Performance anomaly analysis in a communication network

Abstract

A computer-implemented method may comprise: Acquiring data associated with a communication network comprising a plurality of cells, wherein the data is associated with a time period. Calculating a first set of values for a key performance indicator. Calculating, in response to detecting a presence of a first anomaly in the first set of key performance indicator values, per cell aggregation within a plurality of cell aggregations for the plurality of cells, a second set of values for the key performance indicator. Generating, in response to detecting a presence of a second anomaly similar to the first anomaly in one or more sets of key performance indicator values within the second sets of key performance indicator values, an output for controlling the communication network, wherein the output indicates one or more cell aggregations associated with the one or more sets of key performance indicator values.

Description

[0001] Some example embodiments relate to analyzing key performance indicator anomalies in a communication network.

[0002] BACKGROUND

[0003] A wireless communication network may be analyzed and optimized in many different ways, e.g., based on key performance indicators (KPI) of the network. One example of such a KPI is the dropped call rate (DCR). KPI monitoring and analysis can be used for, e.g., identifying problems in the network, finding network elements where optimization activities should be targeted, or monitoring performance after implementing changes in the network.

[0004] Identifying aggregations of network elements that have an impact on KPI anomalies detected within the communication network may be a nonstraightforward and time-consuming task if conducted based on individual KPI values. Therefore, there is a need for enabling a solution for analyzing KPI anomalies throughout different aggregations of network elements within the communication network.

[0005] SUMMARY

[0006] This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

[0007] Example embodiments of the present disclosure enable a contributionbased analysis of performance of a communication network comprising a plurality of cells. This benefit may be achieved by the features of the independent claims. Further example embodiments are provided in the dependent claims, the detailed description, and the drawings.

[0008] According to a first aspect, a computer-implemented method is disclosed. The method may comprise: Acquiring data associated with a communication network comprising a plurality of cells, wherein the data is associated with a time period. Calculating, based on the acquired data, a first set of values for a key performance indicator, wherein the first set of key performance indicator values is associated with the communication network and with a set of successive time intervals within the time period, key performance indicator value per time interval. Calculating, in response to detecting a presence of a first anomaly in the first set of key performance indicator values, per cell aggregation within a plurality of cell aggregations for the plurality of cells, based on the acquired data, a second set of values for the key performance indicator, wherein the second set of key performance indicator values is associated with the cell aggregation and with the set of successive time intervals, key performance indicator value per time interval. Generating, in response to detecting a presence of a second anomaly similar to the first anomaly in one or more sets of key performance indicator values within the second sets of key performance indicator values, an output for controlling the communication network, wherein the output indicates one or more cell aggregations from within the plurality of cell aggregations, the one or more cell aggregations being associated with the one or more sets of key performance indicator values comprising the presence of the second anomaly. With such a method, presence of anomalies within key performance indicator values associated with the communication network or parts of it may be detected and localized automatically.

[0009] According to an example embodiment of the first aspect, the first anomaly may comprise a sudden change. With such a method, acute or abrupt changes in key performance values may be detected and localized automatically.

[0010] According to an example embodiment of the first aspect, the detecting the presence of the sudden change in a set of key performance indicator values, that may be the first set of key performance indicator values or the second set of key performance indicator values, may comprise: Calculating a mean value for a subset of key performance indicator values within the set of key performance indicator values, wherein the subset of key performance indicator values is associated with a subset of successive time intervals within the time period. Calculating a standard deviation value for the subset of key performance indicator values. Calculating a Z-score for a key performance indicator value associated with a time interval subsequent to the subset of successive time intervals, based on the mean value and the standard deviation value. Detecting, in response to the Z-score meeting a pre-determined Z-score threshold, the sudden change. With such a method, acute or abrupt changes in key performance values may be detected and localized automatically.

[0011] According to an example embodiment of the first aspect, the first anomaly may comprise a trend change. With such a method, gradual changes in key performance values may be detected and localized automatically.

[0012] According to an example embodiment of the first aspect, the detecting the presence of the trend change in a set of key performance indicator values, that may be the first set of key performance indicator values or the second set of key performance indicator values, may comprise: Fitting the set of key performance indicator values on a linear curve. Determining a slope value associated with the linear curve. Detecting, in response to an absolute value of the slope value meeting a pre-determined slope threshold, the trend change. With such a method, gradual changes in key performance values may be detected and localized automatically.

