WO2021151503A1 - Nœud analytique et procédé associé - Google Patents

Nœud analytique et procédé associé Download PDF

Info

Publication number
WO2021151503A1
WO2021151503A1 PCT/EP2020/052443 EP2020052443W WO2021151503A1 WO 2021151503 A1 WO2021151503 A1 WO 2021151503A1 EP 2020052443 W EP2020052443 W EP 2020052443W WO 2021151503 A1 WO2021151503 A1 WO 2021151503A1
Authority
WO
WIPO (PCT)
Prior art keywords
network
cell
uds
events
node
Prior art date
Application number
PCT/EP2020/052443
Other languages
English (en)
Inventor
László HÉVIZI
Attila BÁDER
Gábor MAGYAR
Original Assignee
Telefonaktiebolaget Lm Ericsson (Publ)
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Telefonaktiebolaget Lm Ericsson (Publ) filed Critical Telefonaktiebolaget Lm Ericsson (Publ)
Priority to PCT/EP2020/052443 priority Critical patent/WO2021151503A1/fr
Publication of WO2021151503A1 publication Critical patent/WO2021151503A1/fr

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition

Definitions

  • the present invention relates to identifying wireless network coverage problems.
  • the present invention relates in particular to an analytics node configured to identify geographical areas experiencing network coverage problems and method thereof.
  • Radio coverage evaluations in wireless networks are typically performed by drive tests and offline radio analysis tools. Performing such drive tests have the disadvantage of being relative expensive and time consuming. A further drawback of such conventional methods is that they require specific equipment, radio optimization experts and substantial manual work. A further drawback of such conventional methods is that the results and possibly a solution to a coverage problem is only available after several hours or days of processing.
  • the existing offline analysis tools typically work on aggregated data, where coverage problems appear as unfavorable statistics on radio link failures and handovers.
  • 3GPP specified features that involve network management to collect data from regular subscribers in order to evaluate various performance indicators on network performance, see e.g. “Self-Organizing Networks (SON) 3GPP TS 32.521 v11.1.0”. 3GPP describes an operation framework for these optimization functions, but it does not provide directives how to process such data and what algorithms to apply.
  • SON Self-Organizing Networks
  • MDT Minimization of Drive Tests
  • MDT itself is suitable to detect but not to solve coverage issues, so expert knowledge and human workhours are still needed to classify coverage problems. Persistent coverage problems can result in significant revenue loss and consequently subscriber churn for the network operator.
  • the solution to a coverage problem does not necessarily involves installing more hardware in the network, it may be sufficient to tune antennas, RRC parameters, etc. To decide on which kind of solution is appropriate to select requires both deep and expensive radio network expertise.
  • the objects of the invention is achieved by a method performed by an analytics node configured to identify geographical areas experiencing network coverage problem types in a wireless communications network.
  • the communications network comprises a plurality of wireless access nodes, one or more core network nodes and a plurality of user devices.
  • Each of the wireless access nodes is controlling one or more cells, the cells at least transmitting signals to the UDs, the method comprising obtaining, by the analytics node, event data, indicative of network coverage events in the communications network, generating trajectories for each of the plurality of UDs by selecting event data related to each corresponding UD, identifying geographical areas where one or more UDs are experiencing various network coverage problem types by selecting segments of the UD trajectories using predetermined conditions of transmitted signal characteristics and classifying the selected segments using a trained model, wherein each selected segment is labelled with a network coverage problem type by the trained model.
  • the advantage of the first aspect includes at least reducing time for identifying and resolving coverage problems.
  • a further advantage is that the amount of labor for identifying and resolving coverage problems can be reduced.
  • a further advantage is that the complexity for identifying and resolving coverage problems can be reduced.
  • the objects of the invention is achieved by an analytics node configured to identify geographical areas experiencing network coverage problem types in a wireless communications network.
  • the communications network comprising a plurality of wireless access nodes, one or more core network nodes and a plurality of user devices, UDs, each of the wireless access nodes is controlling one or more cells, the cells at least transmitting signals to the UDs, the analytics node comprising processing circuitry, a memory comprising instructions executable by the processing circuitry, causing the processing circuitry to perform the method according to the first aspect.
  • the objects of the invention is achieved by a computer program comprising computer-executable instructions for causing a node, when the computer-executable instructions are executed on processing circuitry comprised in the node, to perform the method according to the first aspect.
  • a computer program product comprising a computer-readable storage medium, the computer- readable storage medium having the computer program according to the third aspect embodied therein
  • the objects of the invention is achieved by a carrier containing the computer program according the third aspect, wherein the carrier is one of an electronic signal, optical signal, radio signal, or computer readable storage medium.
  • Fig. 1 illustrates a wireless communications network according to one or more embodiments of the present disclosure.
  • Fig. 2 illustrates an example of one or more cells transmitting signals or wireless signals to user devices.
  • Fig. 3 illustrates identification of a geographical area experiencing a network coverage problem according to one or more embodiments of the present disclosure.
  • Fig. 4 shows a flowchart of a method according to one or more embodiments of the present disclosure.
  • Fig. 5 illustrates a coverage problem of missing coverage between settlements in populated areas.
  • Fig. 6 illustrates a coverage problem of coverage gaps between settlements in populated areas.
  • Fig. 7 illustrates a coverage problem of poor indoor coverage.
  • Fig. 8 illustrates a coverage problem of sudden coverage change at tunnel entrances. Tunnels are usually covered by indoor cells or repeaters.
  • Fig. 9 illustrates a coverage problem of shadowing object.
  • Fig. 10 illustrates a coverage problem of poor coverage in private zones.
  • Fig. 11 illustrates a selected segment according to one or more embodiments of the present disclosure.
  • Fig. 12 shows a flowchart of a method according to one or more embodiments of the present disclosure.
  • Fig. 13 shows details of a node/computer device/ computer system according to one or more embodiments of the present disclosure.
  • An Artificial Intelligence (Al) method and system are disclosed for using a trained model for detecting, classifying and optionally identifying the root cause of mobile-network coverage issues in real-time.
  • the technique analyzes e.g. the time dependency and the mutual relations of reported signal strengths from the serving and neighboring cells, especially, by focusing on the preceding period of radio link failures and the period following the radio reconnection and handover situations.
  • a real-time, event-based analytics system continuously collects the radio environment measurement reports from both the user devices and network-side transceivers.
  • the user-specific Radio Access Network, RAN, measurements are real-time merged and correlated or synchronized with radio resource control (RRC) level events and data session information that belong to the user in an analytical framework.
  • RRC radio resource control
  • Machine learning techniques in the form of unsupervised clustering method is disclosed, which groups the various coverage problems into categories, such as indoor or outdoor coverage holes, low signal strength between neighboring cells, overshoot from neighbors, presence of shadowing objects, failed handovers, interference sensitivity, etc.
  • the different symptoms including the pre- and post-event histories separate these situations into categories, which may call for specific solution.
  • subscriber behavior, motion, data traffic, equipment type are also included in the analysis, so the proposed classifying technique estimates the number of affected subscribers, the relative occurrences and the characteristic time and locations (if exist) of the identified coverage problems. This information leads to the root cause and the network operator can work out the solution.
