] Although some embodiments are exemplified as being applicable for communication equipment 10 in the form of a communication device 10D (e.g., UE) performing positioning measurements on positioning signals received on a downlink (DL) from a communication network, embodiments herein may be similarly applied for communication equipment 10 in the form of a network node performing positioning measurements on positioning signals (e.g., SRS) received on an uplink (UL) from a communication device and / or for communication equipment 10 in the form of a communication device 10D (e.g., UE) performing positioning measurements on positioning signals (e.g., SL-PRS) received on a sidelink (SL) from another communication device (e.g., an anchor or assistance UE). Target equipment 14 herein may thereby be a communication device (e.g., a target wireless device) or a network node, and communication equipment 10 may similarly be a communication device or a network node, e.g., in the form of a radio network node, a central unit (CU) of a radio network node, a distributed unit (DU) of a radio network node, a TRP, a location server (e.g., LMF), or any other network node.

[0072] For example, some embodiments herein may be applicable for communication equipment 10 in the form of a user equipment (UE) that performs DL positioning measurements by using its ML model 12 or estimating its location 14L based on the ML model 12. Other embodiments herein are applicable for communication equipment 10 in the form of a network node (referred to as NW Node 1 , NW1) that performs positioning measurements on SRS resources transmitted by a UE.

[0073] As another example, other embodiments are applicable for communication equipment 10 in the form of a Positioning Reference Unit (PRU) that uses the ML model 12 to perform positioning measurements or estimate its location. Such a PRU may be deployed at a known location or can estimate its own location. The PRU can perform and report positioning measurements upon being configured by another network node referred to for convenience as NW Node 2 (NW2). In another example, still further embodiments are applicable for communication equipment 10 in the form of a network node (NW1) that performs positioning measurements on SRS resources transmitted by a PRU.

[0074] In the above examples, note that NW1 may be a serving TRP, reference TRP or neighbor TRP transmitting positioning signal(s), such as PRS, for positioning measurements. NW1 may alternatively or additionally be capable of performing UL positioning measurements by using the ML model 12. NW2 may be a location server, e.g., implementing an LMF, in a communication network 50 which provides assistance data to the UE for positioning measurements. NW2 can alternatively or additionally configure NW1 to perform positioning measurements on reference signals transmitted by the UE in the UL.Generally, then, some embodiments include communication equipment 10 (e.g., a UE) that exploits PRS resources transmitted in different carrier frequencies or positioning frequency layers (e.g., from the same node or TRP, or from the same set of nodes or TRPs) to generate input for the ML model 12 for model inferencing, to validate or monitor performance of the ML model 12 that is deployed to support positioning functionality. That is, the communication equipment 10 makes use of the PRS resources transmitted by network node(s) on multiple carrier frequencies or positioning frequency layers to monitor or validate performance of its ML model 12 that is deployed to support positioning functionality.

[0075] Embodiments herein may thereby exploit the possibility to generate multiple model inputs, by using positioning signal resources received in multiple carriers or positioning frequency layers from the same node or the same set of nodes, in order to self-monitor the performance of the ML model 12.

[0076] Some embodiments herein provide one or more of the following advantages. Some embodiments provide self-monitoring of the performance of the ML model 12 deployed at the communication equipment 10, without the need for additional information or assistance information from a location server. Advantageously, then, no additional information is needed to be transmitted from the location server to the communication equipment 10 to assist the communication equipment 10 on performance monitoring of its ML model 12 for positioning. Some embodiments may thereby reduces signaling overhead for the location server when the communication equipment 10 with deployed ML model 12 is responsible for performance monitoring of its own ML model 12 for positioning.

[0077] Note also that embodiments herein are applicable for any type of measurement from which a location 14L of target equipment 14 is determinable. That is, the estimate 24 and / or estimates 24-1 ...24-N from the ML model 12 may each be an estimate of any type of measurement from which a location 14L of target equipment 14 is determinable. Such measurements herein may for example include Reference Signal Time Difference (RSTD) measurements, Reference Time of Arrival (RTOA) measurements, Uplink Relative RTOA measurements, reference signal received power (RSRP) measurements, reference signal received path power (RSRPP) measurements, Positioning Reference Signal Reference Signal Received Power (PRS-RSRP) measurements, Positioning Reference Signal Reference Signal Received Power Perceived (PRS-RSRPP) measurements, Sounding Reference Signal Reference Signal Received Power (SRS-RSRP) measurements, Sounding Reference Signal Reference Signal Received Power Perceived (SRS-RSRPP) measurements, the User Equipment Receive-Transmit Time Difference (UE Rx-TxTime Difference) measurements, Next-Generation NodeB Receive-Transmit (gNB Rx-Tx) Time Difference measurements, Round Trip Time (RTT) measurements, Time of Arrival (TOA) measurements, Channel Impulse Response (CIR) measurements, Timing Advance (TA)measurements, Angle of Departure (AoD) measurements, Angle of Arrival (AoA) measurements, Power Delay Profile (PDP) measurements, and / or Delay Profile (DP) measurements.

[0078] Note furthermore that embodiments herein are applicable for any type of positioning method or mode, whether assisted or direct positioning. For assisted positioning for example, the range or distance of a UE from a TRP may be predicted by using the ML model 12. Or, for direct positioning, the positioning of a UE can be predicted by using the ML model 12.

[0079] Some embodiments herein are applicable for artificial intelligence (Al) or machine learning (ML) techniques that comprise one or more algorithms for using a set of data as input fortraining the ML model 12. The output of the ML model 12 may be used by the communication equipment 10 for performing certain operations or taking certain decisions (e.g. handover etc.), fully or partially based on the prediction, which in turn depends on the trained model. The ML model 12 can be trained in the communication equipment 10 online (or on-fly while processing the data) or offline in the background. More specifically, online training is an ML training process where the model being used for inference is (typically continuously) trained in (near) real-time with the arrival of new training samples or data. Offline training is an ML training process where the model is trained based on collected samples or data, and where the trained model is later used or delivered for inference. ML model inference refers to a process of using a trained ML model 12 to produce a set of outputs based on a set of inputs. The ML model 12 can be trained in the communication equipment 10. The ML model 12 can be broadly classified as: (i) for embodiments where the communication equipment 10 is a UE, a UE-side model whose inference is performed entirely at the UE; or (ii) for embodiments where the communication equipment 10 is a network node, a network-side model whose inference is performed entirely at the network node. From another perspective, the ML model 12 can be classified as (i) a one-sided model that is either a UE-side model or a Network-side model; or (ii) a two-sided model. A two-sided model here is a paired ML model over which joint inference is performed, where joint inference comprises ML Inference whose inference is performed jointly across the UE and the network, i.e., the first part of inference is firstly performed by UE and then the remaining part is performed by gNB, or vice versa.

[0080] For both approaches, a UE ora gNB, depending on capability, can have a trained model stored inside the communication equipment 10, or have an untrained ML model that can be trained on-the-fly to either produce measurements that are required to localize a UE within a radio access network (RAN) coverage area or directly predict / determine the UE location by exploiting the measurements performed by the UE or gNB on reference signals such as positioning reference signal (PRS), sounding reference signal (SRS) etc. within aRAN coverage area.

[0081] In some embodiments, the positioning measurements herein are performed by a UE / gNB by using the ML model 12. After completion, the positioning measurements are then reported to a location server (e.g., LMF). The location server upon receiving measurements determines the location of the UE within the RAN coverage area. The location server depending on the need may forward the UE location to another node within the network to facilitate provisioning of UE location information to the application layer or the third party that is interested or has requested the positioning of UE within the RAN coverage area for further action to be taken.

[0082] In other embodiments, the measurements performed by a UE / gNB are not reported to the location server. The positioning engine or the ML model 12 to predict or determine the UE location within the RAN coverage area resides within the UE node or the gNB node or the location server. After determining the UE position within the RAN coverage area, the estimated UE positioning is then reported to the location server in a deployment or scenario where LMF is not deployed with ML capability to localize a UE. The location server depending on the need may forward the UE location to another node within the network to facilitate provisioning of UE location information to the application layer or the third party that is interested or has requested the positioning of UE within the RAN coverage area for further action to be taken.

[0083] Either way, embodiments herein may involve performing one or more positioning measurements on DL RS (e.g. PRS) and / or uplink (UL) RS (e.g. SRS) transmitted between the UE and one or more cells. A cell herein may also be called as or be associated with a transmission reception point (TRP) or node.

[0084] To perform these measurements, a UE may make use of a trained model acquired before being deployed or may need to train its model on-the-fly before performing ML-based positioning measurements to be reported to the network node such as location server. In either of the cases, the UE may require assistance information / data from the network to determine or identify how and when to train its AML model and what information (positioning measurements or estimated position) to report to the network node such as location server.