[0013] According to an example embodiment of the first aspect, the method may further comprise: Performing correlation analysis for the second sets of key performance indicator values associated with the one or more cell aggregations. Generating a further output indicating a presence of at least one pair of cell aggregations from within the one or more cell aggregations, wherein the at least one pair of cell aggregations is associated with a correlating pair of sets of key performance indicator values from within the second sets of key performance indicator values. With such a method, correlation between cells that contribute to anomalies in key performance indicator values can be analyzed. According to an example embodiment of the first aspect, the method may further comprise: Calculating, per cell within the one or more cell aggregations associated with the one or more sets of key performance indicator values, a contribution value associated with the cell. Generating a further output indicating a presence of one or more cells from within the one or more cell aggregations, wherein the one or more cells are associated with largest absolute values within the contribution values calculated. With such a method, contribution-based impact of cells on network performance may be analyzed.

[0014] According to an example embodiment of the first aspect, the method may further comprise: Generating further output indicating a presence of at least one worst performing cell aggregation from within the one or more cell aggregations. With such a method, information on worst performing cell aggregations may be automatically obtained.

[0015] According to an example embodiment of the first aspect, the controlling the communication network may comprise targeting optimization activities on at least one cell aggregation within the one or more cell aggregations indicated. With such a method, optimization activities may be targeted efficiently based on the automatic detection and localization of cell aggregations.

[0016] According to an example embodiment of the first aspect, the method may further comprise: Generating, in response to not detecting the presence of the second anomaly similar to the first anomaly in one or more sets of key performance indicator values within the second sets of key performance indicator values, an automated alert. With such a method, the user may be alerted to a need of a further investigation of the network.

[0017] According to a second aspect, an apparatus may comprise at least one processor and at least one memory including computer program code. The at least one memory and the computer code may be configured to, with the at least one processor, cause the apparatus at least to perform: Acquiring data associated with a communication network comprising a plurality of cells, wherein the data is associated with a time period. Calculating, based on the acquired data, a first set of values for a key performance indicator, wherein the first set of key performance indicator values is associated with the communication network and with a set of successive time intervals within the time period, key performance indicator value per time interval. Calculating, in response to detecting a presence of a first anomaly in the first set of key performance indicator values, per cell aggregation within a plurality of cell aggregations for the plurality of cells, based on the acquired data, a second set of values for the key performance indicator, wherein the second set of key performance indicator values is associated with the cell aggregation and with the set of successive time intervals, key performance indicator value per time interval. Generating, in response to detecting a presence of a second anomaly similar to the first anomaly in one or more sets of key performance indicator values within the second sets of key performance indicator values, an output for controlling the communication network, wherein the output indicates one or more cell aggregations from within the plurality of cell aggregations, the one or more cell aggregations being associated with the one or more sets of key performance indicator values comprising the presence of the second anomaly.

[0018] According to an example embodiment of the second aspect, the at least one memory and the computer program code may be configured to, with the at least one processor, cause the apparatus further to perform detecting a presence of a sudden change in a set of key performance indicator values, that may be the first set of key performance indicator values or the second set of key performance indicator values, wherein the first anomaly comprises the sudden change, by: Calculating a mean value for a subset of key performance indicator values within the set of key performance indicator values, wherein the subset of key performance indicator values is associated with a subset of successive time intervals within the time period. Calculating a standard deviation value for the subset of key performance indicator values. Calculating a Z-score for a key performance indicator value associated with a time interval subsequent to the subset of successive time intervals. Detecting, in response to the Z-score calculated meeting a pre-determined Z-score threshold, the sudden change.

[0019] According to an example embodiment of the second aspect, the at least one memory and the computer program code may be configured to, with the at least one processor, cause the apparatus further to perform detecting a presence of a trend change in a set of key performance indicator values, that may be the first set of key performance indicator values or the second set of key performance indicator values, wherein the first anomaly comprises the trend change, by: Fitting the set of key performance indicator values on a linear curve. Determining a slope value associated with the linear curve. Detecting, in response to an absolute value of the slope value meeting a pre-determined slope threshold, the trend change.

[0020] According to a third aspect, a computer program product may comprise computer-readable program code configured to, when read and executed by a computer system, cause the computer system at least to perform: Acquiring data associated with a communication network comprising a plurality of cells, wherein the data is associated with a time period. Calculating, based on the acquired data, a first set of values for a key performance indicator, wherein the first set of key performance indicator values is associated with the communication network and with a set of successive time intervals within the time period, key performance indicator value per time interval. Calculating, in response to detecting a presence of a first anomaly in the first set of key performance indicator values, per cell aggregation within a plurality of cell aggregations for the plurality of cells, based on the acquired data, a second set of values for the key performance indicator, wherein the second set of key performance indicator values is associated with the cell aggregation and with the set of successive time intervals, key performance indicator value per time interval. Generating, in response to detecting a presence of a second anomaly similar to the first anomaly in one or more sets of key performance indicator values within the second sets of key performance indicator values, an output for controlling the communication network, wherein the output indicates one or more cell aggregations from within the plurality of cell aggregations, the one or more cell aggregations being associated with the one or more sets of key performance indicator values comprising the presence of the second anomaly.