  • the network side can classify user related symptoms in real time and can automatically take preventive actions or solve problematic situations, e.g. it can redirect the user to other carrier or radio access technology.
  • the network operator may retune, upgrade or extend its network to eliminate acute coverage problems. There will be several cases, e.g. when only a few subscribers are affected, then the operator will live with the problem, but at least the operator will be aware of the root cause and can monitor further occurrences of the problem
  • the disclosure described herein monitors the radio environment of a large-scale mobile network and it automatically detects and classifies the radio-related issues using the primarily the time variation of the radio signals strength reported by mobile devices.
  • the coverage problems are augmented with subscriber related data, such as the number of affected subscribers, their location and used services, if available.
  • the detailed time-variant histories of measured radio signal strengths reveal issues that are not possible to detect with traditional processing, e.g. with 5-15-minute performance counters, KPIs, which are aggregated data.
  • KPIs which are aggregated data.
  • the Al based algorithms operate in a combined offline and stream-processing mode, i.e. the detailed data allows us to build a model, then classify in real time, but afterwards the data can be dropped. Hence only a buffer of recent detailed data is kept in data bases.
  • the most critical coverage problems such as handover and radio link failure issues, can be identified and directions towards a possible solution can be inferred.
  • the technique also explores the root cause and evaluates the severity of the problem, so that the network operator can work out the solution and estimate its cost.
  • the preventive step or solution can be automated and executed automatically by the analytical system.
  • ⁇ EA is used interchangeably with the term “Ericsson Expert Analytics”.
  • RAT is used interchangeably with the term “Radio Access Technology”.
  • RLF radio Link Failure
  • UD is used interchangeably with the term “User Device”. Unless otherwise noted, the term UD may be used interchangeably herein with user equipment (UE). Communicating wirelessly may involve transmitting and/or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and/or other types of signals suitable for conveying information through air.
  • a UD may be configured to transmit and/or receive information without direct human interaction. For instance, a UD may be designed to transmit information to a network on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the network.
  • Examples of a UD include, but are not limited to, a smart phone, a mobile phone, a cell phone, a voice over IP (VoIP) phone, a wireless local loop phone, a desktop computer, a personal digital assistant (PDA), a wireless cameras, a gaming console or device, a music storage device, a playback appliance, 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, etc.
  • VoIP voice over IP
  • PDA personal digital assistant
  • LOE laptop-embedded equipment
  • LME laptop-mounted equipment
  • CPE wireless customer-premise equipment
  • a UD may support device-to-device (D2D) communication, for example by implementing a 3GPP standard for sidelink communication, and may in this case be referred to as a D2D communication device.
  • D2D device-to-device
  • a UD may represent a machine or other device that performs monitoring and/or measurements, and transmits the results of such monitoring and/or measurements to another UD and/or a network node.
  • the UD may in this case be a machine- to-machine (M2M) device, which may in a 3GPP context be referred to as a machine-type communication (MTC) device.
  • M2M machine- to-machine
  • MTC machine-type communication
  • the UD may be a UE implementing the 3GPP narrow band internet of things (NB-loT) standard.
  • NB-loT 3GPP narrow band internet of things
  • machines or devices are sensors, metering devices such as power meters, industrial machinery, or home or personal appliances (e.g. refrigerators, televisions, etc.) personal wearables (e.g., watches, fitness trackers, etc.).
  • a UD may represent a vehicle or other equipment that is capable of monitoring and/or reporting on its operational status or other functions associated with its operation.
  • a UD as described above may represent the endpoint of a wireless connection, in which case the device may be referred to as a wireless terminal.
  • a UD as described above may be mobile, in which case it may also be referred to as a mobile device or a mobile terminal.
  • Fig. 1 illustrates a wireless communications network 151 according to one or more embodiments of the present disclosure.
  • the wireless communications network 151 comprises an analytics node 101 configured to identify geographical areas experiencing network coverage problem types in the wireless communications network.
  • the wireless communications network 151 further comprises a plurality of user devices 131- 133, UDs.
  • the wireless communications network 151 further comprises a plurality of wireless access nodes 111-113.
  • the wireless access nodes 111-113 are communicatively coupled to the analytics node 101 , and configured to at least send data or event data, such as cell trace events, radio resource control, RRC, events and handover events to the analytics node 101.
  • Each of the wireless access nodes 111-113 is controlling one or more cells C1-C3.
  • the cells are at least transmitting signals or wireless signals to the UDs 131-133.
  • the cell trace events or RRC cell trace events may e.g. comprise periodic radio measurement reports, which may e.g. include the signal strength (e.g. RSRP) and signal quality (e.g. RSRQ) of the serving cell and visible neighbor cells.
  • the cell trace events may include handover related RRC events, e.g. the handover RRC measurement trigger events received from UEs. Then handover events may comprise events that log the handover preparation and completion messages among the source and target cells as well as the reports about the attempt, success and failed handovers.
  • the wireless communications network 151 further comprises one or more core network nodes 121 communicatively coupled to the analytics node 101 and to the wireless access nodes H I- 113.
  • the one or more core network nodes 121 are configured to send data, such as general packet radio service, GPRS, tunneling protocol events to the analytics node 101.
  • the GPRS tunneling protocol events may e.g. include GPRS Tunneling Protocol, GTP-C, events, where the signaling messages are used to correlating the radio events with user context information. Such events are e.g. the bearer setup, modification (in case of handover) and termination.
  • the wireless communications network 151 further comprises an operations and maintenance, O&M, node 141 communicatively coupled to the analytics node 101 and configured to send data, such as cell reference data coupled to the analytics node 101.
  • the cell reference data may e.g. comprise base station location, sectors, antenna orientation, tilt, frequency assignment, etc.
  • the different types of data are typically sent between the different nodes comprised in wired or wireless signals via one or more communication interfaces.
  • the information needed for coverage problem classification comes, at least partially, from the radio access network, which may involve several radio access technologies and radio frequency carriers.
  • the information needed for coverage problem classification may further partially come from the core network, where primarily the UE specific data, control- plane events, messages and decisions are of interest.
  • the desired information or event data is thus already available in network analytics subsystems.
  • Fig. 2 illustrates an example of one or more cells C1-C3 transmitting signals or wireless signals to the UDs 131-133.
  • a first wireless access node 111 comprises a cell C1 , in which coverage area a first UD 131 and a second UD 132 are located.
  • a second wireless access node 112 comprises a second cell C2, in which coverage area the second UD 132 and a third UD 133 are located.
  • a third wireless access node 113 comprises a third cell C3, in which coverage area the second UD 132 and the third UD 133 are located.
  • areas or sub-areas may be defined, shown as areas Z1-Z5 in Fig. 2.
  • An increased resolution of such areas or sub- areas may be achieved by the use of fingerprinting techniques, in other words mapping similar wireless signal characteristics to a similar position or sub-area.
