WO2022185325A1

WO2022185325A1 - First node, second node, communications system and methods performed thereby for handling a prediction of an event

Info

Publication number: WO2022185325A1
Application number: PCT/IN2021/050209
Authority: WO
Inventors: Bandyopadhyay SUBHADIP; Sisodia ARPIT; Biswas RAJIB; Kumar Vuppala SUNIL
Original assignee: Telefonaktiebolaget Lm Ericsson (Publ)
Priority date: 2021-03-04
Filing date: 2021-03-04
Publication date: 2022-09-09

Abstract

A method performed by a first node (111). The method is for handling a prediction of an event. The first node (111) obtains (201), from a second node (112), a first indication. The first indication is of an event the probability of occurrence of which is to be predicted by the first node (111). The event is indicative of a performance of at least a part of a communications system (100). The first node (111) determines (204) the probability of occurrence of the event during a first time period. The determining (204) is based on estimating a probability of survival over time of the event, defined by a first variable, via reliability modelling. The first node (111) sends (205) another indication to the second node (112) or to another node (113, 114) comprised in the communications system (100). The another indication indicates the determined probability of occurrence of the event over a second time period.

Description

FIRST NODE, SECOND NODE, COMMUNICATIONS SYSTEM AND METHODS PERFORMED THEREBY FOR HANDLING A PREDSCTION OF AN EVENT

TECHNICAL FIELD

The present disclosure relates generally to a first node, and methods performed thereby, for handling the prediction of the event. The present disclosure also relates generally to a second node and methods performed thereby, for handling the prediction of the event. The present disclosure also relates generally to a communications system, and methods performed thereby, for handling a prediction of an event. The present disclosure further relates generally to computer program products, comprising instructions to carry out the actions described herein, as performed by the first node and the second node. The computer program products may be stored, respectively, on a computer-readable storage medium.

BACKGROUND

Computer systems in a communications network may comprise one or more nodes, which may also be referred to simply as nodes. A node may comprise one or more processors which, together with computer program code may perform different functions and actions, a memory, a receiving port and a sending port. A node may be, for example, a server. Nodes may perform their functions entirely on the cloud.

Internet of Things (IoT)

The Internet of Things (ioT) may be understood as an internetworking of devices, e.g., physical devices, vehicles, which may also referred to as "connected devices" and "smart devices", buildings and other items — embedded with electronics, software, sensors, actuators, and network connectivity that may enable these objects to collect and exchange data. The IoT may allow objects to be sensed and/or controlled remotely across an existing network infrastructure.

"Things." in the IoT sense, may refer to a wide variety of devices such as heart monitoring implants, biochip transponders on farm animals, electric clams in coastal waters, automobiles with built-in sensors, DNA analysis devices for environmental/food/pathogen monitoring, or field operation devices that may assist firefighters in search and rescue operations, home automation devices such as for the control and automation of lighting via e.g., cameras, light monitors, heating, e.g. a "smart" thermostat, ventilation, air conditioning, and appliances such as washers, dryers, ovens, refrigerators or freezers that may use telecommunications for remote monitoring. These devices may collect data with the help of various existing technologies and then autonomously flow the data between other devices. Prediction related to telecommunication networks has mostly been observed from a problem specific context such as prediction of values of Key Performance Indicators (KPI), prediction of occurrence of some specific fault or specific alarm etc.

There are few familiar approaches which may be used to address this problem from different perspectives. A first approach may be to address the prediction as a classification problem. According to this first approach, the prediction may be considered as a two class problem where the objective may be considered to be to predict the failure class, which may be understood as a state of a related KPI/network feature, based on recent data from network traffic. A second approach may be considered to be based on a regression and one or more rules. According to this second approach, the prediction may be achieved by fitting a forecasting model to predict a quantity of interest, e.g., KPI and/or counters, and transferthe predicted value as an indicator of alarm by a rule, such as by comparing the predicted value with a threshold. A third approach may be considered to be an anomaly prediction. According to this third approach an extreme event may be considered as an anomaly that may need to be predicted.

Several works have been conducted on prediction of events such as time to faiiure for hardware devices and survival of human life. Some of such studies are: US20200084087, which deals with intelligent anomaly detection and root cause analysis in mobile networks, US20200213202, drawn to a system and method for predicting key performance indicator (KPI) in a telecommunication network. US8735549, describing a predictive maintenance display system, US9439092, dealing with detection of component fault at ceil towers, US8085654, describing a method for reducing file detection time in a telecommunication network, US9716633 drawn to an alarm prediction in a telecommunication network and US0972252, disclosing a system and method for a telecommunications system fault diagnostics.

Some KPis may be considered to be naturally predictable. Naturally predictable, in this context, may be understood to mean that these KPis may be observed and a prediction model may be fit based on historical data to predict the values for any future time points. There may be some other KPis such as CGI which, although measurable, may involve intermediate external factors such as environment etc. due to which the current prediction approach may not be applicable directly. Examples of KPis that may be considered to be naturally predictable may be Physical Resource Block (PRB) utilization, downlink (DL) throughput, uplink (UL)- Received Signal Strength Indicator (RSSI), call drop rate, Call Setup Success Rate (CSSR), packet loss rate, Session Setup Success Rate (SSSR), Session Abnormal Release Rate (SSAR), UpLink User Throughput (ULUT), Down Link User Throughput (DLUT), Downlink Latency (LATJDL), Evolved Universal Terrestrial Radio Access Network Radio Access Bearer {ERAS), handover success rate etc. From the perspective of the health of a network, specific events defined on these KPIs may be of interest and not the whole range of the KPI values.

For example, it may be strategically useful in orderto plan a certain action a priori to be able to know when the DLJthroughput will be below some pre-defined threshold, which may be considered to be an event.

SUMMARY

The current approaches to predict events In telecommunication networks have a number of limitations. First, they are characterized by a lack generality. Although the prediction aspect in different use cases may be considered to have a general link, where the use cases may be mapped to a general event prediction procedure, mostly use case specific solutions have been observed instead a generic treatment. Thus, different use cases are provided as separate solutions, although many of those use cases may be treated as special cases of a core general procedure. Hence, existing methods grossly ignore the re~use and/or portability of the different solutions. Second, existing methods lack the view of dynamic profiling of the probabiiity of occurrence of an event over future time points. Hence, in most of the cases, any understanding of the relative progression of the degradation of the performance of the networks is missing. Third, existing methods lack a modelling aspect of the system degradation. If any network abnormality is considered as an event, a system level performance degradation modelling is a more fundamental and appropriate approach to understanding how certain events appear as a natural outcome of a progressive degradation of a system over time. Any of the current approaches mentioned in the Background section do not address this core issue. The current approaches try to build a straightforward data-based modelling rather a system level performance degradation process modelling. Fourth, existing methods are not supportive enough for strategic decision making. Current approaches do not provide an easily comparable view of predictive performance of a network with respect to different events. For example, if cell battery malfunctioning and physical resource block are two events, if is not easy to compare the probable performance of a network over the next few days, and hence take an informed decision to prioritize or to de-prioritize certain corrective actions. Fifth, existing methods lack insight of predictive performance at a collective level, e.g., at a level of a cluster of cells. Current approaches provide prediction of use case specific event occurrence at granular level, such as at a cell level in general but no further insight on how that may affect the network at a collective level, e.g., at a cluster of cell level. A cluster of cells may represent, for example, cells from a geographical region or some cells sharing some common feature such as being connected through a transport layer. It is an object of embodiments herein to improve the handling of a prediction of an event in a communications system. It is a particular object of embodiments herein to improve the prediction of the event by identifying clusters of nodes, or sets of nodes, in the communications system, and facilitating a dynamic selection of leader nodes in the identified clusters, thereby facilitating the handling the prediction of the event by the respective leader nodes between clusters, and in some particular embodiments, across layers in a layered architecture of a communications system.

According to a first aspect of embodiments herein, the object is achieved by a method performed by a first node. The method is for handling a prediction of an event. The first node operates in a communications system. The first node obtains, from a second node operating in the communications system, a first indication. The first indication is of an event the probability of occurrence of which is to be predicted by the first node 111. The event is indicative of a performance of at least a part of the communications system. The first node determines the probability of occurrence of the event in the communications system during a first time period. The determining is based on estimating a probability of survival overtime of the event, defined by a first variable, via reliability modelling. The first node sends another indication to the second node or to another node comprised in the communications system. The another indication Indicates the determined probability of occurrence of the event over a second time period.

According to a second aspect of embodiments herein, the object is achieved by a method performed by the second node. The method is for handling the prediction of the event. The second node operates in the communications system. The second node sends, to the first node operating in the communications system, the first indication of the event the probability of occurrence of which is to be predicted by the first node. The event is indicative of the performance of at least a part of the communications system. The second node receives the another indication from the first node. The another indication indicates the probability of occurrence of the event over the second time period, as determined by the first node. The another indication is based on the determined probability of survival overtime of the event, defined by the first variable, as determined by the first node, via reliability modelling.

According to a third aspect of embodiments herein, the object is achieved by a method performed by a communications system, comprising a first node, a second node and a third node. The method is for handling the prediction of the event. The communications system comprises the first node and the second node operating in the communications system. The method comprises sending, by the second node to the first node, the first indication of the event the probability of occurrence of which is to be predicted by the first node. The event is indicative of the performance of at least a part of the communications system. The method also comprises obtaining, by the first node from the second node, the first indication. The method then comprises determining, by the first node, the probability of occurrence of the event in the communications system during the first time period. The determining is based on estimating the probability of survival overtime of the event, defined by the first variable, via reliability modelling. The method further comprises sending by the first node, the another indication to the second node or to another node comprised in the communications system. The another indication indicates the determined probability of occurrence of the event over the second time period. The method also comprises receiving, by the second node, the another indication from the first node.