[0085] Note that performance monitoring in general can be performed by different nodes in a cellular network. In one scenario, a network node such as location server or LMF performs performance monitoring to determine if an ML model at a UE / gNB is working as it is intended to, based on the measurements reported by UE / gNB by exploiting the deployed AI / ML model. By contrast, in another scenario, the node where the ML model is deployed itself monitors the performance of its ML model. Embodiments herein may address this latter case. In a situation when the performance of the deployed model degrades, actions such as, but not limited to, model switching, model retraining, model update and retraining can beperformed to make sure predictions / inferencing is precise / accurate in scenarios other than the ones for which the ML model 12 is trained for. Given a situation where there is no possibility to perform model switching, model retraining, model update and retraining, a UE / gNB may fall back to legacy procedure for positioning measurement or estimation of UE position.

[0086] In view of the modifications and variations herein, Figures 9A-9B depict a method performed by communication equipment 10 in accordance with particular embodiments. The method includes obtaining different input datasets 22-1...22-N that are respectively formed from results 21 -1...21 -N of measurements on positioning signals 18 received by the communication equipment 10 on different sets 20-1...20-N of positioning signal resources 19 (Block 900). The method also comprises determining, from inputting each of the different input datasets 22-1...22-N into a machine learning model 12 deployed at the communication equipment 10, a respective estimate 24-1...24-N that is output from the machine learning model 12. In some embodiments, each respective estimate 24-1 ...24-N comprises an estimation of a location 14L of target equipment 14 or an estimation of a result of a measurement from which the location 14L of the target equipment 14 is determinable. In some embodiments, the target equipment 14 is the same as or different than the communication equipment 10 (Block 910). The method also comprises evaluating a performance 28 of the machine learning model 12 based on comparing the estimates 24-1 ...24-N that are output from the machine learning model 12 for the different input datasets 22-1...22-N (Block 920).

[0087] In some embodiments, the positioning signals 18 received on different sets 20-1 ...20-N of positioning signal resources 19 are received from different transmission points 15-1 ...15-X and / or belong to different positioning frequency layers 17-1 ...17-Y.

[0088] In some embodiments, at least some of the positioning signals 18 received on different sets 20-1 ...20-N of positioning signal resources 19 the positioning signals 18 received on different positioning signal resources 19 belong to different positioning frequency layers 17-1 ...17-Y. In some embodiments, at least some of the positioning signals 18 received on different sets 20-1 ...20-N of positioning signal resources 19 are received from the same transmission point 15-1 ...15-X or from the same set 15S of transmission points 15-1...15-X.

[0089] In some embodiments, at least some of the positioning signals 18 received on different sets 20-1 ...20-N of positioning signal resources 19 are received from different sets of transmission points 15-1 ...15-X and belong to different positioning frequency layers 17-1...17-Y.

[0090] In some embodiments, the method further comprises receiving signaling indicating sets of positioning signal resources 19 on which the communication equipment 10 is toperform measurements for locating the target equipment 14, selecting a first subset of the indicated sets of positioning signal resources 19 as one or more sets of positioning signal resources 19 on which to perform measurements for locating the target equipment 14 using the machine learning model 12, and selecting a second subset of the indicated sets of positioning signal resources 19 as the different sets 20-1...20-N of positioning signal resources 19 on which to evaluate the performance 28 of the machine learning model 12. In some embodiments, the different input datasets 22-1...22-N are respectively formed from results 21-1...21 -N of measurements on positioning signals 18 received by the communication equipment 10 on the sets of positioning signal resources 19 in the second subset

[0091] In some embodiments, said evaluating comprises evaluating a performance 28 of the machine learning model 12 based on how close the estimates 24-1 ...24-N output for the different input datasets 22-1 ...22-N are to one another. In some embodiments, said evaluating comprises determining that the machine learning model 12 has a first level of performance 28 if any pair of estimates 24-1 ...24-N output for different input datasets 22-1 ...22-N differ from one another by at least a threshold amount. In other embodiments, said evaluating comprises determining that the machine learning model 12 has a second level of performance 28 if each pair of estimates 24-1...24-N output for different input datasets 22-1 ...22-N differ from one another by less than the threshold amount. In some embodiments, the method further comprises receiving signaling indicating the threshold amount.

[0092] In some embodiments, the method further comprises deciding, based on said evaluating, whether to perform one or more actions to address a problem with the performance 28 of the machine learning model 12 (Block 930). In some embodiments, the one or more actions include at least updating or retraining the machine learning model 12. In other embodiments, the one or more actions include at least switching to using a different machine learning model 12. In other embodiments, the one or more actions include at least switching to a different positioning method that does not use any machine learning model 12.

[0093] In some embodiments, the method further comprises receiving assistance data indicating the different sets 20-1 ...20-N of positioning signal resources 19 (Block 940).

[0094] In some embodiments, the communication equipment 10 is a communication device configured to receive service from a communication network. In some embodiments, the positioning signals 18 are downlink positioning signals received from the communication network. In other embodiments, the communication equipment 10 is network equipment of a communication network configured to provide service to one or more communication devices. In some embodiments, the positioning signals 18 are uplink signals received from a communication device.In some embodiments, the method further comprises receiving a request for an estimate 24-1...24-N comprising an estimation of the location 14L of the target equipment M oran estimation of a result of a measurement from which the location 14L of the target equipment 14 is determinable, In some embodiments, the request requests that the estimate 24-1 ...24-N be determined from the machine learning model 12 deployed at the communication equipment 10 and from results 21-1...21 -N of measurements on positioning signals 18 received by the communication equipment 10 on the different positioning signal resources 19 (Block 950). In some embodiments, the method further comprises transmitting a response to the request. In some embodiments, the response includes the requested estimate 24-1...24-N and an indication of whether or not the estimate 24-1 ...24-N included in the response was determined from the machine learning model 12 deployed at the communication equipment 10 (Block 960).

[0095] In some embodiments, the indication indicates that the estimate 24-1 ...24-N included in the response was not determined from any machine learning model 12 deployed at the communication equipment 10. In some embodiments, the response further includes a reason why the estimate 24-1 ...24-N included in the response was not determined from the machine learning model 12 deployed at the communication equipment 10. In some embodiments, the reason is a problem with the performance 28 of the machine learning model 12 deployed at the communication equipment 10 as determined from said evaluating.

[0096] Figure 10 depicts a method performed by communication equipment 10 in accordance with other particular embodiments. The method includes receiving assistance data indicating different sets 20-1 ...20-N of positioning signal resources 19 on which the communication equipment 10 is to perform measurements for locating target equipment 14. In some embodiments, the target equipment 14 is the same as or different than the communication equipment 10 (Block 1000). The method also includes receiving a request for an estimate 24-1 ...24-N comprising an estimation of a location 14L of the target equipment 14 or an estimation of a result of a measurement from which the location 14L of the target equipment 14 is determinable. In some embodiments, the request requests that the estimate 24-1...24-N be determined from a machine learning model 12 deployed at the communication equipment 10 and from results 21-1...21 -N of measurements on positioning signals 18 received by the communication equipment 10 on the different sets 20-1 ...20-N of positioning signal resources 19 (Block 1010). The method also includes transmitting a response to the request. In some embodiments, the response includes the estimate 24-1 ...24-N and an indication of whether or not the estimate 24-1 ...24-N included in the response was determined from the machine learning model 12 deployed at the communication equipment 10 (Block 1020).In some embodiments, the indication indicates that the estimate 24-1 ...24-N included in the response was not determined from any machine learning model 12 deployed at the communication equipment. In some embodiments, the response further includes a reason why the estimate 24-1 ...24-N included in the response was not determined from the machine learning model 12 deployed at the communication equipment. In some embodiments, the reason is a problem with performance 28 of the machine learning model 12 deployed at the communication equipment. In some embodiments, the problem is that respective estimates 24-1 ...24-N output by the machine learning model 12 for the different sets 20-1...20-N of positioning signal resources 19 are not close enough together. In some embodiments, the method further comprises receiving signaling indicating a minimum level of performance 28 that the machine learning model 12 at the communication equipment must have in order for the requested estimate 24-1 ...24-N to be determined from the machine learning model 12. In some embodiments, the signaling indicates the minimum level of performance 28 in terms of a maximum allowable amount by which respective estimates 24-1 ...24-N output by the machine learning model 12 forthe different sets 20-1 ...20-N of positioning signal resources 19 can differ from one another in order for the machine learning model 12 to be used to determine the requested estimate 24-1 ...24-N.

[0097] In some embodiments, the different sets 20-1...20-N of positioning signal resources 19 are sets of positioning signal resources 19 on which the communication equipment is to receive positioning signals that are from different transmission points 15-1...15-X and / or that belong to different positioning frequency layers 17-1 ...17-Y.