  • each UD Over time each UD will be involved in or associated to various events, typically consecutive in time, that may be identified as trajectories 210, 220, 230.
  • the trajectories are shown as spatial trajectories indicative of how the UDs have changed position geographically, however it is understood that a trajectory can be formed also for a geographically stationary UD, when coverage conditions change for the geographically stationary UD.
  • the UD may be involved in a handover triggered by load conditions of the cells and not triggered by movement of the UD.
  • the overlap of coverage areas of cells can be used to determine a position/location of an UD using different fingerprint techniques, e.g. using the wireless signal signature from all cells, which is derived from any combination of signal characteristics such as amplitude, phase, delay, direction, and polarization information of the received signals.
  • fingerprint techniques e.g. using the wireless signal signature from all cells, which is derived from any combination of signal characteristics such as amplitude, phase, delay, direction, and polarization information of the received signals.
  • the more parameters used the higher the accuracy of the position generated by fingerprinting will be.
  • UDs can be determined to be in the same location by monitoring characteristics of received signals, by the respective UD, from different cells.
  • FIG. 3 illustrates identification of a geographical area experiencing a network coverage problem according to one or more embodiments of the present disclosure.
  • a first wireless access node 111 comprising a first cell C31 and a second cell C32 is shown.
  • Geographical areas are identified A1-A2, where one or more UDs are experiencing network coverage problems of a similar or same type.
  • the analytics node 101 obtains event data, indicative of network coverage events in the communications network. Trajectories are generated for each of the plurality of UDs by selecting or filtering out event data related to each corresponding UD, e.g. based on UD identity. Segments of the trajectories are selected using predetermined conditions of transmitted and received signal characteristics, e.g. predetermined conditions indicative of a particular network coverage problem type.
  • a subset of the selected segments may be generated or filtered out for each cell or serving cell C31-C32, e.g. a subset of segments where cell C31 is the serving cell.
  • the selected segments may be associated to different UDs, and thus be indicative of a coverage problem affecting multiple UDs.
  • a further subset 311 of the generated subset for cell C31 can be formed for segments having the same or similar “fingerprint” or signal signature, which is derived from signal characteristics of each segment, and/or a network coverage problem of the same type.
  • the area A1 can then be identified as an area inferred by the “fingerprint” or signal signature.
  • the segments of the further subset can be considered to be located within the same geographical area A1 , based on the fact that they display or have the same or similar “fingerprint” or signal signature and/or having a network coverage problem of the same type.
  • a second further subset 312 of a generated subset for cell C32 can be formed for segments having the same or similar “fingerprint” or signal signature, which is derived from signal characteristics of each segment, and/or a network coverage problem of the same type.
  • the area A2 can then be identified as an area inferred by the “fingerprint” or signal signature.
  • the segments of the second further subset can be considered to be located within the same geographical area A2, based on the fact that they display or have the same or similar “fingerprint” or signal signature and/or having a network coverage problem of the same type.
  • Fig. 4 shows a flowchart of a method 400 according to one or more embodiments of the present disclosure.
  • the method performed by an analytics node 101 configured to identify geographical areas A1-A2 experiencing network coverage problem types or network coverage problems of different types in a wireless communications network 151.
  • the communications network further comprises a plurality of wireless access nodes 111-113, one or more core network nodes 121 and a plurality of user devices 131-133, UDs.
  • Each of the wireless access nodes is controlling one or more cells, the cells at least transmitting signals to the UDs.
  • the method comprises:
  • Step 410 obtaining, by the analytics node 101 , event data, indicative of network coverage events in the communications network.
  • the event data is obtained by the analytics node 101 from a selection of any of the wireless access nodes 111-113, the one or more core network nodes 121 and the O&M node 141.
  • obtaining the event data comprises receiving, by the analytics node, RRC cell trace events along the UD trajectories, from the plurality of wireless access nodes, the RRC cell trace events including radio signal strength measurement data (RSRP), receiving, by the analytics node, RRC cell trace events along the UD trajectories, from the plurality of wireless access nodes, the RRC cell trace events including radio quality measurement data (RSRQ), receiving, by the analytics node, handover events along UD trajectories, from the from the plurality of wireless access nodes, receiving, by the analytics node, GPRS, tunneling protocol events along the UD trajectories, from the one or more core network nodes, indicative of at least bearer setup, bearer modification and bearer termination, retrieving, by the analytics node, cell characteristics from an operations and maintenance node (141), indicative of at least geographical location of each cell of the plurality of cells, antenna orientation of each cell, antenna tilt of each cell and frequency allocation of each cell, and combining and synchronizing
  • the analytics node 101 obtains event data by receiving signals indicative of cell trace events and/or RRC events and/or handover events from the plurality of wireless access nodes 111-113. In a further example, the analytics node 101 obtains event data by receiving signals indicative of GPRS tunneling protocol events from the one or more core network nodes 121. In one further example, the analytics node 101 obtains event data by receiving signals indicative of cell characteristics from the O&M node 141. All the received events are then synchronized and merged into a total set of events, comprised in the event data.
  • event data in the form of periodic RRC measurement reports from active UDs are obtained.
  • the period of consecutive measurements can be on the time scale of 5-10s. This periodicity will not load the network management with overwhelming amount of data, yet the network side will know the radio environment even of fast-moving UEs, so that tight sampling of field strengths allows fast reaction in the radio resource control loop.
  • Operators may not exploit fully the option of periodic RRC measurement reporting, and they may limit data collection to the basic mobility related trigger events, such as when UEs report handover situation (A3 mobility event) or weak signal (A2 mobility event).
  • A3 mobility event handover situation
  • A2 mobility event weak signal
  • the incoming information is less in this case, but the analysis of coverage problems is still possible. Anyhow, if coverage problems persist in an area, then the operator can configure UEs residing in that area for periodic reporting.
  • Step 420 generating trajectories for each of the plurality of UDs by selecting event data related to each corresponding UD.
  • the trajectories are generated by determining UD specific subsets of event data. This may e.g. be achieved by filtering the event data using identities of the UDs.
  • each trajectory is indicative of a selection of geographical positions of a corresponding UD, cell trace events indicative of at least received signal strength and received signal quality of the transmitting cells, radio resource control, RRC, events, handover events, general packet radio service, GPRS, tunneling protocol events.
  • the data processing step following 420 the data fusion step from multiple sources 410, where event data is generated is to sort the information per individual UDs.
  • the user records/events are tagged with different and temporary identities.
  • the purpose of step 420 is to generate a time-sequenced data trajectory per UD, which includes selected event data from all sources.
  • trajectories for each of the plurality of UDs are generated by finding/determining/filtering UD-related events as a subset of the event data. Segments of these UD-related events are then selected using predetermined conditions of transmitted signal characteristics, e.g. an event alone or in combination with other events, which indicate poor signal quality from the serving cell.