According to a fourth aspect of embodiments herein, the object is achieved by the first node. The first node is for handling the prediction of the event. The first node is configured to operate In the communications system. The first node is configured to obtain, from the second node configured to operate in the communications system, the first indication of the event the probability of occurrence of which is to be predicted by the first node. The event is configured to be indicative of the performance of at least a part of the communications system. The first node is also configured to determine the probability of occurrence of the event in the communications system during the first time period. The determining is configured to be based on estimating the probability of survival overtime of the event, configured to be defined by the first variable, via reliability modelling. The first node is also configured to send the another indication to the second node or to another node configured to be comprised in the communications system. The another indication is configured to indicate the probability of occurrence of the event configured to be determined over the second time period.

According to a fifth aspect of embodiments herein, the object is achieved by the second node. The second node is for handling the prediction of the event. The second node is configured to operate in the communications system. The second node is further configured to send, to the first node configured to operate in the communications system, the first indication of the event the probability of occurrence of which is to be predicted by the first node. The event is configured to be indicative of the performance of at least a part of the communications system. The second node is also configured to receive the another indication from the first node. The another indication is configured to indicate the probability of occurrence of the event configured to be determined over the second time period, as configured to be determined by the first node. The another indication is configured to be based on a probability of survival overtime of the event, configured to be defined by the first variable, as configured to be determined by the first node, via reliability modelling.

According to a sixth aspect of embodiments herein, the object is achieved by the communications system. The communications system is for handling the prediction of the event. The communications system is configured to comprise the first node and the second node configured to operate in the communications system. The communications system is configured to send, by the second node to the first node, the first indication of the event the probability of occurrence of which is to be predicted by the first node. The event is configured to be indicative of the performance of at least a part of the communications system. The communications system is further configured to obtain, by the first node from the second node, the first indication. The communications system is further configured to determine, by the first node, the probability of occurrence of the event in the communications system during the first time period. The determining is configured to be based on estimating the probabiiity of survival overtime of the event, configured to be defined by the first variable, via reliability modelling. The communications system is further configured to send by the first node, the another indication to the second node or to another node configured to be comprised in the communications system. The another indication is configured to indicate the probability configured to be determined of occurrence of the event over the second time period. The communications system is further configured to receive, by the second node, the another indication from the first node.

According to a seventh aspect of embodiments herein, the object is achieved by a computer program, comprising instructions which, when executed on at least one processor, cause the at least one processor to carry out the method performed by the first node.

According to an eighth aspect of embodiments herein, the object is achieved by a computer-readable storage medium, having stored thereon the computer program, comprising instructions which, when executed on at least one processor, cause the at least one processor to carry out the method performed by the first node.

According to a nlneth aspect of embodiments herein, the object is achieved by a computer program, comprising instructions which, when executed on at least one processor, cause the at least one processor to carry out the method performed by the second node.

According to a tenth aspect of embodiments herein, the object is achieved by a computer-readable storage medium, having stored thereon the computer program, comprising instructions which, when executed on at least one processor, cause the at least one processor to carry out the method performed by the second node.

By the second node sending and the first node obtaining the first indication, the first node may be enabled to determine the probability of occurrence of the event in the communications system, based on the definition of the event provided by the second node, that is, dynamically and flexibly, with a same general approach. Advantageously, a user of the second node is enabled to define any set of events of interest. By the first node determining the probability of occurrence of the event in the communications system during the first time period, predicting the survival probability profile of the event occurrence, the first node may gain insight on the degradation of the performance of the communications system over time with an approach where a modelling view of the degradation process of the communications system may be adopted. The degradation process of the performance of the communications system may be modeled through a reliability modelling technique. That is, the first node may be able to determine how the event occurrence probability may change over a future time duration of interest. This may be understood to provide a view on the progression of the degradation of the performance of the communications system over time, which may be understood to be contextual to the use case. The fitted survival model may be understood to capture the degradation behavior of the communications system from normal to an alarmed state. The first node may thereby be enabled to bring out a dynamic profiling of the probability of occurrence of the event and thus may provide a view on the progression of the degradation of the performance of the communications system over time with respect to aspect(s) that may be contextual to the use case.

The first node may then be enabled to send the another Indication to the second node, and/or the another node, and in turn enable at least one of them to take action to address the predicted occurrence of the event, ahead of the occurrence of the event, so that the event may be prevented or its potential adverse effects, mitigated.

BRIEF DESCRIPTION OF THE DRAWINGS

Examples of embodiments herein are described in more detail with reference to the accompanying drawings, and according to the following description.

Figure 1 is a schematic diagram illustrating two non-limiting embodiments, in panel a) and panel b) a communications system, according to embodiments herein.

Figure 2 is a flowchart depicting a method in a first node, according to embodiments herein. Figure 3 is a flowchart depicting a method in a second node, according to embodiments herein.

Figure 4 is a flowchart depicting a method in a communications system, according to embodiments herein.

Figure 5 is an illustration of a probability profile plot, according to embodiments herein.

Figure 6 is a schematic diagram of a non-limiting example of a method in a communications system, according to embodiments herein.

Figure 7 depicts an example of a survival probability profile, according to embodiments herein. Figure 8 is a schematic diagram of another non-limiting example of a method in a communications system, according to embodiments herein.

Figure 9 is a schematic block diagram illustrating two non-limiting examples, a) and b), of a first node, according to embodiments herein.

Figure 10 is a schematic block diagram illustrating two non-limiting examples, a) and b), of a second node, according to embodiments herein.

Figure 11 is a schematic block diagram illustrating two non-limiting examples, a) and b), of a communications system, according to embodiments herein.

DETAILED DESCRIPTION

Certain aspects of the present disclosure and their embodiments may provide solutions to the challenges discussed earlier. There are, proposed herein, various embodiments which address one or more of the issues disclosed herein.

In telecommunications, network health monitoring and prediction of events that may impact functionality and quality of network service, may be understood to be critically important. Different KPIs may capture different aspects of a network health, namely, availability, accessibility, retainability, integrity, mobility etc. and many KPIs reflecting these aspects of network health may be predictable by their inherent nature. For example, a set of such predictable KPIs may be PRB utilisation, DL throughput, UL-RSSI, call drop rate, CSSR, packet loss rate, SSSR, SSAR, ULUT, DLUT, LAT_DL, ERAS, handover success rate etc. The health of a network may be understood via events defined based on these predictable KPIs and hence prediction of occurrence of these events a priori may bring a unique scope of proactive intervention resulting in a smoothly running network.

Embodiments herein may be understood to be drawn, in generai, to solving the general problem of event prediction based on predictable KPIs, where an event may be flexibly defined in terms of predictable KPIs as per requirement of any use case.

When an event of interest is identified, domain knowledge may provide a direction to identify relevant covariates that may hoid information on the occurrence pattern of the event as well and may help to build a better solution to an event a prediction problem.

More particularly, embodiments herein may be understood to be drawn to event prediction in telecommunications using a reliability-based approach and network performance prediction at a ceil duster level. A reliability-based approach may be understood as fitting a survival function.

Some of the embodiments contemplated will now be described more fully hereinafter with reference to the accompanying drawings, in which examples are shown, in this section, the embodiments herein wili be illustrated in more detail by a number of exemplary embodiments. Other embodiments, however, are contained within the scope of the subject matter disclosed herein. The disclosed subject matter should not be construed as limited to only the embodiments set forth herein; rather, these embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art. It should be noted that the exemplary embodiments herein are not mutually exclusive. Components from one embodiment may be tacitly assumed to be present in another embodiment and it will be obvious to a person skilled in the art how those components may be used in the other exemplary embodiments.

Note that although terminology from LTE/5G has been used in this disclosure to exemplify the embodiments herein, this should not be seen as limiting the scope of the embodiments herein to only the aforementioned system. Other wireless systems with similar features, may also benefit from exploiting the ideas covered within this disclosure.

Figure 1 depicts two non-limiting examples, in panel a) and panel b), respectively, of a communications system 100, In which embodiments herein may be implemented, in some example implementations, such as that depicted in the non-limiting example of panel a), the communications system 100 may be a computer network, in other example implementations, such as that depicted in panel b), the communications system 100 may be implemented in a telecommunications network, sometimes also referred to as a cellular radio system, cellular network or wireless communications system. In some examples, the telecommunications network may comprise network nodes which may serve receiving nodes, such as wireless devices, with serving beams.

In some examples, the telecommunications network may for example be a network such as 5G system, or Next Gen network or an Internet service provider (ISP)-oriented network.

The telecommunications system 100 may also support other technologies, such as a Long- Term Evolution (LTE) network, e.g. LTE Frequency Division Duplex (FDD), LTE Time Division Duplex (TDD), LTE Half-Duplex Frequency Division Duplex (HD-FDD), LTE operating in an unlicensed band, Wideband Code Division Multiple Access (WCDMA), Universal Terrestrial Radio Access (UTRA) TDD, GSM/Enhanced Data Rate for GSM Evolution (EDGE) Radio Access Network (GERAN) network, Ultra-Mobiie Broadband (UMB), EDGE network, network comprising of any combination of Radio Access Technologies (RATs) such as e.g. Multi- Standard Radio (MSR) base stations, multi-RAT base stations etc., any 3rd Generation Partnership Project (3GPP) ceiiular network, Wireless Local Area Network/s (WLAN) or WiFi network/s. Worldwide Interoperability for Microwave Access (WiMax), IEEE 802.15.4-based low-power short-range networks such as IPv6 over Low-Power Wireless Personal Area Networks (6LowPAN), Zigbee. Z-Wave, Bluetooth Low Energy (BLE), or any cellular network or system. A plurality of nodes may be comprised in the communications system 100, whereof a first node 111, a second node 112, and another node 113, 114 are depicted in Figure 1.