[0098] In some embodiments, the different sets 20-1...20-N of positioning signal resources 19 19belong to different positioning frequency layers 17-1 ...17-Y. In some embodiments, the different sets 20-1 ...20-N of positioning signal resources 19 are sets of positioning signal resources 19 on which the communication equipment is to receive positioning signals from the same transmission point or from the same set 15S of transmission points 15-1...15-X .

[0099] In some embodiments, the different sets 20-1...20-N of positioning signal resources 19 are sets of positioning signal resources 19 on which the communication equipment is to receive positioning signals that are from the different sets of transmission points 15-1...15-X and that belong to different positioning frequency layers 17-1...17-Y.

[0100] In some embodiments, the communication equipment is a communication device configured to receive service from a communication network, wherein the positioning signals are downlink positioning signals received from the communication network. In other embodiments, the communication equipment is network equipment of a communication network configured to provide service to one or more communication devices, wherein the positioning signals are uplink positioning signals received from a communication device.In some embodiments, the indication implicitly indicates a performance 28 of the machine learning model 12 as evaluated by the communication equipment. In some embodiments, the indication implicitly indicates the performance 28 of the machine learning model 12 as evaluated by the communication equipment based on a comparison of respective estimates 24-1 ...24-N that are output by the machine learning model 12 for different input datasets formed from results of measurements on the different positioning signal resources 19.

[0101] Embodiments herein also include corresponding apparatuses. Embodiments herein for instance include communication equipment 10 configured to perform any of the steps of any of the embodiments described above for the communication equipment 10.

[0102] Embodiments also include communication equipment 10 comprising processing circuitry and power supply circuitry. The processing circuitry is configured to perform any of the steps of any of the embodiments described above for the communication equipment 10. The power supply circuitry is configured to supply power to the communication equipment 10.

[0103] Embodiments further include communication equipment 10 comprising processing circuitry. The processing circuitry is configured to perform any of the steps of any of the embodiments described above for the communication equipment 10. In some embodiments, the communication equipment 10 further comprises communication circuitry.

[0104] Embodiments further include communication equipment 10 comprising processing circuitry and memory. The memory contains instructions executable by the processing circuitry whereby the communication equipment 10 is configured to perform any of the steps of any of the embodiments described above for the communication equipment 10.

[0105] Embodiments moreover include a user equipment (UE). The UE comprises an antenna configured to send and receive wireless signals. The UE also comprises radio frontend circuitry connected to the antenna and to processing circuitry, and configured to condition signals communicated between the antenna and the processing circuitry. The processing circuitry is configured to perform any of the steps of any of the embodiments described above for the communication equipment 10. In some embodiments, the UE also comprises an input interface connected to the processing circuitry and configured to allow input of information into the UE to be processed by the processing circuitry. The UE may comprise an output interface connected to the processing circuitry and configured to output information from the UE that has been processed by the processing circuitry. The UE may also comprise a battery connected to the processing circuitry and configured to supply power to the UE.

[0106] More particularly, the apparatuses described above may perform the methods herein and any other processing by implementing any functional means, modules, units, or circuitry.In one embodiment, for example, the apparatuses comprise respective circuits or circuitry configured to perform the steps shown in the method figures. The circuits or circuitry in this regard may comprise circuits dedicated to performing certain functional processing and / or one or more microprocessors in conjunction with memory. For instance, the circuitry may include one or more microprocessor or microcontrollers, as well as other digital hardware, which may include digital signal processors (DSPs), special-purpose digital logic, and the like. The processing circuitry may be configured to execute program code stored in memory, which may include one or several types of memory such as read-only memory (ROM), random-access memory, cache memory, flash memory devices, optical storage devices, etc. Program code stored in memory may include program instructions for executing one or more telecommunications and / or data communications protocols as well as instructions for carrying out one or more of the techniques described herein, in several embodiments. In embodiments that employ memory, the memory stores program code that, when executed by the one or more processors, carries out the techniques described herein.

[0107] Figure 11 for example illustrates communication equipment 10 as implemented in accordance with one or more embodiments. As shown, the communication equipment 10 includes processing circuitry 1110 and communication circuitry 1120. The communication circuitry 1120 (e.g., radio circuitry) is configured to transmit and / or receive information to and / or from one or more other nodes, e.g., via any communication technology. Such communication may occur via one or more antennas that are either internal or external to the communication device 1100. The processing circuitry 1110 is configured to perform processing described above, e.g., in Figure 9 and / or Figure 10, such as by executing instructions stored in memory 1130. The processing circuitry 1110 in this regard may implement certain functional means, units, or modules.

[0108] Those skilled in the art will also appreciate that embodiments herein further include corresponding computer programs.

[0109] A computer program comprises instructions which, when executed on at least one processor of communication equipment 10, cause the communication equipment 10 to carry out any of the respective processing described above. A computer program in this regard may comprise one or more code modules corresponding to the means or units described above.

[0110] Embodiments further include a carrier containing such a computer program. This carrier may comprise one of an electronic signal, optical signal, radio signal, or computer readable storage medium.

[0111] In this regard, embodiments herein also include a computer program product stored on a non-transitory computer readable (storage or recording) medium and comprisinginstructions that, when executed by a processor of communication equipment 10, cause the communication equipment 10 to perform as described above.

[0112] Embodiments further include a computer program product comprising program code portions for performing the steps of any of the embodiments herein when the computer program product is executed by communication equipment 10. This computer program product may be stored on a computer readable recording medium.

[0113] Figure 12 shows an example of a communication system 1200 in accordance with some embodiments.

[0114] In the example, the communication system 1200 includes a telecommunications network 1202 that includes an access network 1204, such as a radio access network (RAN), and a core network 1206, which includes one or more core network nodes 1208. The access network 1204 includes one or more access network nodes or base stations of various types, access network nodes 1210A and 1210B are depicted (which may be collectively referred to as network nodes 1210), or any other similar 3rdGeneration Partnership Project (3GPP) access nodes or non-3GPP access points (APs). Some embodiments of the access network 1204 may include more than one access network technology. The network nodes 1210 of access network 1204 facilitate direct or indirect connection of wireless devices, also referred to as user equipments (UEs), such as by connecting UEs 1212A, 1212B, 1212C, and 1212D (one or more of which may be generally referred to as UEs 1212) to the core network 1206 over one or more wireless connections.

[0115] Moreover, a network node is not necessarily limited to an implementation in which a radio portion and a baseband portion are supplied and integrated by a single vendor. Thus, it will be understood that network nodes include disaggregated implementations or portions thereof. For example, in some embodiments, the telecommunications network 1202 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a network node in the telecommunications network 1202 that supports an ORAN specification (e.g., a specification published by the O-RAN Alliance, or any similar organization) and may operate alone or together with other network nodes to implement one or more functionalities of any network node in the telecommunications network 1202, including one or more access network nodes 1210 and / or core network nodes 1208.

[0116] Examples of an ORAN network node include an open radio unit (O-RU), an open distributed unit (O-DU), an open central unit (O-CU), including an O-CU control plane (O-CU-CP) or an O-CU user plane (O-CU-UP), a RAN intelligent controller (near-real time or non-real time) hosting software or software plug-ins, such as a near-real time control application (e.g., xApp) ora non-real time control application (e.g., rApp), or any combination thereof (the adjective “open” designating support of an ORAN specification). An ORAN network node may support a specification by, for example, supporting an interface definedby the ORAN specification, such as an A1 , F1 , W1 , E1 , E2, X2, Xn interface, an open fronthaul user plane interface, or an open fronthaul management plane interface. Moreover, an ORAN network node may be a logical node in a physical node. Furthermore, an ORAN network node may be implemented in a virtualization environment (described further below) in which one or more network functions are virtualized. For example, the virtualization environment may include an O-Cloud computing platform orchestrated by a Service Management and Orchestration Framework via an 0-2 interface defined by the O-RAN Alliance or comparable technologies.