  • Such events are typically RAT specific, e.g. in case of 3GPP-conform networks, the RRC Event A2, further described in 3GPP TS 36.133 Section 8, followed by a handover failure or radio link failure.
  • the analytics node and/or network management system may trigger on. If periodic field strength measurements are available from the UD during the time interval framing these events, then a more detailed evidence of signal quality degradation is preserved.
  • These selected segments or UD event sequences should be copied out from the UD-related trajectory together with a sufficiently long segment of historical events related to the UD.
  • These UD-related events or UD event sequences can further be augmented with the event logs of recovery or reattachment even if the reappearance of UD in the network happens long after the serving signal degradation or loss.
  • the hereby assembled event data or event sequences are then tagged with the unique UDs id and serving cell id, as well as potentially several neighbor cell ids and signal strength measurements preserving the timestamps of various stages of the signal degrading and recovery process.
  • This data set may be referred to as a selected segment or UE trouble trajectory. Then the selected segments may further be sorted by the serving cells, where the coverage problem started.
  • Step 430 identifying geographical areas A1-A2 where one or more UDs are experiencing network coverage problem types.
  • the areas are identified by selecting segments of the UD trajectories using predetermined conditions of transmitted signal characteristics.
  • the selected segments are then classified using a trained model, wherein each selected segment is classified by classifying each selected segment with a network coverage problem type by the trained model.
  • the selected segment may e.g. be classified as any one of: “indoor coverage hole”, “outdoor coverage hole”, “low signal strength between neighboring cells”, “overshoot from neighbor cell/s”, “presence of shadowing objects”, “failed handover”, “interference sensitivity”.
  • the predetermined conditions of transmitted signal characteristics selects segments indicative of a transmitted signal quality below a first threshold and/or selects segments indicative of a transmitted signal strength below a second threshold.
  • the selected segments are classified as any one of “indoor coverage hole”, “outdoor coverage hole”, “low signal strength between neighboring cells”, “overshoot from neighbor cell/s”, “presence of shadowing objects”, “failed handover”, “interference sensitivity”.
  • the trained model is a classification model trained on annotated event data.
  • the annotated event data is annotated with labels including “indoor coverage hole”, “outdoor coverage hole”, “low signal strength between neighboring cells”, “overshoot from neighbor cell/s”, “presence of shadowing objects”, “failed handover”, “interference sensitivity”.
  • the classification model is selected from any one of a decision tree model, a Naive Bayes model, a Neural Network model, a k-Nearest Neighbor model.
  • the trained model is validated using any one method selected from cross-validation, Precision and Recall, Receiver Operating Characteristics.
  • coverage problem indicators are continuously collected and preprocessed, so that information may be obtained in each area A1-A2 or on each coverage problem spot.
  • the identified coverage problem spots may be continuously ranked by the analytics node. Based on the estimated cost of the coverage problem remedy, and based on the estimated gain, i.e. , how many users will have better customer experience, and what kind of users are involved (e.g. VIP users or any particularly ranked users, e.g. by ARPU (Average Revenue Per Unit)), the ranking allows the operators to plan actions.
  • the hereby proposed analytics system is to provide the network operator with reliable facts and estimates and to help decision makers in planning network maintenance and upgrades with respect to network coverage.
  • the method 400 further comprises ranking the identified geographical areas A1-A2 using ranking criteria and an estimated amount of UDs, of each identified geographical area, experiencing the labelled network coverage problem type, and/or an estimated amount of resources, of each identified geographical area, required to resolve a network coverage problem of the corresponding labelled network coverage problem type.
  • the amount of UDs is estimated by aggregating selected segments having the same serving cell and corresponding wireless access node.
  • the amount of resources is estimated using historical records of required resources needed to resolve a network coverage problem of the corresponding labelled network coverage problem type.
  • a computer program is provided and comprising computer-executable instructions for causing a node 101 when the computer-executable instructions are executed on processing circuitry comprised in the node 101 to perform any of the method steps according described herein.
  • a computer program product comprising a computer-readable storage medium, the computer-readable storage medium having the computer program described above embodied therein.
  • a carrier is provided and containing the computer program described above, wherein the carrier is one of an electronic signal, optical signal, radio signal, or computer readable storage medium.
  • Fig. 5 illustrates a coverage problem of missing coverage between settlements in populated areas. Missing coverage is the most commonly occurring type of coverage problem in a wireless network. The operators are often fully aware of such areas, and such coverage problems can mostly only be resolved by providing extra access node installations. Such coverage problems are characterized by phenomena such as: Variable number of UDs in historically reoccurring or not reoccurring individuals suffer radio-link time-out, which is preceded with a weakening signal level from a single base station. There is a relatively long time period to the next reconnection (tracking or location update) by the UD, moreover, the reconnections can spread over base stations and areas. This situation can be distinguished from simple turning off/on equipment, since the weakening signal and reconnection location can follow recognizable patterns.
  • Fig. 6 illustrates a coverage problem of coverage gaps between settlements in populated areas. This is also a commonly occurring type of coverage problem, typically along roads and train tracks, where a significant number of subscribers may suffer coverage outage. The network operators may be aware of such areas, but they do not necessarily know if the problem can be solved without the installation of extra equipment. After classification of such problems, it can be decided if retuning some network parameters and procedures would give some relief to some of the subscribers.
  • Such coverage problems are characterized by phenomena such as a variable number of UDs in historically reoccurring or not reoccurring individuals suffer radio link time out, which is preceded with weakening signal level from a single base station. The difference is that here the coverage interruption time compared to the scenario in Fig.
  • the outage problem may be two-way in the context of a base station pair, so that a symmetric process happens to UDs moving in the opposite directions. Since this type of coverage problem affects many UDs in a well recognizable pattern, the operator may apply special RRC configuration to UDs approaching such a coverage hole.
  • One strategy might be to set the time out periods longer on the UD side and to keep the UD context longer on the core network side and/or preparing the UD for fast recovery on the other end of the coverage hole. This might be an instruction to the UD how to perform network search while in the coverage hole.
  • Fig. 7 illustrates a coverage problem of poor indoor coverage. This is also a commonly occurring type of coverage problem. The operators are fully aware of such areas, and only extra installations, if it is worth the cost for the operator, can solve the problem.
  • Such coverage problems are characterized by phenomena such as variable number of UEs with historically reoccurring or not reoccurring individuals suffer radio link time out, which is typically preceded with sudden signal level drops from a single or multiple base station.
  • the interruption time is of variable length and the spot of reconnection can be also variable, but still within a defined set of surrounding base stations.
