WO2022207967A1

WO2022207967A1 - A method for recognising an incorrectly operating antenna in

Info

Publication number: WO2022207967A1
Application number: PCT/FI2022/050148
Authority: WO
Inventors: Riku ERTIMO
Original assignee: Elisa Oyj
Priority date: 2021-04-01
Filing date: 2022-03-09
Publication date: 2022-10-06
Also published as: FI20215401A1; FI130827B1

Abstract

A computer implemented method for recognizing an incorrectly operating beamforming antenna that serves a sector of a cell of a communication network.The method comprises forming a statistical model based on test data, the test data comprising prior beam-level performance indicator data or statistics of one or more other beamforming antennas, obtaining a data set comprising beam-level performance indicator data or statistics of a target beamforming antenna, and providing output information indicating whether the target beamforming antenna is operating incorrectly by applying the model on said data set.

Description

A METHOD FOR RECOGNISING AN INCORRECTLY OPERATING ANTENNA IN A COMMUNICATION NETWORK

TECHNICAL FIELD

The present disclosure generally relates to performance analysis of a communication network. The disclosure relates particularly, though not exclusively, to a method for recognition of an incorrectly operating antenna in a cell of a communication network.

BACKGROUND

This section illustrates useful background information without admission of any technique described herein representative of the state of the art.

Cellular communication networks are complex systems comprising a plurality of cells serving users of the network. In order for a communication network to operate as intended and to provide a planned quality of service, cells of the communication network need to operate as planned. Cells of communication networks are provided with transmitting and receiving antennas which may be placed at dedicated antenna towers, on the roof of various buildings or at similar locations. Instead of omnidirectional antennas it is typical to use sector antennas serving only a sector. For example, three sector antennas divided at angular separation of 120 degrees may be used to cover a whole 360 degrees area of a cell.

In advanced networks, the sector antennas are implemented as beamforming antennas. The beamforming antennas are capable of producing narrow beams within the sector they are serving to further improve the service provided to the users. The correct operation of beamforming antennas require that the antennas are configured correctly. However, during configuration, there are a plurality of output ports in remote radio units that must be connected by cables to respective antenna ports manually, and sometimes the cables end up being connected incorrectly. Wrong cabling is typically caused by a human error, but in some cases also instructions have been insufficient causing systematic errors. When beamforming is activated and if antenna configuration is performed incorrectly, antenna patterns are not correct, leading to capacity and quality losses.

Now a new approach for recognizing such incorrectly operating beamforming antennas is provided.

SUMMARY

The appended claims define the scope of protection. Any examples and technical descriptions of apparatuses, products and/or methods in the description and/or drawings not covered by the claims are presented not as embodiments of the invention but as background art or examples useful for understanding the invention.

According to a first example aspect of the present invention, there is provided a computer implemented method for recognizing an incorrectly operating beamforming antenna that serves a sector of a cell of a communication network, the method comprising: forming a statistical model based on test data, the test data comprising prior beam- level performance indicator data or statistics of one or more other beamforming antennas; obtaining a data set comprising beam-level performance indicator data or statistics of a target beamforming antenna; and providing output information indicating whether the target beamforming antenna is operating incorrectly by applying the model on said data set.

In certain example embodiments, the test data comprises performance indicator data and/or data obtained or calculated based on performance indicator data.

In certain example embodiments, the data set comprises performance indicator data and/or data obtained or calculated based on performance indicator data. The data set in certain embodiments comprises performance indicator data or statistics relating to a plurality of target beamforming antennas.

In certain example embodiments, the incorrect antenna operation is identified as an incorrectly connected radio signal cable or cables.

In certain example embodiments, the beam-level performance indicator data or statistics of the target beamforming antenna comprise performance indicator statistics of individual beams formed by the target beamforming antenna.

In certain example embodiments, the prior (historical) beam-level performance indicator data or statistics comprise performance indicator data or statistics from time periods before and after a time instant of a known correction of operation of one or more of the said one or more other antennas.

In certain example embodiments, the output information indicates a probability on whether the target beamforming antenna is operating incorrectly.

