Identify and correct anomalies in a packet synchronized system

Abstract

A computer-implemented method performed by a computing device is provided to correct anomalies in a packet synchronized system associated with a telecommunications network. The method includes identifying (1810) an anomaly in synchronization in a transport network based on an evaluation of performance of the packet synchronized system with a graph-based ML model. The anomaly includes a time misalignment between a plurality of radio access nodes in the telecommunications network. The method further includes initiating (1812) a remedial action to correct the time misalignment.

Description

IDENTIFY AND CORRECT ANOMALIES IN A PACKET SYNCHRONIZED SYSTEMTECHNICAL FIELD

[0001] The present disclosure is related to wireless communication systems and more particularly to a computer implemented method performed by a computing device to detect and correct anomalies in a packet synchronized system associated with a telecommunications network.BACKGROUND

[0002] In today's digital era, telecommunications networks are considered crucial to accelerate digital transformation towards the “Fourth Industrial Revolution” (Industry 4.0). Efficient connectivity infrastructure is important to enable machine interaction in a flexible, secure, and consistent manner. Industrial automation applications have stringent service requirements on high availability, low latency, and precise time synchronization. Therefore, precise time synchronization may be critical in industries where real-time coordination and interaction among devices is needed (e.g., smart manufacturing, vehicular communication, robotic-assisted surgery, etc.).

[0003] Commercial fifth generation (5G) networks use different time synchronization solutions to achieve time alignment between antenna reference points (ARPs) in the radio access network. Traditionally, each node in the radio access network is equipped with a local reference that has traceability to a common time reference, for example global positioning system (GPS) System Time. The local reference can be provided by a global navigation satellite system (GNSS) receiver that receives GPS System Time. Alternatively, a common reference time (CRT) can be carried over the backhaul network, e.g. via a timing protocol such as Precision Time Protocol (PTP), to the radio access network nodes.SUMMARY

[0004] Some approaches regarding measuring and improving time synchronization accuracy in a packet synchronized system may not be scalable; may not identify time misalignment between ARPS; may not estimate route delay from a PTP clock; may not use over-the-air synchronization to correct time alignment; may not identify a root cause of time misalignment; may not be automated; and / or may not identify time misalignment between multivendor equipment.

[0005] Certain aspects of the disclosure and their embodiments may provide solutions to these or other challenges. In some embodiments, a computer implemented method performed bya computing device is provided to correct anomalies in a packet synchronized system associated with a telecommunications network. In other words, there is provided a method for handling anomalies in a packet synchronized system associated with a telecommunications network. The method includes identifying an anomaly in synchronization in a transport network based on an evaluation of performance of the packet synchronized system with a graph-based machine learning (ML) model. The anomaly includes a time misalignment between a plurality of radio access nodes in the telecommunications network. The method further includes initiating a remedial action to correct the time misalignment.

[0006] According to other embodiments, a computing device or non-transitory readable medium is provided to perform the above method or, in other words, a computing device or non- transitory readable medium is provided and adapted to perform the above method.

[0007] Certain embodiments may provide one or more of the following technical advantages. In some embodiments, identifying and / or initiating correction of anomalies in packet networks used for time synchronization is provided using a graph-based ML model, which may address challenges due to time errors in time sensitive networks, such as various components in an open-radio access network (O-RAN) network. Moreover, the identification and / or initiation of correction may enhance observability in a packet synchronized system; may alleviate expenses for tasks that are often handled by customer support as well as troubleshooting activities by network engineers; may help to minimize efforts to find anomalies which may lead to increased network reliability and availability; and / or the process of some embodiments may be standardized, which may enable localization of a fault(s) regardless of network technology.BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this application, illustrate certain non-limiting embodiments of inventive concepts. In the drawings:

[0009] Figure l is a schematic drawing illustrating an example synchronization system that includes a transport domain with PTP support in accordance with some embodiments;

[0010] Figure 2 is a schematic drawing of an example of use two synchronization paths for time synchronization;

[0011] Figure 3 i is a schematic drawing of an example of the first packet synchronized system deployment scenario in accordance with some embodiments;

[0012] Figure 4 is a schematic drawing of an example of the second packet synchronized system deployment scenario in accordance with some embodiments;

[0013] Figure 5 is a schematic drawing of an example of the third packet synchronized system deployment scenario in accordance with some embodiments;

[0014] Figure 6 is a schematic drawing of an example of the fourth packet synchronized system deployment scenario in accordance with some embodiments;

[0015] Figure 7 is a flow chart of an example process to diagnose site issues caused by anomalies in synchronization deployment in accordance with some embodiments;

[0016] Figure 8 is a schematic drawing of an example of a synch path between a CRT and an ARP in accordance with some embodiments;

[0017] Figure 9 is a schematic drawing of an example of how a plurality of synch paths are related in accordance with some embodiments;

[0018] Figure 10 is a schematic drawing of an example of a path trace between a CRT and an ARP in accordance with some embodiments;

[0019] Figure 11 is a schematic drawing of an example of type-length-variable (TLV) additional information to a PTP message in accordance with some embodiments;

[0020] Figure 12 is a flow chart of an example process to construct two graphs in accordance with some embodiments;

[0021] Figure 13 is a schematic drawing of an example of different types of nodes in a time synch system in accordance with some embodiments;

[0022] Figure 14 is a block diagram showing an example of how data can be mapped for different nodes in a TN sync domain in accordance with some embodiments;

[0023] Figures 15A and 15B are schematic drawings of two examples of identified anomalies in a packet synchronized network in accordance with some embodiments;

[0024] Figures 16 and 17 are schematic drawings of eexamples of open-radio access network (O-RAN) deployment scenarios for synchronization in accordance with some embodiments;

[0025] Figure 18 is a flow chart illustrating an example of operations performed by a computing device in accordance with some embodiments;

[0026] Figure 19 is a block diagram of a computing device in accordance with some embodiments;

[0027] Figure 20 is a block diagram of a communication system in accordance with some embodiments;

[0028] Figure 21 is a block diagram of a user equipment (UE) in accordance with some embodiments;

[0029] Figure 22 is a block diagram of a network node in accordance with some embodiments; and

[0030] Figure 23 is a block diagram of a virtualization environment in accordance with some embodiments.DETAILED DESCRIPTION

[0031] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art, in which examples of embodiments of the present disclosure are shown. The present disclosure may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of present inventive concepts to those skilled in the art. It should also be noted that these embodiments are not mutually exclusive. Components from one embodiment may be tacitly assumed to be present / used in another embodiment.

[0032] As time synchronization has become important for industrial automation applications in the era of 5G, there may be a need to track synchronization problems in the network and detect anomalies in a timely manner. With advanced artificial intelligence (Al) techniques, it may be possible to optimize and simplify such troubleshooting processes to expedite operations while reducing the need for human participation and supervision.

[0033] Figure 1 is a schematic drawing of an example synchronization system 100 that includes a transport domain 106 with PTP support. The transport domain 106 includes a router(s) 108. In an effort to optimize time synchronization solutions, in one approach, a software (SW) feature may allow mobile operators to accurately measure and monitor cell time alignment at antennas of radio units (RUs) 102a, 102b and / or 102c of a site 104. The feature may make it possible to discover insufficient alignment of ARPs of RU(s) 102a, 102b, 102c caused by insufficient alignment of ARPs to CRT (e.g., enhanced Primary Reference Time Clock (ePRTC) 110) which in turn may be caused by poor installation of a global navigation satellite system (GNSS) 112 antenna or large asymmetries in the timing protocol path.

[0034] Fault detection and time misalignment localization for time synchronization in 5G- and-beyond networks is now discussed. Before rolling out a new software (SW) feature in an operational network, a SW typically goes through a rigorous development and review process in a controlled environment. Once a SW passes the test process, the new SW feature can be deployed in a telecommunications network. However, there may be a gap between the test environment and an operational network due to reasons such as changes in unseen environmental conditions, underlaying SW / hardware (HW) coordination that can lead to performance degradation, etc.