The another node may be any of a third node 113 and a fourth node 114

Any of the first node 111, the second node 112, the third node 113, and the fourth node 114 may be understood, respectively, as a first computer system or server, a second computer system or server, a third computer system or server, and a fourth computer system or server. Any of the first node 111, the second node 112, the third node 113 and the another node 114, may be implemented as a standalone server in e.g., a host computer in the cloud 115. In other examples, any of the first node 111, the second node 112, the third node 113 and the fourth node 114 may be a distributed node or distributed server, such as a virtual node in the cloud 115, and may perform some of its respective functions locally, e.g., by a client manager, and some of its functions in the cloud 115, by e.g., a server manager. In other examples, any of the first node 111, the second node 112, the third node 113 and the fourth node 114, may perform its functions entirely on the cloud 115, or partially, in collaboration or collocated with a radio network node. Yet in other examples, any of the first node 111, the second node 112, the third node 113 and the fourth node 114, may also be implemented as processing resource in a server farm. Any of the first node 111, the second node 112, the third node 113 and the fourth node 114, may be under the ownership or control of a service provider, or may be operated by the service provider or on behalf of the service provider.

The first node 111, may be, e.g., a first core network node in a core network, which may be e.g., a 3GPP SBA based 5GG core network, which may have a capability to determine, e.g., derive or calculate, one or more machine-learning models.

The second node 112 may be understood as a node which may be interested in predicting a probability of occurrence of an event in the communications system 100. The second node 112 may be a second core network node in the core network of the communications system 100, or a node managed by e.g., an operator of the communications system 100.

The third node 113 may be understood as a third core network node In the communications system 100, which may store historical information on the operations of the communications system 100. The third node 113 may be e.g., a database.

The fourth node 114 may be understood as a fourth core network node in the communications system 100, which may also have an interest in the probability of occurrence of the event in the communications system 100. For example, the fourth node 114 may a node responsible for taking action in order to prevent the event from happening or to counteract its occurrence In some examples, any of the first node 111, the second node 112, the third node 113, and the another node 114 may be co-located, or be the same node. In typical embodiments, however, the first node 111, the second node 112, the third node 113, and the another node 114 may be iocated in separate locations geographically.

The communications system 100 may comprise one or more radio network nodes, whereof a radio network node 120 is depicted in Figure 1b. The radio network node 120 may typically be a base station or Transmission Point (TP), or any other network unit capable to sorve a wireless device or a machine type node in the communications system 100. The radio network node 120 may be e.g., a 5G gNB, a 4G eNB, or a radio network node in an alternative 5G radio access technology, e.g., fixed or WiFi. The radio network node 120 may be e.g., a Wide Area Base Station, Medium Range Base Station, Local Area Base Station and Home Base Station, based on transmission power and thereby also coverage size. The radio network node 120 may be a stationary relay node or a mobile relay node. The radio network node 120 may support one or several communication technologies, and its name may depend on the technology and terminology used. The radio network node 120 may be directly connected to one or more networks and/or one or more core networks.

The telecommunications network may cover a geographical area, which in some embodiments may be divided into cell areas, wherein each cell area may be served by a radio network node, although, one radio network node may serve one or several cells, in the example of Figure 1 , the telecommunications network comprises a plurality of ceils 130, and the radio network node 120 serves a cell 131. The radio network node 120 may be of different classes, such as, e.g., macro eNodeB, home eNodeB or plco base station, based on transmission power and thereby also cell size. In some examples, the radio network node 120 may serve receiving nodes with serving beams. The radio network node may support one or several communication technologies, and its name may depend on the technology and terminology used. Any of the radio network nodes that may be comprised in the communications network 100 may be directly connected to one or more core networks.

The communications system 100 may comprise a device 140. The device 140 may be a UE or a Customer Premises Equipment (CPE) which may be understood to be enabled to communicate data, with another entity, such as a server, a laptop, a Maehine-to-Maehine (M2M) device, device equipped with a wireless interface, or any other radio network unit capable of communicating over a wired or radio link in a communications system such as the communications system 100. The device 140 may be also e.g., a mobile terminal, wireless device, wireless terminal and/or mobile station, mobile telephone, cellular telephone, or laptop, just to mention some further examples. The device 140 may be. for example, portable, pocket- storable, hand-held, computer-comprised, a sensor, camera, ora vehicle-mounted mobile device, enabled to communicate voice and/or data, via a RAN, with another entity, such as a server, a laptop, a Personal Digital Assistant (PDA), or a tablet computer, sometimes referred to as a tablet with wireless capability, or simply tablet, a Machine-to-Machine (M2M) device, a device equipped with a wireless interface, such as a printer or a file storage device, modem, Laptop Embedded Equipped (LEE), Laptop Mounted Equipment (LME), USB dongles or any other radio network unit capable of communicating over a wired or radio link in the communications system 100. Any of the devices in the plurality of client computing devices 120 may be enabled to communicate wirelessly in the communications system 100. The communication may be performed e.g., via a RAN and possibly one or more core networks, comprised within the communications system 100. The device 140 may have a capability to collect data about an event over time.

The first node 111 may communicate with the second node 112 over a first link 151, e.g., a radio Sink or a wired Sink. The first node 111 may communicate with the third node 113 over a second link 152, e.g., a radio link or a wired iink. The third node 113 may communication with any of the one or more ceils 120 over a respective third link 153, e.g., a radio link. The first node 111 may communicate with the fourth node 114, over a fourth iink 154, e.g., a radio link or a wired link. The radio network node 120 may communicate with the third node 113 over a fifth iink 155, e.g., a radio link or a wired link. The radio network node 120 may communicate with the device 140 over a sixth link 15S, e.g., a radio link. Any of the respective first link 151 , the second iink 152, the respective third iink 153, the fourth link 154, the fifth link 155 and the respective sixth link 156 may be a direct iink or it may go via one or more computer systems or one or more core networks in the communications system 100, or it may go via an optional intermediate network. The intermediate network may be one of, or a combination of more than one of, a public, private or hosted network; the intermediate network, if any, may be a backbone network or the internet, which is not shown in Figure 1.

In general, the usage of “first”, “second”, “third”, “fourth”, “fifth” and/or “sixth”, herein may be understood to be an arbitrary way to denote different elements or entities, and may be understood to not confer a cumulative or chronological character to the nouns they modify.

Generally, ail terms used herein are to be interpreted according to their ordinary meaning in the relevant technical field, unless a different meaning is clearly given and/or is implied from the context in which it is used. Ai! references to a/an/the element, apparatus, component, means, step, etc. are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, step, etc., unless explicitly stated otherwise. The steps of any methods disclosed herein do not have to be performed in the exact order disclosed, unless a step is explicitly described as following or preceding another step and/or where it is implicit that a step must follow or precede another step. Any feature of any of the embodiments disclosed herein may be applied to any other embodiment, wherever appropriate. Likewise, any advantage of any of the embodiments may apply to any other embodiments, and vice versa. Other objectives, features and advantages of the enclosed embodiments will be apparent from the following description.

Although terminology from Long Term Evolution (LTE)/5G has been used in this disclosure to exemplify the embodiments herein, this should not be seen as limiting the scope of the embodiments herein to only the aforementioned system. Other wireless systems, supporting similar or equivalent functionality may also bene® from exploiting the ideas covered within this disclosure. In future radio access, e.g., in the sixth generation (6G), the terms used herein may need to be reinterpreted in view of possible terminology changes in future radio access technologies.

Several embodiments are comprised herein. It should be noted that the examples herein are not mutually exclusive. Components from one embodiment may be tacitly assumed to be present in another embodiment and it will be obvious to a person skilled in the art how those components may be used in the other exemplary embodiments.

Embodiments of a method, performed by the first node 111, will now be described with reference to the flowchart depicted in Figure 2. The method may be understood to be for handling a prediction of an event. The first node 111 may operate in the communications system 100.

The method may comprise the actions described below. In some embodiments, some of the actions may be performed. In some embodiments, all the actions may be performed. In Figure 2, optional actions are indicated with a dashed box. One or more embodiments may be combined, where applicable. Ail possible combinations are not described to simplify the description. It should be noted that the examples herein are not mutually exclusive. Components from one example may be tacitly assumed to be present in another example and it will be obvious to a person skilled in the art how those components may be used in the other examples.