[0117] The network nodes 1210 facilitate direct or indirect connection of one or more UEs 1212 to the core network 1206 over one or more wireless connections. Example wireless communications over a wireless connection include transmitting and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information without the use of wires, cables, or other material conductors. Moreover, in different embodiments, the communication system 1200 may include any number of wired or wireless networks, network nodes, UEs, and / or any other components or systems that may facilitate or participate in the communication of data and / or signals whether via wired or wireless connections. The communication system 1200 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0118] The UEs 1212 may be any of a wide variety of communication devices, including wireless devices arranged, configured, and / or operable to communicate wirelessly with the network nodes 1210 and other communication devices. Similarly, the network nodes 1208, 1210 are arranged, capable, configured, and / or operable to communicate directly or indirectly (e.g., via other devices of telecommunications network 1202) with the UEs 1212 and / or with other network nodes or equipment in the telecommunications network 1202 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in the telecommunications network 1202. More specifically, UEs 1212 may send messages, data, and / or other signals to network nodes 1208, 1210 or other elements of the telecommunications network 1202 by transmitting such signals to the relevant device directly without the signals passing through any intervening devices or by transmitting such signals to the relevant device indirectly through an intervening device (or multiple intervening devices) that then transmit the signal to the relevant device. Similarly, network nodes 1208, 1210 may send messages, data, and other signals to UEs 12122, other network nodes 1208, 1210, and other devices in telecommunications network 1202 directly or indirectly. As one specific example, a core network node 108 may transmit a particular message to a UE 1212 by transmitting the message to an access network node 1210 that will then transmit the message to theintended UE 1212. Similarly, a core network node 108 may receive a particular message from a UE 1212 by receiving the message from an access network node 1210 that itself received the message from the UE 1212.

[0119] In the depicted example, the core network 1206 connects elements of the access network 1204 (e.g., one or more of the network nodes 1210) to one or more host computing systems, such as host 1216. These connections may be direct or indirect via one or more intermediary networks or devices. In other examples, network nodes may be directly coupled to hosts. The core network 1206 includes one or more core network nodes (e.g., core network node 1208) of various types, one or more of which may be generally referred to as network nodes 1208. Network nodes 1208 are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the UEs, access network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node 1208. Example core network nodes provide functions of one or more of a Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (AUSF), Subscription Identifier De-concealing function (SIDF), Unified Data Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).

[0120] The host 1216 may be under the ownership or control of a service provider other than an operator or provider of the access network 1204 and / or the telecommunications network 1202. The host 1216 may be operated by the service provider or on behalf of the service provider. The host 1216 may host a variety of applications to provide one or more service. Examples of such applications include live and pre-recorded audio / video content, data collection services such as retrieving and compiling data on various ambient conditions detected by a plurality of UEs, analytics functionality, social media, functions for controlling or otherwise interacting with remote devices, functions for an alarm and surveillance center, or any other such function performed by a server.

[0121] As a whole, the communication system 1200 of Figure 12 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication system 1200 may be configured to operate according to predefined rules or procedures, such as specific standards that include, but are not limited to: Global System for Mobile Communications (GSM); Universal Mobile Telecommunications System (UMTS); Long Term Evolution (LTE), and / or other suitable 2G, 3G, 4G, 5G standards, or any applicable future generation standard (e.g., 6G); wireless local area network (WLAN) standards, such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards (Wi-Fi); and / or any other appropriate wireless communication standard, such as the Worldwide Interoperability forMicrowave Access (Wi-Max), Bluetooth, Z-Wave, Near Field Communication (NFC) ZigBee, Li-Fi, and / or any low-power wide-area network (LPWAN) standards such as LoRa and Sigfox. Moreover, the communication system 1200 may be configured to support multiple different standards, protocols, or other rule sets, with individual components supporting all of the relevant rule sets or with different components or sub-systems within the communication system 1200 supporting different standards, protocols, or rule sets.

[0122] As one example, in certain embodiments, access network 1204 may contain some access network nodes 1210 that support 3GPP radio access technologies (RAT), such as LTE or NR, while other access network nodes 1210 support (or the same access network nodes 1210 additionally support) non-3GPP RATs, such as Wi-Fi ora proprietary RAT. As another example, telecommunications network 1202 may support multiple generations of related communication standards (e.g., 4G and 5G 3GPP communication standards) and, as a result, may include an access network 104 and / or a core network 106 that supports multiple different standard generations or may include multiple access networks 104 and / or multiple core networks 106 with individual networks 104, 106 supporting different standard generations.

[0123] Telecommunications network 1202 may support network slicing to provide different logical networks to different devices that are connected to the telecommunications network 1202. For example, the telecommunications network 1202 may provide Ultra Reliable Low Latency Communication (URLLC) services to some UEs, while providing Enhanced Mobile Broadband (eMBB) services to other UEs, and / or Massive Machine Type Communication (mMTC)ZMassive loT services to yet further UEs.

[0124] In some examples, one or more of the UEs 1212 are configured to transmit and / or receive information without direct human interaction. For instance, a UE may be designed to transmit information to the access network 1204 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 1204. Additionally, a UE may be configured for operating in single- or multi-RAT or multi-standard mode. For example, a UE may operate with any one or combination of Wi-Fi, NR (New Radio) and LTE, i.e. being configured for multi-radio dual connectivity (MR-DC), such as E-UTRAN (Evolved-UMTS Terrestrial Radio Access Network) New Radio - Dual Connectivity (EN-DC).

[0125] In the example, the hub 1214 communicates with the access network 1204 to facilitate indirect communication between one or more UEs (e.g., UE 1212C and / or 1212D) and network nodes (e.g., network node 1210B). In some examples, the hub 1214 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 1214 may be a broadband router enabling access to the core network 1206 for the UEs. As another example, the hub 1214may be a controller that sends commands or instructions to one or more actuators in the UEs. Commands or instructions may be received from the UEs, network nodes 1210, or by executable code, script, process, or other instructions in the hub 1214.

[0126] As another example, the hub 1214 may be a data collector that acts as temporary storage for UE data and, in some embodiments, may perform analysis or other processing of the data. As another example, the hub 1214 may be a content source. For example, for a UE that is a VR headset, display, loudspeaker or other media delivery device, the hub 1214 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub 1214 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 1214 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy loT devices.

[0127] The hub 1214 may have a constant / persistent or intermittent connection to the network node 121 OB. The hub 1214 may also allow fora different communication scheme and / or schedule between the hub 1214 and UEs (e.g., UE 1212C and / or 1212D), and between the hub 1214 and the core network 1206. In other examples, the hub 1214 is connected to the core network 1206 and / or one or more UEs via a wired connection.

[0128] Moreover, the hub 1214 may be configured to connect to an M2M service provider over the access network 1204 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 1210 while still connected via the hub 1214 via a wired or wireless connection. In some embodiments, the hub 1214 may be a dedicated hub - that is, a hub whose primary function is to route communications to / from the UEs from / to the network node 1210B. In other embodiments, the hub 1214 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node 1210B, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0129] Figure 13 is another example of a communication system 1300 according to some embodiments. As used herein, the communication system 1300 includes multiple access points (APs) 1310 (with four exemplary APs 1310A, 1310B, 1310C, and 1310D being depicted) and multiple wireless devices, referred to in the context of communication system 1300 as stations (STAs) 1312 (referred to individually as STA 1312A, STA 1312B, STA 1312C, STA 1312D, and STA 1312E). STA 1312A is served by AP 1310A in a first basic service set (BSS) 1320A. STA 1310B and STA 1310C are served by AP 1310B in a second BSS, BSS 1320B. STA 1312D is served by AP 1310C in a third BSS, BSS 1320C. STA 1312E is served by AP 1310D in a fourth BSS, BSS 1320D. Stations 1312 may be non-AP STAs and correspond to various kinds of wireless devices, for example, user terminals, such as mobile or stationary computing devices like smartphones, laptop computers, desktopcomputers, tablet computers, gaming devices, head-mounted displays (HMDs) for Augmented Reality (AR) or Virtual Reality (VR), or the like. Further, stations 1312 could, for example, correspond to other kinds of equipment like smart home devices, printers, multimedia devices, data storage devices, or the like.

[0130] Each of STAs 1312 may connect through a radio link to one of APs 1310. For example, depending on location or channel conditions experienced by a given STA 1312, the STA may select an appropriate AP and BSS for establishing the radio link. The radio link may be based on one or more orthogonal frequency-division multiplexing (OFDM) carriers from a frequency spectrum that is shared on the basis of a contention-based mechanism, e.g., an unlicensed or license exempt band like 2.4 GHz Industrial, Scientific, and Medical (ISM) band, the 5 GHz band, the 6 GHz band, or the 60 GHz band.

[0131] Each AP 1310 may provide data connectivity to STAs 1312 connected to a particular AP 1310. As illustrated, APs 1310 may be connected to a data network 1330. In this way, APs 1310 may also provide data connectivity between STAs 1312 and other entities, e.g., to one or more servers, service providers, data sources, data sinks, user terminals, or the like. Accordingly, the radio link established between a given STA 1312 and its serving AP 1310 may be used for providing various kinds of services to STA 1312, e.g., a voice service, a multimedia service, or other data service. Such services may be based on applications that are executed on STA 1312 and / or on a device linked to STA 1312. Byway of example, Figure 13 illustrates an application service platform 1332 provided in data network 1330. The application(s) executed on STA 1312 and / or on one or more other devices linked to STA 1312 may use the radio link for data communication with one or more other STA 1312 and / or the application service platform 1332, thereby enabling utilization of the corresponding service(s) at STA 1312.