[0035] In order to mitigate performance degradation in a SW module, mobile operators can collect logs, events, and counters to enable instant feedback and alerts for any abnormal behavior in the system. Efforts to troubleshoot a packet synchronized system often can depend on a threshold-based process to detect anomalies and rely on domain experts to inspect logs and pinpoint to faults causing the problem. However, such a process is not scalable. A challenge to diagnosis synch module anomalies may include the interdependency on other subsystems (e.g., PTP, etc.), the complexity of proprietary telecommunications vendor software, and topographic factors in deployment settings. Moreover, when deploying a new SW feature in a network, it can be important to understand why the problem occurred to mitigate the anomaly from happening again. The process of debugging such capabilities individually without taking into account the macro-level dynamics can lead to sub-optimal decisions.

[0036] An 0-RAN and a challenge if time synchronization in 5G-and-beyond networks is now discussed. The advent of telecommunication technologies, the innovation provided by network virtualization, and the new architectural standardization by the 0-RAN Alliance have paved the way to leverage the potential of Al through new modular design that aim to introduce virtualized network elements, openness, and intelligence to RAN management. The new 0-RAN architecture may unlock new potential solutions. However, considering the openness of 0-RAN components, a process to mitigate faults and time misalignment when using multi-vendor equipment may be needed. A multi-vendor scenario can include challenges for time synchronization.

[0037] A 5G network can be divided into a multitude of components that network across standardized interfaces and well-defined application interfaces (APIs). The 0-RAN architecture, for example, specifies components including the concept of xAPPs and rAPPs. For example, a 0-RAN architecture and reference design of a non-real time (non-RT) RAN intelligent controller (RIC radio) and near RT-RIC as a framework may contain a multitude of xAPPs and rAPPs. An 0-RAN architecture may make it accessible for a myriad of multi-vendor 0-RAN compliant products with different design to work in parallel. As telecommunications network behavior and characteristics components may not be fully standardized, a challenge can arise when a time clock of multiple base stations, with different vendors, start to deviate. Another potential challenge may be to automate the process of selection and management of correcting the time.

[0038] Telecommunications Al, 0-RAN, and time synchronization standardization efforts are now discussed. The Third Generation Partnership Project (3GPP), for Release 17 of the 5G system, expanded the support for time synchronization and time sensitive communications for any application.

[0039] Additionally, there has been a discussion to start standardizing telecommunication network behavior and characteristics components. Time Synchronization standardization is being discussed as part of O-RAN work group 4 (WG4).

[0040] Moreover, there are multiple efforts to standardize how to use Al in 5G networks and O-RAN. For example, there are requirements on how to use O-RAN Al / machine learning (ML) Workflow Description and Requirements 1.03 in 0-RAN.WG2.AIML-v01.03 Technical Specification, July 2021.

[0041] There currently exist certain challenges regarding time synchronization accuracy. Challenges may include that some approaches rely on human expertise to troubleshoot faults in the network. However, such methods are not scalable. Other approaches may view a RAN node as one entity and troubleshoot time alignment between nodes rather than between ARPs.

[0042] Further, for time synchronization, a time difference between clocks of network components is negligible or small. Another approach may use a process to maintain accuracy and consistency between different network components, often referred as time synchronization, which can use different protocols. Time synchronization may be achieved using a PTP protocol, for example, in the transport layer. A PTP protocol can use PTP messages to transfer time synchronization from a PTP grandmaster clock to other PTP clocks, and the messages can circulate in both directions. This message exchange may make it possible to estimate the route delay and distribute the time from the PTP grandmaster.

[0043] Still other approaches may use over-the air (OTA) synchronization to find time alignment between ARPs. OTA synchronization can compare time information of an ARP with its neighboring ARP(s) to detect a time error differences value, which can lead to anomaly detection. Potential challenges of such an approach, however, may be that it does not indicate the source of the error; and / or that this approach may not be used to correct the time misalignment.

[0044] Moreover, current counters may not be enough to identify a root cause if a time misalignment. For example, network elements may report a network problem perceived by the network elements (or individually). In an example, a large packet delay variation may indicate a potential problem, but this may not be a reliable measure. Thus, collection of data at a network level may be needed.

[0045] Additionally, automation for transport network synchronization may be needed. Manually labeling a faulty case can be a costly and time-consuming process. Due to the complexity and density of network, it may not be possible to have a complete set of equations. For instance, there may be a long distance between CRT and ARP, which can lead to a very long list of possible equations. Figure 2 is a schematic drawing of an example of two synchronizationpaths (Path 1 between GMA-ARP4 and Path 2 between GMA-ARP5) for time synchronization. A challenge may arise, however, because these are two unknowns (ARP3-ARP5 and ARP3- ARP4) and one equation. Thus, there may be a need for a way to approximate the source of the error using other information.

[0046] Moreover, an approach for time synchronization for O-RAN may be needed. For example, existing solutions to automate cloud radio access network (C-RAN) / O-RAN may not have a clear process to detect time misalignment between multi-vendor equipment.

[0047] Some examples of the present disclosure include a computer-implemented process performed by a computing device to identify and correct anomalies in a packet synchronized system associated to deployment of a telecommunications network (in O-RAN, for example). The process can be performed by a network apparatus and include evaluating performance of the packet synchronized system with a ML model to identify anomalies in synchronization in a transport network. The ML model can include a temporal heterogenous graph-based ML model that includes a hyper graph that can characterize synchronization in the transport network synchronization deployment. The process can further include identifying time misalignment based on the evaluation using ML mode; and taking a remedial action to correct time error in faulty components.

[0048] The process of some examples can further include collecting transport synchronization data from at least one radio access node in the RAN. The transport synchronization data can include, without limitation: PTP data; GNSS data (e.g., antenna installation, satellite system to fronthaul); geographical data; OTA measurements between ARPs; link types; and / or devices and components used in the packet synchronized system.

[0049] Further, the process of some examples can include identifying and labeling faulty data including, without limitation: validating and correcting values in the OTA using the obtained transport synchronization data; and / or identifying and labeling faulty paths from a CRT using cycles.

[0050] Still other examples can include determining an end-to-end hypergraph over synch distribution using (1) a graph of ARP -ARP pairs with (2) a synch path graph through the transport network.

[0051] Yet other examples can include preparing ML features for respective nodes and edges in a synch hyper heterogenous graph.

[0052] Other examples can include training a temporal graph-based ML model to identify anomalies.

[0053] In some examples, the remedial action can include correcting a time error in a faulty ARP.

[0054] Some examples include conceptualizing an end-to-end packet synchronized system using a heterogeneous multi-layer graph which can help in locating a synchronization anomaly. The heterogenous multi-layer graph of some examples includes combination of a graph of ARP- ARP pairs with a synchronization path graph through the transport network.

[0055] In some examples, a process is provided for time misalignment (which also may be referred to as an anomaly) detection between time sensitive components in O-RAN.

[0056] Some examples include using a graph-based ML model to identify anomalies in the packet synchronized system.

[0057] Observability in a packet synchronized system in a telecommunications network may be enriched based on including, without limitation: (1) a path trace that can be visible to analyze different nodes; (2) TLV, where a boundary clock(s) adds uncertainties through a path (e.g., a trustable measure); and / or (3) synch including (a) a path trace (e.g., set of identities) combined with (b) time accuracy / error calculated by each time error of a device in the path, and (c) round trip delay.

[0058] In some examples, time error correction is provided in a packet synchronized system.

[0059] Network synchronization implementations may traditionally seek to minimize a relative Time Error (rTE) at the ARPs of radio access network nodes in a network to the CRT, by continuously adjusting each radio access network node’s clock to a local reference that has traceability to the CRT. This may be achieved using a GNSS receiver that receives a CRT, or carried over the backhaul network, e.g., via a timing protocol such as PTP, to the radio access network nodes.

[0060] Due to inherited complexity of synch deployment scenarios, it may be difficult to locate the problem. In the following, different non-exhaustive synch deployment scenarios that may be observed in the field are discussed.

[0061] A first synch deployment scenario provides time synchronization via GNSS. Figure3 is a schematic drawing of an example of a first synch deployment scenario. A local reference is provided in this scenario by a GNSS receiver 112a, 112b, 112c that receives GPS system time and is attached to radio nodes (e.g., gNodeBs (gNBs)) that includes ARP(A), ARP(B), and ARP(C), respectively.

[0062] A second synch deployment scenario provides time synchronization via PTP. Figure4 is a schematic drawing of an example of the second synch deployment scenario. A CRT 400 may be carried over the backhaul network, e.g. via a timing protocol such as PTP, to the radio access network node(s) such as gNBs that include ARP(A0, ARP(B), ARP(C). This deploymentscenario may include two processes (1) frequency over transport, and / or (2) time / phase over transport.