In certain example embodiments, the method comprises: updating the statistical model based on verified correctness of the output information.

In certain example embodiments, the statistical model is a logistic regression model.

In certain example embodiments, the target beamforming antenna is a sector antenna of a fifth generation, 5G, or a further generation mobile communication network. According to a second example aspect of the present invention, there is provided an apparatus, comprising: a processor; and a memory including computer program code, the memory and the computer program code being configured, with the processor, to cause the apparatus to perform the method of the first aspect or any related embodiment.

According to a third example aspect of the present invention, there is provided a computer program comprising computer executable program code which when executed by a processor causes an apparatus to perform the method of the first aspect or any related embodiment. According to a fourth example aspect there is provided a computer program product comprising a non-transitory computer readable medium having the computer program of the third example aspect stored thereon.

According to a fifth example aspect there is provided an apparatus comprising means for performing the method of the first aspect or any related embodiment. Any foregoing memory medium may comprise a digital data storage such as a data disc or diskette, optical storage, magnetic storage, holographic storage, opto- magnetic storage, phase-change memory, resistive random access memory, magnetic random access memory, solid-electrolyte memory, ferroelectric random access memory, organic memory or polymer memory. The memory medium may be formed into a device without other substantial functions than storing memory or it may be formed as part of a device with other functions, including but not limited to a memory of a computer, a chip set, and a sub assembly of an electronic device.

Different non-binding example aspects and embodiments have been illustrated in the foregoing. The embodiments in the foregoing are used merely to explain selected aspects or steps that may be utilized in different implementations. Some embodiments may be presented only with reference to certain example aspects. It should be appreciated that corresponding embodiments may apply to other example aspects as well.

BRIEF DESCRIPTION OF THE FIGURES

Some example embodiments will be described with reference to the accompanying figures, in which:

Fig. 1 schematically shows a scenario according to an example embodiment; Fig. 2 shows a block diagram of an apparatus according to an example embodiment;

Fig. 3 schematically shows operation of a beamforming antenna serving a sector of a cell of a communication network according to an example embodiment; Fig. 4 schematically shows an example of the beamforming antenna and a related radio module according to an example embodiment;

Fig. 5A schematically shows a correct complete radiation pattern in a four-beam example;

Fig. 5B schematically shows an example radiation pattern in a crossed feeder situation;

Fig. 6 shows a flow chart according to an example embodiment; and Fig. 7 shows a flow chart according to another example embodiment. DETAILED DESCRIPTION

In the following description, like reference signs denote like elements or steps.

Fig. 1 shows an example scenario according to an embodiment. The scenario shows a communication network 110 serving a plurality of user devices 112 (user equipment, UE) and comprising a plurality of cells and base station sites and other network devices, and an automated system 111 configured to implement recognition of incorrectly operating antennas of the communication network 110.

In an embodiment, the scenario of Fig. 1 operates as follows: In phase 101 , the automated system 111 obtains performance indicators and other data from or via a cell or cells of base station sites of the network 110.

In phase 102, the automated system 111 uses the received performance indicators to monitor and analyze operation of the cells to detect problems in operation of one or more antennas of the base station sites.

In phase 103, any determined problems are output for further actions such as for example maintenance of the base station sites.

Fig. 2 shows a block diagram of an apparatus 20 according to an embodiment. The apparatus 20 is for example a general-purpose computer or server or some other electronic data processing apparatus. The apparatus 20 can be used for implementing at least some embodiments of the invention. That is, with suitable configuration the apparatus 20 is suited for operating for example as the automated system 111.

The apparatus 20 comprises a communication interface 25, a processor 21 , a user interface 24, and a memory 22.

The communication interface 25 comprises in an embodiment a wired and/or wireless communication circuitry, such as Ethernet, Wireless LAN, Bluetooth, GSM, CDMA, WCDMA, LTE, and/or 5G circuitry. The communication interface can be integrated in the apparatus 20 or provided as a part of an adapter, card or the like, that is attachable to the apparatus 20. The communication interface 25 may support one or more different communication technologies. The apparatus 20 may also or alternatively comprise more than one communication interface 25. The processor 21 may be a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a graphics processing unit, an application specific integrated circuit (ASIC), a field programmable gate array, a microcontroller or a combination of such elements.