Action 201 in the course of operations of the communications system 100, it may be of interest to supervise the performance of the communications system 100 and determine the probability of occurrence of an event in the communications system 100. An event may be understood as a scenario where a value of a specific indicator of performance of the communications system 100, such as a KPI, or a similar parameter, may lie in a set defined by a user, e.g., KPI > some threshold or KPI < some threshold or KPI belongs to an Interval or a collection of intervals so as to represent certain behaviour of the communications system 100. The following are some examples of events in specific use case scenarios of the communications system 100. A first example of an event may be a transformation of a status of a ceil from active cell into sleeping cell. The probability to be predicted by the first node 111 may in that case be a probability profile of a sleeping state of a cell getting triggered in the next ‘h’ hours. Covariates of this variable, that is. variables which may eo-vary, or vary similarly, in time, may be KPIs such as Random Access attempts and/or success, DL UE and/or cell throughout and RRC attempt count. Another example of an event may be a site outage, in which case what may be desirable to predict may be understood to be the time that may remain from a current time until the next outage may happen, A variable which may be a covariate of a site outage may be historical load data. Another event may be battery failure. In this case, it may be desirable to predict when the next battery failure may happen. Another event may be alarm prediction. In this case, a wide range of KPIs may serve as covariates, such as number of connected users, software versions in the node, throughput etc. Yet another example of event may be an emergence of a ceil maintenance activity. Particularly, it may be of interest to predict maintenance, e.g., upgrade/repair and/or replacement, Expected Time of Arrival (ETA) of telecommunications equipment, e.g., an antenna or a cable.

The event of interest may be typically expressed as a KPi meeting a condition that may flag an event occurrence which may be of interest to predict. For example, an event may be defined as { DL__Throughput < some low value }, such as, e.g., di__throughput < 10, that is, a bad dMihroughput scenario.

In embodiments herein, the second node 112 may be a node having an interest in knowing the probability of occurrence of a certain event. The second node 112 may, for example, oversee at least some aspect of the performance of the communications system 100, and may define the event, as will be explained later, in relation to Figure 3. In this Action 201 , the first node 111 may obtain, from the second node 112 operating in the communications system 100, a first indication. The first indication is of an event the probability of occurrence of which is to be predicted by the first node 111. The event is indicative of a performance of at least a part of the communications system 100.

The receiving in this Action 201 may be impiemented through a peer-to-peer, or broadcast, protocol, e.g., via the first link 151.

The first indication may be, for example, input via an Application Programming Interface

(API).

The part of the communications system 100 may be, forexamp!e, an entity, component, cell, region, function, etc... In some embodiments, with the proviso that the event is an indicator of performance of the communications system 100 exceeding or being lower than a first threshold, the first indication may further indicate the first threshold. To illustrate this with the example provided above wherein the event is e.g., dl_throughput < 10. according to the first option, the first indication may indicate the first threshold as 10.

In some embodiments, the obtaining in this Action 201 may further comprise obtaining a second indication. The second indication may indicate at ieast one of the following. According to a first option, the second indication may indicate a second threshold. The second threshold may indicate a value of the probability of occurrence of the event that, when exceeded by the probability of occurrence determined by the first node 111, is to trigger the sending of another indication to the second node 112, or to another node 113, 114, as will be described in Action 205. The another indication may be understood as a notification that the second threshold has been exceeded. The second threshold may be understood as a limit on the notifications the second node 112 may wish to obtain, in other words, as the trigger for the notification. The second threshold may be understood as a probability threshold. That is, a threshold value of probability of the occurrence of the event beyond which an a-priori intervention may be planned. For example, if the estimated Prob(DL_Throughput < a small value) > 0.7 in the next 48 hours, then an inspection may be scheduled a priori by the second node 112. In this example, 0.7 is the probability threshold. This may be understood to enable the second node 112 to define the probability threshold probability threshold relevant to the use case, so as to flag a possible health disruption in the communications system 100 when the predicted event occurrence probability surpasses the threshold. Hence, provision of the second indication may enable the second node 112 to tune the call out facility of a probable performance red flag. Thus, by obtaining the second indication according to the first option, the first node 111 may then be enabled to suppress low level output details and enable that important scenarios surface, through alert generation in Action 205, as per the interest of the second node 112.

According to a second option, the second indication may indicate, e.g., identify, variables having a possibility to co-vary with the first variable defining the event. These variables may also be referred to herein as covariates. Covariates may be understood as variables that may be related with the variable of interest that may define the event, and which is referred to herein as the first variable. Covariates may be time dependent and time independent variables, such as ancillary variables that may be understood to depend on the environment. Covariates may commonly comprise data which may be related with the KPi based on which the event of interest may be constructed. For example, while modelling a throughput-based event, data on PRB utilization may be a potential covariate. There may be more than one covariate as well. However, a eovariate may come from an externa! source such as environmental data, e.g,, temperature, humidity etc.,

According to a third option, the second indication may indicate the plurality of ceils 130 operating in the communications system 100 within a selected area, at a level of which the probability of occurrence is to be determined, as will be described later.

By obtaining the first indication in this Action 201 , the first node 111 may be enabled to determine the probability of occurrence of the event in the communications system 100 in Action 204, based on the definition of the event provided by the second node 112.

Flexibility may thereby be provided to a user to pre define a confidence, as the second threshold, so as to facilitate that, for example, an alarm is generated only when the probability of the event, such as a possible disruption of the stability of the communications system 100, may cross the pre-specified confidence level. This probability of occurrence of the event may then be output from the model as a probability profile in Action 204, as will be described later.

Obtention of the second indication according to the first option may be understood to enable enhanced support for strategic decision making. The second node 112 may be enabled to prioritize event occurrence by using an event specific threshold, depending on the event importance. Hence, a strategic decision on prioritization of predictive maintenance may be automated with ease.

By obtaining the second indication according to the second option, the first node 111 may be enabled to perform a more accurate analysis of the probability of occurrence of the event.

Action 202 in this Action 202, the first node 111 may retrieve data from the third node 113 operating in the communications system 100. The data may comprise observed data from the components of the communications system 100. The observed data may be understood to be indicative of the indicated event.

The retrieving in this Action 202 may be implemented via the second link 152. Nevertheless, there may be examples wherein the third node 113 may be co-!ocalized or be the same node as the second node 112. In such examples, the retrieving in this Action 202 may be implemented via the first link 151.

The retrieving of the data in this Action 203 may be based on the obtained first indication and/or second indication. That is, based on the obtained first and second indications the first node 111 may, in this Action 202, transfer data related to identified, as well as collect covariates, as indicated by the second node 112. Additionally, or alternatively, the retrieved data may be forth© indicated plurality of ceils 130, according to the third option of the second indication,

By retrieving the data in this Action 202, the first node 111 may then be enabled to analyze it in Action 204 to determine the probability of occurrence of the event in the communications system 100 in Action 204.

Action 203

Once the first node 111 may have retrieved the data, the first node 111 may, in this Action 203, process the retrieved data. This may be done in order to align the data with a predictive model used for determining the probabiiity of occurrence of the event in the communications system 100 in the next Action 204. in other words, the first node 111 may transform the data to fit a survival analysis paradigm, and this may be performed by, for example, transferring data related to the identified event into binary event data. Following the example provided earlier wherein the event of interest may be defined as di__throughput < 10, the first node 111 may need to transform or convert ali instances of dljtiroughput < 10 as 1 and 0 otherwise.

Although this transformation may have some use case specific aspects, two major features to be constructed in general may be a time interval between events and any representation of censoring in the data. The first aspect may comprise to identify a sequence of occurrence of an event defined by the second node 112 in the data and construct a feature that may capture a time interval between events. A feature may be understood as specific information that may need to be extracted from the data which may otherwise be implicit. This duration may be represented in terms of time units, wherein a time unit may be measured as the time granularity considered. For example, if the time granularity being considered is 15 minutes, which corresponds to 1 time unit, and the time difference between two successive events is one hour, the time difference may be considered to be 4 units. That is, 1 hour - 4 blocks of 15 minute each.

Regarding the second aspect, censoring may be understood as a discontinuation of observance of an event due to circumstantial intervention that may eventually happen. The identification of censoring phenomenon may be understood to be relevant. For example, if the data comprises cell maintenance notification data, since notification may be understood to be an ongoing process, any data observed up to the next maintenance date may be understood to be considered as censored data since the view of the data may be understood to be interrupted.

Accordingly, in some embodiments, in this Action 203, the processing may be performed by identifying censoring in the retrieved data. In other words, the first node 111 may transform the data to align with reliability paradigm by identifying censoring in the data. The identification of censoring in the retrieved data may be understood to be use case specific. In a data set, the last observed time point may serve as the censoring time point. Typically, it may be assumed that if the data collection continues, the event will be observed again in the future, and between the last observed event and the next yet to be observe event, the eventual intervention, in general the data collection, may happen and hence a censoring phenomenon may be observed.

After identification of censoring, it may be accommodated in the input KPI data stream and the input data stream fed into the reliability modelling module.

Reliability modelling approaches may need the censoring information to be processed with the input data to make the model and hence probability profiling more accurate.

The introduction of the notion of censoring in the data transformation step may be understood to be unique to the reliability-based approach which is not present in other approaches. Censoring may be understood to address event occurrence more fundamentally and hence may bring out the degradation aspect of the performance of the communications system 100 in the modelling process.

By processing the data in this Action 203, the first node 111 may then be enabled to analyze it in Action 204 to determine the probability of occurrence of the event in the communications system 100 in Action 204 and determine the probability with a higher degree of accuracy. The first aspect of processing the retrieved data to align the data with the predictive model used for the determining may be necessary for the reliability model construction. The raw data may not have a natural description of the event the probability of which may be being modelled, as it may have been defined by the user. Hence, it may be necessary to identify the occurrence e.g,, as 1s, and the non-occurrence, e.g., as 0s, of the event corresponding to the input data stream corresponding to each data point, and hence process the same.

By identifying censoring in the retrieved data the first node 111 may then be enabled to process the censoring information with the input data to make the mode! and hence the probability profiling more accurate.