[0132] Figure 14 shows a wireless device 1400, which may be configured to operate in communication system 1200 of Figure 12 or in communication system 1300 of Figure 13. The wireless device 1400 may be alternatively referred to as a UE 1400, like a UE 1212 within the context of communication system 1200, or as a station (STA) 1400 or as a non-access-point station (non-AP STA) 1400, like a STA 1312 within the context of the communication system 1300, in accordance with respective embodiments. As used herein, a wireless device refers to a device capable, configured, arranged and / or operable to communicate wirelessly with network nodes and / or other wireless devices. Examples of a wireless device include, but are not limited to, a smart phone, mobile phone, cell phone, voice over IP (VoIP) phone, wireless local loop phone, desktop computer, personal digital assistant (PDA), wireless cameras, gaming console or device, music storage device, playback appliance, wearable terminal device, wireless endpoint, mobile station, tablet, laptop, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), smart device,wireless customer-premise equipment (CPE), vehicle, vehicle-mounted or vehicle embedded / integrated wireless device, and wireless terminal. Other examples include any type of UE identified by the 3rd Generation Partnership Project (3GPP), including a narrow band internet of things (NB-loT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0133] A wireless device 1400 may support device-to-device (D2D) communication, for example by implementing a 3GPP standard for sidelink communication, Dedicated Short-Range Communication (DSRC), vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), or vehicle-to-everything (V2X). In other examples, wireless device 1400 may not necessarily have a user in the sense of a human user who owns and / or operates the relevant device. Instead, wireless device 1400 may represent a device that is intended for sale to, or operation by, a human user but which may not, or which may not initially, be associated with a specific human user (e.g., a smart sprinkler controller). Alternatively, wireless device 1400 may represent a device that is not intended for sale to, or operation by, an end user but which may be associated with or operated for the benefit of a user (e.g., a smart power meter).

[0134] In particular embodiments, wireless device 1400 includes processing circuitry 1402 that is operatively coupled via a bus 1404 to an input / output interface 1406, a power source 1408, a memory 1410, a communication interface 1412, and / or any other component, or any combination thereof. Certain embodiments of wireless device 1400 may include all ora subset of the components shown in Figure 14. The level of integration between the components may vary from one embodiment of wireless device 1400 to another. In general, in a particular embodiment of wireless device 1400, processing circuitry 1402, input / output interface 1406, power source 1408, memory 1410, and communication interface 1412 may, in whole or in part, represent or include physical components common to or shared by one or more of the other elements of wireless device 1400. Further, certain embodiments of wireless devices 1400 may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.

[0135] The processing circuitry 1402 is configured to process instructions and data and may be configured to implement any sequential state machine operative to execute instructions stored as machine-readable computer programs in the memory 1410. The processing circuitry 1402 may be implemented as one or more hardware-implemented state machines (e.g., in discrete logic, field-programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), etc.); programmable logic together with appropriate firmware; one or more stored computer programs, general-purpose processors, such as a microprocessor or digital signal processor (DSP), together with appropriate software; or any combination of the above. For example, the processing circuitry 1402 may include multiplecentral processing units (CPUs).

[0136] In the example, the input / output interface 1406 may be configured to provide an interface or interfaces to an input device, output device, or one or more input and / or output devices. Examples of an output device include a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smartcard, another output device, or any combination thereof. An input device may allow a user to capture information into wireless device 1400. Examples of an input device include a touch-sensitive or presencesensitive display, a camera (e.g., a digital camera, a digital video camera, a web camera, etc.), a microphone, a sensor, a mouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smartcard, and the like. The presence-sensitive display may include a capacitive or resistive touch sensor to sense input from a user. A sensor may be, for instance, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, a biometric sensor, etc., or any combination thereof. An output device may use the same type of interface port as an input device. For example, a Universal Serial Bus (USB) port may be used to provide an input device and an output device.

[0137] In some embodiments, the power source 1408 is structured as a battery or battery pack. Other types of power sources, such as an external power source (e.g., an electricity outlet), photovoltaic device, or power cell, may be used to supply power to circuitry or to charge an associated battery. The power source 1408 may further include power circuitry for delivering power from the power source 1408 itself, and / or an external power source, to the various parts of wireless device 1400 via input circuitry or an interface such as an electrical power cable. Power source 1408 may perform any formatting, converting, or other modification to make accessible power suitable for the respective components of the wireless device 1400 to which power is supplied.

[0138] The memory 1410 may be or be configured to include memory such as random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, and so forth. In one example, the memory 1410 includes one or more programs 1414, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 1416. The memory 1410 may store, for use by wireless device 1400, any of a variety of various operating systems or combinations of operating systems.

[0139] The memory 1410 may be configured to include a number of physical drive units, such as redundant array of independent disks (RAID), flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, high-density digital versatile disc (HD-DVD) optical disc drive, internal hard disk drive, Blu-Ray optical disc drive, holographicdigital data storage (HDDS) optical disc drive, external mini-dual in-line memory module (DIMM), synchronous dynamic random access memory (SDRAM), external micro-DIMM SDRAM, smartcard memory such as tamper resistant module in the form of a universal integrated circuit card (UICC) including one or more subscriber identity modules (SIMs), such as a USIM and / or ISIM, other memory, or any combination thereof. The UICC may for example be an embedded UICC (eUlCC), integrated UICC (iUICC) ora removable UICC commonly known as ‘SIM card.’ The memory 1410 may allow wireless device 1400 to access instructions, programs and the like, stored on transitory or non-transitory memory media, to off-load data, or to upload data. An article of manufacture, such as one utilizing a communication system may be tangibly embodied as or in the memory 1410, which may be or comprise a device-readable storage medium.

[0140] The processing circuitry 1402 may be configured to communicate with an access network or other network via or using the communication interface 1412. The communication interface 1412 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 1422. The communication interface 1412 may include one or more transceivers used to communicate, such as by communicating with one or more remote transceivers of another device capable of wireless communication (e.g., another wireless device or a network node in an access network). Each transceiver may include a transmitter 1418 and / or a receiver 1420 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter 1418 and receiver 1420 may be coupled to one or more antennas (e.g., antenna 1422) and may share circuit components, software or firmware, or alternatively be implemented separately.

[0141] In the illustrated embodiment, communication functions of the communication interface 1412 may include cellular communication, Wi-Fi communication (e.g., according to an IEEE 802.11 family standard), LPWAN communication, data communication, voice communication, multimedia communication, short-range communications such as Bluetooth, near-field communication, location-based communication such as the use of the global positioning system (GPS) to determine a location, another like communication function, or any combination thereof. Communications may be implemented according to one or more communication protocols and / or standards, such as IEEE 802.11, Code Division Multiplexing Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMax, Ethernet, transmission control protocol / internet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0142] In particular embodiments, wireless device 1400 may provide an output of data captured via a sensor, through its communication interface 1412, via a wireless connectionto a network node, and / or in any appropriate manner. Data captured by sensors of a wireless device 1400 can be communicated through a wireless connection to a network node via another wireless device 1400. In particular embodiments, such output may be periodic (e.g., once every 15 minutes if it reports the sensed temperature), random (e.g., to even out the load from reporting from several sensors), in response to a triggering event (e.g., when moisture is detected an alert is sent), in response to a request (e.g., a user initiated request), ora continuous stream (e.g., a live video feed of a patient).

[0143] As another example, wireless device 1400 comprises an actuator, a motor, or a switch, related to a communication interface configured to receive wireless input from a network node via a wireless connection. In response to the received wireless input the states of the actuator, the motor, or the switch may change. For example, wireless device 1400 may comprise a motor that adjusts the control surfaces or rotors of a drone in flight according to the received input or to a robotic arm performing a medical procedure according to the received input.

[0144] Wireless device 1400, when in the form of an Internet of Things (loT) device, may be a device for use in one or more application domains, these domains comprising, but not limited to, wearable technology, extended industrial application and healthcare. Non-limiting examples of such an loT device are a device which is or which is embedded in: a connected refrigerator or freezer, a TV, a connected lighting device, an electricity meter, a robot vacuum cleaner, a voice controlled smart speaker, a home security camera, a motion detector, a thermostat, a smoke detector, a door / window sensor, a flood / moisture sensor, an electrical door lock, a connected doorbell, an air conditioning system like a heat pump, an autonomous vehicle, a surveillance system, a weather monitoring device, a vehicle parking monitoring device, an electric vehicle charging station, a smart watch, a fitness tracker, a wearable for tactile augmentation or sensory enhancement, a water sprinkler, an animal- or item-tracking device, a sensor for monitoring a plant or animal, an industrial robot, an Unmanned Aerial Vehicle (UAV), and any kind of medical device, like a heart rate monitor or a remote controlled surgical robot. In particular embodiments, wireless device 1400 represents an loT device that comprises circuitry and / or software in dependence of the intended application of the loT device in addition to other components as described in relation to the example embodiment of wireless device 1400 shown in Figure 14.