  • the affected subscribers might be characterized as slow- moving before the radio link failure or connection recovery event. The operator should therefore consider installing indoor coverage.
  • Fig. 8 illustrates a coverage problem of sudden coverage change at tunnel entrances.
  • Tunnels are usually covered by indoor cells or repeaters.
  • the problem affects exclusively quickly moving mobile subscribers.
  • the affected number of subscribers are relatively large, since subscribers are traveling on a highway or on a train.
  • Fig. 9 illustrates a coverage problem of shadowing object. It is a coverage problem that is hard to characterize the situation because it can affect subscribers sporadically. It is difficult to recognize any pattern in signal loss or reconnection. Such a coverage problem can happen suddenly or gradually. The characterizing behavior is a weak signal strength in a spot within the coverage area of the cell.
  • Fig. 10 illustrates a coverage problem of poor coverage in private zones.
  • Phenomena It is a shadow fading coverage problem, which might be similar to the coverage problems described in relation to Fig. 7 and Fig. 9, but it can be tied to a characterizable set of subscribers. Several UDs suffer radio link loss in the same cell and the recover also happens in the same cell.
  • Fig. 11 illustrates a selected segment according to one or more embodiments of the present disclosure.
  • the figure illustrates a possible trajectory of a UD, e.g. of field strength variations, as a vehicle comprising the UD passes through different cells.
  • the UD is moving away from a cell with gradually decreasing field strength.
  • a stronger second cell becomes visible, then the UE performs a handover successfully.
  • the strength of the new cell also drops rapidly and the handover back the previous cell fails due to vanishing signal from both cells.
  • Link recovery happens minutes later in a third cell. Assume that there is a road along with several similar UE troubles occur.
  • the trigger why this UD trajectory gets attention is that a radio link failure occurs.
  • Other events e.g. RRC event A2 (serving cell signal becomes worse than threshold), may also bring attention to UE traces.
  • Interruption interval greater than minute If several traces with these features and involved cells occur
  • Affected UD population diverse (mostly different ones)
  • the following specific features are extracted from the selected segments or UD trouble segments in order to serve as event data or input to the coverage problem clustering and classification module. These can be a mix of numerical and categorical features.
  • the derived input or event data contains the following key data:
  • time of day and day of week attributes of the occurrences can also be applied if those are typical to the coverage problem.
  • Fig. 12 shows a flowchart of a method according to one or more embodiments of the present disclosure.
  • the method performed by the analytics node 101 works as follows. Selected segments of event data or coverage problem data is collected for a given time period, e.g. one week. The selected segments of event data are then sorted by U D/subscriber and then by serving cell or serving cell pairs, counting the number of subscribers in the given serving cell or cell relation. This serves as the input to the coverage analysis node framework.
  • the method of the analytics node works as follows: A preliminary data set of selected segments or UD coverage trouble segments is initially collected to find representative cases of the main types of coverage problem types, e.g., to find those coverage problem types that are shown as examples in Figures 5-10.
  • the selected segments or coverage trouble segments are assessed by telecommunication experts to assign/label data with a root cause and an estimated cost to the representative cases. This process leads to a labeled dataset, which is used to train a supervised learning system or machine learning system.
  • An Al model or trained model is then built to learn how to assign the coverage problem classes so that the model is able to classify the type of new, yet unidentified coverage trouble segments to a known coverage problem class or type.
  • the inferred classification model is applied to categorize the new yet unidentified UE coverage trouble segments to the known classes, statistics are computed for each class based on the number and type of users involved, and based on the estimated cost of the network improvement and repair, a ranking is performed among the identified coverage problem classes in order to provide the most return on network investment.
  • the training of the Al model can be repeated periodically with experts’ supervision, e.g. every half year, to enable finding new coverage problem types.
  • UE coverage trouble segments are collected for a sufficiently large time period so that all presumed coverage problem types occur may times.
  • the initial grouping of UE coverage trouble segments is performed by unsupervised learning techniques.
  • the feature set described above is extracted for each selected segment or UD trouble segment, then the selected segments are clustered based on their feature set into groups.
  • the number of groups is roughly proportional to the number of trouble spots in the network area.
  • a group typically contains UD trouble segments which have similar signal strength dynamics, similar mobility events, similar link recovery patterns and associated with the same serving cell.
  • the selected segments or distinguished UD trouble segment groups are then assessed by telecommunication experts to validate them and to label them by assigning a name and coverage problem type/class to them (e.g., tunnel, basement, etc.).
  • the groups found by unsupervised learning does not necessarily fit the known types of coverage problems, so the experts are free to define new problem classes in this processing step.
  • the experts also associate a cost to the coverage problem classes, which cost reflects the investment necessary to cure the type of coverage problem. For example, it can be that changing an RRC parameter or procedure, or modifying antenna settings might be sufficient, while in other situations, installing additional HW resources at sites might provide the remedy.
  • Typical cases are shown in Figures 5-10, for illustration, though the coverage trouble types are not limited to only those cases.
  • the main goal of continuously operating the coverage problem analytics node is to categorize and sort all the occurring coverage troubles and rank them based on severity, previously described above.
  • the selected segments or UE trouble segments labelled by telecommunication experts are used as training data to a classification model.
  • the resulting trained model can then provide type-classification for all new occurrences of UE coverage problems.
  • the involved cells and secondary features, such as the number and mix of users involved the problem will comprise the descriptor of each area A1-A2 or coverage trouble spot in a network.
  • Fig. 13 shows details of a node/computer device/ computer system 101 according to one or more embodiments of the present disclosure.
  • the computer device 101 may be in the form of a selection of any of network node, a desktop computer, server, laptop, mobile device, a smartphone, a tablet computer, a smart-watch etc.
  • the computer device 101 may comprise processing circuitry 1312.
  • the computer device 101 may optionally comprise a communications interface 1304 for wired and/or wireless communication. Further, the computer device 101 may further comprise at least one optional antenna (not shown in figure).
  • the antenna may be coupled to a transceiver of the communications interface 1304 and is configured to transmit and/or emit and/or receive a wireless signals, e.g. in a wireless communication system.
  • the processing circuitry 1312 may be any of a selection of processor and/or a central processing unit and/or processor modules and/or multiple processors configured to cooperate with each-other.
  • the computer device 101 may further comprise a memory 1315.
  • the memory 1315 may contain instructions executable by the processing circuitry 1312, that when executed causes the processing circuitry 1312 to perform any of the methods and/or method steps described herein.
  • the communications interface 130 e.g. the wireless transceiver and/or a wired/wireless communications network adapter, which is configured to send and/or receive data values or parameters as a signal to or from the processing circuitry 1312 to or from other external nodes
  • the communications interface 1304 communicates directly between nodes or via a communications network.