[0063] As specified by the Institute of Electrical and Electronics Engineers (IEEE) 1588, for example, PTP can be used in the telecommunications industry to distribute accurate time synchronization from an accurate master, such as GNSS. The basic concept is to distribute time synchronization from a PTP grandmaster clock to leaf PTP clocks, using PTP messages.

[0064] A third synch deployment scenario provides time synchronization via an external clock. Figure 5 is a schematic drawing of an example of the third synch deployment scenario. In this scenario, a CRT is obtained directly from a clock.

[0065] A fourth synch deployment scenario provides OTA synchronization. Figure 6 is a schematic drawing of an example of the fourth synch deployment scenario.

[0066] Figure 7 is a flow chart of an example process to diagnose site synch issues. In operation 1, synch data is collected. Network data from an operational network can be used to collect one or more of the following examples of synch data:(1) PTP attributes and data from a PTP mixed observation (MO) class;(2) GNSS data including, without limitation, data about satellites in view, antenna position coordinates, etc.;(3) geographic data. For example, data can be extracted from geographic properties of a tile. Spatial data can include, but is not restricted to, building layer, points of interest (POIs), type of terrain, etc. While some approaches may rely only on telecommunications data, some examples herein include data for environmental conditions because environmental conditions can play a role in how a GNSS signal propagates, and how the synch functionality works. The data collected can include, without limitation: a building(s) footprint to capture the shape and size of a building(s); and / or POIs ((e.g., bus stations, airport, etc.) and land use information (e.g., commercial, educational, etc.).(4) Cell attributes for each network node (e.g., gNB) ARP pairs. Cell attributes for NR cells can be extracted from configuration management (CM) data. The following Table 1 shows a summary of example attributes:Etc.(5) Time alignment error measurements. For example, gNB ARP pairs data can be obtained from a gNB ARP pair, as illustrated in Figure 3, and are stored in a MO class. When the process is activated, a feature captures time-series data, which can be referred to as time alignment error measurements. Performance management (PM) data can be used to gauge feature performance. PM data may be captured at regular intervals; and a time alignment error PM counter may be a scalar. Table 2 shows an example of gNB ARP pair configuration data; and Table 3 shows an example of gNB ARP Time Alignment PM data:It is noted that there may not be a common scheme to store such information for different vendors to convey similar information within a method of moments (MOM). Thus, vendors may have different logging formats.(6) Network synch paths. Time information can propagate from a CRT (e.g., ePRTC 110) to other connected nodes RU 102, 102b, 102c, through network paths as illustrated in Figure 8, for example. The synch paths can be constructed from the information describing each node’s synchronization solution, such as, currently selected synchronization reference, PTP data sets, GNSS data, etc. As illustrated in the example in Figure 9, synch paths can be compared to identify common sub-paths. As shown in the example in Figure 9, Synch Pathl, Synch_Path2, and Synch_Path3 are compared to identify common sub-paths. Unique sub paths in the network are found and correlated with a time alignment error (TAE) as shown: TAE1 = Synch Pathl - Synch_Path2; TAE2 = Synch_Path2 - Synch_Path3; and TAE3 = Synch_Path3 - Synch Pathl.(7) Data that may enrich synch observability data. For example, a packet synchronized system 100 may include (a) a path trace (set of identities) combined with (b) time accuracy / error calculated by each time error of a device in the path, and (c) round trip delay. An example of a path trace is shown in Figure 10 between ePRTC 110, through transport domain 106 with PTP support, site 104, and ARP1 of RU 102c. Thus, a path trace can characterize a path between ePTRC and ARP, for example, which also may be standardized. The path trace can make a path visible to analyze from different nodes.Enhanced accuracy TLV also may be collected. For example, a draft standardization may be approved in the International Telecommunication Union Telecommunication (ITU-T), and has been approved in IEEE 1588a. Each boundary clock can add uncertainties through a path, as shown in the example in Figure 11. A TLV 1100 can be attached to messages to carry information on the performance (e.g., timing error (TE)) that can be achieved across a PTP network. In particular, each clock can add its contribution to the accumulated TE (which can be referred to as path TE).Additionally or alternatively, component characterization information can be collected that may help profile components in the network (e.g., device manufacturing information, etc.).

[0067] Referring again to Figure 7, operation 2 includes synch data validation and correction. In operation 2, OTA measurements can be collected to find and label ARP -ARP pairs with a time alignment error bigger than a threshold. Operation 2 can include: (1) Calculate a time alignment error for each ARP -ARP pair; (2) If Time alignment is greater than a threshold value, label it as a time alignment error; and (3) Determine a TN synch fault based on the time alignment error. For example, if all ARP -ARP pairs have a time alignment error, the label can be faulty equipment; or if the ARP -ARP pairs do not have a time alignment error, the label can be faulty ARP.

[0068] Operation 3 in Figure 7 includes synch hypergraph preparation. The synch hypergraph can be constructed using (1) a synch path graph. The synch path graph may allow to find common / not common transport equipment between the two ARP nodes in an ARP -ARP pair, for example; and (2) an OTA graph, which may allow to find ARP -ARP pairs that exchange time information, for example.

[0069] Figure 12 is a flow chart of an example process to construct the two graphs. In operation 1 of Figure 12, data is obtained from th packet synchronized system. In operation 2, OTA synch can be represented as a graph Qota= (Vota, £ota) with ^ota nodes and dotadimensional features JCotaG IR. The graph includes nodes Vota(ARPs) that are connected with edges £ota(ARP-ARP relation), represented as an OTA synch graph.

[0070] In operation 3, synch paths can be represented as a graph Qsynch path =nodes and d^synch path dimensional features^synch patheThe graph includes nodespath(ARPs and GM) that are connected with edgesSynch path (GM- ARP relation), represented as a synch paths graph.

[0071] In operation 4, an overlap is determined between grandmaster (GM)-ARP relations £ synch path ARP -ARP relations £otathat reveals common transport equipment.

[0072] In operation 5, a hyper graph Qtn-Synch (which is a non-limiting example of a graphbased ML model) is determined using overlaid Qotaand Q synch path graphs.

[0073] An example synch hyper graph includes three heterogenous nodes as shown in Figure 13: (1) a GM 1300, which is a main source of a highly accurate time reference. GM 1300 is a device that propagates the timing signal from the primary reference clock to all devices within the network; (2) Boundary clock(s) (BC) 1302, which are intermediate devices that pass the timing signal from GM 1300 down the network. A PTP protocol is a communication protocol that may assume symmetry in time error; and (3) an ARP of a RAN node (e.g., gNB) 1304a, 1304b, 1304c that receives time.

[0074] The dependencies between the heterogeneous nodes can be seen in Figure 13 and include: GM 1300-ARP 1304a, 1304b, 1304c synch path to show how time information has been received; and ARP ARP pair in the OTA network.

[0075] Referring again to Figure 7, operation 4 includes preparing features for the synch hypergraph. Combining data for different layers in the packet synchronized system may give a comprehensive and holistic view on the behavior of time sensitive components in the network and may help in assessing the packet synchronized system and locating faults. Figure 14 is a block diagram showing an example of how data can be mapped for different nodes in a packet synchronized system.

[0076] In the example in Figure 14, the packet synchronized network 1404 includes a GNSS 112, a GM 110, a transport domain 106 with PTP support, radio access nodes 102a, 102b, 102c that respectively include at least one ARP, and user equipment (UEs) 1408. The hyper graph 1400 includes layers 1402. Layers 1402 include a layer 1402a for graph Qsynch path including the synch path and a layer 1402b for graph Qotaincluding the ARP -ARP pairs. Observability data (e.g., node / edge features) 1406 includes GNSS data 1410 , PTP data 1410a, other data 1410b, ARP data 1412, GM- ARP data 1414, and ARP -ARP data 1416.

[0077] GNSS 112 in this example is characterized using the following example information 1410: GNSS data can include data about satellites in view, antenna position coordinates, etc.; GNSS receiver and antenna vendors, cable compensation values; and / or device information.

[0078] PTP data 1410b is collected, but other data 1410a like link lengths and types, connectors / SFP modules used, etc., also can be included.

[0079] An ARP (e.g., 102a, 102b, 102c, etc.) can be characterized using the following example information 1412: RAN node configuration attributes, a path trace, enhanced accuracy TLV, etc.