[0021] According to an example embodiment of the third aspect, the computer program product may be embodied on a computer-readable medium readable by the computer system. Any example embodiment may be combined with one or more other example embodiments. Many of the attendant features will be more readily appreciated as they become better understood by reference to the following detailed description considered in connection with the accompanying drawings.

[0022] DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which are included to provide a further understanding of the example embodiments and constitute a part of this specification, illustrate example embodiments and together with the description help to understand the example embodiments. In the drawings:

[0024] FIG. 1(a) and FIG. 1(b) illustrate a schematic block diagram of an example communication network;

[0025] FIG. 2 illustrates a schematic block diagram of an apparatus configured to practice one or more example embodiments;

[0026] FIG. 3 illustrates a schematic flow chart of key performance indicator anomaly analysis according to an example embodiment;

[0027] FIG. 4 illustrates a schematic flow chart of key performance indicator anomaly analysis according to another example embodiment; and

[0028] FIG. 5 illustrates a schematic flow chart of key performance indicator anomaly analysis according to yet another example embodiment.

[0029] DETAILED DESCRIPTION

[0030] Reference will now be made in detail to example embodiments, examples of which are illustrated in the accompanying drawings. The detailed description provided below in connection with the appended drawings is intended as a description of the present examples and is not intended to represent the only forms in which the present example may be constructed or utilized. The description sets forth the functions of the example and the sequence of steps for constructing and operating the example. However, the same or equivalent functions and sequences may be accomplished by different examples.

[0031] Although the specification may refer to “an”, “one”, or “some” embodiment(s) in several locations, this does not necessarily mean that each such reference is to the same embodiment(s), or that the feature may not apply to other embodiments. Single features of different embodiments may also be combined to provide other embodiments. Furthermore, words “comprising” and “including” should be understood as not limiting the described embodiments / example, and the embodiments / examples may contain also features / structures that have not been specifically mentioned.

[0032] Furthermore, although the numerative terminology, such as “first”, “second”, etc., may be used herein to describe various embodiments, elements, or features, it should be understood that these embodiments, elements, or features should not be limited by this numerative terminology. This numerative terminology is used herein only to distinguish one embodiment, element, or feature from another embodiment, element, or feature. For example, a first cell discussed below could be called a second cell, and vice versa, without departing from the teachings of the present disclosure.

[0033] According to an example embodiment, key performance indicator values are calculated based on acquired data, wherein the data is associated with a communication network and with a time period. If an anomaly is detected within the calculated key performance indicator values, related key performance indicator values are calculated for cell aggregations within the communication network. If a similar anomaly is detected within some of these related key performance indicator values, an output indicating those cell aggregations that are associated with the similar anomaly is generated.

[0034] According to the example embodiment, it may be possible to automatically detect a presence of an anomaly within key performance indicator values associated with the communication network. Further, parts of the network causing or contributing to the anomaly may be detected and localized automatically. When the anomaly is localized it may be possible to perform necessary corrective actions in order to optimize the performance of the identified parts of the network. Depending on the situation, the actions may be different. Utilizing performance anomaly analysis may increase the speed and effectiveness of controlling the communication network. FIG. 1(a) illustrates an example embodiment of a communication network, for which the key performance indicator anomaly analysis may be utilized. The communication network 100 may comprise one or more devices 110, which may be also referred to as client nodes, user nodes, or user equipment (UE). An example of a device is a UE 110, which may communicate with one or more access nodes of a radio access network (RAN) 120. The communication network 100 may therefore comprise a radio network. The RAN 120 may comprise one or more transmission sites, also simply referred to as sites (e.g., Sites 1 to 3). A site may comprise one or more access nodes. A transmission site may be further configured to provide communication services in one or more sectors, as will be further described with reference to FIG. 1(b). One access node may be configured to serve one or more sectors and / or one or more cells, illustrated in FIG. 1(a) with dotted circles, which may correspond to geographical area(s) covered by signals transmitted by the access node for a corresponding cell. Signals transmitted by an access node to the UE 110 may be referred to as downlink signals. Signals transmitted by the UE 110 to an access node may be referred to as uplink signals. An access node may be also referred to as an access point or a base station.

