Method and system for determining network performance for a user equipment, UE, group

Abstract

Embodiments of present disclosure provide system (200) and method (300) determining network performance for UE group. First reference UE group (208) and second UE group (210) are formed. Plurality of UEs (1000-A, 1000-B) in first reference UE group (208) are different from plurality of UEs (1000-A, 1000-B) in second UE group (210), first reference UE group (208) and second UE group (210) adapted to operate according to respective group property. UE performance data is obtained for UE (1002-A, 1002-B) belonging to first reference UE group (208) and second UE group (210). First reference UE group performance model and second UE group performance model are generated from UE performance data to determine whether network performance of the second UE group (210) is different from network performance of the first reference UE group (208) based on comparison of the second UE group performance model with the first reference UE group performance model.

Description

[0001] METHOD AND SYSTEM FOR DETERMINING NETWORK PERFORMANCE FOR A USER EQUIPMENT, UE, GROUP

[0002] TECHNICAL FIELD

[0003] The present disclosure relates to a method and a system for determining network performance for a user equipment, UE, group from a plurality of UE groups.

[0004] BACKGROUND

[0005] Wireless networks are becoming more and more complex, as a consequence of constant strive for improving spectral efficiency and network performance. Generally, the network performance of a single link of a terminal / User Equipment, UE, depends on a complex combination of the wireless network, and hardware and software of the UE and Next Generation Node B, gNB.

[0006] Further, for instance the following two aspects impact the behaviour of the UE, which affect the network performance. Firstly, the behaviour of the UE is impacted by mandated 3rd Generation Partnership Project, 3GPP, standards, and secondly the behaviour of the UE is impacted by certain features that are optional to be implemented in the UE according to the 3GPP standards.

[0007] SUMMARY

[0008] When two UEs of the same model are running the same software and are connected to the same Base Station, BS, they typically will experience similar performance. When the two UEs are different models, they will experience different performance. Now, in an example scenario, an uplink throughput is considered while the UEs are moving along a drive route. The uplink throughput is measured along the drive route for the two different phone / UE models. In such a scenario, the two different UE / phone models may exhibit similar trends in certain aspects, while they may exhibit different trends in some other aspects. Thus, when having two different UE / phone models in the same cell in similar conditions, they might experience different performance. However, even if the performance is different, the trend, for example over a UE movement trajectory, or change configurations, is often similar between these UEs / phones. Further, based on repeated measurements of the uplink throughput with multiple phones / UEs from different manufacturers it may be observed that, most phones of the same model from one manufacturer behave / operate in a similar manner. On the other hand, two different models of the phone / UE such as high-end and low-end versions that are from the same manufacturer may have different characteristics as the two different models of the phone / UE are targeting different user groups. Thus, there is a need for providing an improved method to overcome the limitations occurring in the wireless network.

[0009] Also, as mentioned above, wireless networks are becoming more and more complex. Thus, it is difficult to assess the cause of various issues that are occurring in the UE without performing elaborate troubleshooting. An issue could be experienced at the UE side, even when the UE side is not the cause of the issue. For example, handsets / phones / UEs are today sent for repair, which takes time and is costly, and in a significant number of cases there is no fault in the phone / handsets / UEs. For instance, a large number of mobile phones / UEs may be sent for repair when Downlink, DL or Uplink, UL performance drastically drops overnight.

[0010] In an example, the issue may be related to a network upgrade, and not from the mobile phones / UEs. That is, the network upgrade may involve swapping of radios from one vendor to another vendor. This may result in non-functioning of certain features of some models of the mobile phones / UEs, whereas some models do not experience any change due to the network upgrade. Further, for an operator, from a network perspective, certain features may not provide expected gains as terminals / UEs or group of terminals / UEs are not behaving as expected.

[0011] Additionally, the issues as listed herein are likely to increase when Artificial Intelligence, Al, algorithms, become more common in handsets / UEs as well as in the networks.

[0012] Therefore, there is a need for improving determination of network performance using different UE populations, whereby for example time otherwise consumed in determining network performance can be reduced.

[0013] It is therefore an object of the present disclosure to provide a system and a method for determining a network performance for a UE group from a plurality of UE groups, to thereby mitigate, alleviate, or eliminate all or at least some of the above-discussed drawbacks of presently known solutions. This and other objects are achieved by means of a system, and a method defined in the appended claims. The term exemplary is in the present context to be understood as serving as an instance, example or illustration.

[0014] According to a first aspect of the present disclosure, disclosed is a method implemented by a system for determining network performance for a User Equipment, UE, group from a plurality of UE groups comprising a plurality of UEs in the network. The method comprises of forming a first reference UE group and a second UE group from the plurality of UE groups, wherein the plurality of UEs in the first reference UE group are different UEs than a plurality of UEs in the second UE group, wherein the first reference UE group and the second UE group are adapted to operate in a wireless communication network according to a respective group property; obtaining UE performance data for the plurality of UEs comprised in the first reference UE group and for the plurality of UEs (1000-B) comprised in the second UE group; generating a first reference UE group performance model and a second UE group performance model from the UE performance data for the respective UE group; and determining whether the network performance of the second UE group is different from the network performance of the first reference UE group, wherein the difference in the network performance is determined based on a comparison of the second UE group performance model with the first reference UE group performance model.

[0015] Optionally, the group property is common for the UEs in the first reference UE group. Further, the group property is common for the UEs in the second UE group. Further, the group property for the first reference UE group is different from the group property for the second UE group.

[0016] Optionally, the group property for the respective UE group comprises a UE model for the UEs of the first reference UE group and of the second UE group; a UE network configuration comprising at least one of: one or more UE parameters of the respective UE group, and features to be used or not used by the UEs of the respective UE group; and features to be used by the wireless communication network in communication with the UEs of the respective UE group.

[0017] Optionally, the UE performance data comprises at least one Key Performance Indicator, KPI of the respective UE, wherein the KPI comprises at least one of: throughput, latency, fraction of retransmissions, handover failures, uplink data rate, downlink data rate, signal to noise ratio, SNR, signal to interference plus noise, SINR, and Reference Signal Received Power, RSRP.

[0018] Optionally, the performance data of the UEs in the first reference UE group and the second UE group is related to at least one network property, wherein the at least one network property comprises at least one of: time information, position of the UE, position of a serving gNB in the wireless communication network, cell identifier, cell ID, and load.

[0019] Optionally, each of the first reference and the second UE group performance model comprises a respective performance metric comprising at least one of: an average value of a Key Performance indicator, KPI, of the UEs of the respective UE group, wherein the respective performance metric is related to at least one network property, and a correlation between at least two different KPIs defined for at least one UE of the respective UE group.

[0020] Optionally, the determining the difference in performance of the second UE group and the first reference UE group comprises identifying whether there is an overlap or a non-overlap between the performance metrics of the second UE group and the performance metrics of the first reference UE group based on the comparison of the first reference UE group performance model and the second UE group performance model.

[0021] Optionally, the performance metrics for the first reference UE group performance model comprises network threshold values for each performance data.

[0022] Optionally, the network threshold values comprise performance data threshold values within which the plurality of UEs of the respective UE group is operational in the wireless communication network.

