WO2024110055A1

WO2024110055A1 - Classification of network disturbance events in a network

Info

Publication number: WO2024110055A1
Application number: PCT/EP2022/083327
Authority: WO
Inventors: Martin Sjödin; Paolo Debenedetti; Marcello MORCHIO; Anders Kvist; Paolo TORRENTE; Annamaria FULIGNOLI
Original assignee: Telefonaktiebolaget Lm Ericsson (Publ)
Priority date: 2022-11-25
Filing date: 2022-11-25
Publication date: 2024-05-30

Abstract

There is provided techniques for classification of probable cause of a network disturbance event in a network comprises point-to-point wireless links sharing groups of end-points. A method is performed by a controller entity. The method comprises obtaining, per each wireless link in a set of the wireless links, timestamped link disturbance events and position indicating information for each of the end-points of the wireless link. The timestamped link disturbance events and the position indicating information per each wireless link define a pattern of link disturbance events. The method comprises classifying the probable cause of the network disturbance event by correlating the patterns of link disturbance events of all the wireless links in the set of the point-to-point wireless links.

Description

CLASSIFICATION OF NETWORK DISTURBANCE EVENTS IN A NETWORK

TECHNICAL FIELD

Embodiments presented herein relate to a method, a controller entity, a computer program, and a computer program product for classification of the probable cause of a network disturbance event in a network.

BACKGROUND

In a wireless communication system, digital information is sent over point-to-point wireless links between two nodes. These two nodes can typically be spaced from a few hundred meters up to several kilometers. Each node comprises link equipment, such as an antenna, a radio for frequency up- and down-conversion, and a modem for digital signal processing, used for transmission and reception of wireless signals over the point-to-point wireless links.

Point-to-point wireless links are sometimes subjected to disturbances. Wireless link performances may be impacted by several factors, such as weather conditions as well as the alignment between the two endpoints of a wireless link, or an obstacle being placed (either temporarily or permanently) between the endpoints of the wireless link. As one non-limiting example, when the antennas in the endpoints get misaligned, the received signal power is reduced. As another non-limiting example, in case of rotation of the antennas, the polarization might also be affected. Such disturbances affect the received signal power and quality. This might trigger alarms that are sent to the network operator. When a network operator suspects that the link equipment is not working properly, a common response is to make a site visit (i.e., to send maintenance personnel to inspect the link equipment). Such a site visit sometimes results in the link equipment, or at least part thereof, being shipped back to the manufacturer for maintenance, or even replacement.

It has been found during inspections that a significant fraction of the link equipment sent back to the manufacturer in fact does not suffer from impaired operation and no faults are found. This indicates that resources, such as time and money, might be saved if network operators are provided with more accurate feedback about their network equipment.

Some disturbances may be due to site conditions (e.g., tower swaying) or external factors, such as local environmental issues (e.g., local obstacles) and not relevant to a specific end-point. In this respect, measurements made on the wireless link and its neighbors can be elaborated via artificial intelligence (Al) or machine learning (ML) processing in order to classify in advance the probable cause for any faulty or degraded link, such as weather conditions and/or antenna swaying impacting the link performance.

However, existing technology cannot easily locate the geographical location of the probable cause. SUMMARY

An object of embodiments herein is to address the above issues and shortcomings of existing technology.

According to a first aspect there is presented a controller entity for classification of probable cause of a network disturbance event in a network comprises point-to-point wireless links sharing groups of endpoints. The controller entity comprises processing circuitry. The processing circuitry is configured to cause the controller entity to obtain, per each wireless link in a set of the wireless links, timestamped link disturbance events and position indicating information for each of the end-points of the wireless link. The timestamped link disturbance events and the position indicating information per each wireless link define a pattern of link disturbance events. The processing circuitry is configured to cause the controller entity to classify the probable cause of the network disturbance event by correlating the patterns of link disturbance events of all the wireless links in the set of the point-to-point wireless links.

According to a second aspect there is presented a controller entity for classification of probable cause of a network disturbance event in a network comprises point-to-point wireless links sharing groups of endpoints. The controller entity comprises an obtain module configured to obtain, per each wireless link in a set of the wireless links, timestamped link disturbance events and position indicating information for each of the end-points of the wireless link. The timestamped link disturbance events and the position indicating information per each wireless link define a pattern of link disturbance events. The controller entity comprises a classify module configured to classify the probable cause of the network disturbance event by correlating the patterns of link disturbance events of all the wireless links in the set of the point-to-point wireless links.