[0035] The communication network 100 may be configured for example in accordance with the 4thor 5thgeneration (4G, 5G) digital cellular communication networks, as defined by the 3rdGeneration Partnership Project (3GPP). For example, the communication network 100 may be configured to operate according to 3GPP (4G) LTE (Long-Term Evolution) and / or 3GPP 5G NR (New Radio) specifications. It is however appreciated that example embodiments presented herein are not limited to these example networks and may be applied in any present or future wireless communication networks, or combinations thereof, for example other type of cellular networks such as Global System for Mobile communication (GSM) or universal mobile telecommunication system (UMTS), short-range wireless networks, multicast networks, broadcast networks, or the like. Access nodes 122, 124, 126 of the RAN 120 may for example comprise 5thgeneration access nodes (gNB) or 4thgeneration access nodes (eNodeB). FIG. 1(b) illustrates an example of cells of a sector of a transmission site, where Site 1 of FIG. 1(a) is used as an example. The access node 122 may be configured to serve three sectors (A to C). In this example, two cells 132-1 and 132-2 may be configured at Sector B, but in general a sector may comprise one or more cells. The cells may be identified with different cell identifiers (e.g., physical cell ID). Cells associated with the same sector may be configured to operate at different frequencies or with different code bases in case of a code division multiple access (CDMA) system. As illustrated in FIG. 1(b), coverage areas of the cells of the same sector may overlap. Contribution value according to an example embodiment may be calculated, e.g., for a subset of cells comprising cells associated with the same sector or for a subset of cells configured to operate at a frequency or with a code basis.

[0036] Referring to FIG. 1(a), the communication network 100 may further comprise a core network 130, which may comprise various network functions (NF) for establishing, configuring, and controlling data communication sessions of users, for example the UE 110. The data communication sessions may carry data traffic, for example application data associated with one or more applications running on the UE 110. The communication network 100 may further comprise a network controller 140, for example a centralized selforganized network (C-SON) controller, which may be responsible of configuring various operations of the RAN 120. The network controller 140 may be also referred to as a centralized network controller. The network controller 140 may interface an operations support system (OSS) 150, which may be configured to deliver various information, such as for example inventory management (IM) data, configuration management (CM) data, or performance management (PM) data between the RAN 120 and the network controller 140. Even though illustrated as a separate entity, network controller 140 may be also embodied as part of any suitable network device of function, for example as part of the OSS 150. Even though some operations have been described as being performed by the network controller 140, it is understood that similar functions may be performed alternatively by other network device(s) or network function(s) of the communication network 100, which may be in general referred to as network objects. The operations may be performed by an automated network monitoring and controlling system or an automated network operation center (NOC) such as, e.g., a virtual NOC. The automated NOC may be understood as a network object responsible for monitoring power failures, communication line alarms, and other performance issues that may affect the network. In telecommunication environments the automated NOC may track details of call flows. One task of the network controller 140 may be to analyze performance of the communication network 100, or network object(s) thereof, e.g., in order to determine how to target optimization activities.

[0037] Operational characteristics of the communication network 100 may be analyzed and optimized with many different methods and based on various key performance indicators (KPI), including, but not limited to, the following: traffic channel (TCH) setup success rate, standalone dedicated control channel (SDCCH) setup success rate, cell availability, TCH drop rate, SDCCH drop rate, SDCCH traffic, TCH traffic, SDCCH congestion time, downlink EDGE (Enhanced Data rates for GSM Evolution) traffic, circuit-switched (CS) success rate, packet-switched (PS) success rate, radio resource control (RRC) mobile- oriented success rate, RRC mobile-terminated (MT) success rate, PS call drop rate, CS call drop rate, high-speed uplink packet access (HSUPA) traffic, CS traffic, high-speed downlink packet access (HSDPA) traffic, RRC setup success rate, evolved-UMTS terrestrial radio access network (E-UTRAN) radio access bearer (E-RAB) setup success rate, RRC abnormal release rate, E-RAB drop rate, downlink data volume, uplink data volume, average reported channel quality indicator (CQI), and multiple input multiple output (MIMO) rank indicator. Analyzing KPI values for individual cells and cell aggregations manually may comprise time-consuming tasks. Example embodiments of the present disclosure provide methods for overcoming such challenges. Anomaly analysis may be utilized for any key performance indicator available.