Action 204 in this Action 204, the first node 111 determines the probability of occurrence of the event in the communications system 100 during a first time period.

Determining may be understood as calculating, deriving, or similar. The determining in Action 204 may be performed by analyzing the retrieved data in Action 202. The first time period may be understood to be a future time period that may be of interest, e.g., to the second node 112. in some examples, the first node 111 may have obtained a further indication from the second node 112 indicating the first time period that may be of interest.

The determining in this Action 204 is based on estimating a probability of survival over time of the event, defined by a first variable. In the non-limiting illustrative example, the first variabie is “dl_throughput. The determining in Action 204 may be performed based on the obtained first indication, indicating the first threshold, e.g., based on dl- t hroughpu t < 10.

A probability of survival at some future time point t may be understood as the probability that the corresponding event will not happen until time point t from the current time point to. Hence if we define an event e - KPI > threshold, then probability of survival corresponding to the event e at time point t = P(KPI < threshold till time point t given that the current time point is to).

The determining in this Action 204 is based on estimating the probability of survival over time of the event, defined by the first variable, via reliability modelling. That is, in this Action 204, the first node 111 may predict the event through reliability modelling. Reliability modelling may be understood as fitting a mode! to compute the probability of survival using past data of occurrences of the event, and possibly of a set of covariates.

For example, the determining in this Action 204 may comprise fitting a survival model to capture the degradation behavior of the communications system 100 from a norma! to an alarmed state. Fitting of the survival model according to this Action 204 may comprise the following steps.

Fit the survival model through estimation of a hazard function

Reliability-based modelling may comprise estimation of a hazard function. First, the first node 111 may estimate a hazard function which may capture the degradation in the performance of the communications system 100 mathematically. There may be understood to be a wide array of techniques that may be selected to estimate the hazard function, ranging from statistical models, such as parametric models, semi-parametric models, and/or non- parametric models, to Machine Learning (ML) models, such as survival forest and DL applications, e.g., non-parametric. A few examples of such statistical models may be found in references 17-21. A few examples of such ML models may be found in references 5-8. This richness in the reliability field may be understood to represent an advantage while implementing, since there may be ample choices of models fitting to different use case scenarios. For example, in a scenario with limited data, a parametric model may be chosen, and in a scenario with rich data, the first node 111 may opt for ML modeis. Accordingly, the model for h(t) above may be replaced by any suitable model and estimation procedure. For example, a Weibull distribution-based model and Recurrent Neural Network (RNN)-based approach for estimating Weibull distribution. For illustration purposes, a Cox proportional hazard model is used herein.

The Hazard function h(t) may be formulated based on both time dependent and time independent variables, e.g,_s X and X* below, according to a Cox proportional hazard modet

wherein hO(t) may be a base hazard function chosen appropriately.

The first node 111 may know that H(t):

where H(t) - Cumulative Hazard Rate.

After this first step, the first node 111 may have determined, with past event data, the time points where the event occurred, the time interval between successive events and the censoring, if any, took place.

Second, fitting may comprise that the first node 111 utilizes the hazard function to estimate a cumuiative hazard. That is, the first node 111 may calcuiate the distribution of probabiiities of the event over time, taking into account how this may be affected by the occurrence of the event at an earlier time point.

Third, the fitting may comprise estimating a survival probability using the cumuiative hazard. In other words, the first node 111 may estimate the probability of the next event to happen in a future time duration using the cumulative hazard function.

In estimating the survival probability of the event, the first node 111 may consider the covariates indicated by the second node 112. That is, the determining 204 may be performed based on the obtained second indication, according to the second option.

The first node 111 may then, as part of this Action 204, estimate the probability profile of survival of the event over the first time period, that is, a future time duration of interest, e.g., next week, next “t” weeks etc.. Estimation of survival probability may be understood to be performed for a single future time point. When an increasing sequence of time pointe spanning a future time interval is considered, and a survival probability for each time point is calculated to portray how the survival probability may change over a future time interval, the result may be understood as a probability profile.

The first node 111 may estimate the probability profile, according to the following:

Probability Profile ~ P(the event will not occur fill time ~ t) ~ exp(-H(t))

Based on the foregoing, the first node 111 may compute the survival probability profile, and determine the second threshold, either by computing it itself, or based on the second indication obtained from the second node 112, and may then transferthe estimated probability profile to the event prediction alert by comparing the transferred probability profile with the second threshold. The determining in Action 204 may therefore be performed based on the obtained second indication. The second threshold used by the first node 111, may be understood as a probability threshold relevant to the use case, to raise a flag for the occurrence of an event based on a comparison of a survival probability profile and the proposed threshold. If the estimated probability is larger than the second threshold, the event is likely to occur. Otherwise, it may be considered as being unlikely. As explained earlier, by determining the probability of occurrence of the event in the communications system 100 based on the second threshold, the first node 111 may be enabled to generate an alert so that only the scenario of interest may surface, suppressing any other non-interesting output details.

The estimation of a probability profile may be understood to provide a progressive view of how the chance of an event to occur may change, e.g., increase, over a next few future time points. The threshold here may indicate the maximum stretch up to which the probability of occurrence of the event may be considered ignorabie, in a loose sense. When the predicted survival probability crosses the threshold, that is, when some member in the probability profile, and hence each subsequent members, crosses the threshold, the stake of ignoring it may be understood to become prohibitive, in terms of severity of impact, and hence it may serve for an alert. Typically, some proactive action may be intended to be performed before the first time point in the probability profile corresponding to which the estimated survival probability crosses the threshold.

Extension of ceil level event prediction to cluster of cell level performance prediction in some embodiments, the probability of occurrence may be determined at a level of a cell, such as the cell 131, operating in the communications system 100. That is, for example, the prediction of the event may define a fault as a probability of occurrence of the event exceeding the second threshold, which may be defined by a user, such as the second node 112, at the level of the cell 131. The cell 131 may be considered as an entity.

The approach may be extendible from the health monitoring at the cell level to health monitoring at a level of cluster of cells and may therefore provide an opportunity for broader monitoring and control. That is, in some embodiments, the prediction of the performance of the communications system 100 may be extended to at a collective level, such as to a cluster of cells, by extending the prediction of the event at the cell level to a prediction of performance at a cluster of cell level. Accordingly, in some embodiments, the probability of occurrence may be determined at a level of the plurality of cells 130 operating in the communications system 100 within a selected area. The plurality of cells 130 may be understood as a duster. From cell level reliability model, the chance of dysfunction of the cell 131 may be known. A region may be understood as a combination of e.g., 'K' cells. The first node 111 , or the second node 112, may need to identify the plurality of cells 130, based on the given use case whose performance monitoring may be planned, and specify the number of cells in the cluster that may need to work properly to define an acceptable duster level performance. The individual cell level performance prediction may then be combined using a probabilistic approach to derive a formula to determine a dynamic probabilistic performance profile, that is, the chance that the performance of the at the level of the plurality of cells 130 is satisfactory for a future duration of interest. If the plurality of cells 130 is indicated by the second node 112, the determining 204 may therefore be performed based on the obtained second indication, according to the third option.

To extend the cell level event prediction to the duster cell level performance prediction, it may be assumed that the performances of the cells in the plurality of cells 130 are independent from each other. Then, for example, the event that the cell 131 dysfunctions in next day may be mapped to a coin and head. The probability of head may be understood to be available from the reliability models at the cell level. Next, Y may be defined as Y = number of ceils dysfunction in next day = number of heads from 'K' trials. It may be noted that the trials may be independent but not identical, meaning that the chance of head in each trial may have a possibly of having a different probability. That is, a different chance of dysfunction for every different cell. The probability of a problem to appear at an individual ceil level may be estimated as a probability profile via the fitted cell level reliability model. This probability distribution of Y may be understood to be known and may be computed given the individual probability of heads. The second node 112 may have provided the second indication to specify the second threshold, collectively for a cell cluster, which may be referred to herein as a third threshold, of an allowable limit on degradation of the performance of the total number cells, for example = n_0. 1. There are e.g., N ceils in the cluster. For each ceil, the event may have been defined and a respective second threshold. When the estimated survival probability crosses the second threshold, a possible ‘failure’ may be alerted to occur. That is, the chance that the cell will perform poorly as the chance of the event to occur is high enough. Collectively for the cluster, another threshold, the third threshold, may be defined as n_G which may be understood as the number of acceptable poorly performing cells. When the estimated probability of the event “number of cells to perform poorly is more than n_0” is high enough, the cluster may be predicted to perform poorly. The third threshold may be understood to indicate that the estimated probability of the event “ number of ceiis to perform pooriy is more than n_J3” is high enough, that is, that it exceeds the third threshold The first node 111 may then estimate, using the probability distribution, the chance of observing at most n_0 heads the next day. Then, the first node 111 may compute the same for the next 'h' days and create a probability profile of the health of the communications system 100 in the region. The node receiving an indication on the resuit of the determination in this Action 204, as will be described later in Action 205, may then be enabled to take a strategic decision fora timely intervention, in order to keep the communication system 100 in the region performing smoothly.