[0080] A GM- ARP can be characterized using the following example information 1416: time-dependent synch path measurements, link length between GNSS 112 and a first ARP 102, etc.

[0081] An ARP -ARP pair can be characterized using the following example information1416: alignment error measurements.

[0082] Step 5 in Figure 7 includes training a temporal graph-based ML model. The temporal graph-based ML model can include a heterogeneous temporal graph neural network (HTGNN) model, for example.

[0083] Graph neural networks (GNN) and their variants can be used in applications on graph datasets. An idea behind such models is to aggregate neighboring nodes’ content features while taking graph structures (edges / topology) into consideration. A HTGNN is a sub-family of GNN models that integrates both spatial and temporal dependencies while preserving heterogeneity to learn and leverage node representations for different tasks.

[0084] ML model features are now discussed. There can be different implementations and architectures of a HTGNN that take in consideration (1) a heterogeneous nature of nodes (2) graph dependency between nodes.

[0085] As discussed with respect to operation 3 of Figure 7, for example, a synch hyper graph includes nodes and edges. A node is characterized using a set of features, processed in operation 4 of Figure 7: an ARP is characterized by, but not limited to, using RAN node configuration attributes, etc.; and a GM can be a PTP GM, a transport network element, or a GNSS. A GM can use a GNSS receiver to synchronize to a CRT. lin that case the CRT is the global time distributed through the satellite system. In a small autonomous network, CRT also can be a time that a GM has. In that case, the GM is not synchronized to GNSS but has a built-in clock with an arbitrary time. A GM also can be characterized by a vendor and / or by whether it uses GNSS or not.

[0086] One-hot encoding can be generated for categorical data, and normalization can be applied on continuous data points.

[0087] An edge can be characterized using a set of features which were processed in operation 4 of Figure 7. The edge characterization can include that a GM- ARP pair is characterized by, but not limited to, using time-dependent synch path measurements; and that anARP -ARP pair is characterized by, but not limited to, using time-dependent time alignment error measurements.

[0088] Fault detection labeling for ML model training is now discussed. Step 6 in Figure 7 includes identifying anomalies using the trained graph-based ML model. For example, a process of labeling a fault can use the combination of the graph of ARP -ARP pairs with the synch path graph through the transport network. By this process, it may be possible to find what network device is causing a problem. For example, this process includes:(1) Label ARP -ARP pairs using time alignment information;(2) From the synch path graph, analyze what is common / not common transport equipment between the two ARP nodes in the ARP -ARP pair;(3) If the ARP nodes do not share any common equipment, reiterate to see if another ARP sharing the same equipment has similar ARP -ARP time alignment errors a. If they have a similar time alignment error, it may be likely that the equipment is the cause of error, as shown in the example in Figure 15A illustrating an identified fault at a radio node level; b. If they do not have a similar time alignment error, it may be more likely that a CRT is faulty, as shown in the example in Figure 15B illustrating an identified fault at the CRT level.(4) If the ARP nodes share equipment, it is likely that the fault is in one of the ARP’s.

[0089] ML model training is now discussed. The HTGNN is then trained on a set of labeled data to generalize on unseen conditions in versatile networks to realize a retained network timesensitive performance, maintain time correctness, and achieve better sustainable resilience.

[0090] Using the ML model for anomaly detection generalization may be particularly important for O-RAN, for example, where the network contains multi-vendor equipment that may be difficult to label using common product-specific thresholds.

[0091] Referring to Figure 7, operation 7 includes a remedial action(s). Locating problems using a hyper graph for radio network time synchronization may help in finding which node or component is faulty. One example remedial action is to make a time offset correction.

[0092] The example process of Figure 7 may help to locate a problem for at least one or more of the following reasons. Multiple graphs of time sources using hyper graph for radio network time synchronization data may help in locating which product in the network and RAN node led to a fault. This may be particularly important for O-RAN deployment when multivendors interwork because it may help to find the vendor that needs to conduct troubleshooting. Further, a hyper graph for radio network time synchronization may help in locating the sources of time, which may help to monitor the time error in each component. Moreover, a hyper graphfor radio network time synchronization may help locating problems that propagate from the same CRT. For instance, a GNSS can experience environmental problems that can cause a fault in other components down in the system.

[0093] It is noted that some cases may be more difficult to resolve. For example, in rural areas where the number of relations is small because there may not be a reference point; and in situations where there is missing information about a path.

[0094] Example O-RAN implementations are now discussed. O-RAN can include four different deployment scenarios for synch as shown in the examples in Figure 16 and Figure 17. A case referred to as Cl deployment in Figure 16 includes a trivial front haul network and synchronization is provided from the O-DU 1604a via a direct link to the O-RU 1606a using PTP associated with PTP GM 1602a.

[0095] For a case referred to as C2 deployment in Figure 16, the O-DU 1604b delivers synchronization to the O-RU 1606b through a network that includes network elements acting as PTP boundary clocks. In case C2, for example, a process for detecting and identifying synchronization anomalies may be very useful.

[0096] A case referred to as C3 deployment in Figure 17 includes a PTP GM 1602a connected directly to the front haul network and PTP provides synchronization both to the O-RU 1606a and the O-DU 1604a. Similar to the C2 case, the network includes network elements with PTP boundary clocks and a process for identifying synchronization problems may be very useful.

[0097] In the last example deployment scenario referred to as C4 deployment in Figure 17, the synchronization of the O-DU 1604b and the O-RU 1606b are totally separated.

[0098] Operations of a computing device 1900 (implemented using the structure of Figure 19) will now be discussed with reference to the flow chart of Figure 18 according to some embodiments of the present disclosure. For example, modules may be stored in memory 1905 or graph-based ML model 1911 of Figure 19, and these modules may provide instructions so that when the instructions of a module are executed by respective computing device processing circuitry 1903, computing device 1900 performs respective operations of the flow chart.

[0099] In some embodiments, a computer-implemented method is provided that is performed by a computing device to correct anomalies in a packet synchronized system associated with a telecommunications network. The method includes identifying (1810) an anomaly in synchronization in a transport network based on an evaluation of performance of the packet synchronized system with a graph-based ML model. The anomaly includes a time misalignment between a plurality of radio access nodes in the telecommunications network. The method further includes initiating (1812) a remedial action to correct the time misalignment.

[0100] In some embodiments, the graph-based ML model includes a temporal heterogeneous graph-based ML model that includes a hypergraph that characterizes the synchronization in the transport network.

[0101] The evaluation of performance of the packet synchronized system with the graphbased ML model can include identification of the anomaly based on a path trace combined with a time error in the path trace and a round trip delay.

[0102] The path trace can include a path between an ePRTC and an ARP of a radio access node.

[0103] The time error can be identified from a TLV including a timing error in a clock.

[0104] In some embodiments, the method further includes collecting (1800), from at least one node in the telecommunication network, data relating to synchronization in the transport network. The data includes one or more of the following: PTP data; GNSS data; geographical properties data; OTA measurements between at least one pair of ARPs of a radio access node in the telecommunications network; link types in the packet synchronized system; and an identity of at least one of a device and a component on a synch path in the packet synchronized system.

[0105] In other embodiments, the OTA measurements include at least one of (i) cell attributes for the at least one pair of ARPs of the radio access node and (ii) a time alignment error measurement for at least one pair of ARPs of the radio access node, and the method further includes performing (1902) at least one of validate and correct at least one value in the OTA measurements.

[0106] The time misalignment between a plurality of radio access nodes in the telecommunications network can be in a synch distribution paths between a CRT and the plurality of radio access nodes.

[0107] In some embodiments, the method further includes constructing (1804) the hypergraph that characterizes the synchronization in the transport network based on use of (i) a graph of a plurality ARP to ARP pairs in the telecommunications network with (ii) a graph of synchronization paths in the transport network.

[0108] The hypergraph can include (i) a plurality of nodes including at least first node comprising a master time reference clock, a second node comprising a boundary clock, and a third node comprising an ARP of a radio access node, and (ii) a plurality of edges between pairs of nodes comprising at a first edge between the first node and third node and second edge between a pair of third nodes.

[0109] In other embodiments, the method further includes preparing (1806) ML features for respective nodes in the plurality of nodes and respective edges in the plurality of edges.