The user interface 24 may comprise a circuitry for receiving input from a user of the apparatus 20, e.g., via a keyboard, graphical user interface shown on the display of the apparatus 20, speech recognition circuitry, or an accessory device, such as a headset, and for providing output to the user via, e.g., a graphical user interface or a loudspeaker.

The memory 22 comprises a work memory 23 and a persistent (non-volatile, NL/) memory 26 configured to store computer program code 27 and data 28. The memory 26 may comprise any one or more of: a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a random-access memory (RAM), a flash memory, a data disk, an optical storage, a magnetic storage, a smart card, a solid state drive (SSD), or the like.

The apparatus 20 may comprise a plurality of memories 26. The memory 26 may be constructed as a part of the apparatus 20 or as an attachment to be inserted into a slot, port, or the like of the apparatus 20 by a user or by another person or by a robot. The memory 26 may serve the sole purpose of storing data, or be constructed as a part of an apparatus 20 serving other purposes, such as processing data.

A skilled person appreciates that in addition to the elements shown in Fig. 2, the apparatus 20 may comprise other elements, such as microphones, displays, as well as additional circuitry such as an input/output (I/O) circuitry, memory chips, application-specific integrated circuits (ASIC), a processing circuitry for specific purposes such as a source coding/decoding circuitry, a channel coding/decoding circuitry, a ciphering/deciphering circuitry, and the like. Additionally, the apparatus 20 may comprise a disposable or rechargeable battery (not shown) for powering the apparatus 20 when external power if external power supply is not available.

Further, it is noted that only one apparatus is shown in Fig. 2, but the embodiments of the invention may equally be implemented in a cluster of shown apparatuses. Fig. 3 schematically shows operation of a beamforming antenna serving a sector of a cell of a communication network according to an example embodiment. The transmission of data and control information to any individual user device 112 (such as a smart phone or another mobile communication device) is done with the aid of narrow beams. Each individual beam is a signal limited in space (narrow beam) intended to reach a certain user device (or devices) 112 located within the coverage area of that specific beam. In the example shown in Fig. 3, there are six beams 310 formed by a beamforming antenna 301 that serves the sector 302 of a cell of a mobile communication network (in other embodiments, the number of beams may vary). In the leftmost drawing of the example, the user device 112 that is marked with a black circle is within the coverage of the third beam 310 calculated from the left, and in the rightmost drawing that presents a situation after a period of time has passed, the user device 112 in question has moved into the coverage of the rightmost beam 310.

Fig. 4 schematically shows an example of the beamforming antenna 301 and a related radio module 410 (a remote radio unit). The beamforming antenna 301 comprises a plurality of antenna elements 311. The beamforming antenna 301 further comprises a plurality of antenna ports 312 in each of the elements 311. In the example shown in Fig. 4, the number of antenna elements (which is also the number of beams) is four. Flowever, as has been already described in the preceding, the number of antenna elements varies between different embodiments. Similarly, the number of antenna ports 312 is two for each of the elements 311. The radio module comprises a plurality of output ports 412 to be connected to respective antenna ports 314 by cables (radio signal cables). In the example shown in Fig. 4, the correspondence of the output ports 412 and the antenna ports 312, is as follows:

In this example, this represents a correct cabling, whereas if any of the two or more cables are not connected as shown in the preceding table, there is a crossed feeder situation (i.e., an incorrect cabling).

Fig. 5A schematically shows an example of a complete radiation pattern (beam power depending on direction) in such a four-beam example where the cables are correctly connected, whereas Fig. 5B shows the radiation pattern in an example in which cables are crossed (i.e., in the case of an incorrect cabling).

When the obtained power is compared, it is observed that there is a significant drop in the obtained power in Fig. 5B in the edge areas, which will result in less sharp beams and antenna coverage losses.