[0145] As yet another specific example, in an loT scenario, wireless device 1400 may represent a machine or other device that performs monitoring and / or measurements, and transmits the results of such monitoring and / or measurements to another wireless device and / or a network node. Wireless device 1400 may in this case be an M2M device, which may in a 3GPP context be referred to as an MTC device. As one particular example, wireless device 1400 may implement the 3GPP NB-loT standard. In other scenarios,wireless device 1400 may represent a vehicle, such as a car, a bus, a truck, a ship and an airplane, or other equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation.

[0146] In practice, any number of wireless devices 1400 may be used together with respect to a single use case. For example, a first wireless device 1400 might be or be integrated in a drone and provide the drone’s speed information (obtained through a speed sensor) to a second wireless device 1400 that is a remote controller operating the drone. When a user makes changes from the remote controller, the first wireless device 1400 may adjust the throttle on the drone (e.g. by controlling an actuator) to increase or decrease the drone’s speed. The first and / or the second wireless device 1400 can also include more than one of the functionalities described above. For example, wireless device 1400 might comprise the sensor and the actuator, and handle communication of data for both the speed sensor and the actuators.

[0147] Figure 15 shows a network node 1500 in accordance with some embodiments. As used herein, network node refers to equipment capable, configured, arranged and / or operable to communicate directly or indirectly with a UE and / or with other network nodes or equipment, in a telecommunications network. In accordance with respective embodiments, network node 1500 may be configured to operate in communication system 1200 of Figure 12, like network nodes 1208 or 1210, or in communication system 1300 of Figure 13, like an AP 1310 or a station 1312. Examples of network nodes include, but are not limited to, access points (APs) (e.g., radio access points), base stations (BSs) (e.g., radio base stations, Node Bs, evolved Node Bs (eNBs) and NR NodeBs (gNBs)), O-RAN nodes or components of an O-RAN node (e.g., O-RU, O-DU, O-CU).

[0148] Network nodes 1500 may be categorized based on the amount of coverage they provide (or, stated differently, their transmit power level) and so, depending on the provided amount of coverage, may be referred to as femto base stations, pico base stations, micro base stations, or macro base stations. Network node 1500 may be a relay node or a relay donor node controlling a relay. Network nodes 1500 may also include one or more (or all) parts of a distributed radio base station such as centralized digital units, distributed units (e.g., in an O-RAN access node) and / or remote radio units (RRUs), sometimes referred to as Remote Radio Heads (RRHs). Such remote radio units may or may not be integrated with an antenna as an antenna integrated radio. Parts of a distributed radio base station may also be referred to as nodes in a distributed antenna system (DAS).

[0149] Other examples of network nodes 1500 include multiple transmission point (multi-TRP) 5G access nodes, multi-standard radio (MSR) equipment such as MSR BSs, network controllers such as radio network controllers (RNCs) or base station controllers (BSCs), base transceiver stations (BTSs), transmission points, transmission nodes, multi-cell / multicast coordination entities (MCEs), Operation and Maintenance (O&M) nodes, Operations Support System (OSS) nodes, Self-Organizing Network (SON) nodes, positioning nodes (e.g., Evolved Serving Mobile Location Centers (E-SMLCs)), and / or Minimization of Drive Tests (MDTs).

[0150] In particular embodiments, network node 1500 includes a processing circuitry 1502, a memory 1504, a communication interface 1506, and a power source 1508. In general, in a particular embodiment of network node 1500, processing circuitry 1502, memory 1504, communication interface 1506, and power source 1508 may, in whole or in part, represent or include physical components common to or shared by one or more of the other elements of network node 1500.

[0151] The network node 1500 may be composed of multiple distinct network entities (e.g., a NodeB entity and a RNC entity, or a BTS entity and a BSC entity, etc.), which may each have or utilize their own respective physical components. In certain scenarios in which the network node 1500 comprises multiple such entities (e.g., BTS and BSC), one or more of the separate entities may be shared among several network nodes. For example, a single RNC may control multiple NodeBs. In such a scenario, each unique NodeB and RNC pair, may in some instances be considered a single separate network node. In some embodiments, the network node 1500 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memories 1504 or portions of memory 1504 for different RATs) and some components may be reused (e.g., a same antenna 1510 may be shared by different RATs). The network node 1500 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 1500, for example GSM, WCDMA, LTE, NR, Wi-Fi (e.g., according to an IEEE 802.11 family standard), Zigbee, Z-wave, LoRaWAN, Radio Frequency Identification (RFID) or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within network node 1500.

[0152] The processing circuitry 1502 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and / or encoded logic operable to provide, either alone or in conjunction with other components, such as the memory 1504, to provide network node 1500 functionality.

[0153] In some embodiments, the processing circuitry 1502 includes a system on a chip (SOC). In some embodiments, the processing circuitry 1502 includes one or more of radio frequency (RF) transceiver circuitry 1512 and baseband processing circuitry 1514. In some embodiments, the RF transceiver circuitry 1512 and the baseband processing circuitry 1514may be on separate chips (or sets of chips), boards, or units, such as radio units and digital units. In alternative embodiments, part or all of RF transceiver circuitry 1512 and baseband processing circuitry 1514 may be on the same chip or set of chips, boards, or units.

[0154] The memory 1504 may comprise any form of volatile or non-volatile computer-readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD)), and / or any other volatile or non-volatile, non-transitory device-readable and / or computer-executable memory devices that store information, data, and / or instructions that may be used by the processing circuitry 1502. The memory 1504 may store any suitable instructions, data, or information, including a computer program, software, an application including one or more of logic, rules, code, tables, and / or other instructions capable of being executed by the processing circuitry 1502 and utilized by the network node 1500. The memory 1504 may be used to store any calculations made by the processing circuitry 1502 and / or any data received via the communication interface 1506. In some embodiments, the processing circuitry 1502 and memory 1504 is integrated.

[0155] The communication interface 1506 is used in wired or wireless communication of signaling and / or data with UEs, other network nodes, and / or any other network equipment. In the illustrated embodiment, communication interface 1506 comprises port(s) / terminal(s) 1516 to send and receive data, for example to and from a network over a wired connection. In particular embodiments, network node 1400 may be capable of wireless communication and communication interface 1506 may also include radio front-end circuitry 1518 that may be coupled to, or in certain embodiments a part of, an antenna 1510. Particular embodiments of radio front-end circuitry 1518 include filter(s) 1520 and amplifier(s) 1522. The radio front-end circuitry 1518 may be connected to an antenna 1510 and processing circuitry 1502. The radio front-end circuitry may be configured to condition signals communicated between antenna 1510 and processing circuitry 1502. The radio front-end circuitry 1518 may receive digital data that is to be sent out to other network nodes or UEs via a wireless connection. The radio front-end circuitry 1518 may convert the digital data into a radio signal(s) having the appropriate channel and bandwidth parameters using a combination of filters 1520 and / or amplifiers 1522. The radio signal(s) may then be transmitted via the antenna 1510. Similarly, when receiving data, the antenna 1510 may collect radio signals which are then converted into digital data by the radio front-end circuitry 1518. The digital data may be passed to the processing circuitry 1502. In other embodiments, the communication interface may comprise different components and / or different combinations of components.In certain alternative embodiments, network node 1500 may be capable of wireless communication but does not include separate radio front-end circuitry 1518, instead, the processing circuitry 1502 includes radio front-end circuitry and is connected to the antenna 1510. Similarly, in some embodiments, all or some of the RF transceiver circuitry 1512 is part of the communication interface 1506. In still other embodiments, the communication interface 1506 includes one or more ports or terminals 1516, the radio front-end circuitry 1518, and the RF transceiver circuitry 1512, as part of a radio unit (not shown), and the communication interface 1506 communicates with the baseband processing circuitry 1514, which is part of a digital unit (not shown).

[0156] The antenna 1510 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 1510 may be coupled to the radio front-end circuitry 1518 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 1510 is separate from the network node 1500 and connectable to the network node 1500 through one or more interfaces or ports.