According to a third aspect there is presented a method for classification of probable cause of a network disturbance event in a network comprises point-to-point wireless links sharing groups of end-points. The method is performed by a controller entity. The method comprises obtaining, per each wireless link in a set of the wireless links, timestamped link disturbance events and position indicating information for each of the end-points of the wireless link. The timestamped link disturbance events and the position indicating information per each wireless link define a pattern of link disturbance events. The method comprises classifying the probable cause of the network disturbance event by correlating the patterns of link disturbance events of all the wireless links in the set of the point-to-point wireless links.

According to a fourth aspect there is presented a computer program for classification of the probable cause of a network disturbance event in a network. The network comprises point-to-point wireless links sharing groups of end-points. The computer program comprises computer code which, when run on processing circuitry of a controller entity, causes the controller entity to perform actions. One action comprises the controller entity to obtain, per each wireless link in a set of the wireless links, timestamped link disturbance events and position indicating information for each of the end-points of the wireless link. The timestamped link disturbance events and the position indicating information per each wireless link define a patern of link disturbance events. One action comprises the controller entity to classify the probable cause of the network disturbance event by correlating the paterns of link disturbance events of all the wireless links in the set of the point-to-point wireless links.

According to a fifth aspect there is presented a computer program product comprising a computer program according to the fourth aspect and a computer readable storage medium on which the computer program is stored. The computer readable storage medium could be a non-transitory computer readable storage medium.

Advantageously, these aspects enable detection and discrimination of events affecting the network infrastructure.

Advantageously, these aspects enable classification of the probable cause of network disturbance events defined by paterns of link disturbance events, and hence to classify network disturbance events across multiple wireless links in the network.

Other objectives, features and advantages of the enclosed embodiments will be apparent from the following detailed disclosure, from the atached dependent claims as well as from the drawings.

Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to "a/an/the element, apparatus, component, means, module, step, etc." are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, module, step, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated.

BRIEF DESCRIPTION OF THE DRAWINGS

The inventive concept is now described, by way of example, with reference to the accompanying drawings, in which:

Fig. 1 is a schematic diagram illustrating a network according to embodiments;

Fig. 2 schematically illustrates performance-affecting events along a timeline according to an embodiment;

Fig. 3 schematically illustrates a system according to an embodiment;

Fig. 4 schematically illustrates operation of a network correlation engine according to an embodiment;

Fig. 5 is a flowchart of methods according to embodiments;

Figs. 6 and 7 schematically illustrate time-varying network graphs according to an embodiment; Fig. 8 is a schematic diagram showing functional units of a controller entity according to an embodiment;

Fig. 9 is a schematic diagram showing functional modules of a controller entity according to an embodiment; and

Fig. 10 shows one example of a computer program product comprising computer readable storage medium according to an embodiment.

DETAILED DESCRIPTION

The inventive concept will now be described more fully hereinafter with reference to the accompanying drawings, in which certain embodiments of the inventive concept are shown. This inventive concept may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided by way of example so that this disclosure will be thorough and complete, and will fully convey the scope of the inventive concept to those skilled in the art. Like numbers refer to like elements throughout the description. Any step or feature illustrated by dashed lines should be regarded as optional.

Fig. 1 is a schematic diagram illustrating a network 100 where embodiments presented herein can be applied. The network 100 comprises point-to-point wireless links 120 (eight in total) extending between endpoints 110 (seven in total). Each of the endpoints 110 can be a microwave transceiver. For illustrative purposes, the network 100 is illustrated as overlaying a map of a geographical area 130.

In Fig. 2 is shown an example timeline 200 extending for 24 hours, and where detected performanceaffecting events have been identified for three different wireless links (denoted A, B, and C). It is shown that a respective event has been detected to occur at times tO and tl for all three wireless links. Further, it has been detected that at time t2 a respective event is occurring for wireless links A and C but not for wireless link B. Further, it has been detected that at time t3 an event is occurring only for wireless link B.