[0023] Optionally, the second UE group is identified as a network performance matched UE group in case of the identification of the overlap between the performance metrics of the second UE group and the performance metrics of the reference UE group or the second UE group is identified as a network performance mismatched UE group in case of the identification of the non-overlap between the performance metrics of the second UE group and the performance metrics of the first reference UE group. Optionally, the overlap indicates that the performance data of the plurality of UEs of the second UE group is within the network threshold values.

[0024] Optionally, the non-overlap indicates that the performance data of the at least one UE of the plurality of UEs of the second UE group is outside the network threshold values.

[0025] Optionally, performing, one or more actions upon identifying, the second UE group as the network performance mismatched UE group based on the identification of the non-overlap, wherein the one or more actions comprise transmitting at least one notification, and / or automatic reconfiguration of the wireless communication network and / or of the plurality of UEs (1000-B) in the second UE group.

[0026] Optionally, the at least one notification is transmitted to: a user of the network performance mismatched UE in the network performance mismatched UE group, and / or an operator of the network performance mismatched UE group and / or a network manager of the network performance mismatched UE group, and / or UE manufacturer of the network performance mismatched UE group.

[0027] According to a second aspect of the present disclosure, a system is provided. The system is arranged in the wireless communication network 106 for determining a network performance for a User Equipment, UE group from a plurality of UE groups comprising a plurality of UEs according to some embodiments. The system comprises at least one processing circuitry arranged to form a first reference UE group and a second UE group from the plurality of UE groups. The plurality of UEs in the first reference UE group are different UEs than a plurality of UEs in the second UE group. Each of the first reference UE group and the second UE group are adapted to operate in a wireless communication network according to a respective group property. The processing circuitry is further arranged to obtain UE performance data for a plurality of UEs comprises in the first reference UE group and for the plurality of UEs in the second UE group and generate a first reference UE group performance model and a second UE group performance model from the UE performance data for the respective UE group, and determine whether the network performance of the second UE group is different from the network performance of the first reference UE group, wherein the difference in the performance is detected based on a comparison of the second UE group performance model with the first reference UE group performance model. According to a third aspect of the present disclosure, there is provided a computer program product comprising a non-transitory computer readable medium, having thereon a computer program comprising program instructions. The computer program is loadable into a data processing unit and configured to cause execution of the method according to the first and second aspects when the computer program is run by the data processing unit.

[0028] Some embodiments disclosed herein have one or more of the following advantages:

[0029] - Providing a method which provides / offers additional information on the network / entity performance, which could facilitate terminal / UE troubleshooting and result in cost saving.

[0030] - Providing a method that enables adapting of configuration of features for different user groups / UE groups, which in turn enhances the overall performance of the wireless network and improves energy usage.

[0031] - Enabling controlled introduction of features with unknown performance characteristics in the wireless network. This may be the case for example when considering various Al-based features where e.g., one vendor's implementation may differ substantially from some other vendor's implementation. Alternatively, it could be the configuration of the Al model that differs between two sets of UEs.

[0032] - Generating a database comprising network link performance statistics. This allows for detection of UEs showing network performance mismatch, also referred to as performance outliers, in the wireless network. Further, based on type and characteristics of the detected performance outliers, suitable actions are taken to limit / minimise tedious troubleshooting when the cause is actually dependent on something other than expected.

[0033] - Reducing time consumption in identifying performance outliers and correcting issues related to the performance outliers.

[0034] Other advantages may be readily apparent to one having skill in the art. Certain embodiments may have none, some, or all of the recited advantages.

[0035] BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The foregoing will be apparent from the following more particular description of the example embodiments, as illustrated in the accompanying drawings in which like reference characters refer to the same parts throughout the different views. The drawings are not necessarily to scale, emphasis instead being placed upon illustrating the example embodiments.

[0037] FIG. 1 discloses an example of a wireless communication system;

[0038] FIG. 2a discloses a schematic diagram of an example of a system for determining a network performance for a UE group from a plurality of UE groups;

[0039] FIG. 2b is a schematic block diagram illustrating an example UE arranged in a wireless communication system;

[0040] FIG. 3a and 3b is a flowchart illustrating example steps for a method for determining a network performance for a UE group from a plurality of UE groups;

[0041] FIGs. 4a-4c illustrate graphs showing various steps of method for determining the network performance for a UE group from a plurality of UE groups;

[0042] FIGs. 5a-5c illustrate graphs showing various results of the network performance determined for the UE group from a plurality of UE groups; and

[0043] FIG. 6 discloses an example computing environment.

[0044] DETAILED DESCRIPTION

[0045] Aspects of the present disclosure will be described more fully hereinafter with reference to the accompanying drawings. The system and methods disclosed herein can, however, be realized in many different forms and should not be construed as being limited to the aspects set forth herein. Like numbers in the drawings refer to like elements throughout.

[0046] The terminology used herein is for the purpose of describing particular aspects of the disclosure only and is not intended to limit the invention. It should be emphasized that the term "comprises / comprising" when used in this specification is taken to specify the presence of stated features, integers, steps, or components, but does not preclude the presence or addition of one or more other features, integers, steps, components, or groups thereof. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0047] Embodiments of the present disclosure will be described and exemplified more fully hereinafter with reference to the accompanying drawings. The solutions disclosed herein can, however, be realized in many different forms and should not be construed as being limited to the embodiments set forth herein.

[0048] It will be appreciated that when the present disclosure is described in terms of a platform and a method, it may also be embodied in one or more processors and one or more memories coupled to the one or more processors, wherein the one or more memories store one or more programs that perform the steps, services and functions disclosed herein when executed by the one or more processors.

[0049] FIG. 1 discloses an example wireless communication system 100. Although the subject matter described herein may be implemented in any appropriate type of system using any suitable components, the examples disclosed herein are described in relation to a wireless communication system / wireless network 100, such as the example wireless communication system 100 described in FIG. 1.

[0050] The wireless communication system 100 may comprise and / or interface with any type of communication, telecommunication, data, cellular, and / or radio network or other similar type of system. The wireless communication system 100 may be configured to operate according to specific standards or other types of predefined rules of procedures. Thus, the wireless communication system 100 may implement communication standards, such as, but 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, or 5G standards, wireless local area network, WLAN, standards such as, IEEE 802.11 standards, and / or any other appropriate wireless communication standards, such as, worldwide interoperability for microwave access, WiMax, Bluetooth, Z-Wave and / or ZigBee standards.

[0051] For simplicity, as depicted in FIG. 1, the wireless communication system 100 comprises a system 200, a User Equipment, UE 1000, a network node 104, and a network 106 also referred as a wireless communication network 106. The system 200, the UE 1000, the network node 104, and the wireless communication network 106 operate together in order to provide wireless connections in the wireless communication system 100. The wireless communication network 106 may comprise one or more backhaul networks, core networks, IP networks, public switched telephone networks, PSTNs, packet data networks, optical networks, wide- area networks, WANs, local area networks, LANs, wireless local area networks, WLANs, wired networks, wireless communication networks, metropolitan area networks, and other networks to enable communication between devices (for example, wireless devices and a network node).