Time interval granularity

The first node 111 may determine a granularity of the first time period, that is, a time interval such as week or month etc, dynamically, based on a time series analysis of the failure data, that is, the retrieved data, processed to align the data with the predictive model used for determining, e.g., the binary transformed KPI data where the KPI data may be expressed as a sequence of event occurrence, or 1 , and non-occurrence, e.g., 0. The first node 111 may need to identify an appropriate time granuiarity for data aggregation. For example, a ROP file collected from the radio network node 120 may have a granularity as low as 15 minutes, whereas the KPI aggregation may make sense at an hourly level, since corrective action may need an hour advance prediction. In such a scenario, hourly level aggregation may be understood to be more relevant. Similarly, if a response is needed at a day level, the first node 111 may tune data aggregation and model building at the day level, so that event prediction may be performed a day in advance to accommodate enough time to plan a proactive action, in another scenario, sheer data volume at low time granularity may trigger the need of aggregation at a higher time granularity. That is, if a fine time granularity is used, it may lead to a iot of data. For example, data observed at minute level may result with 60 data points per hour and hence 2400 data points per day. If the event appears at week level, that is, once or twice weekly, then the event sequence data after binary transformation may be sparse, that is, lots of ^eros and very few ones, leading to model estimation difficu!ty. Hence, a re-scaling to hourly or higher level, that is, to aggregation, may handle this issue.

The problem of predicting health of the communications system 100 may comprise framing as a survival probability estimation problem and may be solved according to embodiments herein by utilising a reliability modelling technique.

By the first node 111 determining the probability of occurrence of the event in the communications system 100 during the first time period, predicting the survivai probabiiity profile of the event occurrence, the first node 111 may gain insight on the degradation of the performance cf the communications system 100 over time. That is, the first node 111 may be able to determine how the event occurrence probability may change over a future time duration of interest. This may be understood to provide a view on the progression of the degradation of the performance of the communications system 100 overtime, captured through the predictable KP!s, which may be understood to be contextual to the use case. The fitted survival model may be understood to capture the degradation behavior of the communications system 100 from normal to an alarmed state.

Furthermore, by the first node 111 modelling the process of degradation of the communications system 100, by fitting a reliability model on any predictable KPI data, the problem may be addressed directly from a perspective of system behavior, rather than transferring it into a known problem of regression/classification/anomaly detection, and hence avoids any lack of explicabiiity. It may be understood that regression and classification output cannot be directly translated to perceive how the probability of the event occurrence may be increasing over time as a result of the system degrading over time.

In the case of the reliability model, the first node 111 may start with modelling of the hazard rate which may be understood as a mathematical representation of the degradation of the underlying data generating system over time. Hence, the estimated survival probability profile of the event, derived from the modelled hazard function, may be interpreted as a result of the system degradation patern overtime. Thus, the probability of the event occurrence progression overtime may be quantified through the estimated survival probability profile.

Action 205

In this Action 205, the first node 111 sends another indication, which may be understood as a third indication, to the second node 112, or the another node 113, 114 comprised in the communications system 100. The another indication indicates the determined probability of occurrence of the event over a second time period.

As output of the determination of Action 204, the first node 111 may indicate in this Action 205, the reliability based model(s) along with the determined probability profile of the occurrence of the event through the second time period, that is, a future time duration of interest.

In particular examples, the another indication may be, for example, an alert.

In typical embodiments, the first time period may be the same time period as the second time period. However, this may not necessarily be the case, in other embodiments, the second time period may be different than the first time period and may have a selected level of granularity.

The sending in this Action 304 may be implemented through a peer-to-peer, or broadcast, protocol, e.g., via the first link 151 , the second link 152 and/or the fourth link 154. in some embodiments, the sending of the another indication in this Action 205 may be performed based on the determined probability of the occurrence of the event exceeding the second threshold. This may enable the first node 111 to set up an alarm on the event, and provide an alert for any of the second node 112 and/or the another node 113, 114, only when the scenario of interest may surface, suppressing any other non-interesting output details,

The second threshold may be understood as the probability threshold relevant to the use case, to raise a flag for the occurrence of the event based on a comparison of a survival probability profile and the proposed threshold. For example, if the estimated probability is larger than threshold, the event is likely to occur. Otherwise, it may be considered as being unlikely. For example, in the illustrative example used herein, of dLthroughpui < 10, the first threshold may be 10, and the second threshold may be, e.g., 0.8. Hence, the first node 111 may alert the second node 112 and/or the another node 113, 114 only when such a scenario may surface. Following the illustrative example, only when there may be an 80% probability that the dLthroughput may be lower than 10.

The sending in this Action 205 may be performed based on the obtained second indication, according to one or more of the first option, the second option and/or the third option. That is, based on the event as defined by the first threshold, based on the second threshold, the covariates, and/or based on the indicated plurality of cells 130.

The first node 111 may then enable the second node 112, and/or the another node 113,

114 to make a strategic decision. For more than one event related to the communications system 100, such an analysis may enable the second node 112, and/or the another node 113, 114 to compare the probability of occurrence of different events and enable to perform a decision on prioritization of any corrective action. For example, if a more important event has a probability of occurrence similar to a less important event, corrective action for the important event may be prioritizes.

Embodiments of a method performed by the second node 112, will now be described with reference to the flowchart depicted in Figure 3, The method is for handling the prediction of the event. The second node 112 may operate in the communications system 100.

The method comprises the following actions. Several embodiments are comprised herein. One or more embodiments may be combined, where applicable. All possible combinations are not described to simplify the description. If should be noted that the examples herein are not mutually exclusive. Components from one example may be tacitly assumed to be present in another example and it will be obvious to a person skilled in the art how those components may be used in the other examples. In Figure 3, optional actions are represented in boxes with dashed lines.

The detailed description of some of the following corresponds to the same references provided above, in relation to the actions described for the first node 111 and will thus not be repeated here to simplify the description. For example, the another Indication may be an alert. Action 301

The second node 112 may be managed by a user, e.g,, an operator, of the communications system 100, The user, via the second node 112 may define or identify the event the occurrence of which it may want the first node 111 to predict based on the use case in order to for example manage the occurrence of an some aiarming behavior in the communications system 100 whenever it may surface. The aiarming behaviour may be, for example, a change in the status of a network feature. The non-occurrence of the change may be considered to be a normai scenario. For example, the increase in PRB utilization beyond 90% may be identified or defined as an event.

The second node 112 may, in this Action 301 send, to the first node 111 operating in the communications system 100, the first indication of the event the probability of occurrence of which is to be predicted by the first node 111. The event is indicative of the performance of at least a part of the communications system 100. The event may be indicated as defined by the user of the second node 111, based on the particular use case at hand.

The sending in this Action 301 may be impiemented through a peer-to-peer, or broadcast, protocol, e.g., via the first link 151.

In some embodiments, with the proviso that the event is an indicator of performance of the communications system 100 exceeding or being lower than the first threshold, the first Indication may further indicate the first threshold.

This flexibility of defining a use case specific event may be understood to allow the user to utilize the same framework and address multiple prediction problems, simultaneously or sequentially. Advantageously, the user of the second node 112 may be enabled to define any set of events of interest, for example, based on predictable KPI contextual to a certain problem and may supply related data.

The sending of the first indication in this Action 301 may be understood to have comprised to define the event to map with the reliability framework that may then be used by the first node 111 to determine the probability of occurrence of the event in Action 204. Reliability modelling may be understood to require definition of an event and event occurrence data, e.g., 1 for occurrence and 0 for non-occurrence, to start with. Hence, any data may be understood to have to be mapped with a reliability modelling framework with these two contexts.

In some embodiments, the sending in this Action 301 may further comprise sending the second indication indicating at least one of the following options. According to a first option, the second indication may Indicate the second threshold indicating the value of the probability of occurrence of the event that, when exceeded by the probability of occurrence determined by the first node 111, is to trigger the first node 111 to send the another indication to the second node 112 or to the another node 113, 114 comprised in the communications system 100. The second threshold indicated by the second indication may enable the second node 112 to set the condition for the occurrence of the event that may raise a flag, based on the comparison of the survival probability profile and the proposed second threshold, if the estimated probability is larger than the second threshold, the event is likely to occur and the second node 112 wants to receive a notification. Otherwise, the event may be considered as being unlikely, and the second node 112 may avoid receiving a notification.

According to a second option, the second indication may indicate variables having the possibility to co-vary with the first variable defining the event.

According to a third option, the second indication may indicate the plurality of cells 130 operating in the communications system 100 within the selected area, at a level of which the probability of occurrence is to be determined.

Action 302 in this Action 302, the second node 112 receives the another Indication from the first node 111. The another indication indicates the determined probability of occurrence of the event over the second time period, as determined by the first node 111. The another indication is based on the probability of survival overtime of the event, defined by the first variable, as determined by the first node 111 via reliability modelling.

In some embodiments, the another indication may be based on the sent first indication. That is on the event, e.g., as defined by the second node 112.

In some embodiments, the probability of occurrence may be indicated as being determined at the level of at least one of: a) the cell 131 operating in the communications system 100, and b) the plurality of cells 130 operating in the communications system 100 within the selected area.

The another indication may be based on the first threshold as indicated by the second node 112.

In some embodiments, the receiving in this Action 302 may be performed based on the determined probability of the occurrence of the event exceeding the second threshold.

In particular embodiments, the received another indication may be based on the sent second indication, according to the first option, comprising the second threshold.

The received another indication may be based on the sent second indication, according to the second option. That is, the another indication may be based on the covariates that may have been specified by the second node 112. The receiving in this Action 302 may be implemented through a peer-to-peer, or broadcast, protocol, e.g., via the first link 151.

Embodiments of a method performed by the communications system 100, will now be described with reference to the flowchart depicted in Figure 4. The method is for handling the prediction of the event. The communications system 100 comprises the first node 111 and the second node 112 operating in the communications system 100.