  • the computer device 101 may further comprise an input device 1317, configured to receive input or indications from a user and send a user-input signal indicative of the user input or indications to the processing circuitry 1312.
  • the computer device 101 may further comprise a display 1318 configured to receive a display signal indicative of rendered objects, such as text or graphical user input objects, from the processing circuitry 1312 and to display the received signal as objects, such as text or graphical user input objects.
  • a display signal indicative of rendered objects such as text or graphical user input objects
  • the display 1318 is integrated with the user input device 1317 and is configured to receive a display signal indicative of rendered objects, such as text or graphical user input objects, from the processing circuitry 1312 and to display the received signal as objects, such as text or graphical user input objects, and/or configured to receive input or indications from a user and send a user-input signal indicative of the user input or indications to the processing circuitry 1312.
  • a display signal indicative of rendered objects such as text or graphical user input objects
  • the computer device 101 may further comprise one or more sensors (not shown).
  • the processing circuitry 1312 is communicatively coupled to the memory 1315 and/or the communications interface 1304 and/or the input device 1317 and/or the display 1318 and/or the one or more sensors.
  • the communications interface and/or transceiver 1304 communicates using wired and/or wireless communication techniques.
  • the one or more memory 1315 may comprise a selection of a hard RAM, disk drive, a floppy disk drive, a magnetic tape drive, an optical disk drive, a CD or DVD drive (R or RW), or other removable or fixed media drive.
  • the computer device 101 may further comprise and/or be coupled to one or more additional sensors (not shown) configured to receive and/or obtain and/or measure physical properties pertaining to the computer device or the environment of the computer device, and send one or more sensor signals indicative of the physical properties to the processing circuitry 1312.
  • additional sensors not shown
  • a computer device comprises any suitable combination of hardware and/or software needed to perform the tasks, features, functions and methods disclosed herein.
  • the components of the computer device are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, a computer device may comprise multiple different physical components that make up a single illustrated component (e.g., memory 1315 may comprise multiple separate hard drives as well as multiple RAM modules).
  • the computer device 101 may be composed of multiple physically separate components, which may each have their own respective components.
  • the communications interface 1304 may also include multiple sets of various illustrated components for different wireless technologies, such as, for example, GSM, WCDMA, LTE, NR, WiFi, or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within the computer device 101.
  • Processing circuitry 1312 is configured to perform any determining, calculating, or similar operations (e.g., certain obtaining operations) described herein as being provided by a computer device 101. These operations performed by processing circuitry 1312 may include processing information obtained by processing circuitry 1312 by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and/or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination.
  • processing information obtained by processing circuitry 1312 by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and/or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination.
  • Processing circuitry 1312 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and/or encoded logic operable to provide, either alone or in conjunction with other computer device 101 components, such as device readable medium, computer 101 functionality.
  • processing circuitry 1312 may execute instructions stored in device readable medium 1315 or in memory within processing circuitry 1312. Such functionality may include providing any of the various features, functions, or benefits discussed herein.
  • processing circuitry 1312 may include a system on a chip.
  • processing circuitry 1312 may include one or more of radio frequency, RF, transceiver circuitry and baseband processing circuitry.
  • RF transceiver circuitry and baseband processing circuitry may be on separate chips or sets of chips, boards, or units, such as radio units and digital units.
  • part or all of RF transceiver circuitry and baseband processing circuitry may be on the same chip or set of chips, boards, or units
  • processing circuitry 1312 executing instructions stored on device readable medium 1315 or memory within processing circuitry 1312.
  • some or all of the functionality may be provided by processing circuitry 1312 without executing instructions stored on a separate or discrete device readable medium, such as in a hard-wired manner.
  • processing circuitry 1312 can be configured to perform the described functionality. The benefits provided by such functionality are not limited to processing circuitry 1312 alone or to other components of computer device 101 , but are enjoyed by computer device 101 as a whole, and/or by end users.
  • Device readable medium or memory 1315 may comprise any form of volatile or non-volatile computer readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) ora Digital Video Disk (DVD)), and/or any other volatile or non-volatile, non-transitory device readable and/or computer- executable memory devices that store information, data, and/or instructions that may be used by processing circuitry 1312.
  • volatile or non-volatile computer readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) ora Digital Video Disk (DVD)), and/or any other volatile or non-
  • Device readable medium 1315 may store any suitable instructions, data or information, including a computer program, software, an application including one or more of logic, rules, code, tables, etc. and/or other instructions capable of being executed by processing circuitry 1312 and, utilized by computer device 101.
  • Device readable medium 1315 may be used to store any calculations made by processing circuitry 1312 and/or any data received via interface 1304.
  • processing circuitry 1312 and device readable medium 1315 may be considered to be integrated.
  • the communications interface 1304 is used in the wired or wireless communication of signaling and/or data between computer device 101 and other nodes.
  • Interface 1304 may comprise port(s)/terminal(s) to send and receive data, for example to and from computer device 101 over a wired connection.
  • Interface 1304 also includes radio front end circuitry that may be coupled to, or in certain embodiments a part of, an antenna. Radio front end circuitry may comprise filters and amplifiers. Radio front end circuitry may be connected to the antenna and/or processing circuitry 1312.
  • Examples of a computer device 101 include, but are not limited to an edge cloud node, a smart phone, a mobile phone, a cell phone, a voice over I P (Vol P) phone, a wireless local loop phone, a tablet computer, a desktop computer, a personal digital assistant (PDA), a wireless cameras, a gaming console or device, a music storage device, a playback appliance, 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, etc.
  • an edge cloud node a smart phone, a mobile phone, a cell phone, a voice over I P (Vol P) phone, a wireless local loop phone, a tablet computer, a desktop computer, a personal digital assistant (PDA), a wireless cameras, a gaming console or device, a music storage device, a play
  • the communication interface may 1304 encompass wired and/or wireless networks such as a local-area network (LAN), a wide-area network (WAN), a computer network, a wireless network, a telecommunications network, another like network or any combination thereof.
  • the communication interface may be configured to include a receiver and a transmitter interface used to communicate with one or more other devices over a communication network according to one or more communication protocols, such as Ethernet, TCP/IP, SONET, ATM, optical, electrical, and the like).
  • the transmitter and receiver interface may share circuit components, software or firmware, or alternatively may be implemented separately.
  • a computer device 101 is provided and is configured to perform any of the method steps described herein.
  • each of the wireless access nodes 111-113, the one or more core network nodes 121, O&M node 141 and a plurality of user devices 131-133 comprises all or a selection of the features of the computer device 101 described in relation to Fig. 13.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