[0052] The network node 104 may refer to equipment capable, configured, arranged, and / or operable to and / or with other network nodes or equipment in the wireless communication system 100 to enable and / or provide wireless access and / or to perform other functions (for example, administration) in the wireless communication system 100. Examples of the network node 104 include, but are not limited to, access points, APs (for example, radio access points), base stations, BSs (for example, radio base stations, nodeBs, evolved NodeBs, eNBs, new radio, NR, nodes (gNBs), or the like). The BSs may be categorized based on an amount of coverage the BSs provide (or, stated different, their transmit power level) and may then also be referred to as femto BSs, pico BSs, micro-BSs, macro-BSs. The BS may be a relay node or a relay donor node controlling a relay.

[0053] The system 200 may be implemented in the network node 104. In an example, the system 200 may be implemented as a distributed system. The system may comprise one or more devices capable, configured, arranged and / or operable to communicate wirelessly with the network node 104, the wireless communication network 106 and / or other wireless devices.

[0054] The UE 1000 may refer to a device capable, configured, arranged and / or operable to communicate wirelessly with the network node 104, the wireless communication network 106 and / or other wireless devices.

[0055] In some examples, the system 200 may include one or more of: computing devices, wireless devices, ultra-low power wireless devices, Internet of Things, loT, devices, and so on.

[0056] The UE 1000 may include one or more of: computing devices, wireless devices, ultra-low power wireless devices, Internet of Things, loT, devices, and so on.

[0057] Examples of the computing devices may include, but are not limited to, a smart phone, a mobile phone, a cell phone, a voice over Internet Protocol, IP, VoIP, phone, a wireless local loop phone, a desktop computer, a personal digital assistant, PDA, a wireless camera, a gaming console or device, a wearable terminal device, a wireless endpoint, a mobile station, a tablet, a laptop, a laptop-embedded equipment, LEE, a laptop-mounted equipment, LME, a smart device, a wireless customer-premise equipment, CPE, a vehicle- mounted wireless terminal device, and so on.

[0058] It should be understood that the system 200 or the UE 1000 may not be limited to the abovedescribed wireless devices. The system 200 or the UE 1000 may be extended to other wireless devices of different classes or categories providing different services while supporting, for example, Enhanced Mobile Broadband, eMBB, massive Machine-Type Communication, MTC, Ultra-Reliable Low Latency Communication, URLLC, Time Sensitive Networking, TSN, or the like.

[0059] In the wireless communication system 100, the network node 104, the UE 1000 and the system 200 are connected to 3GPP 5G core network, CN, where specific network services and operations are provided through software components called network functions, NFs. The wireless communication system 100 hosts large scale applications.

[0060] The wireless communication network 106 as discussed in above paragraphs is becoming more and more complex. Thus, it is difficult to assess cause of various issues without performing elaborate troubleshooting. For example, an issue could be experienced at the UE side, even if the UE side is not the cause of the issue. For example, handsets / phones / UEs today are sent for repair, which consumes a lot of time and is costly, and in a significant number of cases there is no fault in the phone / handsets / UEs.

[0061] In an example, one or more network nodes, such as the network node 104, or the wireless communication network 106, as shown in FIG. 1, may be arranged to communicate directly or indirectly with one or more components of the system 200 to enable and / or provide wireless access within the system 200 so that performance of the UE 1000 may be determined.

[0062] Thus, the present disclosure presents a wireless communication network 106, a network node 104, the UE 1000, the system 200, wherein the system 200 is adapted for determining network performance for a UE group 208, 210 from a plurality of UE groups 208, 210. The system 200 thus reduces time consumption in updating network performance of the at least one UE 1002-B. The system 200 also characteristically reduces cost involved in the performance improvement. FIG. 2a discloses a schematic diagram illustrating an example wireless communication network 106 and the system 200 arranged in the wireless communication network 106 for determining the network performance for the UE group 208, 210 from the plurality of UE groups 208, 210 comprising a plurality of UEs 1000-A, 1000-B in the wireless communication network 106 according to some embodiments.

[0063] Further, the system 200 comprises a processing circuitry 202 (or controlling circuitry 1008 as shown in FIG. 2b) arranged for forming a first reference UE group 208 and a second UE group 210 from the plurality of UE groups 208, 210. The plurality of UEs 1000-A in the first reference UE group 208 are different UEs than a plurality of UEs 1000-B in the second UE group 210. The first reference UE group 208 and the second UE group 210 are adapted to perform in the wireless communication network 106 according to a respective group property.

[0064] In an example, the first reference UE group 208 and the second UE group 210 performs in the wireless communication network 106 according to the respective group property set for the first reference UE group 208 and the second UE group 210.

[0065] The processing circuitry 202 is further arranged for obtaining UE performance data for the plurality of UEs 1000-A, 1000-B comprised in the first reference UE group 208 and for the plurality of UEs 1000-B comprises in the second UE group and generating a first reference UE group performance model and a second UE group performance model from the UE performance data for the respective UE group 208, 210 and determining whether the network performance of the second UE group 208 is different from the network performance of the first reference UE group 208, wherein the difference in the performance is detected based on a comparison of the second UE group performance model with the first reference UE group performance model.

[0066] Optionally, the group property is common for the UEs 1002-A in the first reference UE group 208, wherein the group property is common for the UEs 1002-B in the second UE group 210, and wherein the group property for the first reference UE group 208 is different from the group property for the second UE group 210.

[0067] Optionally, the group property for the respective UE group (208, 210) comprises: a UE model for the UEs 1002-A, 1002-B of the first reference UE group 208 and the second UE group 210, a UE network configuration comprising at least one of: one or more UE parameters of the respective UE group 208, 210, and features to be used or not used by the UEs 1002-A, 1002- B of the respective UE group 208, 210; and features to be used by the wireless communication network 106 in communication with the UEs 1002-A, 1002-B of the respective UE group 208, 210.

[0068] In an example, the UE model may refer to a phone or handset model Al of a UE manufacturer B2.

[0069] Optionally, the UE performance data comprises at least one Key Performance Indicator, KPI, of the respective UE 1002-A, 1002-B, wherein the KPI comprises at least one of: throughput, latency, fraction of retransmissions, handover failures, uplink data rate, downlink data rate, signal to noise ratio, SNR, signal to interference plus noise, SINR, and Reference Signal Received Power, RSRP.

[0070] Optionally, performance data of the UEs 1000-A, 1000-B in the first reference UE group 208 and the second UE group 210 is relates to at least one network property, wherein the at least one network property comprises at least one of: time information, position of the UE 1002- A, 1002-B, position of a serving gNB in the wireless communication network 106, cell identifier, cell ID, and load.

[0071] Optionally, the each of the first reference and the second UE group performance model comprises a respective performance metrics comprising at least one of: an average value of a Key Performance indicator, KPI, of the UEs 1002-A, 1002-B of the respective UE group 208, 210, wherein the respective performance metric is related to at least one network property, and a correlation between at least two different KPIs defined for at least one UE 1002-A, 1002- B of the respective UE group 208, 210.