As noted above, existing technology cannot easily locate the geographical location of the probable cause. Existing technology is applied per each individual wireless link at a time. The latter implies that existing technology cannot be used to determine whether multiple wireless links in the same area are impacted by the same geographical event or not, such as the tower swaying, building instability, or even geological events such as a landslide or an earthquake.

With reference again to Fig. 2, assuming that a set of the wireless links have one end-point in common, it could be that the cause for the events occurring at time tO and tl is located at the common end-point (depending on the type of event that has been detected for each of the wireless links) but that the cause for at least the event occurring at time t3 is not located at the common end-point. However, existing technology cannot be used to arrive at this conclusion. The embodiments disclosed herein therefore relate to techniques for classification of the probable cause of a network disturbance event in a network 100. In order to obtain such techniques, there is provided a controller entity 310, 800, 900, a method performed by the controller entity 310, 800, 900, a computer program product comprising code, for example in the form of a computer program, that when run on a controller entity 310, 800, 900, causes the controller entity 310, 800, 900 to perform the method. One example realization of the controller entity 610 is illustrated in Fig. 3.

In Fig. 3 is illustrated a system 300 comprising the end-points 110 of Fig. 1 (with wireless links 120 extending between the end-points 110), and where the end-points are configured to provide data to a controller entity 310 over (backhaul) links 330 about performance degradation on the wireless links 120. The controller entity 310 comprises a data collecting system 312, a local correlation engine 314, and a network correlation engine 316. The controller entity 310 has access to a network topology database 320 which holds position indicating information of the end-points 110.

The data collecting system 312 is configured to retrieve data provided by the end-points 110.

The local correlation engine 314 is configured to computer local inferences, in terms of vectors of timestamped link disturbance events, in the network 100. The input to the local correlation engine 314 is the data as retrieved by the data collecting system 312 from the end-points 110, The output vectors describe the probability of the possible link disturbance events within a given time window. In some examples the local correlation engine 314 determines which end-point of each wireless link is affected by a link disturbance event, for example antenna swaying, etc. The local correlation engine 314 might thereby identify link disturbance events limited to the scope of each individual wireless link. Further, the local correlation engine 314 can also report long-term link disturbance events that can be seamlessly combined by the network correlation engine 316 to classify network disturbance events, such as landslides or tower displacements.

The network correlation engine 316 is configured to computer network-level inferences in the network 100. The inputs to the network correlation engine 316 are the vectors of timestamped link disturbance events generated by the local correlation engine 314 and the position indicating information of the endpoints 110. In some examples the network correlation engine 316 takes advantage of the link classification built by the local correlation engine 314, combined with additional information on the network topology and the end-point locations. The output from the network correlation engine 316 is a classification, which can classify the status of the network 100, or a subnetwork, on a time granularity based on the history of the network 100 within a given time interval. In particular, the network correlation engine 316 is configured to classify the probable cause of the network disturbance event. The output of the network correlation engine 316 can be provided as a graph or a table of the decision classes.

In Fig. 4 is illustrated detailed operation of the network correlation engine 316. The network correlation engine 316 takes as input n vectors 410a, 410b, ..., 41 On of timestamped link disturbance events generated by the local correlation engine 314 and the position indicating information of the end-points 110. In the example of Fig. 2, n = 3, with one vector for time tO, one vector for time tl and one vector for time t2. Each vector is provided as input to a classifier 420, which outputs the probable cause of the network disturbance event.

According to at least some of the herein disclosed embodiments, measurement data is, together with their relevant timestamp and position indicating information, correlated across different wireless links.

According to at least some of the herein disclosed embodiments the position indicating information can be provided with variable resolution, thereby enabling correlation of events at different geographical resolutions levels. This can be useful for example to distinguishing antenna swaying of end-points placed at the same building from antenna swaying of end-points not placed at the same building.

According to at least some of the herein disclosed embodiments, measurements can be mapped to a graph where end-points, or antennas, sharing the same geographical coordinates can be aggregated within site locations, with their wireless links being mapped as links connecting sites.

According to at least some of the herein disclosed embodiments, the graph can be analyzed in the spatial and time domains via Al and/or ML techniques to detect link performance patterns affecting multiple wireless links at the same time.

According to at least some of the herein disclosed embodiments, if multiple nodes in the graph that correspond to the same geographical area are affected by a similar disturbance, it is possible to determine that these nodes are either impacted by the same geological event or by the same weather conditions (with the possibility to distinguish between different types of events).