[0038] FIG. 2 illustrates an example embodiment of an apparatus 200 configured to perform operations of one or more example embodiments, e.g., functionalities described below with reference to FIG. 3 to 5. The apparatus 200 may be for example used to implement the network controller 140. The apparatus 200 may comprise at least one processor 202. The at least one processor 202 may comprise, for example, one or more of various processing devices or processor circuitry, such as for example a co-processor, a microprocessor, a controller, a digital signal processor (DSP), a processing circuitry with or without an accompanying DSP, or various other processing devices including integrated circuits such as, for example, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a microcontroller unit (MCU), a hardware accelerator, a special-purpose computer chip, or the like.

[0039] The apparatus 200 may further comprise at least one memory 204. The at least one memory 204 may be configured to store, for example, computer program code or the like, for example operating system software and application software. The at least one memory 204 may comprise one or more volatile memory devices, one or more non-volatile memory devices, and / or a combination thereof. For example, the at least one memory 204 may be embodied as magnetic storage devices (such as hard disk drives, floppy disks, magnetic tapes, etc.), optical magnetic storage devices, or semiconductor memories (such as mask ROM, PROM (programmable ROM), EPROM (erasable PROM), flash ROM, RAM (random access memory), etc.).

[0040] The apparatus 200 may further comprise a communication interface 208 configured to enable apparatus 200 to transmit and / or receive information to / from other devices, functions, or entities. In one example, the apparatus 200 may use communication interface 208 to transmit or receive information over a service-based interface (SBI) message bus of the core network 130, for example to the core network 130 and / or the RAN 120. The communication interface 208 may therefore comprise a data communication interface and be configured for communication between devices, for example according to one or more data communication protocols. The apparatus 200 maybe for example configured to transmit indication(s) of verified or non-verified performance, for example to an automated service ticket system, or to provide network configuration instructions to the RAN 120 to cause reconfiguration of network object(s). The apparatus 200 may further comprise a user interface 210, for example for providing user output by the apparatus, such as for example visual and / or audible signal(s), for example by speaker(s), display(s), light(s), or the like. User interface 210 may be used for example for outputting indication(s) of verified or non-verified performance to a human user.

[0041] When the apparatus 200 is configured to implement some functionality, some component and / or components of the apparatus 200, such as for example the at least one processor 202 and / or the at least one memory 204, may be configured to implement this functionality. Furthermore, when the at least one processor 202 is configured to implement some functionality, this functionality may be implemented using program code 206 comprised, for example, in the at least one memory 204.

[0042] The functionality described herein may be performed, at least in part, by one or more computer program product components such as for example software components. According to an example embodiment, the apparatus 200 comprises a processor or processor circuitry, such as for example a microcontroller, configured by the program code when executed to execute the embodiments of the operations and functionality described. A computer program or a computer program product may therefore comprise instructions for causing, when executed, the apparatus 200 to perform the method(s) described herein. Alternatively, or in addition, the functionality described herein can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, illustrative types of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), application-specific Integrated Circuits (ASICs), application-specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), Graphics Processing Units (GPUs).

[0043] The apparatus 200 comprises means for performing at least one method described herein. In one example, the means comprises the at least one processor 202, the at least one memory 204 including the program code 206 configured to, when executed by the at least one processor, cause the apparatus 200 to perform the method. The apparatus 200 may comprise a computing device such as for example an access point, an access node, a base station, a server, a network device, a network function device, or the like. Although the apparatus 200 is illustrated as a single device it is appreciated that, wherever applicable, functions of the apparatus 200 may be distributed to a plurality of devices, for example to implement example embodiments as a cloud computing service.

[0044] FIG. 3 illustrates a flow chart according to an example embodiment of a computer-implemented method for identifying cell aggregations based on similarities within detected key performance indicator anomalies. The apparatus 200 illustrated with FIG. 2 is configured to perform the operation of the method in the communication network 100 illustrated with FIG. 1(a) and 1(b).