[0072] Optionally, the determining the difference in performance of the second UE group 210 with respect of the first reference UE group 208 comprises identifying whether there is an overlap or a non-overlap between the performance metrics of the second UE group 210 and the performance metrics of the first reference UE group 208 based on the comparison of the first reference UE group performance model and the second UE group performance model, wherein the performance metrics for the first reference UE group model comprises network threshold values for each performance data. Optionally, the network threshold values comprise performance data threshold values within which the plurality of UEs 1000-A, 1000-B of the respective UE group 208, 210 is operational in the wireless communication network 106.

[0073] Examples of the network threshold values are discussed later in FIG. 5a to FIG. 5c.

[0074] Optionally, the second UE group 210 is identified as a network performance matched UE group 210 in case of the identification of the overlap between the performance metrics of the second UE group 210 and the performance metrics of the reference UE group 208 or the second UE group 210 is identified as a network performance mismatched UE group 210 in case of the identification of the non-overlap between the performance metrics of the second UE group 210 and the performance metrics of the first reference UE group 208.

[0075] Optionally, the overlap indicates that the performance data of the plurality of UEs 1002-B of the second UE group 210 is within the network threshold values.

[0076] Optionally, the non-overlap indicates that the performance data of the at least one UE 1002- B of the plurality of UEs 1000-B of the second UE group 210 is outside the network threshold values.

[0077] Optionally, the processing circuitry 202 is arranged for performing, one or more actions upon identifying, the second UE group 210 as the network performance mismatched UE group 210 based on the identification of the non-overlap, wherein the one or more actions comprise transmitting at least one notification, and / or automatic reconfiguration of the wireless communication network 106 and / or of the plurality of UEs 1000-B in the second UE group 210.

[0078] Optionally, the at least one notification is transmitted to a user of the network performance mismatched UE 1002-B in the network performance mismatched UE group 210, and / or an operator of the network performance mismatched UE group 210 and / or a network manager of the network performance mismatched UE group 210, and / or UE manufacturer of the network performance mismatched UE group 210.

[0079] In an example, additional detail / information regarding FIG. 2a is provided herein. For example, FIG. 2a shows the plurality of UEs 1000-A of the first reference UE group 208 and the plurality of UEs 1000-B of the second UE group 210. The first reference UE group 208 comprises UE 1, UE 2... to UE n referred as 1000-A. Further, UE 1 of group 1 i.e., the first reference UR group 208 is also referred as 1002-A. Similarly, the second UE group 210 comprises UE 1, UE 2... to UE n referred as 1000-B. Further, UE 1 of the second UE group 210 is also referred as 1002-B. The system 200 collects UE performance data of each UE 1000-A, i.e., UE 1 to UE n of the first reference UE group 208 and UE performance data of each UE 1000-B, i.e., UE 1 to UE n of the second UE group 210. The UE performance data is in relation to at least one network property such as time information, position of the UE 1002-A, 1002- B, position of serving gNB in the wireless communication network 106, cell identifier, cell ID, load. The UE performance data also comprises at least one KPI of each UE 1000 such as throughput, latency, fraction of retransmissions, handover failures, uplink data rate, downlink data rate, Reference Signal Received Power, RSRP and the like. Upon collecting the UE performance data, the system 200 generates the first reference UE group performance model for the reference UE group 208 of UEs 1000-A and the second UE group performance model for the second UE group 210 of UEs 1000-B.

[0080] In FIG. 2b, the example UE 1000 or UE 1002-A, or UE 1002-B, is illustrated comprising one or more modules. The one or more modules may comprise a memory 1004, a processor 1006, a controlling circuitry 1008, and a driver 1010. The controlling circuitry 1008, may be adapted to control the other modules.

[0081] The memory 1004, the processor 1006 and the driver 1010 as well as the controlling circuitry 1008, may be operatively connected to each other.

[0082] The memory 1004 may be adapted to store the UE performance data relating to a communication attempt from the system 200.

[0083] The processor 1006 may be adapted to identify that the system 200 may be configured to determine whether the second UE group 210 is the network performance matched UE group or the network performance mismatched UE group with respect to the first reference UE group 208. The processor 1006 may be adapted to transmit the UE performance data to the system 200 for determining the network performance using two or more UE populations 1000-A, 1000-B.

[0084] The controlling circuitry 1008 / or the processing circuitry 202 may be adapted to control the steps as executed by the UE 1002-A, 1002-B. For example, the controlling circuitry 1008 may be adapted to transmit the UE performance data to the system 200 and receive at least one notification, and / or automatic reconfiguration of the wireless communication network 106 in the UE 1002-A in the second UE group 208.

[0085] FIG. 3a shows a flowchart illustrating example steps for a method 300 performed in the wireless communication network 106 for determining the network performance for the UE group 1000 from the plurality of UE groups 1000-A, 1000-B, the UE group 208, 210 having a plurality of UEs 1002-A, 1002-B in the wireless communication network 106.

[0086] At step 302, the method 300 forms the first reference UE group 208 and the second UE group 210 from the plurality of UE groups 208, 210. The plurality of UEs 1000-A in the first reference UE group 208 are different UEs than the plurality of UEs 1000-B in the second UE group 210. The first reference UE group 208 and the second UE group 210 are adapted to perform in the wireless communication network 106 according to the respective group property.

[0087] At step 304, the method 300 obtains the UE performance data for the UE 1002-A, 1002-B in the wireless communication network 106 comprised in the first reference UE group (208) and for the plurality of UEs 1000-B comprised in the second UE group (210).

[0088] At step 306, the method 300 generates the first reference UE group performance model and the second UE group performance model from the UE performance data for the respective UE group 208, 210 and for the respective plurality of UEs 1000-A, 1000-B in the respective UE group 208, 210.

[0089] At step 308, the method 300 determines whether the network performance of the second UE group 210 is different from the network performance of the first reference UE group 208, wherein the difference in the network performance is determined based on the comparison of the second UE group performance model with the first reference UE group performance model.

[0090] Optionally, the group property for the respective UE group 208, 210 is common for the UEs 1002-A, 1002-B in the first reference UE group 208, wherein the group property is common for each UE 1002-B in the second UE group 210, and wherein the group property for the first reference UE group 208 is different from the group property for the second UE group 210. Optionally, the group property for the respective UE group 208, 210 comprises the UE model for UEs 1002-A, 1002-B of the first reference UE group 208 and of the second UE group 210; the UE network 106 configuration comprising at least one of: one or more UE parameters of the respective UE group 208, 210, and features to be used or not used by the UEs 1002-A, 1002-B of the respective UE group 208, 210; and features to be used by the wireless communication network 106 in communication with the UEs 1002-A, 1002-B of the respective UE group 208, 210.

[0091] Optionally, the UE performance data comprises at least one Key Performance Indicator, KPI, of the respective UE 1002-A, 1002-B, wherein the KPI comprises at least one of: throughput, latency, fraction of retransmissions, handover failures, uplink data rate, downlink data rate, signal to noise ratio, SNR signal to interference plus noise, SINR, and Reference Signal Received Power, RSRP.

[0092] Optionally, the performance data of the UEs 1000-A. 1000-B in each of the first reference UE group 208 and the second UE group 210 is related to at least one network property, wherein the at least one network property comprises at least one of: time information, position of the UE 1002-A, 1002-B, position of a serving gNB in the wireless communication network 106, cell identifier, cell ID, and load.