According to at least some of the herein disclosed embodiments, if a permanent or long-term degradation is detected, the degradation might be classified as a landslide event. For this purpose, at least some of the herein disclosed embodiments are based on processing of long-term data.

According to at least some of the herein disclosed embodiments If short-term oscillations (e.g., few seconds or minutes) degradation is detected, and the affected end-points are geographically distributed around an epicenter or according to waves, the degradation might be classified as tremors or earthquake events.

Fig. 5 is a flowchart illustrating embodiments of methods for classification of the probable cause of a network disturbance event in a network 100. The network 100 comprises point-to-point wireless links 120 sharing groups of end-points 110. The methods are performed by the controller entity 310, 800, 900. The methods are advantageously provided as computer programs 320. S102: The controller entity 310, 800, 900 obtains, per each wireless link 120 in a set of the wireless links, timestamped link disturbance events and position indicating information for each of the end-points 110 of the wireless link 120. The timestamped link disturbance events and the position indicating information per each wireless link 120 define a pattern of link disturbance events.

S 104: The controller entity 310, 800, 900 classifies the probable cause of the network disturbance event by correlating the patterns of link disturbance events of all the wireless links 120 in the set of the point-to- point wireless links 120.

Advantageously, this method enables detection and discrimination of events affecting the network infrastructure.

Advantageously, this method enables classification of the probable cause of network disturbance events defined by patterns of link disturbance events, and hence to classify network disturbance events across multiple wireless links in the network.

Embodiments relating to further details of classification of the probable cause of a network disturbance event in a network 100 as performed by the controller entity 310, 800, 900 will now be disclosed with continued reference to Fig. 5.

In some aspects, also the probable cause of the network disturbance event is localized. Therefore, in some embodiments, the controller entity 310, 800, 900 is configured to perform (optional) step S106:

S 106: The controller entity 310, 800, 900 localizes the probable cause of the network disturbance event. The probable cause of the network disturbance event is localized by the controller entity 310, 800, 900 correlating the patterns of link disturbance events of all the wireless links 120 in the set of the point-to- point wireless links 120.

In yet further aspects, step SI 06 represents a mandatory action whereas step SI 04 represents an optional action. Therefore, in some embodiments, a method for localizing the probable cause of a network disturbance event in a network 100 comprising point-to-point wireless links 120 sharing groups of endpoints 110 comprises above disclosed steps SI 02 and SI 06, where step SI 04 is an optional step.

In some aspects, some action is taken in response to having classified the probable cause of the network disturbance event (and possibly also in response to having localized the root cause of the network disturbance event). Therefore, in some embodiments, the controller entity 310, 800, 900 is configured to perform (optional) step SI 08:

S 108: The controller entity 310, 800, 900 performs an action in response to having classified the probable cause of the network disturbance event. The action is performed to counteract the probable cause of the network disturbance events. There may be different types of wireless links 120. In some examples, the wireless links 120 are wireless microwave links 120, and the link disturbance events comprise variations of received power and/or attenuation on either side of the wireless microwave links 120. In other examples, the wireless links 120 are free space optical links 120, and wherein the link disturbance events comprise variations of received power on either side of the free space optical links 120. In yet other examples, the wireless links 120 are Terahertz (THz) links.

There may be different types of position indicating information. In some non-limiting examples, the position indicating information is any, or any combination, of: the geographical coordinates of each endpoint 110, the relative positions of the end-points 110, the distances between the end-points 110. The position indicating information for any given wireless link 120 might further pertain to the spatial orientation of the end-points 110 of this given wireless link 120. The geographical coordinates might be provided in terms of global navigation satellite system coordinates or regional navigation satellite system coordinates. The global navigation satellite system might be any of the Global Positioning System, Global'naya Navigatsionnaya Sputnikovaya Sistema, BeiDou Navigation Satellite System, Galileo satellite navigation system, etc.