[0110] In still other embodiments, the method further includes training (1808) the temporal heterogeneous graph-based ML model to identify anomalies.

[0111] Training (1808) the graph-based ML model can be performed based on use of a heterogeneous graph neural network ML model.

[0112] In other embodiments, training (1808) includes (i) identifying data including the time misalignment between the plurality of radio access nodes in the telecommunications network; and (ii) labeling, in a synch hypergraph, a fault that is associated with the time misalignment.

[0113] Identifying data can include identifying an OTA measurement that includes a time alignment error that exceeds a threshold value for pair of ARPs in the telecommunications network.

[0114] In some embodiments, the remedial action includes a correction of a time error in an ARP in the telecommunications network.

[0115] In some embodiments, the telecommunications network includes an O-RAN.

[0116] Various operations from the flow chart of Figure 18 may be optional with respect to some embodiments of computing devices network nodes configured to correct anomalies in a packet synchronized system associated with a telecommunications network. For example, the operations of blocks 1800-1808 may be optional in some embodiments.

[0117] Figure 19 shows a computing device 1900 in accordance with some embodiments. As used herein, computing device refers to equipment capable, configured, arranged and / or operable to perform operations discussed herein. Examples of computing devices include, but are not limited to, servers, computers, base stations (BSs) (e.g., radio base stations, Node Bs, eNBs, NR NodeBs (gNBs)), O-RAN nodes, or components of an O-RAN node (e.g., intelligent controller, O-RU, O-DU, O-CU).

[0118] The computing device 1900 includes processing circuitry 1903, a memory 1905 including program code 1909, a network interface 1907, a graph-based ML model 1911, and a power source (not shown). The computing device 1900 may be composed of multiple physically separate components, which may each have their own respective components. In certain scenarios in which the computing device 1900 comprises multiple separate components, one or more of the separate components may be shared among several computing device. In some embodiments, the computing device 1900 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memory 1905 for different RATs) and some components may be reused. The computing device 1900 may also include multiple sets of the various illustrated components for different wireless technologies integrated into computing device 1900, for example GSM, WCDMA, LTE, NR,WiFi, Zigbee, Z-wave, LoRaWAN, Radio Frequency Identification (RFID) or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within computing device 1900.

[0119] The processing circuitry 1903 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 computing device 1900 components, such as the memory 1905 and / or graph-based ML model 1911, to provide computing device 1900 functionality.

[0120] In some embodiments, the processing circuitry 1903 includes a system on a chip (SOC). In some embodiments, the processing circuitry 1903 includes one or more of radio frequency (RF) transceiver circuitry and baseband processing circuitry. In some embodiments, the radio frequency (RF) transceiver circuitry and the baseband processing circuitry may be on separate chips (or sets of chips), boards, or units, such as radio units and digital units. In alternative embodiments, part or all of RF transceiver circuitry and baseband processing circuitry may be on the same chip or set of chips, boards, or units.

[0121] The memory 1905 and / or graph-based ML model 1911 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 1903. The memory 1905 and / or graph-based ML model 1911 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 1903 and utilized by the computing device 1900. The memory 1905 and / or graph-based ML model 1911 may be used to store any calculations made by the processing circuitry 1903 and / or any data received via the network interface 1907. In some embodiments, the processing circuitry 1903, memory 1905 and / or graph-based ML model 1911 are integrated.

[0122] The network interface 1907 is used in wired or wireless communication of signaling and / or data between a computing device, another device, a network node, access network, and / or UE. The network interface 1907 can comprise port(s) / terminal(s) to send and receive data, forexample to and from a computing device or other device over a wired connection. The network interface 1907 also can include radio front-end circuitry that may be coupled to, or in certain embodiments a part of, an antenna. A radio signal may then be transmitted via the antenna. Similarly, when receiving data, the antenna may collect radio signals which are then converted into digital data by the radio front-end circuitry. The digital data may be passed to the processing circuitry 1903. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0123] In certain alternative embodiments, the computing device 1900 does not include separate radio front-end circuitry, instead, the processing circuitry 1903 includes radio front-end circuitry and is connected to an antenna. Similarly, in some embodiments, all or some of the RF transceiver circuitry is part of the network interface 1907. In still other embodiments, the network interface 1907 includes one or more ports or terminals, the radio front-end circuitry, and the RF transceiver circuitry, as part of a radio unit (not shown), and the network interface 1907 communicates with baseband processing circuitry, which is part of a digital unit (not shown).

[0124] The power source provides power to the various components of computing device 1900 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source may further comprise, or be coupled to, power management circuitry to supply the components of the computing device 1900 with power for performing the functionality described herein. For example, the computing device 1900 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. As a further example, the power source 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.

[0125] Embodiments of the computing device 1900 may include additional components beyond those shown in Figure 19 for providing certain aspects of the computing device’s functionality, including any of the functionality described herein and / or any functionality necessary to support the subject matter described herein. For example, the computing device 1900 may include user interface equipment to allow input of information into the computing device 1900 and to allow output of information from the computing device 1900. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the computing device 1900.

[0126] Figure 20 shows an example of a communication system 2000 in accordance with some embodiments.

[0127] In the example, the communication system 2000 includes a telecommunication network 2002 that includes an access network 2004, such as a RAN, and a core network 2006, which includes one or more core network nodes 2008. The access network 2004 includes one or more access network nodes, such as network nodes 2010a and 2010b (one or more of which may be generally referred to as network nodes 2010), or any other similar 3 GPP access node or non- 3 GPP access point. Moreover, as will be appreciated by those of skill in the art, the network nodes 2010 are 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 the network nodes 2010 may include disaggregated implementations or portions thereof. For example, in some embodiments, the telecommunication network 2002 includes one or more ORAN network nodes (e.g., computing device 1900). An ORAN network node is a node in the telecommunication network 2002 that supports an ORAN specification (e.g., a specification published by the O-RAN Alliance, or any similar organization) and may operate alone or together with other nodes to implement one or more functionalities of any node in the telecommunication network 2002, including one or more network nodes 2010 and / or core network nodes 2008.

[0128] As discussed herein, examples of an ORAN network node include an O-RU, an O- DU, an O-CU, including an O-CU-CP or an 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 RAN control application (e.g., xApp) or a non-real time RAN automation application (e.g., rApp), or any combination thereof (the adjective “open” designating support of an ORAN specification). The network node may support a specification by, for example, supporting an interface defined by the ORAN specification, such as an Al, Fl, Wl, El, E2, X2, Xn interface, an open fronthaul user plane interface, or an open fronthaul management plane interface. Intents and content- aware notifications described herein may be communicated from a 3 GPP network node or an ORAN network node over 3GPP-defined interfaces (e.g., N2, N3) and / or ORAN Alliance- defined interfaces (e.g., Al, 01). 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 SMO Framework via an O-2 interface defined by the O-RAN Alliance. The network nodes 2010 facilitate direct or indirect connection of user equipment (UE), such as by connecting wireless devices 2012a, 2012b, 2012c, and 2012d (one or more of which may begenerally referred to as UEs 2012) to the core network 2006 over one or more wireless connections. The network nodes 2010 facilitate direct or indirect connection of user equipment (UE), such as by connecting UEs 2012a, 2012b, 2012c, and 2012d (one or more of which may be generally referred to as UEs 2012) to the core network 2006 over one or more wireless connections. The computing device 1900 may be a cloud-based device communicatively coupled to the telecommunications network 2002.

[0129] 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 2000 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 2000 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0130] The UEs 2012 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 2010 and other communication devices. Similarly, the network nodes 2010 are arranged, capable, configured, and / or operable to communicate directly or indirectly with the UEs 2012 and / or with other network nodes or equipment in the telecommunication network 2002 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in the telecommunication network 2002.

[0131] In the depicted example, the core network 2006 connects the network nodes 2010 to one or more hosts, such as host 2016. 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 2006 includes one more core network nodes (e.g., core network node 2008) that are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the UEs, network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node 2008. Example core network nodes include functions of one or more of a Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (AUSF), Subscription Identifier De-concealing function (SIDF), Unified Data Management (UDM), Security EdgeProtection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).

[0132] The host 2016 may be under the ownership or control of a service provider other than an operator or provider of the access network 2004 and / or the telecommunication network 2002, and may be operated by the service provider or on behalf of the service provider. The host 2016 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.