[0093] Optionally, each of the first reference and the second UE group performance model comprises a respective performance metric comprising at least one of: an average value of the Key Performance indicator, KPI, of the respective UE group 208, 210, wherein the respective performance metric is related to at least one network property, and the correlation between at least two different KPIs defined for at least one UE 1002-A, 1002-B of the respective UE group 208, 210.

[0094] Optionally, as shown in FIG. 3b, the step of determining 302 the difference in the performance of the second UE group 210 and the first reference UE group 208 comprises identifying in step 310, whether there is an overlap or a non-overlap between the performance metrics of the second UE group 210 and the performance metrics of the first reference UE group 208 based on the comparison of the first reference UE group performance model and the second UE group performance model. Optionally, the performance metrics for the first reference UE group performance model comprises network threshold values for each performance data.

[0095] Optionally, the network threshold values comprise performance data threshold values within which the plurality of UEs 1000-A, 1000-B of the respective UE group 208, 210 is operational in the wireless communication network 106.

[0096] Examples of the network threshold values are discussed later in FIG. 5a to FIG. 5c.

[0097] Optionally, as shown in FIG. 3b, the method 300 comprises identifying in step 312a, the second UE group 210 as the network performance matched UE group 210 in case of the identification of the overlap between the performance metrics of the second UE group 210 and the performance metrics of the reference UE group 208; or identifying in step 312b, the second UE group 210 as the network performance mismatched UE group 210 in case of the identification of the non-overlap between the performance metrics of the second UE group 210 and the performance metrics of the first reference UE group 210.

[0098] Optionally, the overlap indicates that the performance data of the plurality of UEs 1002-B of the second UE group (210) is within the network threshold values.

[0099] Optionally, the non-overlap indicates that the performance data of the at least one UE (1002- B) of the plurality of UEs (1000-B) of the second UE group 210 is outside the network threshold values.

[0100] Optionally, as shown in FIG. 3b, the method 300 comprises performing in step 314, one or more actions upon identifying the second UE group 210 as the network performance mismatched UE group 210 based on the identification of the non-overlap, wherein the one or more actions comprise transmitting at least one notification, and / or automatic reconfiguration of the wireless communication network 106 and / or the plurality of UEs 1000- B in the second UE group 210.

[0101] Optionally, the at least one notification is transmitted to: a user of the network performance mismatched UE 1002-B in the network performance mismatched UE group 210, and / or an operator of the network performance mismatched UE group 210 and / or a network manager of the network performance mismatched UE group 210, and / or UE manufacturer of the network performance mismatched UE group 210. In an example, the system 200 and the method 300 perform collection of the UE performance data, also referred as link performance, from each UE 1000-A of the first reference UE group 208 and from each UE 1000-B of the second UE group 210. The UE performance data may comprise, but are not limited to, for example uplink / downlink data rate, Reference Signal Received Power, RSRP, and so on. Upon collection of the UE performance data, the system 200 and the method 300 classify the UE performance data / link performance by comparing performance of the second UE group 210 with performance of the first reference UE group 208 as also discussed above.

[0102] The system 200 and the method 300 use the UEs 1000 grouped in the first reference UE group 208 to identify the network performance of the second UE group 210 with respect to the first reference UE group 208. The difference in the network performance may be caused by a difference in the performance of the one UE 1000-B, within the second UE group 210 when compared to the performance of the first reference UE group 208. Further, based on the determination of the network performance, the system 200 and the method 300 provide problem mitigation guideline. The problem mitigation guidelines would be the one or more actions that is provided upon identifying the performance mismatch of at least one UE in a group of UEs with any reference group of UEs. For example, performance mismatch of the at least one UE 1002-B in the second UE group 210 with respect to the first reference UE group 208 may be considered as the performance mismatched UE 1002-B. Such performance mismatched UE 1002-B may also be referred as a performance outlier in the wireless communication network 106. The one or more actions may be, but are not limited to, transmitting the at least one notification, and / or the automatic reconfiguration of the wireless communication network 106 in the UE in the second UE group 210. For example, in case of phone / UE 1002-A outlier from a group of phones: the system 200 and the method 300 may send phone / UE 1000 for repair / trouble shooting. In case of group of UEs behaving as the performance outlier compared to other groups of UEs: the system 200 and the method 300 may prevent phone models from using certain configuration known to cause unwanted behavior.

[0103] In another example, the system 200 and the method 300 may be applied in the wireless communication network 106, where the UE performance data is collected in a database. Upon collecting, the UE performance data is tagged with the terminal group identifiers. Further, upon tagging, the network performance outliers are detected from an expected UE or group of UEs 1000-B, such as the second UE group 210. Thereupon, the one or more actions are performed to limit / remedy the performance mismatch of the at least one UE 1002-B in the second UE group 210 caused in the wireless communication network 106.

[0104] Further, an example of how the UE network performance is related to the at least one network property is presented in FIG. 4a and is shown as 402. The at least one network property may be distance between the UE 1000 and the gNB 104. Further, a number of measurements are conducted, which are represented with small circles in FIG. 4a, and a line fitting technique is utilized to produce either the first reference UE group or the second UE group performance models, as illustrated with the solid line 402 in FIG. 4a. In another example, the UE group performance model may be user throughput vs received signal power. In this case, the distance between UE 1000 and gNB 104 determines signal strength, and the signal strength normally decreases with distance but varies greatly depending on environment. Upon generating the first reference UE group and the second UE group performance model, the system 200 determines whether the network performance of the second UE group 210 is different from the network performance of the first reference UE group 208 based on the comparison of the second UE group performance model with the first reference UE group performance model.

[0105] For example, FIG. 4b shows comparison of two different models, i.e., the first reference UE group and the second UE group performance model and explains the overlap and the nonoverlap. FIG. 4b illustrates one performance model which is shown as upper solid line 402 with corresponding thresholds representing interval where the performance is expected to be within dashed lines 406. This then corresponds to one UE group, say the first reference UE group 208. Further, another set of measurements are illustrated down in FIG. 4b with the corresponding performance model shown as lower solid line 404. Consequently, any other UE group, for example, the second UE group 210, does not overlap with the model extracted from the other UE group, i.e., the first reference UE group 208. The second UE group 210 is thus considered to be the network performance mismatched UE group with respect to the reference UE group 208. In a second example as shown in FIG. 4c, an overlap between the two performance models is shown, as the second solid line 404 is now within the thresholds corresponding to the first reference UE group performance model. Thereafter, upon identifying or determining either the overlap or the non-overlap between the first reference UE group and the second UE group performance model. The system 200 identifies whether the second UE group 210 is the network performance mismatched UE group or not with respect to the reference UE group 208.

[0106] In an example, the following steps describe additional details of the system 200 and the method 300: Firstly, there are at least two different plurality of UEs 1000-A, 1000-B, also referred as UE populations where each UE population is tied to the group property. For example, the group property may include but are not limited to, precoder mode such as codebook or reciprocity, sounding reference signal, SRS, configuration including parameters such as periodicity and number of sounding antennas, link / rank / Modulation and Coding Scheme, MCS adaptation scheme, Single User, SU / Multiple User, MU configuration, carrier aggregation configuration. For instance, the UE group may be the reference UE group 208 and the second UE group 210 comprising the first UE population 1000-A and the second different UE population 1000-B, respectively from the two or more UE populations 1000-A, 1000-B. The UE group may comprise e.g., a phone, a phone model or all phones in the wireless communication network 106.