The method may comprise the following actions. Several embodiments are comprised herein. In some embodiments, some actions may be performed, in other embodiments, all actions may be performed. One or more embodiments may be combined, where applicable. AH possible combinations are not described to simplify the description. It should be noted that the examples herein are not mutually exclusive. Components from one example may be tacitly assumed to be present in another example and it will be obvious to a person skilled in the art how those components may be used in the other examples. In Figure 4, optional actions are represented in boxes with dashed lines.

The detailed description of some of the following corresponds to the same references provided above, in relation to the actions described for the first node 111 and the second node 112 and will thus not be repeated here to simplify the description. For example, the another indication may be an alert.

Action 401

This Action corresponds to Action 301 described earlier.

In this Action 401 , the first node 111 sends, by the second node 112 to the first node

111, the first indication of the event the probability of occurrence of which is to be predicted by the first node 111. The event is indicative of the performance of at least the part of the communications system 100,

With the proviso that the event is an indicator of performance of the communications system 100 exceeding or being lower than the first threshold, the first indication may further indicate the first threshold,

Action 402

This Action corresponds to Action 201 described earlier.

In this Action 402, the first node 111 obtains, by the first node 111 from the second node

112, the first indication.

In some embodiments, the sending in Action 401 may further comprise sending the second indication and the obtaining in this Action 402 may further comprise obtaining the second indication. The second indication may indicate at least one of the following. According to a first option, the second threshold. The second threshold indicating the value of the probability of occurrence of the event that, when exceeded by the probability of occurrence determined by the first node 111, is to trigger the sending in Action 406 of the another indication, to the second node 112 or to the another node 113, 114. According to another option, the second indication may indicate the variables having the possibility to eo-vary with the first variable defining the event.

Action 403

This Action corresponds to Action 202 described earlier.

In this Action 403, the first node 111 may retrieve the data from the third node 113 operating in the communications system 100. The data comprises the observed data from the components of the communications system 100. The observed data is indicative of the indicated event.

Action 404

This Action corresponds to Action 203 described earlier.

The first node 111, in this Action 404 may process the retrieved data to align the data with the predictive model used for the determining of the probability of occurrence of the event in Action 204 by identifying censoring in the retrieved data.

Action 405

This Action corresponds to Action 204 described earlier.

In this Action 403, the first node 111 determines the probability of occurrence of the event in the communications system 100 during the first time period. The determining is based on estimating the probability of survival over time of the event, defined by the first variable, via reliability modelling.

The determining in this Action 405, 204 may be performed by analyzing the retrieved data.

The determining in this Action 405 may be performed based on the first indication sent by the second node 112 and obtained by the first node 111. in some embodiments, one of the following may apply, in some embodiments, the first time period may be the same time period as the second time period. In other embodiments, the second time period may be different than the first time period and may have a seieeted fevei of granularity. The probability of occurrence may be determined by the first node 111 at a level of at least one of: a) the ceil 131 operating in the communications system 100, and b) the plurality of cells 130 operating in the communications system 100 within the selected area.

The determining in this Action 405 may be performed based on the obtained second indication.

Action 406

This Action corresponds to Action 205 described earlier.

In this Action 406, the first node 111 sends the another indication to the second node 112 or the another node 113, 114 comprised in the communications system 100. The another indication indicates the determined probability of occurrence of the event over the second time period.

In some embodiments, the sending in this Action 406 may be performed based on the obtained second indication.

The sending in this Action 406, 205 may be performed based on the determined probability of the occurrence of the event exceeding the second threshold.

Action 407

This Action corresponds to Action 303 described earlier.

In this Action 407, the second node 112 receives the another indication from the first node 111.

Figure 5 is an illustration of a probability profile plot for the non-limiting illustrative example used herein of the event being dLthroughput < 10. For illustration purposes, a Cox- proportional hazard model has been fit with one month of real dLthroughput data. At the outset, dLthroughput data is transferred, according to Action 404, 203, to the event occurrence sequence as 1 and 0. As a result dLthroughput < 10 is provided as an event occurrence and hence is coded as 1 , and 0 otherwise depicting no event. Thirty days of dLthroughput data have been considered, collected with a granularity of 15 minutes. The first variable considered here is user_dlthroughput observed during the same time duration. There may be any network KP! that may have a correlation with dLthroughput and those KP!s may be used as covariate in the model to enhance prediction accuracy. First, the first node 111 has, according to Action 405, 204, fit a simple Cox proportional hazard model based on 30 days of dLthroughput data and regressor data. Then, input data for future time points, corresponding to which the survival probability prediction may be required, may be supplied to the fitted model. This input data may comprise the future time points and also the covariate data if the model building itself was performed using covariate information. Considering this new regressor data point as the observed new data, the first node 111 has predicted the probability of next occurrence of the event corresponding to 6 future time points using the fitted model mentioned above. This is how the predicted probability profile, mentioned before, may be generated according to Action 204. The x-axis in the diagram of Figure 5 shows the next 6 time points after the test data point is observed, and the y-axis shows the probability of an event occurrence, that is. the probability that dM:hroughpu t < 10 in the corresponding 6 future time points. As the ROP file is 15 min, the difference between two consecutive time point is 15 min. it may be noted that the chance of the event happening is calculated at a 15-min interval level. The time granularity of the input data may be tailored as desired. The probability profile may be understood to serve the purpose discussed in the description of Action 204. For example, if the first threshold is set as 0.9, then the chance of experiencing dMihroughput < 10 is expected after 1.2 time units roughly or after approximately 15*1.2 - 18 minutes from the current time stamp, it may be noted, however, that in a real implementation, it may make more practical sense to work at an hourly or daily level, and the same may be done by changing the time granularity of the input data.

Figure 8 is a schematic representation of an end to end method that may be performed by the nodes comprised in the communications system 100 for event prediction modelling at a ceil level, according to a non-limiting example of embodiments herein. The actions are drawn to handling the prediction of the event. A user of the second node 112, according to Action 301 , sends the first indication of the event it wants to obtain the probability of occurrence for, as defined by the user. The provision of the second indication comprising the input on the probability threshold is optional. Depending on the probability threshold, a flag of possible performance degradation may be requested to be called out in the context of the specific use case. The backward arrow from the third node 113 to the first node 111 depict the output that are obtained from the historical data store as a request for data by the compute layer of the first node 111 to the third node 113, according to Action 202. This request of data is derived from the specification by the user of the second node 112 on the KPIs that are mentioned in the event definition and covariates. The first node 111 may, according to Action 204, build a model at a cell and/or cluster of cells level, depending on the event definition, and create a probability profile. The backward arrow from the first node 111 to the second node 112 also depict the output from the fitted reliability model from the compute layer that is published by the first node 111 to the user, according to Action 205. This output may comprise mainly the probability profile. Figure 7 depicts an example of a survival probability profile for strategic decision that may be determined by the first node 111 according to Action 204. Each of the two curves depicted correspond to a survival probability, or, a probability of occurrence of two events, respectiveiy, nameiy event 1, related to a first KPI, KP! 1 , and event 2, related to a second KPI, KP! 2, over days ranging from 0 to 15. Note that as the performance of the part of the communications system 100 the respective KPIs measure degrades over time, the chance of occurrence of one of the events increases and the same is reflected via the increasing curve. A user may define the second threshold, a probability threshold, and flexibly tune the first node 111 to call out for a probable red flag event. For example, the first node 111 may raise a red flag that on the 12^th day onwards, the chance of event 1 to occur is high, as the probability of occurrence of the KPI 1 -based event surpasses the second threshold of 0.6. According to embodiments herein, the notification of the occurrence of an event may be prioritized by using an event specific second threshold, depending on the importance of the event. For example, in Figure 7, event 2 is more severe and hence a lower threshold in comparison to event 1 may be chosen for when a red flag for event 2 may need to he raised. This may be understood to facilitate that the second node 111 , or the another node 113, 114, may decide to take a strategic action such as, e.g., act for KPI 2 based event first, by the comparative view through the probability profile of the occurrence of the event as depicted above, and which may be comprised in the another indication.

Figure 8 is a schematic representation of an end to end method that may be performed by the nodes comprised in the communications system 100 for prediction of performance at a level of duster of cells, from reliability modelling at a cell level, according to another non- limiting example of embodiments herein. The actions are drawn to handling the prediction of the event. A user of the second node 112, according to Action 301 , sends the first indication of the event it wants to obtain the probability of occurrence for, as defined by the user, in this example, the user of the second node 112 indicates that that the use case is specific for a of a duster of cells specification. It also indicates the event specific probability threshold as the second threshold, and the cluster level performance specification as the least number of cells to perform the corresponding event probability threshold. The first node 111 specifies the cells obtained as input from the user of the second node 112, as described in Figure 6, and it retrieves the cell level event prediction function from its compute layer, based on the determined cell level reliability modelling. The compute layer of the first node 111 then determines a binomial probability distribution based on the cluster of ceil level performance prediction. Embodiments herein may be understood to provide dear advantages in implementation aspects. Reliability may be understood to be a matured and heavily researched discipline which is being continually advancing through widespread applications spanning diverse fields like medical and engineering. Beyond standard parametric and non-parametric statistical methods which form the core, recent applications from deep learning have expanded the landscape further by leveraging the latest advances from A! and ML. Applications such as federated learning and edge computing have also started flowing, which opens further possibilities such as node level reliability computation and cloud level collection, to predict larger network level performance, see for example, References 5-8, 17-21.