La présente divulgation concerne un procédé effectué par un nœud analytique (101) configuré pour identifier des zones géographiques (A1-A2) subissant des types de problèmes de couverture de réseau dans un réseau de communication sans fil (151), le réseau de communication comprenant une pluralité de nœuds d'accès sans fil (111-113), un ou plusieurs nœuds de réseau central (121) et une pluralité de dispositifs utilisateur (UD) (131-133), chacun des nœuds d'accès sans fil commandant une ou plusieurs cellules, les cellules transmettant au moins des signaux aux UD, le procédé consistant à obtenir, par le nœud analytique, des données d'événement indiquant des événements de couverture de réseau dans le réseau de communication, à générer des trajectoires pour chacun de la pluralité de UD par sélection des données d'événement associées à chaque UD correspondant, à identifier des zones géographiques dans lesquelles un ou plusieurs UD subissent divers types de problèmes de couverture de réseau par sélection de segments des trajectoires UD à l'aide de conditions prédéterminées de caractéristiques de signal émise et à classifier des segments sélectionnés à l'aide d'un modèle formé, chaque segment sélectionné étant marqué par le modèle entraîné avec un type de problème de couverture de réseau.
PCT/EP2020/052443 2020-01-31 2020-01-31 Nœud analytique et procédé associé WO2021151503A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/EP2020/052443 WO2021151503A1 (fr) 2020-01-31 2020-01-31 Nœud analytique et procédé associé