[0107] The group property may comprise e.g., a given network configuration or a given UE configuration, e.g., UE parameters or which feature to use / not use in the wireless communication network 106 and / or UE 1002-A, 1002-B. For multiple UEs, the system 200 and the method 300 of the wireless communication network 106, collects the UE performance data, in relation to the at least one network property, where the UE 1000 is part of the at least one of the UE populations 1000-A, 1000-B of the respective UE group 208, 210 of UEs. The at least one network property may comprise e.g., time information, positions of UE and / or serving gNB, cell ID, load.

[0108] The system 200 processes the collected UE performance data through the system 200 and the method 300 and produces the performance model for each of the at least two UE populations 1000-A, 1000-B, i.e., the first reference UE group performance model and the second UE group performance model. The performance model may be e.g., average value of Key Performance Indicator, KPI, over a given time period, confidence interval of KPI, the correlation between two different KPIs and so on. The performance model may or may not be a function of the at least one network property. This means for example, in some cases the UE performance data is collected based on a network property, consider e.g., the case of a time interval as illustrated in FIG. 4a, but all this collected UE performance data is instead represented in form of its statistical properties like e.g., mean, max / min, variance or probability density function, pdf which is a probability of the performance of UE related to the network property per unit length of the UE performance model (the solid line 402) . In such a case comparing two performance models, i.e., the reference UE group and the second UE group performance model may for instance imply that the system 200 and the method 300 would compare two statistical properties like e.g. compare two pdfs or mean values of the reference UE group and the second UE group performance model to determine whether there is the difference in the network performance by determining whether the second UE group performance model overlaps or not with respect to the reference UE group performance model .

[0109] Thereafter, the system 200 and the method 300 compare two performance models, i.e., the first reference UE group and the second UE group performance model representing different UE populations 1000-A, 1000-B of respective UE group 208, 210. The system 200 and the method 300 determine if the second UE group performance model is sufficiently overlapping, i.e., the performance data of the plurality of UEs 1000-B in the second UE group 210 is within the network threshold values or not with respect to the reference UE group performance model. Based on the outcome of said above comparison, an action is taken. The system 200 may share the notification to an operator / network manager or UE owners to notify about the discovered artifact and how to remedy. Thus, the notification may comprise information about how to improve the performance of the at least one UE 1002-B identified as the network mismatched UE in the second UE group 210. For example, remedy may include an automatic reconfiguration of a network feature in the network mismatched UE 1002-B though the operator / network manager of the network mismatched UE 1002-B. The automatic reconfiguration of the network feature may also be performed by the network mismatched UE 1002-B itself.

[0110] FIGs. 5a-5c illustrates graphs showing various results achieved through the system 200 and the method 300 for determining the network performance using two or more UE populations 1000-A, 1000-B. The proposed system 200 and the method 300 are implemented in the wireless communication network 106 for determining the network performance mismatched UE group by using two or more UE populations 1000-A, 1000-B. This is performed by collecting the UE performance data from terminals / group of UEs / two or more UE populations 1000-A, 1000-B that is then coupled with the respective group property. The group property may distinguish a specific handset / UE or a group of handsets / UEs. One such network property available is the International Mobile Equipment Identity, IMEI, number which is not only unique per terminal / UE, but an identifier that can provide information of which model / brand the terminal / UE belongs to.

[0111] The system 200 and the method 300 is further explained using a few examples by elaborating on performance vs. time. It should however be noted that 'performance' is general and could represent any KPI like e.g., throughput, latency, energy efficiency etc. Further, 'time' is general and could represent any property related to the at least one network property such as UE position, cell ID, network load etc. as well as time expressed in minutes / hours / days.

[0112] In an example, consider a scenario, where performance of the UE, say UE 1 is measured over time. At a certain point in time, t=1500, performance issue occurs, as shown in FIG. 5a. Let the dashed line 504 exemplify the average performance of a specific terminal / UE model. The terminal / UE model could be model C5, H8, or any other model. The area represented by 502 exemplifies the spread of the performance for all terminals / UEs of the given model. The line represented by 506 exemplifies the terminal / UE 1 under consideration. At time t=1500 consider that performance issue happens with a specific phone, i.e., UE 1, which deteriorates performance of the phone. Given that the performance drop is only visible for one phone and not the complete model group / group of UEs 1000, it is determined that there is a terminal fault, i.e., fault in the UE 1. This information can be used by the operator as input passively when phone is sent for troubleshooting, or actively by sending a notification to the user highlighting the issue and recommending to schedule a repair time.

[0113] In another example, again, considering FIG. 5a, let the dashed line 504 exemplify the average performance of all terminal models / group of UEs 1000, and the area 502 exemplifies the spread of the performance for all terminals / UEs of the given model. The line 506 exemplifies the performance of a specific model group, for example model C5, H8, or any other model. At time t=1500 say a performance issue happens within the wireless communication network 106 which impacts the performance for this whole group of UEs. It is extremely unlikely that a phone hardware issue impacts the whole group of UEs at the same time. More likely, the cause of the performance drop originates from a network change or a batch upgrade / push of UE software which is likely installed on the larger UE group. As each user only experiences its own link performance degrade it is likely that multiple reports of broken phones may be filed, however most of these phones are likely working as supposed, and no handset troubleshooting is necessary. Instead, the issue should be correlated with network changes like roll-out of new hardware or features, software updates or similar.

[0114] In another example, similar to above two examples, this method can be used to identify the benefit of a feature for a specific type of terminal / UE to later use as input for how to configure transmissions for this specific terminal group / group of UEs 1000. With reference to FIGs 5b and 5c, let the dashed line 504 exemplify the average performance of all terminal models / group of UEs 1000-A, 1000-B, and the area 502 exemplifies the spread of the performance for all terminals / UEs of the given model. The line 506 in FIG. 5b exemplifies the performance of a specific model group, for example model C5, H8, or any other model, whereas the line 506 in FIG. 5c exemplifies the performance for another model group for example model D6, G9, or other model. The operator turns on a feature with a specific configuration at time t=1000 and can thus identify that the feature provides benefit for one model type / group of UEs 1000 but not the other group of UEs. Thus, only FIG. 5b model group should be configured like this in the future. An example of such a feature / differentiator could be Sounding Reference Signal, SRS configurations in scenarios of poor Signal-to-Noise ratio, SNR. Another example could be how the gNB interprets feedback coming from the terminal / UE that performs Artificial Intelligence, Al, based channel characterization or Channel State Information, CSI compression. The decision based on this is that the reference UE group 208 of UE 1000-A is eligible for this specific feature in the future, whereas the second UE group 210 of UE 1000-B is not.