[0133] As a whole, the communication system 2000 of Figure 20 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication system may be configured to operate according to predefined rules or procedures, such as specific standards that include, but are not limited to: Global System for Mobile Communications (GSM); Universal Mobile Telecommunications System (UMTS); Long Term Evolution (LTE), and / or other suitable 2G, 3G, 4G, 5G standards, or any applicable future generation standard (e.g., 6G); wireless local area network (WLAN) standards, such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards (WiFi); and / or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (WiMax), Bluetooth, Z-Wave, Near Field Communication (NFC) ZigBee, LiFi, and / or any low- power wide-area network (LPWAN) standards such as LoRa and Sigfox.

[0134] In some examples, the telecommunication network 2002 is a cellular network that implements 3 GPP standardized features. Accordingly, the telecommunications network 2002 may support network slicing to provide different logical networks to different devices that are connected to the telecommunication network 2002. For example, the telecommunications network 2002 may provide Ultra Reliable Low Latency Communication (URLLC) services to some UEs, while providing Enhanced Mobile Broadband (eMBB) services to other UEs, and / or Massive Machine Type Communication (mMTC) / Massive loT services to yet further UEs.

[0135] In some examples, the UEs 2012 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 2004 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 2004. 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).

[0136] In the example, the hub 2014 communicates with the access network 2004 to facilitate indirect communication between one or more UEs (e.g., UE 2012c and / or 2012d) and network nodes (e.g., network node 2010b). In some examples, the hub 2014 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 2014 may be a broadband router enabling access to the core network 2006 for the UEs. As another example, the hub 2014 may be a controller that sends commands or instructions to one or more actuators in the UEs. Commands or instructions may be received from the UEs, network nodes 2010, or by executable code, script, process, or other instructions in the hub 2014. As another example, the hub 2014 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 2014 may be a content source. For example, for a UE that is a VR headset, display, loudspeaker or other media delivery device, the hub 2014 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub 2014 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 2014 acts as a proxy server or orchestrator for the UEs, in particular in if one or more of the UEs are low energy loT devices.

[0137] The hub 2014 may have a constant / persistent or intermittent connection to the network node 2010b. The hub 2014 may also allow for a different communication scheme and / or schedule between the hub 2014 and UEs (e.g., UE 2012c and / or 2012d), and between the hub 2014 and the core network 2006. In other examples, the hub 2014 is connected to the core network 2006 and / or one or more UEs via a wired connection. Moreover, the hub 2014 may be configured to connect to an M2M service provider over the access network 2004 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 2010 while still connected via the hub 2014 via a wired or wireless connection. In some embodiments, the hub 2014 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 2010b. In other embodiments, the hub 2014 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node 2010b, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0138] Figure 21 shows a UE 2100 in accordance with some embodiments. As used herein, a UE refers to a device capable, configured, arranged and / or operable to communicate wirelesslywith network nodes and / or other UEs. Examples of a UE include, but are not limited to, a smart phone, mobile phone, cell phone, voice over IP (VoIP) phone, wireless local loop phone, desktop computer, personal digital assistant (PDA), wireless cameras, gaming console or device, music storage device, playback appliance, wearable terminal device, wireless endpoint, mobile station, tablet, laptop, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), smart device, wireless customer-premise equipment (CPE), vehicle, vehicle-mounted or vehicle embedded / integrated wireless device, etc. Other examples include any UE identified by the 3rd Generation Partnership Project (3 GPP), including a narrow band internet of things (NB-IoT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0139] A UE may support device-to-device (D2D) communication, for example by implementing a 3 GPP standard for sidelink communication, Dedicated Short-Range Communication (DSRC), vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), or vehicle- to-everything (V2X). In other examples, a UE may not necessarily have a user in the sense of a human user who owns and / or operates the relevant device. Instead, a UE may represent a device that is intended for sale to, or operation by, a human user but which may not, or which may not initially, be associated with a specific human user (e.g., a smart sprinkler controller). Alternatively, a UE may represent a device that is not intended for sale to, or operation by, an end user but which may be associated with or operated for the benefit of a user (e.g., a smart power meter).

[0140] The UE 2100 includes processing circuitry 2102 that is operatively coupled via a bus 2104 to an input / output interface 2106, a power source 2108, a memory 2110, a communication interface 2112, and / or any other component, or any combination thereof. Certain UEs may utilize all or a subset of the components shown in Figure 21. The level of integration between the components may vary from one UE to another UE. Further, certain UEs may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.

[0141] The processing circuitry 2102 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 2110. The processing circuitry 2102 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 2102 may include multiple central processing units (CPUs).

[0142] In the example, the input / output interface 2106 may be configured to provide an interface or interfaces to an input device, output device, or one or more input and / or output devices. Examples of an output device include a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smartcard, another output device, or any combination thereof. An input device may allow a user to capture information into the UE 2100. Examples of an input device include a touch-sensitive or presence-sensitive display, a camera (e.g., a digital camera, a digital video camera, a web camera, etc.), a microphone, a sensor, a mouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smartcard, and the like. The presence-sensitive display may include a capacitive or resistive touch sensor to sense input from a user. A sensor may be, for instance, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, a biometric sensor, etc., or any combination thereof. An output device may use the same type of interface port as an input device. For example, a Universal Serial Bus (USB) port may be used to provide an input device and an output device.

[0143] In some embodiments, the power source 2108 is structured as a battery or battery pack. Other types of power sources, such as an external power source (e.g., an electricity outlet), photovoltaic device, or power cell, may be used. The power source 2108 may further include power circuitry for delivering power from the power source 2108 itself, and / or an external power source, to the various parts of the UE 2100 via input circuitry or an interface such as an electrical power cable. Delivering power may be, for example, for charging of the power source 2108. Power circuitry may perform any formatting, converting, or other modification to the power from the power source 2108 to make the power suitable for the respective components of the UE 2100 to which power is supplied.

[0144] The memory 2110 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 readonly memory (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, and so forth. In one example, the memory 2110 includes one or more application programs 2114, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 2116. The memory 2110 may store, for use by the UE 2100, any of a variety of various operating systems or combinations of operating systems.

[0145] The memory 2110 may be configured to include a number of physical drive units, such as redundant array of independent disks (RAID), flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, high-density digital versatile disc (HD-DVD) optical disc drive, internal hard disk drive, Blu-Ray optical disc drive, holographic digital datastorage (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 (eUICC), integrated UICC (iUICC) or a removable UICC commonly known as ‘ SIM card.’ The memory 2110 may allow the UE 2100 to access instructions, application programs and the like, stored on transitory or non-transitory memory media, to off-load data, or to upload data. An article of manufacture, such as one utilizing a communication system may be tangibly embodied as or in the memory 2110, which may be or comprise a device-readable storage medium.

[0146] The processing circuitry 2102 may be configured to communicate with an access network or other network using the communication interface 2112. The communication interface 2112 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 2122. The communication interface 2112 may include one or more transceivers used to communicate, such as by communicating with one or more remote transceivers of another device capable of wireless communication (e.g., another UE or a network node in an access network). Each transceiver may include a transmitter 2118 and / or a receiver 2120 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter 2118 and receiver 2120 may be coupled to one or more antennas (e.g., antenna 2122) and may share circuit components, software or firmware, or alternatively be implemented separately.

[0147] In the illustrated embodiment, communication functions of the communication interface 2112 may include cellular communication, Wi-Fi communication, LPWAN communication, data communication, voice communication, multimedia communication, short- range communications such as Bluetooth, near-field communication, location-based communication such as the use of the GPS to determine a location, another like communication function, or any combination thereof. Communications may be implemented in according to one or more communication protocols and / or standards, such as IEEE 802.11, Code Division Multiplexing Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMax, Ethernet, transmission control protocol / internet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0148] Regardless of the type of sensor, a UE may provide an output of data captured by its sensors, through its communication interface 2112, via a wireless connection to a network node.Data captured by sensors of a UE can be communicated through a wireless connection to a network node via another UE. The output may be periodic (e.g., once every 15 minutes if it reports the sensed temperature), random (e.g., to even out the load from reporting from several sensors), in response to a triggering event (e.g., when moisture is detected an alert is sent), in response to a request (e.g., a user initiated request), or a continuous stream (e.g., a live video feed of a patient).