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/EP2020/052443 WO2021151503A1 (fr) 2020-01-31 2020-01-31 Nœud analytique et procédé associé

Publications (1)

Publication Number Publication Date
WO2021151503A1 true WO2021151503A1 (fr) 2021-08-05

Family

ID=69467527

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2020/052443 WO2021151503A1 (fr) 2020-01-31 2020-01-31 Nœud analytique et procédé associé

Country Status (1)

Country Link
WO (1) WO2021151503A1 (fr)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113795032A (zh) * 2021-09-26 2021-12-14 中国联合网络通信集团有限公司 室分隐形故障的判断方法、装置、存储介质及设备
CN114698005A (zh) * 2022-03-30 2022-07-01 中国联合网络通信集团有限公司 异常小区的识别方法、装置、设备及可读介质
CN114707363A (zh) * 2022-05-31 2022-07-05 国网浙江省电力有限公司 用于配网工程管理的问题数据处理方法及系统
WO2023236548A1 (fr) * 2022-06-06 2023-12-14 中兴通讯股份有限公司 Procédé et appareil d'ajustement de paramètre de configuration de réseau et système de gestion de réseau

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130143592A1 (en) * 2011-12-06 2013-06-06 At&T Mobility Ii Llc Closed loop heterogeneous network for automatic cell planning
US20140036656A1 (en) * 2012-08-03 2014-02-06 Joey Chou Coverage adjustment in e-utra networks
US20160162783A1 (en) * 2014-12-09 2016-06-09 Futurewei Technologies, Inc. Autonomous, Closed-Loop and Adaptive Simulated Annealing Based Machine Learning Approach for Intelligent Analytics-Assisted Self-Organizing-Networks (SONs)
US20170111803A1 (en) * 2014-03-28 2017-04-20 Telefonaktiebolaget Lm Ericsson (Publ) Method and device for controlling an autonomous device

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130143592A1 (en) * 2011-12-06 2013-06-06 At&T Mobility Ii Llc Closed loop heterogeneous network for automatic cell planning
US20140036656A1 (en) * 2012-08-03 2014-02-06 Joey Chou Coverage adjustment in e-utra networks
US20170111803A1 (en) * 2014-03-28 2017-04-20 Telefonaktiebolaget Lm Ericsson (Publ) Method and device for controlling an autonomous device
US20160162783A1 (en) * 2014-12-09 2016-06-09 Futurewei Technologies, Inc. Autonomous, Closed-Loop and Adaptive Simulated Annealing Based Machine Learning Approach for Intelligent Analytics-Assisted Self-Organizing-Networks (SONs)

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
"3rd Generation Partnership Project; Technical Specification Group Services and System Aspects; Management and orchestration; Study on enhancement of Management Data Analytics (MDA) (Release 17)", 4 November 2019 (2019-11-04), XP051815471, Retrieved from the Internet <URL:https://ftp.3gpp.org/tsg_sa/WG5_TM/TSGS5_127/Docs/S5-196875.zip 28.809-010.docx> [retrieved on 20191104] *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113795032A (zh) * 2021-09-26 2021-12-14 中国联合网络通信集团有限公司 室分隐形故障的判断方法、装置、存储介质及设备
CN113795032B (zh) * 2021-09-26 2023-12-08 中国联合网络通信集团有限公司 室分隐形故障的判断方法、装置、存储介质及设备
CN114698005A (zh) * 2022-03-30 2022-07-01 中国联合网络通信集团有限公司 异常小区的识别方法、装置、设备及可读介质
CN114707363A (zh) * 2022-05-31 2022-07-05 国网浙江省电力有限公司 用于配网工程管理的问题数据处理方法及系统
WO2023236548A1 (fr) * 2022-06-06 2023-12-14 中兴通讯股份有限公司 Procédé et appareil d'ajustement de paramètre de configuration de réseau et système de gestion de réseau

Similar Documents

Publication Publication Date Title
US11641589B2 (en) Contextualized network optimization
WO2021151503A1 (fr) Nœud analytique et procédé associé
US20220190883A1 (en) Beam prediction for wireless networks
US9961571B2 (en) System and method for a multi view learning approach to anomaly detection and root cause analysis
US10600001B2 (en) Determining a target device profile including an expected behavior for a target device
US10361913B2 (en) Determining whether to include or exclude device data for determining a network communication configuration for a target device
EP3818743B1 (fr) Procédé dans un réseau de radiocommunication utilisant la groupement de mesures géospatialement localisées
US20230362758A1 (en) Methods and apparatuses for handover procedures
US10945299B2 (en) Overshoot analysis based on user equipment metrics
Turkka et al. An approach for network outage detection from drive-testing databases
EP2934037B1 (fr) Technique pour l&#39;évaluation d&#39;un paramètre d&#39;ajustement dans un réseau de communication mobile
US11606725B2 (en) Wireless band priority metrics analysis and response
US20230269606A1 (en) Measurement configuration for local area machine learning radio resource management
CN107438264B (zh) 小区性能分析方法及装置
Yu et al. Self‐Organized Cell Outage Detection Architecture and Approach for 5G H‐CRAN
US10582399B1 (en) Roaming analysis based on user equipment metrics
US20230292156A1 (en) Trajectory based performance monitoring in a wireless communication network
US11240679B2 (en) Multidimensional analysis and network response
WO2020088734A1 (fr) Procédé et système de recommandation pour fournir une recommandation de mise à niveau
CN114650598A (zh) 配置通信小区协同关系的方法、网络设备及存储介质
Chernov et al. The influence of dataset size on the performance of cell outage detection approach in LTE-A networks
Rydén et al. Downloadable machine learning for compressed radiolocation applications in radio access networks
US11606772B2 (en) Systems and methods for unmanned aerial vehicle detection
EP3700253B1 (fr) Prédiction de la distribution géographique de la qualité d&#39;un réseau de communication mobile
US20240015554A1 (en) Minimization of drive test report validation

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20703421

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20703421

Country of ref document: EP

Kind code of ref document: A1