[0115] In another example, when introducing a new feature or a new set of UE configuration parameters, one may choose to carry out this introduction tied to performance related to a specific model group, for example model C5, H8, or any other model. The new feature may for instance be introduced for xi % of all UEs belonging to a first UE model group / reference UE group 208 of UEs 1000-A, and consequently it will not be introduced for 100- xi % of the UEs in this model group / reference UE group 208 of UEs 1000-A. In a similar manner the new feature may be introduced for x2% of all UEs belonging to the second UE model group / second UE group 210 of UEs 1000-B.

[0116] Again, considering FIGs. 5b and 5c, let FIG. 5b represent the first reference UE model group and assume that the curve line 506 represents the performance of the xi% of all UEs 1000-A belonging to the reference first UE group / reference UE group 208 of UEs 1000-A where a new feature has been introduced at time=1000. Furthermore, let the dashed line 504 exemplify the average performance of the 100- xi% of UEs in the first model group / reference UE group 208 of UEs 1000-A, and the area 502 exemplifies the spread of the performance for all terminals / UEs of the given model. As can be seen, the feature has improved the performance of the UEs in the first model group / reference UE group 208 of UEs 1000-A and in a second step the value of xi can consequently be increased in a gradual and controlled manner util 100% of the UEs are operating with the new feature. At the same time, let FIG. 5c represent the second UE model / second UE group 210 of UEs 1000-B, notice that the feature does not provide benefits for this UE model / second UE group 210 of UEs 1000-B and consequently one may decide not to introduce the feature for the second UE model / second UE group 210 of UEs 1000-B.

[0117] FIG. 6 illustrates an example-computing environment 600 implementing the system 200 and the method 300 as shown in FIGs. 2a, 3a and 3b for determining the network performance of the UE group 208, 210 in a wireless communication network 106. As depicted in FIG. 6, the computing environment 600 comprises at least one data processing module 606 that is equipped with a control module 602 and an Arithmetic Logic Unit, ALU 604, a plurality of networking devices 608 and a plurality Input output, I / O devices 610, a memory 612, a storage 614. The data processing module 606 may be responsible for implementing the platform and method described in FIGs. 2a, 3a and 3b respectively. For example, the data processing module 606 in some embodiments is equivalent to the controlling circuitry of the platform described above in conjunction with FIGs. 2a, 3a and 3b. The data processing module 606 is capable of executing software instructions stored in memory 612. The data processing module 606 receives commands from the control module 602 in order to perform its processing. Further, any logical and arithmetic operations involved in the execution of the instructions are computed with the help of the ALU 604. The computer program is loadable into the data processing module 606, which may, for example, be comprised in an electronic apparatus, such as the platform. When loaded into the data processing module 606, the computer program may be stored in the memory 612 associated with or comprised in the data processing module 606. According to some embodiments, the computer program may, when loaded into and run by the data processing module 606, cause execution of method steps according to, for example, any of the methods illustrated in FIGs. 2a, 3a and 3b, or otherwise described herein.

[0118] The overall computing environment 600 may be composed of multiple homogeneous and / or heterogeneous cores, multiple CPUs of different kinds, special media and other accelerators. Further, the plurality of data processing modules 606 may be located on a single chip or over multiple chips.

[0119] The algorithm comprising of instructions and codes required for the implementation are stored in either the memory 612 or the storage 614 or both. At the time of execution, the instructions may be fetched from the corresponding memory 612 and / or storage 614 and executed by the data processing module 606.

[0120] In case of any hardware implementations various networking devices 608 or external I / O devices 610 may be connected to the computing environment to support the implementation through the networking devices 608 and the I / O devices 610.

[0121] The embodiments disclosed herein can be implemented through at least one software program running on at least one hardware device and performing network management functions to control the elements. The elements shown in FIG. 6 include blocks which can be at least one of a hardware device, or a combination of hardware device and software module.

Claims

CLAIMS1. A method (300) performed by a system (200) in a wireless communication system (100) for determining network performance for a User Equipment, UE, group (108, 210) from a plurality of UE groups (208, 210) comprising a plurality of UEs (1000-A, 1000-B), the method (300) comprising: forming (302) a first reference UE group (208) and a second UE group (210) from the plurality of UE groups (208, 210), wherein the plurality of UEs (1000-A) in the first reference UE group (208) are different UEs than a plurality of UEs (1000-B) in the second UE group (210), wherein the first reference UE group (208) and the second UE group (210) are adapted to operate in a wireless communication network (106) according to a respective group property; obtaining (304) UE performance data for the plurality of UEs (1000-A, 1000-B) comprised in the first reference UE group (208) and for the plurality of UEs (1000-B) comprised in the second UE group (210); generating (306) a first reference UE group performance model and a second UE group performance model from the UE performance data for the respective UE group (208, 210); and determining (308) whether the network performance of the second UE group (210) is different from the network performance of the first reference UE group (208), wherein the difference in the network performance is determined based on a comparison of the second UE group performance model with the first reference UE group performance model.

2. The method (300) according to claim 1, wherein: the group property is common for the UEs (1002-A) in the first reference UE group (208), wherein the group property is common for the UEs (1002-B) in the second UE group (210), and wherein the group property for the first reference UE group (208) is different from the group property for the second UE group (210).

3. The method (300) according to any of the preceding claims, wherein the group property for the respective UE group (208, 210) comprises: a UE model for the UEs (1002-A, 1002-B) of the first reference UE group (208) and of the second UE group (210); a UE network configuration comprising at least one of: one or more UE parameters of the respective UE group (208, 210), and features to be used or not used by the UEs (1002-A, 1002-B) of the respective UE group (208, 210); and features to be used by the wireless communication network (106) in communication with the UEs (1002-A, 1002-B) of the respective UE group (208, 210).

4. The method (300) according to any of the preceding claims, wherein the UE performance data comprises at least one Key Performance Indicator, KPI, of the respective UE (1002-A, 1002-B), wherein the KPI comprises at least one of: throughput, latency, fraction of retransmissions, handover failures, uplink data rate, downlink data rate, signal to noise ratio, SNR, signal to interference plus noise, SINR, and Reference Signal Received Power, RSRP.

5. The method (300) according to any of the preceding claims, wherein the performance data of the UEs (1000-A. 1000-B) in the first reference UE group (208) and the second UE group (210) is related to at least one network property, wherein the at least one network property comprises at least one of: time information, position of the UE (1002-A, 1002-B), position of a serving gNB in the wireless communication network (106), cell identifier, cell ID, and load.

6. The method (300) according to any of the preceding claims, wherein each of the first reference and the second UE group performance model comprises a respective performance metric comprising at least one of:an average value of a Key Performance indicator, KPI, of the UEs (1002-A, 1002- B) of the respective UE group (208, 210), wherein the respective performance metric is related to at least one network property, and a correlation between at least two different KPIs defined for at least one UE (1002-A, 1002-B) of the respective UE group (208, 210).

7. The method (300) according to claim 6, wherein the determining (302) the difference in the performance of the second UE group (210) and the first reference UE group (208) comprises: identifying (310) whether there is an overlap or a non-overlap between the performance metrics of the second UE group (210) and the performance metrics of the first reference UE group (208) based on the comparison of the first reference UE group performance model and the second UE group performance model.

8. The method (300) according to claim 6, wherein the performance metrics for the first reference UE group performance model comprise network threshold values for each performance data.