There may be different timestamped link disturbance events. In some embodiments, the timestamped link disturbance events for any given wireless link 120 are identified based on timestamped power measurements at the end-points 110 of the given wireless link 120. The timestamped link disturbance events might be identified by aggregating wireless link measurements of transmit and receive power at radio frequency level, polarization noise, etc. according to a predefined sampling rate. Timestamped measurements might therefore be collected at each of the end-points 110. The timestamped measurements for each wireless link 120 might then be processed. For example, timeseries of the transmit and receive power levels, mean square error, polarization noise, etc. might be created. Further, the timestamped measurements might be used to, for each wireless link 120, create timestamped link disturbance events. The timestamped measurements and/or the timestamped link disturbance events might be retrieved from the end-points 110 by a data collection system for the controller entity 310, 800, 900 to be able to process the timestamped measurements and/or the timestamped link disturbance events.

In some aspects, the timestamped measurements are, via the position indicating information, mapped into a time-variant network graph representing the end-points 110 and the wireless links 120 connecting the end-points 110. In particular, in some embodiments, the timestamped link disturbance events are, via the position indicating information, mapped to a time-variant network graph. The time-variant network graph comprises vertices that represent the end-points 110 and edges that represent the wireless links 120. The graphs are time-variant with respect to the fact that the measurements and the link disturbance events are timestamped and thus might change over time. Particularly, in some embodiments, the edge representing any given wireless link 120 is associated with the timestamped link disturbance events of the given wireless link 120. Two illustrative examples of time-variant network graphs 600, 700 are illustrated in Fig. 6 and Fig. 7. Each time-variant network graph 600, 700 is composed of vertices 610a:610g, each representing one end-point 110, and where each of the edges 620a: 620g that extend between the vertices 610a:610g represents one wireless link 120. Edges representing wireless links associated with link disturbance events are illustrated with dotted lines.

In some examples, the time-variant network graphs 600, 700 are represented, arranged, or mapped to, a multidimensional tabular structure. In some examples, the rows and columns of such a tabular structure are the end-points of the network and the different layers (with one layer per each dimension) of the tabular structure carry the various types of information. The actual features matrix can include all probability classes of the link disturbance events, plus their position indicating information and/or other topologically extracted features, such as the orientation and the length of the wireless links. Such a tabular structure can be used as input for classification using a convolutional neural network, which include the time domain. One non-limiting example implementation is realized using a 3D Convolutional Neural Network, denoted 3DCNN, using two spatial dimensions and one time dimension.

In some aspects, the time-variant network graph 600, 700 is based on the variable measurements from the end-points 110 and it is first analyzed using Al and/or ML techniques to recognize degradation signal patterns. In particular, in some embodiments, the link disturbance events are classified by using an Al and/or ML method to analyse the time-variant network graph 600, 700. Further, in some embodiments, the network disturbance event is classified by using an Al and/or ML method to correlate the patterns of link disturbance events in accordance with the time-variant network graph 600, 700. The AI/ML method might use as input data the link measurements and/or the derived local classes, mapped in the timedomain and in the network graph, as attributes of the relevant wireless links.

There can be different types of classification algorithms, and thus different types of Al and/or ML methods. In some non-limiting examples, a neural network trained to detect image patterns, or a graph neural network, is used. Using such methods, it is possible to determine whether two or more wireless links 120 connected to the same end-point 110 have some common anomalies, or link disturbance events. Different classification methods can be used, such as both supervised and unsupervised learning with a preference on heuristic methods based on supervised deep learning methodology.

There can be different types of probable causes. In some non-limiting examples, the probable cause of the network disturbance event is classified to be any, or any combination, of: antenna misalignment, antenna swaying, antenna tower swaying, building swaying, landslide, tremor, earthquake, meteorological events, unclassified events. Hence, in some examples, it is possible to discriminate the following events. According to a first event, the network disturbance event is classified to be caused by landslides, as caused by movements at very low frequency creating permanent degrade on multiple towers or buildings. According to a second event, the network disturbance event is classified to be caused by meteorological events impacting dislocated antennas within a geographical area or with other commonalities (e.g., same orientation). According to a third event, the network disturbance event is classified to be caused by tremors or earthquakes causing short event oscillation of multiple antennas in a common geographical area, possibly with degrading patterns from the epicenter. The unlikely cases such as earthquakes, where all the antennas oscillate at almost the same time, can be detected as it is possible to determine the offset of the oscillations in the time domain for all the antennas involved and exclude local root causes. Further in this respect, if a mast is swaying due to wind, all the wireless links connected to the antennas of the mast will be swaying, suggesting with good probability a network event correlated with the mast. Further, if many antennas with the same orientation sway, they could be affected by the same wind direction (excluding the remote sides). Further, if multiple wireless links from the same tower are swaying at the same time, the problem is likely local either meteorological or structural. Other cases can be classified combining above cases and/or excluding them.