[0045] Referring to FIG. 3, data associated with the communication network 100 comprising a plurality of cells, is acquired in operation 301. The data is associated with a time period, such as, e.g., an hour, a day, or a week. The data may be acquired from one or more data sources, such as communication databases and / or external databases. An external database may be, e.g., a data source providing weather information. A first set of values for a key performance indicator is calculated in operation 302 based on the acquired data. The first set of key performance indicator values is associated with the communication network and with a set of successive time intervals within the time period, a key performance indicator value per time interval. The set of successive time intervals may comprise, e.g., successive hours within a day or successive days within a week or a month. It is determined in operation 303 whether a presence of a first anomaly is detected in the first set of key performance indicator values. If the presence of the first anomaly is detected (303: yes), a second set of values for the key performance indicator is calculated in operation 304, per cell aggregation within a plurality of cell aggregations for the plurality of cells, based on the acquired data. The plurality of cell aggregations may be predetermined, or the plurality of cell aggregations may be determined, e.g., after the first anomaly is detected. The second set of key performance indicator values is associated with the cell aggregation and with the set of successive time intervals, key performance indicator value per time interval. If the presence of the first anomaly is not detected (303: no), more data is acquired in operation 301. It is determined in operation 305 whether a presence of a second anomaly similar to the first anomaly is detected in one or more sets of key performance indicator values within the second sets of key performance indicator values. If the presence of the second anomaly is detected (305: yes), an output for controlling the communication network is generated in operation 306. The output indicates one or more cell aggregations from within the plurality of cell aggregations. The indicated one or more cell aggregations are associated with the one or more sets of key performance indicator values comprising the presence of the second anomaly. If the presence of the second anomaly is not detected (305: no), an automated alert is generated in operation 307. The automated alert may comprise an indication that the presence of the second anomaly is not detected.

[0046] In an example embodiment, the first anomaly comprises a sudden change. The sudden change may be understood as a difference between two successive key performance indicator values being large compared to differences between preceding successive key performance indicator values. The detecting the presence of the sudden change in a set of key performance indicator values may comprise calculating a Z-score as explained in more detail below. The set of key performance indicator values may be the first set of key performance indicator values or the second set of key performance indicator values. A mean value for a subset of key performance indicator values within the set of key performance indicator values is calculated. The subset of key performance indicator values is associated with a subset of successive time intervals within the time period. A standard deviation value for the subset of key performance indicator values is calculated. The Z-score for a key performance indicator value associated with a time interval subsequent to the subset of successive time intervals is calculated based on the mean value and the standard deviation value. The Z-score may be calculated by decreasing the mean value from the key performance indicator value and dividing the result by the standard deviation value. The calculation explained above may be expressed by the following equation: x — / z Z = - , a wherein z may be understood as the Z-score, x may be understood as the key performance indicator value, / z may be understood as the mean value, and a may be understood as the standard deviation value. The presence of the sudden change in the set of key performance indicator values is detected when the calculated Z-score meets a pre-determined Z-score threshold.

[0047] In an example embodiment, the first anomaly comprises a trend change. The trend change may be understood as a gradual change occurring within key performance indicator values associated with successive time intervals. The detecting the presence of the trend change in the set of key performance indicator values may comprise fitting the set of key performance indicator values on a model such as, e.g., a regression model. The set of key performance indicator values may be the first set of key performance indicator values or the second set of key performance indicator values. In an example embodiment, the set of key performance indicator values are fitted on a linear curve. A slope value associated with the linear curve is determined. The linear curve may be, e.g., expressed by the following equation: y = ax + b, wherein y may be understood as the set of key performance indicator values, a may be understood as the slope value, x may be understood as the successive time intervals associated with the set of key performance indicator values, and b may be understood as a constant value. If an absolute value of the slope value meets a pre-determined slope threshold, the trend change is detected.

[0048] FIG. 4 illustrates a flow chart according to an example embodiment of a computer-implemented method for identifying correlating pairs of cell aggregations within the one or more cell aggregations. The apparatus 200 illustrated with FIG. 2 is configured to perform the operation of the method within the communication network 100 illustrated with FIG. 1(a) and 1(b). The functionalities illustrated in FIG. 4 may be carried out after operation 306 in FIG. 3. Referring to FIG. 4, correlation analysis is performed in operation 401 for the second sets of key performance indicator values associated with the one or more cell aggregations. Correlation may be understood as a measure of how two or more variables are related to one another. Correlation analysis may be performed by, e.g., calculating one or more correlation coefficients. A further output indicating a presence of at least one pair of cell aggregations from within the one or more cell aggregations is generated in operation 402. The at least one pair of cell aggregations is associated with a correlating pair of sets of key performance indicator values from within the second sets of key performance indicator values.

[0049] FIG. 5 illustrates a flow chart according to an example embodiment of a computer-implemented method for determining contribution on performance of the one or more cell aggregations. The apparatus 200 illustrated with FIG. 2 is configured to perform the operation of the method within the communication network 100 illustrated with FIG. 1(a) and 1(b). The functionalities illustrated in FIG. 4 may be carried out after operation 306 in FIG. 3.