In order to recognize incorrect operation of a beamforming antenna, embodiments of the invention provide crossed feeder detection in beam forming sectors using OSS (Operations Support Systems) statistics. Accordingly, in step 610 of a flow chart according to an example embodiment shown in Fig. 6, a statistical model is formed based on test data, the test data comprising prior beam-level performance indicator data or statistics of one or more beamforming antennas. The test data comprises performance indicator data as such and/or statistics and/or values calculated based on said performance indicator data. When a particular antenna or particular antennas (target beamforming antenna(s)) is/are under evaluation, the test data should typically comprise prior data from other beamforming antenna(s). The beam-level data in certain embodiments means data/calculated data/statistics reflecting individual beams formed by the beamforming antenna(s) in question. In certain embodiments, the prior beam-level performance indicator data or statistics contains data/statistics being obtained from time periods both before and after a time instant of a known correction of operation of one or more of the said other antennas. For example, incorrect cabling of one or more of said other beamforming antennas may have been corrected at a known time instant so that the test data comprises data/statistics from time periods both before and after that time instant.

In step 620, a data set is obtained, the data set comprising beam-level performance indicator data or statistics of the beamforming antenna under evaluation. In step 630, the statistical model is applied on the data set, and in step 640, output information in provided, the output information indicating whether the target beamforming antenna is operating incorrectly.

The steps 610-640 may be performed by the system 111 as described in the preceding Figs. 1 and 2 by using the interface(s), processor(s), and memories for obtaining or receiving, processing and storing information as required.

Fig. 7 shows a flow chart of a more detailed embodiment. In a data feature engineering phase (phase 1), certain data features are built. The network 110 provides to the system 111 (OSS or similar) a plurality of performance indicators (KPI, Key Performance Indicators). Depending on the embodiment, the recognition of the incorrect operation of a beamforming antenna is based on these performance indicators and/or data features build based on these performance indicators. In example embodiments, the one or more of the following data features may be used:

• Usage of each beam

• Number of UEs and/or samples per beam · Time the UE is in each beam (if the cables are crossed and beam patterns are unclear, the UE spends less time in one beam i.e. changes the beam more often)

• Share of cases where UE is less than a predetermined amount of time, such as 1 second, in the beam · Beam “ping pong” (measuring the UE leaving one beam but arriving immediately back at the original beam)

• Share of toggles (ping pong) between beams

• Traffic volume per toggle, or ping pong event • Power difference (power difference between adjacent beams is greater if the cables are installed correctly)

• Share of cases where RSRP (reference signal received power) difference is less than, e.g., 2 dB between best and second best beam

• handovers/transitions to adjacent beams (statistically the UE should change the beam more often to adjacent beams)

• Share of transitions where UE is moving to an adjacent beam (compared to moving to non-adjacent beams)

• Total traffic volume

• Modulation and coding scheme in use

• Distance between UE and base station (timing advance, TA)

• Rank information (defining the number of data streams provided)

In certain embodiments, at least two of the mentioned data features are selected to be used the recognition of the incorrect operation of a beamforming antenna. In certain embodiments, at least three of the mentioned data features are selected to be used the recognition of the incorrect operation of a beamforming antenna. In certain embodiments, at least four of the mentioned data features are selected to be used the recognition of the incorrect operation of a beamforming antenna.

In phase 2, the test data is imported, and cleaning of the test data is performed. This includes data import, and some basic cleaning, such as null removal and/or out layer detection.

In phase 3, the test data is filtered. For example, small traffic volumes may give false detection, hence cases with very low traffic volume may be filtered out. Other or alternative filtering conditions may include: number of users and/or distance from base station to UE.

In phase 4, the test data is labeled. The test data comprises data before and after an incorrect cabling has been corrected in a known case or known cases. Accordingly, the test data in certain embodiments comprises number of cases where incorrect cabling has been detected by some other means, such as during site visit due to other reasons, or from drive testing data. These cases are labeled, for example manually, based on date/time stamp information on when the correction was performed in the said cases. The labeling defines the impact of incorrect cabling on performance indicators in the prior (reference) cases.