9. The method (300) according to claim 7 or 8, wherein the network threshold values comprise performance data threshold values within which the plurality of UEs (1000- A, 1000-B) of the respective UE group (208, 210) is operational in the wireless communication network (106).

10. The method (300) according to any of the claim 7 to 9, comprising: identifying (312a) the second UE group (210) as a network performance matched UE group (210) in case of the identification of the overlap between the performance metrics of the second UE group (210) and the performance metrics of the first reference UE group (208); or identifying (312b) the second UE group (210) as a network performance mismatched UE group (210) in case of the identification of the non-overlap between the performance metrics of the second UE group (210) and the performance metrics of the first reference UE group (208).

11. The method (300) according to any of the claims ? to 10, wherein the overlap indicates that the performance data of the plurality of UEs (1002-B) of the second UE group (210) is within the network threshold values.

12. The method (300) according to any of the claims 7 to 11, wherein the non-overlap indicates that the performance data of at least one UE (1002-B) of the plurality of UEs (1000-B) of the second UE group (210) is outside the network threshold values.

13. The method (300) according to any of the claims 7 to 12, comprising: performing (314) one or more actions upon identifying the second UE group (210) as the network performance mismatched UE group (210) based on the identification of the non-overlap, wherein the one or more actions comprise transmitting at least one notification, and / or automatic reconfiguration of the wireless communication network (106) and / or of the plurality of UEs (1000-B) in the second UE group (210).

14. The method (300) according to claim 13, wherein the at least one notification is transmitted to: a user of the network performance mismatched UE (1002-B) in the network performance mismatched UE group (210), and / or an operator of the network performance mismatched UE group (210) and / or a network manager of the network performance mismatched UE group (210), and / orUE manufacturer of the network performance mismatched UE group (210).

15. A system (200) for determining network performance for a User Equipment, UE, group (208, 210) from a plurality of UE groups (208, 210) comprising a plurality of UEs (1000-A, 1000-B), the system (200) comprising: at least one processing circuitry (202) arranged to:form a first reference UE group (208) and a second UE group (210) from the plurality of UE groups (208, 210), wherein the plurality of UEs (1000-A) in the first reference UE group (208) are different UEs than a plurality of UEs (1000-B) in the second UE group (210), wherein the first reference UE group (208) and the second UE group (210) are adapted to operate in a wireless communication network (106) according to a respective group property; obtain UE performance data for a plurality of UEs (1000-A, 1000-B) comprised in the first reference UE group (208) and for the plurality of UEs (1000-B) comprises in the second UE group (210); generate a first reference UE group performance model and a second UE group performance model from the UE performance data for the respective UE group (208, 210); and determine whether the network performance of the second UE group (210) is different from the network performance of the first reference UE group (208), wherein the difference in the performance is detected based on a comparison of the second UE group performance model with the first reference UE group performance model.

16. The system (200) according to claim 15, wherein: the group property is common for the UEs (1002-A) in the first reference UE group (208), wherein the group property is common for the UEs (1002-B) in the second UE group (210), and wherein the group property for the first reference UE group (208) is different from the group property for the second UE group (210).

17. The system (200) according to any of the claim 15 or 16, wherein the group property for the respective UE group (208, 210) comprises: a UE model for the UEs (1002-A, 1002-B) of the first reference UE group (208) and of the second UE group (210); a UE network configuration comprising at least one of:one or more UE parameters of the respective UE group (208, 210), and features to be used or not used by the UEs (1002-A, 1002-B) of the respective UE group (208, 210); and features to be used by the wireless communication network (106) in communication with the UEs (1002-A, 1002-B) of the respective UE group (208, 210).

18. The system (200) according to any of the claims 15- 17, wherein the UE performance data comprises at least one Key Performance Indicator, KPI, of the respective UE (1002-A, 1002-B), wherein the KPI comprises at least one of: throughput, latency, fraction of retransmissions, handover failures, uplink data rate, downlink data rate, signal to noise ratio, SNR, signal to interference plus noise, SINR, and Reference Signal Received Power, RSRP.

19. The system (200) according to any of the claims 15-18, wherein the performance data of the UEs (1000-A, 1000-B) in each of the reference UE group (208) and the second UE group (210) is related to at least one network property, wherein the at least one network property comprises at least one of: time information, position of the UE (1002-A, 1002-B), position of a serving gNB in the wireless communication network (106), cell identifier, cell ID, and load.

20. The system (200) according to any of the claim 15-19, wherein each of the reference and the second UE group performance model comprises a respective performance metric comprising at least one of: an average value of a Key Performance indicator, KPI, of the UEs (1002-A, 1002- B) of the respective UE group (208, 210), wherein the respective performance metric is related to at least one network property, and a correlation between at least two different KPIs defined for at least one UE (1002-A, 1002-B) of the respective UE group (208, 210).

21. The system (200) according to any of the claim 15-20, wherein the processing circuitry(202) is arranged to:identify whether there is an overlap or a non-overlap between the performance metrics of the second UE group (210) and the performance metrics of the reference UE group (208) based on the comparison of reference UE group performance model and the second UE group performance model.

22. The system (200) according to claim 21, wherein the performance metrics for the reference UE group model comprises network threshold values for each performance data.

23. The system (200) according to the claim 21 or 22, wherein the network threshold values comprise performance data threshold values within which the plurality of UEs (1000-A, 1000-B) of the respective UE group (208, 210) is operational in the wireless communication network (106).

24. The system (200) according to any of the claims 21 to 22, wherein the processing circuitry (202) arranged to: identify the second UE group (210) as a network performance matched UE group (210) in case of the identification of the overlap between the performance metrics of the second UE group (210) and the performance metrics of the reference UE group (208); or identify the second UE group (210) as a network performance mismatched UE group (210) in case of the identification of the non-overlap between the performance metrics of the second UE group (210) and the performance metrics of the reference UE group (208).

25. The method (300) according to any of the claims 21 to 23, wherein the overlap indicates that the performance data of the plurality of UEs (1002-B) of the second UE group (210) is within the network threshold values.

26. The method (300) according to any of the claims 21 to 24, wherein the non-overlap indicates that the performance data of the at least one UE (1002-B) of the plurality of UEs (1000-B) of the second UE group (210) is outside the network threshold values.

27. The system (200) according to any of the claim 15-26, wherein the processing circuitry (202) is arranged to: perform one or more actions upon identifying the second UE group (210) as the network performance mismatched UE group (210) based on the identification of the non-overlap, wherein the one or more actions comprise transmitting at least one notification, and / or automatic reconfiguration of the wireless communication network (106) and / or of the plurality of UEs (1000-B) in the second UE group (210).

28. The system (200) according to the claim 1 , wherein the at least one notification is transmitted to: a user of the network performance mismatched UE (1002-B) in the network performance mismatched UE group (210), and / or an operator of the network performance mismatched UE group (210) and / or a network manager of the network performance mismatched UE group (210), and / orUE manufacturer of the network performance mismatched UE group (210).

29. A computer program product comprising a non-transitory computer readable medium, having thereon a computer program comprising program instructions, the computer program is loadable into a data processing unit and configured to cause execution of the method according to any of claims 1 through 14 when the computer program is run by the data processing unit.

Images