[0149] As another example, a UE comprises an actuator, a motor, or a switch, related to a communication interface configured to receive wireless input from a network node via a wireless connection. In response to the received wireless input the states of the actuator, the motor, or the switch may change. For example, the UE may comprise a motor that adjusts the control surfaces or rotors of a drone in flight according to the received input or to a robotic arm performing a medical procedure according to the received input.

[0150] A UE, when in the form of an Internet of Things (loT) device, may be a device for use in one or more application domains, these domains comprising, but not limited to, city wearable technology, extended industrial application and healthcare. Non-limiting examples of such an loT device are a device which is or which is embedded in: a connected refrigerator or freezer, a TV, a connected lighting device, an electricity meter, a robot vacuum cleaner, a voice controlled smart speaker, a home security camera, a motion detector, a thermostat, a smoke detector, a door / window sensor, a flood / moisture sensor, an electrical door lock, a connected doorbell, an air conditioning system like a heat pump, an autonomous vehicle, a surveillance system, a weather monitoring device, a vehicle parking monitoring device, an electric vehicle charging station, a smart watch, a fitness tracker, a head-mounted display for Augmented Reality (AR) or Virtual Reality (VR), a wearable for tactile augmentation or sensory enhancement, a water sprinkler, an animal- or item-tracking device, a sensor for monitoring a plant or animal, an industrial robot, an Unmanned Aerial Vehicle (UAV), and any kind of medical device, like a heart rate monitor or a remote controlled surgical robot. A UE in the form of an loT device comprises circuitry and / or software in dependence of the intended application of the loT device in addition to other components as described in relation to the UE 2100 shown in Figure 21.

[0151] As yet another specific example, in an loT scenario, a UE may represent a machine or other device that performs monitoring and / or measurements, and transmits the results of such monitoring and / or measurements to another UE and / or a network node. The UE may in this case be an M2M device, which may in a 3 GPP context be referred to as an MTC device. As one particular example, the UE may implement the 3 GPP NB-IoT standard. In other scenarios, a UE may represent a vehicle, such as a car, a bus, a truck, a ship and an airplane, or other equipmentthat is capable of monitoring and / or reporting on its operational status or other functions associated with its operation.

[0152] In practice, any number of UEs may be used together with respect to a single use case. For example, a first UE might be or be integrated in a drone and provide the drone’s speed information (obtained through a speed sensor) to a second UE that is a remote controller operating the drone. When the user makes changes from the remote controller, the first UE may adjust the throttle on the drone (e.g. by controlling an actuator) to increase or decrease the drone’s speed. The first and / or the second UE can also include more than one of the functionalities described above. For example, a UE might comprise the sensor and the actuator, and handle communication of data for both the speed sensor and the actuators.

[0153] Figure 22 shows a network node 2200 in accordance with some embodiments. As used herein, network node refers to equipment capable, configured, arranged and / or operable to communicate directly or indirectly with a UE and / or with other network nodes or equipment, in a telecommunication network. Examples of network nodes include, but are not limited to, APs (e.g., radio access points), BSs (e.g., radio base stations, Node Bs, eNBs and NR NodeBs (gNBs)), 0-RAN nodes or components of an 0-RAN node (e.g., 0-RU, 0-DU, O-CU).

[0154] Base stations may be categorized based on the amount of coverage they provide (or, stated differently, their transmit power level) and so, depending on the provided amount of coverage, may be referred to as femto base stations, pico base stations, micro base stations, or macro base stations. A base station may be a relay node or a relay donor node controlling a relay. A network node may also include one or more (or all) parts of a distributed radio base station such as centralized digital units, distributed units (e.g., in an 0-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).

[0155] Other examples of network nodes include multiple transmission point (multi-TRP) 5G access nodes, multi-standard radio (MSR) equipment such as MSR BSs, network controllers such as radio network controllers (RNCs) or base station controllers (BSCs), base transceiver stations (BTSs), transmission points, transmission nodes, multi-cell / multicast coordination entities (MCEs), Operation and Maintenance (O&M) nodes, Operations Support System (OSS) nodes, Self-Organizing Network (SON) nodes, positioning nodes (e.g., Evolved Serving Mobile Location Centers (E-SMLCs)), and / or Minimization of Drive Tests (MDTs).

[0156] The network node 2200 includes a processing circuitry 2202, a memory 2204, a communication interface 2206, and a power source 2208. The network node 2200 may becomposed of multiple physically separate components (e.g., a NodeB component and a RNC component, or a BTS component and a BSC component, etc.), which may each have their own respective components. In certain scenarios in which the network node 2200 comprises multiple separate components (e.g., BTS and BSC components), one or more of the separate components may be shared among several network nodes. For example, a single RNC may control multiple NodeB s. 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 2200 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memory 2204 for different RATs) and some components may be reused (e.g., a same antenna 2210 may be shared by different RATs). The network node 2200 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 2200, for example GSM, WCDMA, LTE, NR, WiFi, Zigbee, Z-wave, LoRaWAN, Radio Frequency Identification (RFID) or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within network node 2200.

[0157] The processing circuitry 2202 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and / or encoded logic operable to provide, either alone or in conjunction with other network node 2200 components, such as the memory 2204, to provide network node 2200 functionality.

[0158] In some embodiments, the processing circuitry 2202 includes a system on a chip (SOC). In some embodiments, the processing circuitry 2202 includes one or more of radio frequency (RF) transceiver circuitry 2212 and baseband processing circuitry 2214. In some embodiments, the radio frequency (RF) transceiver circuitry 2212 and the baseband processing circuitry 2214 may be on separate chips (or sets of chips), boards, or units, such as radio units and digital units. In alternative embodiments, part or all of RF transceiver circuitry 2212 and baseband processing circuitry 2214 may be on the same chip or set of chips, boards, or units.

[0159] The memory 2204 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 processingcircuitry 2202. The memory 2204 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 2202 and utilized by the network node 2200. The memory 2204 may be used to store any calculations made by the processing circuitry 2202 and / or any data received via the communication interface 2206. In some embodiments, the processing circuitry 2202 and memory 2204 is integrated.

[0160] The communication interface 2206 is used in wired or wireless communication of signaling and / or data between a network node, access network, and / or UE. As illustrated, the communication interface 2206 comprises port(s) / terminal(s) 2216 to send and receive data, for example to and from a network over a wired connection. The communication interface 2206 also includes radio front-end circuitry 2218 that may be coupled to, or in certain embodiments a part of, the antenna 2210. Radio front-end circuitry 2218 comprises filters 2220 and amplifiers 2222. The radio front-end circuitry 2218 may be connected to an antenna 2210 and processing circuitry 2202. The radio front-end circuitry may be configured to condition signals communicated between antenna 2210 and processing circuitry 2202. The radio front-end circuitry 2218 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 2218 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of filters 2220 and / or amplifiers 2222. The radio signal may then be transmitted via the antenna 2210. Similarly, when receiving data, the antenna 2210 may collect radio signals which are then converted into digital data by the radio front-end circuitry 2218. The digital data may be passed to the processing circuitry 2202. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0161] In certain alternative embodiments, the network node 2200 does not include separate radio front-end circuitry 2218, instead, the processing circuitry 2202 includes radio front-end circuitry and is connected to the antenna 2210. Similarly, in some embodiments, all or some of the RF transceiver circuitry 2212 is part of the communication interface 2206. In still other embodiments, the communication interface 2206 includes one or more ports or terminals 2216, the radio front-end circuitry 2218, and the RF transceiver circuitry 2212, as part of a radio unit (not shown), and the communication interface 2206 communicates with the baseband processing circuitry 2214, which is part of a digital unit (not shown).

[0162] The antenna 2210 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 2210 may be coupled to the radio front-end circuitry 2218 and may be any type of antenna capable of transmitting and receiving data and / orsignals wirelessly. In certain embodiments, the antenna 2210 is separate from the network node 2200 and connectable to the network node 2200 through an interface or port.

[0163] The antenna 2210, communication interface 2206, and / or the processing circuitry 2202 may be configured to perform any receiving operations and / or certain obtaining operations described herein as being performed by the network node. Any information, data and / or signals may be received from a UE, another network node and / or any other network equipment. Similarly, the antenna 2210, the communication interface 2206, and / or the processing circuitry 2202 may be configured to perform any transmitting operations described herein as being performed by the network node. Any information, data and / or signals may be transmitted to a UE, another network node and / or any other network equipment.