In phase 5, a statistical model is created based on the test data set. In an embodiment, a logistic regression model is created. In other embodiments, a statistical model of another type is created.

Once the statistical model has been created based on phases 1-5, a new data set is imported and cleaned in phase 6 and filtered in phase 7. As to phases 6 and 7 a reference is made to preceding phases 2 and 3 concerning test data.

The new data set contains performance indicator data or performance indicator -based data of (target) beamforming antenna(s) without prior information about incorrect cabling, but the task indeed is to identify from this new data set the cases that have incorrect cabling by applying the model on the new data set in phase 8. In an embodiment, phase 8 provides output information indicating a probability on whether the target beamforming antenna is operating incorrectly.

Once incorrect cabling has been recognized in phase 8, the cabling of recognized incorrectly operating beamforming antenna(s) is corrected in phase 9. The result of the correction is verified by a field visit in phase 10.

In phase 11 , verified findings are imported to the model. Accordingly, the statistical model is updated based on verified correctness of the output information. In practice this means that “new” test data is constructed from the ’’old” test data plus the new findings. Based on this, new more accuracy model is created for the next data set.

Without limiting the scope and interpretation of the patent claims, certain technical effects of one or more of the example embodiments disclosed herein are listed in the following. A technical effect is providing an automated method for recognizing incorrectly operating beamforming antennas of a cellular communication network. In this way, improved network monitoring may be provided. Another technical effect is the ability to present findings concerning incorrectly operating sector antennas with reduced field measurement resources/drive testing since the findings can be based on OSS counters/beam-level performance indicator data readily available to the network.

Various embodiments have been presented. It should be appreciated that in this document, words comprise, include and contain are each used as open-ended expressions with no intended exclusivity.

The foregoing description has provided by way of non-limiting examples of particular implementations and embodiments a full and informative description of the best mode presently contemplated by the inventors for carrying out the invention. It is however clear to a person skilled in the art that the invention is not restricted to details of the embodiments presented in the foregoing, but that it can be implemented in other embodiments using equivalent means or in different combinations of embodiments without deviating from the characteristics of the invention.

Furthermore, some of the features of the afore-disclosed example embodiments may be used to advantage without the corresponding use of other features. As such, the foregoing description shall be considered as merely illustrative of the principles of the present invention, and not in limitation thereof. Hence, the scope of the invention is only restricted by the appended patent claims.

Claims

1. A computer implemented method for recognizing an incorrectly operating beamforming antenna that serves a sector of a cell of a communication network, the method comprising: forming a statistical model based on test data, the test data comprising prior beam-level performance indicator data or statistics of one or more other beamforming antennas; obtaining a data set comprising beam-level performance indicator data or statistics of a target beamforming antenna; and providing output information indicating whether the target beamforming antenna is operating incorrectly by applying the model on said data set.

2. The method of claim 1 , wherein the incorrect antenna operation is identified as an incorrectly connected radio signal cable or cables.

3. The method of claim 1 or 2, wherein the beam-level performance indicator data or statistics of the target beamforming antenna comprise performance indicator statistics of individual beams formed by the target beamforming antenna.

4. The method of any preceding claim, wherein the prior beam-level performance indicator data or statistics comprise performance indicator data or statistics from time periods before and after a time instant of a known correction of operation of one or more of the said one or more other antennas.

5. The method of any preceding claim, wherein the output information indicates a probability on whether the target beamforming antenna is operating incorrectly.

6. The method of any preceding claim, comprising: updating the statistical model based on verified correctness of the output information.

7. The method of any preceding claim, wherein the statistical model is a logistic regression model.

8. The method of any preceding claim, wherein the target beamforming antenna is a sector antenna of a fifth generation, 5G, or a further generation mobile communication network.

9. An apparatus, comprising: a processor; and a memory including computer program code, the memory and the computer program code being configured, with the processor, to cause the apparatus to perform the method of any of the claims 1-8.

10. A computer program comprising computer executable program code which when executed by a processor causes an apparatus to perform the method of any of the claims 1-8.