The scope of the classification might be reduced, as the full network can be too widespread to be associated to a specific target event. Therefore, in some aspects, not all timestamped link disturbance events are considered when classifying the probable cause of the network disturbance event. In particular, in some embodiments, the classification of the probable cause of the network disturbance event is a function of event classes of only the timestamped link disturbance events of the wireless links 120 as located within a predefined distance from a point of interest in the time-variant network graph 600, 700. The predefined distance might be defined in terms of either the spatial distance from the point of interest or the number of edges 620 from the point of interest in the time-variant network graph 600, 700. For this, connectivity information can be used to allow defining the scope of the classification to a set of neighboring end-points of a given end-point, using the topology information. Location information can be used to allow defining the scope of the classification to a certain geographical area, using the position indicating information.

The scope of the classification on a global perspective can be achieved by decomposing the network into network portions of the graph, with different number of hops, on the basis of the topological or geographical proximity using well-known methods for site/icon aggregation. The classification of the the network disturbance event can be applied to any network portion, at any time step, and therefore produce a set of network level classifications describing the global status. The only constraint in the size of the network portions is to be consistent with the portion sizes used in the training of the models used by the Al and/or ML methods. The process can be iterated, in parallel, for different number of hops in the graph with edge properties annotated according to the derived data listed above. This configuration is also suitable for Graph Neural Networks inference. In some examples, the process can be run recursively increasing the number of hops starting from the smallest identified network event class (hop = 1) up to the whole network graph.

Fig. 8 schematically illustrates, in terms of a number of functional units, the components of a controller entity 800 according to an embodiment. Processing circuitry 810 is provided using any combination of one or more of a suitable central processing unit (CPU), multiprocessor, microcontroller, digital signal processor (DSP), etc., capable of executing software instructions stored in a computer program product 1010 (as in Fig. 10), e.g. in the form of a storage medium 830. The processing circuitry 810 may further be provided as at least one application specific integrated circuit (ASIC), or field programmable gate array (FPGA).

Particularly, the processing circuitry 810 is configured to cause the controller entity 800 to perform a set of operations, or steps, as disclosed above. For example, the storage medium 830 may store the set of operations, and the processing circuitry 810 may be configured to retrieve the set of operations from the storage medium 830 to cause the controller entity 800 to perform the set of operations. The set of operations may be provided as a set of executable instructions.

Thus, the processing circuitry 810 is thereby arranged to execute methods as herein disclosed. The storage medium 830 may also comprise persistent storage, which, for example, can be any single one or combination of magnetic memory, optical memory, solid state memory or even remotely mounted memory. The controller entity 800 may further comprise a communications (comm.) interface 820 at least configured for communications with other entities, functions, nodes, and devices. As such the communications interface 820 may comprise one or more transmitters and receivers, comprising analogue and digital components. The processing circuitry 810 controls the general operation of the controller entity 800 e.g. by sending data and control signals to the communications interface 820 and the storage medium 830, by receiving data and reports from the communications interface 820, and by retrieving data and instructions from the storage medium 830. Other components, as well as the related functionality, of the controller entity 800 are omitted in order not to obscure the concepts presented herein.

Fig. 9 schematically illustrates, in terms of a number of functional modules, the components of a controller entity 900 according to an embodiment. The controller entity 900 of Fig. 9 comprises a number of functional modules; an obtain module 910 configured to perform step SI 02, and a classify module 920 configured to perform step S 104. The controller entity 900 of Fig. 9 may further comprise a number of optional functional modules, such as any of a localize module 930 configured to perform step S106, and an action module 940 configured to perform step S108. In general terms, each functional module 910:940 may in one embodiment be implemented only in hardware and in another embodiment with the help of software, i.e., the latter embodiment having computer program instructions stored on the storage medium 830 which when run on the processing circuitry makes the controller entity 800, 900 perform the corresponding steps mentioned above in conjunction with Fig 9. It should also be mentioned that even though the modules correspond to parts of a computer program, they do not need to be separate modules therein, but the way in which they are implemented in software is dependent on the programming language used. Preferably, one or more or all functional modules 910:940 may be implemented by the processing circuitry 810, possibly in cooperation with the communications interface 820 and/or the storage medium 830. The processing circuitry 810 may thus be configured to from the storage medium 830 fetch instructions as provided by a functional module 910:940 and to execute these instructions, thereby performing any steps as disclosed herein.