[0157] The antenna 1510, communication interface 1506, and / or the processing circuitry 1502 may be configured to perform some or all of the receiving operations and / or obtaining operations described herein as being performed by the network node 1500. Any information, data and / or signals may be received from a UE, another network node and / or any other network equipment. Similarly, the antenna 1510, the communication interface 1506, and / or the processing circuitry 1502 may be configured to perform some or all of the transmitting or sending operations described herein as being performed by the network node 1500. Any information, data and / or signals may be transmitted to a UE, another network node and / or any other network equipment.

[0158] The power source 1508 provides power to the various components of network node 1500 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source 1508 may further comprise, or be coupled to, power management circuitry to supply the components of the network node 1500 with power for performing the functionality described herein. For example, the network node 1500 may be connectable to an external power source (e.g., the power grid, an electricity outlet) via an input circuitry or interface such as an electrical cable, whereby the external power source supplies power to power circuitry of the power source 1508. As a further example, the power source 1508 may comprise a source of power in the form of a battery or battery pack which is connected to, or integrated in, power circuitry. The battery may provide backup power should the external power source fail.

[0159] Embodiments of the network node 1500 may include additional components beyond those shown in Figure 15 for providing certain aspects of the network node’s functionality,including any of the functionality described herein and / or any functionality necessary to support the subject matter described herein. For example, the network node 1500 may include user interface equipment to allow input of information into the network node 1500 and to allow output of information from the network node 1500. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node 1500.

[0160] Figure 16 is a block diagram illustrating a virtualization environment 1600 in which functions implemented by some embodiments may be virtualized. In the present context, virtualizing means creating virtual versions of apparatuses or devices which may include virtualizing hardware platforms, storage devices and networking resources. As used herein, virtualization can be applied to any device described herein, or components thereof, and relates to an implementation in which at least a portion of the functionality is implemented as one or more virtual components. Some or all of the functions described herein may be implemented as virtual components executed by one or more virtual machines (VMs) implemented in one or more virtual environments 1600 hosted by one or more of hardware nodes, such as a hardware computing device that operates as an access network node, UE, core network node, or host. Further, in embodiments in which a virtual node does not require radio connectivity (e.g., a core network node or host), then the node may be entirely virtualized. In some embodiments, the virtualization environment 1600 includes components defined by the O-RAN Alliance, such as an O-Cloud environment orchestrated by a Service Management and Orchestration Framework via an 0-2 interface.

[0161] Applications 1602 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment Q400 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0162] Hardware 1604 includes processing circuitry, memory that stores software and / or instructions executable by hardware processing circuitry, and / or other hardware devices as described herein, such as a network interface, input / output interface, and so forth. Software may be executed by the processing circuitry to instantiate one or more virtualization layers 1606 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VM 1608A and VM 1608B (which may be collectively referred to as VMs 1608), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. The virtualization layer 1606 may present a virtual operating platform that appears like networking hardware to one or more of the VMs 1608.

[0163] The VMs 1608 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by virtualization layer 1606. Different embodiments of the instance of a virtual appliance 1602 may be implemented on one ormore of VMs 1608, and the implementations may be made in different ways. Virtualization of the hardware is in some contexts referred to as network function virtualization (NFV). NFV may be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches, and physical storage, which can be located in data centers, and customer premise equipment.

[0164] In the context of NFV, each of the VMs 1608 may be a software implementation of a physical machine that runs programs as if they were executing on a physical, non-virtualized machine. Each of the VMs 1608, and that part of hardware 1604 that executes that VM, be it hardware dedicated to that VM and / or hardware shared by that VM with others of the VMs, forms separate virtual network elements. Still in the context of NFV, a virtual network function is responsible for handling specific network functions that run in one or more of the VMs 1608 on top of the hardware 1604 and corresponds to an application 1602.

[0165] Hardware 1604 may be implemented in a standalone network node with generic or specific components. Hardware 1604 may implement some functions via virtualization. Alternatively, hardware 1604 may be part of a larger cluster of hardware (e.g. such as in a data center or CPE) where many hardware nodes work together and are managed via management and orchestration 1610, which, among others, oversees lifecycle management of applications 1602. In some embodiments, hardware 1604 is coupled to one or more radio units that each include one or more transmitters and one or more receivers that may be coupled to one or more antennas. Radio units may communicate directly with other hardware nodes via one or more appropriate network interfaces and may be used in combination with the virtual components to provide a virtual node with radio capabilities, such as a radio access node ora base station. In some embodiments, some signaling can be provided with the use of a control system 1612 which may alternatively be used for communication between hardware nodes and radio units.

[0166] Although the computing devices described herein (e.g., UEs, network nodes, hosts) may include the illustrated combination of hardware components, other embodiments may comprise computing devices with different combinations of components. It is to be understood that these computing devices may comprise any suitable combination of hardware and / or software needed to perform the tasks, features, functions and methods disclosed herein. Determining, calculating, obtaining or similar operations described herein may be performed by processing circuitry, which may process information by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination. Moreover, while components are depicted as single boxes located within a larger box, or nested withinmultiple boxes, in practice, computing devices may comprise multiple different physical components that make up a single illustrated component, and functionality may be partitioned between separate components. For example, a communication interface may be configured to include any of the components described herein, and / or the functionality of the components may be partitioned between the processing circuitry and the communication interface. In another example, non-computationally intensive functions of any of such components may be implemented in software or firmware and computationally intensive functions may be implemented in hardware.

[0167] In certain embodiments, some or all of the functionality described herein may be provided by processing circuitry executing instructions stored on in memory, which in certain embodiments may be a computer program product in the form of a non-transitory computer-readable storage medium. In alternative embodiments, some or all of the functionality may be provided by the processing circuitry without executing instructions stored on a separate or discrete device-readable storage medium, such as in a hard-wired manner. In any of those particular embodiments, whether executing instructions stored on a non-transitory computer-readable storage medium or not, the processing circuitry can be configured to perform the described functionality. The benefits provided by such functionality are not limited to the processing circuitry alone or to other components of the computing device, but are enjoyed by the computing device as a whole, and / or by end users and a wireless network generally.

Claims

CLAIMS1. A method performed by communication equipment (10), the method comprising: obtaining (900) different input datasets (22-1 ...22-N) that are respectively formed from results (21-1 ...21-N) of measurements on positioning signals (18) received by the communication equipment (10) on different sets (20-1...20-N) of positioning signal resources (19);determining (910), from inputting each of the different input datasets (22-1...22-N) into a machine learning model (12) deployed at the communication equipment (10), a respective estimate (24-1 ...24-N) that is output from the machine learning model (12), wherein each respective estimate (24-1 ...24-N) comprises an estimation of a location (14L) of target equipment (14) or an estimation of a result of a measurement from which the location (14L) of the target equipment (14) is determinable, wherein the target equipment (14) is the same as or different than the communication equipment (10); andevaluating (920) a performance (28) of the machine learning model (12) based on comparing the estimates (24-1...24-N) that are output from the machine learning model (12) for the different input datasets (22-1 ...22-N).

2. The method of claim 1 , wherein the positioning signals (18) received on different sets (20-1 ...20-N) of positioning signal resources (19) are received from different transmission points (15-1 ...15-X) and / or belong to different positioning frequency layers (17-1 ...17-Y).

3. The method of any of claims 1-2, wherein at least some of the positioning signals (18) received on different sets (20-1 ...20-N) of positioning signal resources (19) belong to different positioning frequency layers (17-1 ...17-Y).

4. The method of claim 3, wherein at least some of the positioning signals (18) received on different sets (20-1 ...20-N) of positioning signal resources (19) are received from the same transmission point or from the same set (15S) of transmission points (15-1 ...15-X).

5. The method of any of claims 1-2, wherein at least some of the positioning signals (18) received on different sets (20-1 ...20-N) of positioning signal resources (19) are received from different sets of transmission points (15-1 ...15-X) and belong to different positioning frequency layers (17-1...17-Y).

6. The method of any of claims 1-5, further comprising:receiving signaling indicating sets of positioning signal resources (19) on which the communication equipment (10) is to perform measurements for locating the target equipment (14);selecting a first subset of the indicated sets of positioning signal resources (19) as one or more sets of positioning signal resources (19) on which to perform measurements for locating the target equipment (14) using the machine learning model (12); andselecting a second subset of the indicated sets of positioning signal resources (19) as the different sets (20-1 ...20-N) of positioning signal resources (19) on which to evaluate the performance (28) of the machine learning model (12), wherein the different input datasets (22-1...22-N) are respectively formed from results (21- 1...21-N) of measurements on positioning signals (18) received by the communication equipment (10) on the sets of positioning signal resources (19) in the second subset.

7. The method of any of claims 1-6, wherein said evaluating comprises evaluating a performance (28) of the machine learning model (12) based on how close the estimates (24-1 ...24-N) output for the different input datasets (22-1 ...22-N) are to one another.