[0164] The power source 2208 provides power to the various components of network node 2200 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source 2208 may further comprise, or be coupled to, power management circuitry to supply the components of the network node 2200 with power for performing the functionality described herein. For example, the network node 2200 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 2208. As a further example, the power source 2208 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.

[0165] Embodiments of the network node 2200 may include additional components beyond those shown in Figure 22 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 2200 may include user interface equipment to allow input of information into the network node 2200 and to allow output of information from the network node 2200. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node 2200.

[0166] Figure 23 is a block diagram illustrating a virtualization environment 2300 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 asvirtual components executed by one or more virtual machines (VMs) implemented in one or more virtual environments 2300 hosted by one or more of hardware nodes, such as a hardware computing device that operates as a network node, UE, core network node, or host. Further, in embodiments in which the virtual node does not require radio connectivity (e.g., a core network node or host), then the node may be entirely virtualized. In some embodiments, the virtualization environment 2300 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.

[0167] Applications 2302 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment 2300 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0168] Hardware 2304 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 2306 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VMs 2308a and 2308b (one or more of which may be generally referred to as VMs 2308), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. The virtualization layer 2306 may present a virtual operating platform that appears like networking hardware to the VMs 2308.

[0169] The VMs 2308 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by a corresponding virtualization layer 2306. Different embodiments of the instance of a virtual appliance 2302 may be implemented on one or more of VMs 2308, 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.

[0170] In the context of NFV, a VM 2308 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 2308, and that part of hardware 2304 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 isresponsible for handling specific network functions that run in one or more VMs 2308 on top of the hardware 2304 and corresponds to the application 2302.

[0171] Hardware 2304 may be implemented in a standalone network node with generic or specific components. Hardware 2304 may implement some functions via virtualization.Alternatively, hardware 2304 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 2310, which, among others, oversees lifecycle management of applications 2302. In some embodiments, hardware 2304 is coupled to one or more radio units that each include one or more transmitters and one or more receivers that may be coupled to one or more antennas. Radio units may communicate directly with other hardware nodes via one or more appropriate network interfaces and may be used in combination with the virtual components to provide a virtual node with radio capabilities, such as a radio access node or a base station. In some embodiments, some signaling can be provided with the use of a control system 2312 which may alternatively be used for communication between hardware nodes and radio units.

[0172] Although computing devices described herein 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.

[0173] Moreover, while components are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, computing devices may comprise multiple different physical components that make up a single illustrated component, and functionality may be partitioned between separate components. For example, a communication interface may be configured to include any of the components described herein, and / or the functionality of the components may be partitioned between the processing circuitry and the communication interface. In another example, non-computationally intensive functions of any of such components may be implemented in software or firmware and computationally intensive functions may be implemented in hardware.

[0174] 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 certainembodiments may be a computer program product in the form of a non-transitory computer- readable storage medium. In alternative embodiments, some or all of the functionality may be provided by the processing circuitry without executing instructions stored on a separate or discrete device-readable storage medium, such as in a hard-wired manner. In any of those particular embodiments, whether executing instructions stored on a non-transitory computer- readable storage medium or not, the processing circuitry can be configured to perform the described functionality. The benefits provided by such functionality are not limited to the processing circuitry alone or to other components of the computing device, but are enjoyed by the computing device as a whole, and / or by end users and a wireless network generally.

Claims

CLAIMSWhat is Claimed is:

1. A computer implemented method performed by a computing device to correct anomalies in a packet synchronized system associated with a telecommunications network, the method comprising: identifying (1810) an anomaly in synchronization in a transport network based on an evaluation of performance of the packet synchronized system with a graph-based machine learning, ML, model, where the anomaly comprises a time misalignment between a plurality of radio access nodes in the telecommunications network; and initiating (1812) a remedial action to correct the time misalignment.

2. The method of Claim 1, wherein the graph-based ML model comprises a temporal heterogeneous graph-based ML model that includes a hypergraph that characterizes the synchronization in the transport network.

3. The method of any one of Claims 1 to 2, wherein the evaluation of performance of the packet synchronized system with the graph-based ML model comprises identification of the anomaly based on a path trace combined with a time error in the path trace and a round trip delay.

4. The method of Claim 3, wherein the path trace comprises a path between an enhanced primary reference time clock, ePRTC, and an antenna reference point, ARP, of a radio access node.

5. The method of any one of Claims 3 to 4, wherein the time error is identified from a type-length-value, TLV, comprising a timing error in a clock.

6. The method of any one of Claims 1 to 5, further comprising: collecting (1800), from at least one node in the telecommunication network, data relating to synchronization in the transport network, the data comprising one or more of the following: precision time protocol, PTP, data, global navigation satellite system, GNSS, data, geographical properties data,over-the-air, OTA, measurements between at least one pair of antenna reference points, ARPs, of a radio access node in the telecommunications network, link types in the packet synchronized system, and an identity of at least one of a device and a component on a transport network synchronization path in the packet synchronized system.

7. The method of Claim 6, wherein the OTA measurements comprise at least one of (i) cell attributes for the at least one pair of ARPs of the radio access node and (ii) a time alignment error measurement for at least one pair of ARPs of the radio access node, and the method further comprising: performing (1802) at least one of validate and correct at least one value in the OTA measurements.

8. The method of any one of Claims 1 to 7, wherein the time misalignment between a plurality of radio access nodes in the telecommunications network is in a plurality of synchronization paths between a common reference time and the plurality of radio access nodes.

9. The method of any one of Claims 2 to 8, the method further comprising: constructing (1804) the hypergraph that characterizes the synchronization in the transport network based on use of (i) a graph of a plurality of antenna reference point, ARP, to ARP pairs in the telecommunications network with (ii) a graph of synchronization paths in the transport network.

10. The method of any one of Claims 2 to 9, wherein the hypergraph comprises (i) a plurality of nodes comprising at least first node comprising a master time reference clock, a second node comprising a boundary clock, and a third node comprising an antenna reference point, ARP of a radio access node, and (ii) a plurality of edges between pairs of nodes comprising at a first edge between the first node and third node and second edge between a pair of third nodes.

11. The method of Claim 10, and the method further comprises: preparing (1806) ML features for respective nodes in the plurality of nodes and respective edges in the plurality of edges.

12. The method of any one of Claims 1 to 11, further comprising:training (1808) the graph-based ML model to identify anomalies.

13. The method of Claim 12, wherein the training (1808) the graph-based ML model is performed based on use of a heterogeneous graph neural network ML model.

14. The method of any one of Claims 12 to 13, wherein the training (1808) comprises (i) identifying data comprising the time misalignment between the plurality of radio access nodes in the telecommunications network; and (ii) labeling, in a synchronization hypergraph, a fault that is associated with the time misalignment.

15. The method of Claim 14, wherein the identifying data comprises identifying an over- the-air, OTA, measurement that comprises a time alignment error that exceeds a threshold value for pair of antenna reference points, ARPs, in the telecommunications network.

16. The method of any one of Claims 1 to 15, wherein the remedial action comprises a correction of a time error in an antenna reference point, ARP, in the telecommunications network.

17. The method of any one of Claims 1 to 16, wherein the telecommunications network comprises an open-radio access network, O-RAN.

18. A computing device (1900) comprising: processing circuitry (1903); memory (1905, 1911) coupled with the processing circuitry, wherein the memory includes instructions that when executed by the processing circuitry causes the computing device to perform operations comprising: identify an anomaly in synchronization in a transport network based on an evaluation of performance of a packet synchronized system with a graph-based machine learning, ML, model, where the anomaly comprises a time misalignment between a plurality of radio access nodes in a telecommunications network; and initiate a remedial action to correct the time misalignment.

19. The computing device of Claim 18, wherein the operations further comprise any of the operations of Claims 2 to 17.

20. A non-transitory computer readable medium (1905, 1911) including program code (1909, 1911) to be executed by processing circuitry (1903) of a computing device (1900), whereby execution of the program code causes the program code to perform operations comprising: identify an anomaly in synchronization in a transport network based on an evaluation of performance of a packet synchronized system with a graph-based machine learning, ML, model, where the anomaly comprises a time misalignment between a plurality of radio access nodes in a telecommunications network; and initiate a remedial action to correct the time misalignment.

21. The non-transitory computer readable medium (1905) of Claim 20, the operations further comprising any of the operations of Claims 2 to 17.

Images