The controller entity 310, 800, 900 may be provided as a standalone device or as a part of at least one further device. Thus, a first portion of the instructions performed by the controller entity 310, 800, 900 may be executed in a first device, and a second portion of the of the instructions performed by the controller entity 310, 800, 900 may be executed in a second device; the herein disclosed embodiments are not limited to any particular number of devices on which the instructions performed by the controller entity 310, 800, 900 may be executed. Hence, the methods according to the herein disclosed embodiments are suitable to be performed by a controller entity 310, 800, 900 residing in a cloud computational environment. Therefore, although a single processing circuitry 810 is illustrated in Fig. 8 the processing circuitry 810 may be distributed among a plurality of devices, or nodes. The same applies to the functional modules 910:940 of Fig. 9 and the computer program 1020 of Fig. 10.

Fig. 10 shows one example of a computer program product 1010 comprising computer readable storage medium 1030. On this computer readable storage medium 1030, a computer program 1020 can be stored, which computer program 1020 can cause the processing circuitry 810 and thereto operatively coupled entities and devices, such as the communications interface 820 and the storage medium 830, to execute methods according to embodiments described herein. The computer program 1020 and/or computer program product 1010 may thus provide means for performing any steps as herein disclosed.

In the example of Fig. 10, the computer program product 1010 is illustrated as an optical disc, such as a CD (compact disc) or a DVD (digital versatile disc) or a Blu-Ray disc. The computer program product 1010 could also be embodied as a memory, such as a random -access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), or an electrically erasable programmable read-only memory (EEPROM) and more particularly as a non-volatile storage medium of a device in an external memory such as a USB (Universal Serial Bus) memory or a Flash memory, such as a compact Flash memory. Thus, while the computer program 1020 is here schematically shown as a track on the depicted optical disk, the computer program 1020 can be stored in any way which is suitable for the computer program product 1010.

The inventive concept has mainly been described above with reference to a few embodiments. However, as is readily appreciated by a person skilled in the art, other embodiments than the ones disclosed above are equally possible within the scope of the inventive concept, as defined by the appended patent claims.

Claims

1. A controller entity (310, 800, 900) for classification of probable cause of a network disturbance event in a network (100) comprising point-to-point wireless links (120) sharing groups of end-points (110), the controller entity (310, 800, 900) comprising processing circuitry (810), the processing circuitry being configured to cause the controller entity (310, 800, 900) to: obtain, per each wireless link (120) in a set of the wireless links, timestamped link disturbance events and position indicating information for each of the end-points (110) of the wireless link (120), wherein the timestamped link disturbance events and the position indicating information per each wireless link (120) define a pattern of link disturbance events; and classify the probable cause of the network disturbance event by correlating the patterns of link disturbance events of all the wireless links (120) in the set of the point-to-point wireless links (120).

2. The controller entity (310, 800, 900) according to claim 1, wherein the wireless links (120) are wireless microwave links (120), and wherein the timestamped link disturbance events comprise variations of received power on either side of the wireless links (120).

3. The controller entity (310, 800, 900) according to claim 1, wherein the wireless links (120) are free space optical links (120), and wherein the timestamped link disturbance events comprise variations of received power on either side of the wireless links (120).

4. The controller entity (310, 800, 900) according to any preceding claim, wherein the position indicating information is any, or any combination, of: geographical coordinates of each end-point (110), relative positions of the end-points (110), distances between the end-points (110).

5. The controller entity (310, 800, 900) according to claim 4, wherein the position indicating information for one of the wireless links (120) further pertains to spatial orientation of the end-points (110) of said one of the wireless links (120).

6. The controller entity (310, 800, 900) according to any preceding claim, wherein the timestamped link disturbance events for one of the wireless links (120) are identified based on timestamped power measurements at the end-points (110) of said one of the wireless links (120).