[0050] Referring to FIG. 5, a contribution value is calculated in operation 501, per cell within the one or more cell aggregations associated with the one or more sets of key performance indicator values. The contribution value is associated with the cell and its performance. A further output indicating a presence of one or more cells from within the one or more cell aggregations is generated in operation 502. The indicated one or more cells are associated with largest absolute values within the contribution values calculated.

[0051] In an example embodiment, the calculating the contribution value for the cell may comprise decreasing a network key performance indicator value comprising a ratio of a second numerator value and a second denominator value, from a cell-specific key performance indicator value comprising a ratio of a first numerator value and a first denominator value, multiplying the result with the first denominator value, and dividing the result with the second denominator value. The calculations explained above may be expressed by the following equations: where ktmay be understood as the cell-specific key performance indicator value calculated for a cell i, ntmay be understood as the first numerator value, dtmay be understood as the first denominator value, K may be understood as the network key performance indicator value, N may be understood as the second numerator value, D may be understood as the second denominator value, M may be understood as a number of the cells, and cLmay be understood as the contribution value calculated for cell i.

[0052] Although the subject matter has been described in language specific to structural features and / or acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example embodiments of implementing the claims and other equivalent features and acts are intended to be within the scope of the claims.

[0053] It will be understood that the benefits and advantages described above may relate to one example embodiment or may relate to several example embodiments. The example embodiments are not limited to those that solve any or all of the stated problems or those that have any or all of the stated benefits and advantages. It will further be understood that reference to 'an' item may refer to one or more of those items.

[0054] The steps or operations of the methods described herein may be carried out in any suitable order, or simultaneously where appropriate. Additionally, individual blocks may be deleted from any of the methods without departing from the scope of the subject matter described herein. Aspects of any of the example embodiments described above may be combined with aspects of any of the other example embodiments described to form further example embodiments without losing the effect sought. It will be understood that the above description is given by way of example embodiments only and that various modifications may be made by those skilled in the art. The above specification, example embodiments and data provide a complete description of the structure and use of exemplary embodiments. Although various example embodiments have been described above with a certain degree of particularity, or with reference to one or more individual embodiments, those skilled in the art could make numerous alterations to the disclosed example embodiments without departing from scope of this specification.

Claims

CLAIMS1. A computer-implemented method, comprising: acquiring (301) data associated with a communication network (100) comprising a plurality of cells, wherein the data is associated with a time period; calculating (302), based on the acquired data, a first set of values for a key performance indicator, wherein the first set of key performance indicator values is associated with the communication network and with a set of successive time intervals within the time period, key performance indicator value per time interval; calculating (304), in response to detecting a presence of a first anomaly in the first set of key performance indicator values, per cell aggregation within a plurality of cell aggregations for the plurality of cells, based on the acquired data, a second set of values for the key performance indicator, wherein the second set of key performance indicator values is associated with the cell aggregation and with the set of successive time intervals, key performance indicator value per time interval; and generating (306), in response to detecting a presence of a second anomaly similar to the first anomaly in one or more sets of key performance indicator values within the second sets of key performance indicator values, an output for controlling the communication network, wherein the output indicates one or more cell aggregations from within the plurality of cell aggregations, the one or more cell aggregations being associated with the one or more sets of key performance indicator values comprising the presence of the second anomaly.

2. A computer-implemented method according to claim 1, wherein the first anomaly comprises a sudden change; and wherein the detecting the presence of the sudden change in a set of key performance indicator values being the first set of key performance indicator values or the second set of key performance indicator values comprises: calculating a mean value for a subset of key performance indicator values within the set of key performance indicator values, wherein the subset of keyperformance indicator values is associated with a subset of successive time intervals within the time period; calculating a standard deviation value for the subset of key performance indicator values; calculating a Z-score for a key performance indicator value associated with a time interval subsequent to the subset of successive time intervals, based on the mean value and the standard deviation value; and detecting, in response to the Z-score meeting a pre-determined Z-score threshold, the sudden change.

3. A computer-implemented method according to claim 1, wherein the first anomaly comprises a trend change; and wherein the detecting the presence of the trend change in a set of key performance indicator values being the first set of key performance indicator values or the second set of key performance indicator values comprises: fitting the set of key performance indicator values on a linear curve; determining a slope value associated with the linear curve; and detecting, in response to an absolute value of the slope value meeting a predetermined slope threshold, the trend change.