8. The method of claim 7, wherein said evaluating comprises:determining that the machine learning model (12) has a first level of performance (28) if any pair of estimates (24-1 ...24-N) output for different input datasets (22- 1...22-N) differ from one another by at least a threshold amount; or determining that the machine learning model (12) has a second level of performance (28) if each pair of estimates (24-1 ...24-N) output for different input datasets (22-1...22-N) differ from one another by less than the threshold amount.

9. The method of claim 8, further comprising receiving signaling indicating the threshold amount.

10. The method of any of claims 1-9, further comprising deciding, based on said evaluating, whether to perform one or more actions to address a problem with the performance (28) of the machine learning model (12).

11. The method of claim 10, wherein the one or more actions include one or more of: updating or retraining the machine learning model (12);switching to using a different machine learning model (12); orswitching to a different positioning method that does not use any machine learning model (12).

12. The method of any of claims 1-11, further comprising receiving (940) assistance data indicating the different sets (20-1 ...20-N) of positioning signal resources (19).

13. The method of any of claims 1-12, wherein:the communication equipment (10) is a communication device configured to receive service from a communication network, wherein the positioning signals (18) are downlink positioning signals received from the communication network; or the communication equipment (10) is network equipment of a communication network configured to provide service to one or more communication devices, wherein the positioning signals (18) are uplink signals received from a communication device.

14. The method of any of claims 1-13, further comprising:receiving (950) a request for an estimate (24) comprising an estimation of the location (14L) of the target equipment (14) or an estimation of a result of a measurement from which the location (14L) of the target equipment (14) is determinable, wherein the request requests that the estimate (24) be determined from the machine learning model (12) deployed at the communication equipment (10); and transmitting (960) a response to the request, wherein the response includes the requested estimate (24) and an indication of whether or not the estimate (24) included in the response was determined from the machine learning model (12) deployed at the communication equipment (10).

15. The method of claim 14, wherein the indication indicates that the estimate (24) included in the response was not determined from any machine learning model (12) deployed at the communication equipment (10), wherein the response further includes a reason why the estimate (24) included in the response was not determined from the machine learning model (12) deployed at the communication equipment (10), wherein the reason is a problem with the performance (28) of the machine learning model (12) deployed at the communication equipment (10) as determined from said evaluating.

16. Communication equipment (10) configured to:obtain different input datasets (22-1 ...22-N) that are respectively formed from results (21-1 ...21-N) of measurements on positioning signals (18) received by thecommunication equipment (10) on different sets (20-1...20-N) of positioning signal resources (19);determine, from inputting each of the different input datasets (22-1...22-N) into a machine learning model (12) deployed at the communication equipment (10), a respective estimate (24-1 ...24-N) that is output from the machine learning model (12), wherein each respective estimate (24-1 ...24-N) comprises an estimation of a location (14L) of target equipment (14) or an estimation of a result of a measurement from which the location (14L) of the target equipment (14) is determinable, wherein the target equipment (14) is the same as or different than the communication equipment (10); andevaluate a performance (28) of the machine learning model (12) based on comparing the estimates (24-1 ...24-N) that are output by the machine learning model (12) for the different input datasets (22-1 ...22-N).

17. The communication equipment (10) of claim 16, configured to perform the method of any of claims 2-15.

18. A computer program comprising instructions which, when executed by at least one processor of communication equipment (10), causes the communication equipment (10) to perform the method of any of claims 1 -15.

19. A carrier containing the computer program of claim 18, wherein the carrier is one of an electronic signal, optical signal, radio signal, or computer readable storage medium.

20. A method performed by communication equipment (10), the method comprising: receiving (1000) assistance data indicating different sets (20-1 ...20-N) of positioning signal resources (19) on which the communication equipment (10) is to perform measurements for locating target equipment (14), wherein the target equipment (14) is the same as or different than the communication equipment (10); receiving (1010) a request for an estimate (24) comprising an estimation of a location (14L) of the target equipment (14) or an estimation of a result of a measurement from which the location (14L) of the target equipment (14) is determinable, wherein the request requests that the estimate (24) be determined from a machine learning model (12) deployed at the communication equipment (10) and from results (21-1...21-N) of measurements on positioning signals (18) received by the communication equipment (10) on the different sets (20-1 ...20-N) of positioning signal resources (19); andtransmitting (1020) a response to the request, wherein the response includes the estimate (24) and an indication of whether or not the estimate (24) included in the response was determined from the machine learning model (12) deployed at the communication equipment (10).

21. The method of claim 20, wherein the indication indicates that the estimate (24) included in the response was not determined from any machine learning model (12) deployed at the communication equipment (10).

22. The method of claim 21 , wherein the response further includes a reason why the estimate (24) included in the response was not determined from the machine learning model (12) deployed at the communication equipment (10), wherein the reason is a problem with performance (28) of the machine learning model (12) deployed at the communication equipment (10).

23. The method of claim 22, wherein the problem is that respective estimates (24-1...24-N) output by the machine learning model (12) for the different sets (20-1...20-N) of positioning signal resources (19) are not close enough together.

24. The method of any of claims 22-23, further comprising receiving signaling indicating a minimum level of performance (28) that the machine learning model (12) at the communication equipment (10) must have in order for the requested estimate (24) to be determined from the machine learning model (12).

25. The method of claim 24, wherein the signaling indicates the minimum level of performance (28) in terms of a maximum allowable amount by which respective estimates (24-1 ...24-N) output by the machine learning model (12) for the different sets (20-1...20-N) of positioning signal resources (19) can differ from one another in order for the machine learning model (12) to be used to determine the requested estimate (24).

26. The method of any of claims 20-25, wherein the different sets (20-1 ...20-N) of positioning signal resources (19) are sets of positioning signal resources (19) on which the communication equipment (10) is to receive positioning signals (18) that are from different transmission points (15-1 ...15-X) and / or that belong to different positioning frequency layers (17-1...17-Y).

27. The method of any of claims 20-26, wherein the different sets (20-1 ...20-N) of positioning signal resources (19) belong to different positioning frequency layers (17-1 ...17-Y).

28. The method of claim 27, wherein the different sets (20-1 ...20-N) of positioning signal resources (19) are sets of positioning signal resources (19) on which the communication equipment (10) is to receive positioning signals (18) from the same transmission point or from the same set (15S) of transmission points (15-1 ...15-X).

29. The method of any of claims 20-26, wherein the different sets (20-1 ...20-N) of positioning signal resources (19) are sets of positioning signal resources (19) on which the communication equipment (10) is to receive positioning signals (18) that are from the different sets of transmission points (15-1...15-X) and that belong to different positioning frequency layers (17-1...17-Y).

30. The method of any of claims 20-29, wherein:the communication equipment (10) is a communication device configured to receive service from a communication network, wherein the positioning signals (18) are downlink positioning signals received from the communication network; or the communication equipment (10) is network equipment of a communication network configured to provide service to one or more communication devices, wherein the positioning signals (18) are uplink positioning signals received from a communication device.

31. The method of any of claims 20-30, wherein the indication implicitly indicates a performance (28) of the machine learning model (12) as evaluated by the communication equipment (10).

32. The method of claim 31 , wherein the indication implicitly indicates the performance (28) of the machine learning model (12) as evaluated by the communication equipment (10) based on a comparison of respective estimates (24-1...24-N) that are output by the machine learning model (12) for different input datasets (22-1 ...22-N) formed from results (21-1 ...21-N) of measurements on the different sets (20-1 ...20-N) of positioning signal resources (19).

33. Communication equipment (10) configured to:receive assistance data indicating different sets (20-1...20-N) of positioning signal resources (19) on which the communication equipment (10) is to performmeasurements for locating target equipment (14), wherein the target equipment (14) is the same as or different than the communication equipment (10); receive a request for an estimate (24) comprising an estimation of a location (14L) of the target equipment (14) or an estimation of a result of a measurement from which the location (14L) of the target equipment (14) is determinable, wherein the request requests that the estimate (24) be determined from a machine learning model (12) deployed at the communication equipment (10) and from results (21- 1...21-N) of measurements on positioning signals (18) received by the communication equipment (10) on the different sets (20-1...20-N) of positioning signal resources (19); andtransmit a response to the request, wherein the response includes the estimate (24) and an indication of whether or not the estimate (24) included in the response was determined from the machine learning model (12) deployed at the communication equipment (10).

34. The communication equipment (10) of claim 33, configured to perform the method of any of claims 21-32.

35. A computer program comprising instructions which, when executed by at least one processor of communication equipment (10), causes the communication equipment (10) to perform the method of any of claims 20-32.

36. A carrier containing the computer program of claim 35, wherein the carrier is one of an electronic signal, optical signal, radio signal, or computer readable storage medium.

Images