7. The controller entity (310, 800, 900) according to any preceding claim, wherein the timestamped link disturbance events are, via the position indicating information, mapped to a time-variant network graph (600, 700), where the time-variant network graph (600, 700) comprises vertices (310a:610g) that represent the end-points (110) and edges (620a:620g) that represent the wireless links (120).

8. The controller entity (310, 800, 900) according to claim 7, wherein the edge (620) representing one of the wireless links (120) is associated with the timestamped link disturbance events of said one of the wireless links (120).

9. The controller entity (310, 800, 900) according to claim 7 or 8, wherein the timestamped link disturbance events are classified by using an Artificial Intelligence and/or Machine Learning method to analyse the time-variant network graph (600, 700).

10. The controller entity (310, 800, 900) according to any of claims 7 to 9, wherein the network disturbance event is classified by using an Artificial Intelligence and/or Machine Learning method to correlate the patterns of link disturbance events in accordance with the time-variant network graph (600, 700).

11. The controller entity (310, 800, 900) according to claim 9 or 10, wherein the probable cause of the network disturbance event is classified to be any, or any combination, of: antenna misalignment, antenna swaying, antenna tower swaying, building swaying, landslide, tremor, earthquake, unclassified events.

12. The controller entity (310, 800, 900) according to any of claims 7 to 10, wherein the classification of the probable cause of the network disturbance event is a function of event classes of only the timestamped link disturbance events of the wireless links (120) as located within a predefined distance from a point of interest in the time-variant network graph (600, 700).

13. The controller entity (310, 800, 900) according to claim 12, wherein the predefined distance is defined in terms of either spatial distance from the point of interest or number of edges (620) from the point of interest in the time-variant network graph (600, 700).

14. The controller entity (310, 800, 900) according to any preceding claim, the processing circuitry further being configured to cause the controller entity (310, 800, 900) to: perform an action in response to having classified the probable cause of the network disturbance event to counteract the probable cause of the network disturbance events.

15. The controller entity (310, 800, 900) according to any preceding claim, the processing circuitry further being configured to cause the controller entity (310, 800, 900) to: localize the probable cause of the network disturbance event by correlating the patterns of link disturbance events of all the wireless links (120) in the set of the point-to-point wireless links (120).

16. A controller entity (310, 800, 900) for classification of probable cause of a network disturbance event in a network (100) comprising point-to-point wireless links (120) sharing groups of end-points (110), the controller entity (310, 800, 900) comprising: an obtain module (910) configured to obtain, per each wireless link (120) in a set of the wireless links, timestamped link disturbance events and position indicating information for each of the end-points (110) of the wireless link (120), wherein the timestamped link disturbance events and the position indicating information per each wireless link (120) define a pattern of link disturbance events; and a classify module (920) configured to classify the probable cause of the network disturbance event by correlating the patterns of link disturbance events of all the wireless links (120) in the set of the point- to-point wireless links (120).

17. A method for classification of probable cause of a network disturbance event in a network (100) comprising point-to-point wireless links (120) sharing groups of end-points (110), the method being performed by a controller entity (310, 800, 900), the method comprising: obtaining (S102), per each wireless link (120) in a set of the wireless links, timestamped link disturbance events and position indicating information for each of the end-points (110) of the wireless link (120), wherein the timestamped link disturbance events and the position indicating information per each wireless link (120) define a pattern of link disturbance events; and classifying (SI 04) the probable cause of the network disturbance event by correlating the patterns of link disturbance events of all the wireless links (120) in the set of the point-to-point wireless links (120).

18. A computer program (1020) for classification of probable cause of a network disturbance event in a network (100) comprising point-to-point wireless links (120) sharing groups of end-points (110), the computer program comprising computer code which, when run on processing circuitry (810) of a controller entity (310, 800, 900), causes the controller entity (310, 800, 900) to: obtain (S102), per each wireless link (120) in a set of the wireless links, timestamped link disturbance events and position indicating information for each of the end-points (110) of the wireless link (120), wherein the timestamped link disturbance events and the position indicating information per each wireless link (120) define a pattern of link disturbance events; and classify (SI 04) the probable cause of the network disturbance event by correlating the patterns of link disturbance events of all the wireless links (120) in the set of the point-to-point wireless links (120).

19. A computer program product (1010) comprising a computer program (1020) according to claim 18, and a computer readable storage medium (1030) on which the computer program is stored.