4. A computer-implemented method according to any of the preceding claims, further comprising: performing correlation analysis for the second sets of key performance indicator values associated with the one or more cell aggregations; and generating a further output indicating a presence of at least one pair of cell aggregations from within the one or more cell aggregations, wherein the at least one pair of cell aggregations is associated with a correlating pair of sets of key performance indicator values from within the second sets of key performance indicator values.

5. A computer-implemented method according to any of the preceding claims, further comprising:calculating, per cell within the one or more cell aggregations associated with the one or more sets of key performance indicator values, a contribution value associated with the cell; and generating a further output indicating a presence of one or more cells from within the one or more cell aggregations, wherein the one or more cells are associated with largest absolute values within the contribution values calculated.

6. A computer-implemented method according to any of the preceding claims, further comprising: generating further output indicating a presence of at least one worst performing cell aggregation from within the one or more cell aggregations.

7. A computer-implemented method according to any of the preceding claims, wherein the controlling the communication network comprises targeting optimization activities on at least one cell aggregation within the one or more cell aggregations indicated.

8. A computer-implemented method according to any of the preceding claims, further comprising: generating, in response to not detecting the presence of the second anomaly similar to the first anomaly in one or more sets of key performance indicator values within the second sets of key performance indicator values, an automated alert.

9. An apparatus comprising: at least one processor; and at least one memory including computer program code, the at least one memory and computer program code being configured to, with the at least one processor, cause the apparatus at least to perform: acquiring (301) data associated with a communication network comprising a plurality of cells, wherein the data is associated with a time period; calculating (302), based on the acquired data, a first set of values for a key performance indicator, wherein the first set of key performance indicator values isassociated with the communication network and with a set of successive time intervals within the time period, key performance indicator value per time interval; calculating (304), in response to detecting a presence of a first anomaly in the first set of key performance indicator values, per cell aggregation within a plurality of cell aggregations for the plurality of cells, based on the acquired data, a second set of values for the key performance indicator, wherein the second set of key performance indicator values is associated with the cell aggregation and with the set of successive time intervals, key performance indicator value per time interval; generating (306), in response to detecting a presence of a second anomaly similar to the first anomaly in one or more sets of key performance indicator values within the second sets of key performance indicator values, an output for controlling the communication network, wherein the output indicates one or more cell aggregations from within the plurality of cell aggregations, the one or more cell aggregations being associated with the one or more sets of key performance indicator values comprising the presence of the second anomaly.

10. An apparatus according to claim 9, wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus further to perform detecting a presence of a sudden change in a set of key performance indicator values being the first set of key performance indicator values or the second set of key performance indicator values, wherein the first anomaly comprises the sudden change, by: calculating a mean value for a subset of key performance indicator values within the set of key performance indicator values, wherein the subset of key performance indicator values is associated with a subset of successive time intervals within the time period; calculating a standard deviation value for the subset of key performance indicator values; calculating a Z-score for a key performance indicator value associated with a time interval subsequent to the subset of successive time intervals; anddetecting, in response to the Z-score calculated meeting a pre-determined Z-score threshold, the sudden change.

11. An apparatus according to claim 9, wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus further to perform detecting a presence of a trend change in a set of key performance indicator values being the first set of key performance indicator values or the second set of key performance indicator values, wherein the first anomaly comprises the trend change, by: fitting the set of key performance indicator values on a linear curve; determining a slope value associated with the linear curve; and detecting, in response to an absolute value of the slope value meeting a predetermined slope threshold, the trend change.

12. A computer program product comprising a computer-readable program code configured to, when read and executed by a computer system, cause the computer system at least to perform: acquiring (301) data associated with a communication network comprising a plurality of cells, wherein the data is associated with a time period; calculating (302), based on the acquired data, a first set of values for a key performance indicator, wherein the first set of key performance indicator values is associated with the communication network and with a set of successive time intervals within the time period, key performance indicator value per time interval; calculating (304), in response to detecting a presence of a first anomaly in the first set of key performance indicator values, per cell aggregation within a plurality of cell aggregations for the plurality of cells, based on the acquired data, a second set of values for the key performance indicator, wherein the second set of key performance indicator values is associated with the cell aggregation and with the set of successive time intervals, key performance indicator value per time interval; generating (306), in response to detecting a presence of a second anomaly similar to the first anomaly in one or more sets of key performance indicator valueswithin the second sets of key performance indicator values, an output for controlling the communication network, wherein the output indicates one or more cell aggregations from within the plurality of cell aggregations, the one or more cell aggregations being associated with the one or more sets of key performance indicator values comprising the presence of the second anomaly.

13. A computer program product according to claim 12 embodied on a computer-readable medium readable by the computer system.

Images