A unique application of the embodiments herein may be understood to be its direct use in strategic decision making. Users may be enabled to prioritize the notification of the occurrence of an event by using a specific second threshold for an event, depending on the importance of the event. Hence, a strategic decision on prioritization of predictive maintenance is enabled to be automated with ease.

Figure 8 depicts two different examples in panels a) and b), respectively, of the arrangement that the first node 111 may comprise. In some embodiments, the first node 111 may comprise the following arrangement depicted in Figure 8a. The first node 111 may be understood to be for handling the prediction of the event. The first node 111 is configured to operate in the communications system 100.

Several embodiments are comprised herein. It should be noted that the examples herein are not mutually exclusive. One or more embodiments may be combined, where applicable.

All possible combinations are not described to simplify the description. Components from one embodiment may be tacitly assumed to be present in another embodiment and it will be obvious to a person skilled in the art how those components may be used in the other exemplary embodiments, in Figure 9, optional units are indicated with dashed boxes.

The detailed description of some of the following corresponds to the same references provided above, in relation to the actions described for the first node 111 and will thus not be repeated here. For example, the another indication may be configured to be an alert

The first node 111 is configured to perform the obtaining of Action 201, e.g., by means of an obtaining unit 801 within the first node 111, configured to obtain, from the second node 112 configured to operate in the communications system 100, the first indication of the event the probability of occurrence of which is to be predicted by the first node 111. The event is configured to be indicative of the performance of at least a part of the communications system 100. The first node 111 is further configured to perform the determining of Action 204, e,g., by means of a determining unit 902 within the first node 111, configured to determine the probability of occurrence of the event in the communications system 100 during the first time period. The determining is configured to be based on estimating the probability of survivai overtime of the event, configured to be defined by the first variable, via reliability modelling.

The first node 111 is also configured to perform the sending of Action 205, e.g., by means of a sending unit 903 within the first node 111, configured to send another indication to the second node 112 or to another node 113, 114 configured to be comprised In the communications system 100. The another indication is configured to indicate the probability of occurrence of the event configured to be determined over the second time period.

In some embodiments, one of the following may apply: a) the first time period may be configured to be the same time period as the second time period, and b) the second time period may be configured to be different than the first time period and have a selected level of granularity.

In some embodiments, the probability of occurrence may be configured to be determined at a level of at least one of: a) the cell 131 configured to operate in the communications system 100, and b) the plurality of cells 130 configured to operate in the communications system 100 within the selected area.

In some embodiments, with the proviso that the event is an indicator of performance of the communications system 100 exceeding or being lower than the first threshold, the first indication may be further configured to indicate the first threshold. The determining may be configured to be performed based on the first indication configured to be obtained.

To obtain may be further configured to comprise obtaining the second indication configured to indicate at least one of the following. According to the first option, the second threshold configured to indicate the value of the probability of occurrence of the event that, when exceeded by the probability of occurrence configured to be determined by the first node 111 , is to trigger the sending of the another indication, to the second node 112 or to the another node 113, 114. The sending is configured to be performed based on the second indication configured to be obtained. According to the second option, the variables configured to have the possibility to eo-vary with the first variable configured to define the event. The determining may be configured to be performed based on the second indication configured to be obtained. According to the third option, the second indication may be configured to indicate the plurality of cells 130 configured to operate in the communications system 100 within the selected area, at the level of which the probability of occurrence is to be determined.

In some embodiments, the first node 111 may be further configured to perform the retrieving of Action 202, e.g., by means of a retrieving unit 904 within the first node 111, configured to retrieve the data from the third node 113 configured to operate in the communications system 100, The data may be configured to comprise the observed data from the components of the communications system 100. The observed data may be configured to be indicative of the event configured to be indicated. The determining may be configured to be performed by analyzing the data configured to be retrieved. in some embodiments, the first node 111 may be further configured to perform the processing of Action 203, e.g., by means of a processing unit 905 within the first node 111, configured to process the data configured to be retrieved, to align the data with the predictive model configured to be used for the determining by identifying censoring in the data configured to be retrieved, in some embodiments, to send may be configured to be performed based on the probability configured to be determined of the occurrence of the event exceeding the second threshold.

The embodiments herein in the first node 111 may be implemented through one or more processors, such as a processor 90S in the first node 111 depicted in Figure 9a, together with computer program code for performing the functions and actions of the embodiments herein. A processor, as used herein, may be understood to be a hardware component. The program code mentioned above may aiso be provided as a computer program product, for instance in the form of a data carrier carrying computer program code for performing the embodiments herein when being loaded into the first node 111. One such carrier may be in the form of a CD ROM disc. It is however feasible with other data carriers such as a memory stick. The computer program code may furthermore be provided as pure program code on a server and downloaded to the first node 111.

The first node 111 may further comprise a memory 907 comprising one or more memory units. The memory 907 is arranged to be used to store obtained information, store data, configurations, schedulings, and applications etc. to perform the methods herein when being executed in the first node 111. in some embodiments, the first node 111 may receive information from, e.g., the second node 112, the third node 113, the fourth node 114, the radio network node 120 and/or the device 140, through a receiving port 908. in some embodiments, the receiving port 908 may be, for example, connected to one or more antennas in first node 111. In other embodiments, the first node 111 may receive information from another structure in the communications system 100 through the receiving port 908. Since the receiving port 908 may be in communication with the processor 906, the receiving port 908 may then send the received information to the processor 90S. The receiving port 908 may also be configured to receive other information. The processor 906 in the first node 111 may be further configured to transmit or send information to e.g,, the second node 112, the third node 113, the fourth node 114, the radio network node 120, the device 140 and/or or another structure in the communications system 100, through a sending port 909, which may be in communication with the processor 906, and the memory 907.

Those skilled in the art will also appreciate that the units 901 -905 described above may refer to a combination of analog and digital circuits, and/or one or more processors configured with software and/or firmware, e.g., stored in memory, that, when executed by the one or more processors such as the processor 906, perform as described above. One or more of these processors, as well as the other digital hardware, may be included in a single Application- Specific Integrated Circuit (ASIC), or several processors and various digital hardware may be distributed among several separate components, whether individually packaged or assembled into a System-on-a-Chip (SoC).

Also, in some embodiments, the different units 901-905 described above may be implemented as one or more applications running on one or more processors such as the processor 906.

Thus, the methods according to the embodiments described herein for the first node 111 may be respectively implemented by means of a computer program S10 product, comprising instructions, i.e., software code portions, which, when executed on at least one processor 906, cause the at least one processor 906 to carry out the actions described herein, as performed by the first node 111. The computer program 910 product may be stored on a computer- readable storage medium 911. The computer-readable storage medium 911 , having stored there on the computer program 910, may comprise instructions which, when executed on at least one processor 906, cause the at least one processor 906 to carry out the actions described herein, as performed by the first node 111. In some embodiments, the computer- readable storage medium 911 may be a non-transitory computer-readable storage medium, such as a CD ROM disc, or a memory stick. In other embodiments, the computer program 910 product may be stored on a carrier containing the computer program 910 just described, wherein the carrier is one of an electronic signal, optical signal, radio signal, or the computer- readable storage medium 911 , as described above.

The first node 111 may comprise a communication interface configured to facilitate, or an interlace unit to facilitate, communications between the first node 111 and other nodes or devices, e.g., the second node 112, the third node 113, the fourth node 114, the radio network node 120, the device 140 and/or or another structure in the communications system 100. The interface may, for example, include a transceiver configured to transmit and receive radio signals over an air interface in accordance with a suitable standard. In other embodiments, the first node 111 may comprise the following arrangement depicted in Figure 9b. The first node 111 may comprise a processing circuitry 906, e.g., one or more processors such as the processor 906, in the first node 111 and the memory 907. The first node 111 may also comprise a radio circuitry 912, which may comprise e.g., the receiving port 908 and the sending port 909. The processing circuitry 906 may be configured to, or operable to, perform the method actions according to Figure 2, and/or Figure 4-Figure 18, in a similar manner as that described in relation to Figure 9a. The radio circuitry 912 may be configured to set up and maintain at least a wireless connection with the second node 112, the third node 113, the fourth node 114, the radio network node 120, the device 140 and/or or another structure in the communications system 100. Circuitry may be understood herein as a hardware component.

Hence, embodiments herein also relate to the first node 111 operative to operate in the communications system 100. The first node 111 may comprise the processing circuitry 906 and the memory 907, said memory 907 containing instructions executable by said processing circuitry 906, whereby the first node 111 is further operative to perform the actions described herein in relation to the first node 111, e.g., in Figure 2, and/or Figure 4~Figure 8.

Figure 10 depicts two different examples in panels a) and b), respectively, of the arrangement that the second node 112, may comprise. In some embodiments, the second node 112 may comprise the following arrangement depicted in Figure 10a. The second node 112 is for handling the prediction of the event. The second node 112 is configured to operate in the communications system 100.

Several embodiments are comprised herein, it should be noted that the examples herein are not mutually exclusive. One or more embodiments may be combined, where applicable.

Ali possible combinations are not described to simplify the description. Components from one embodiment may be tacitly assumed to be present in another embodiment and it will be obvious to a person skilled in the art how those components may be used in the other exemplary embodiments, in Figure 10, optional units are indicated with dashed boxes.

The detailed description of some of the following corresponds to the same references provided above, in relation to the actions described for the second node 112, and will thus not be repeated here. For example, the another indication may be configured to be an alert.

The second node 112 is configured to perform the sending of Action 301 , e.g., by means of a sending unit 1001 configured to, send, to the first node 111 configured to operate in the communications system 100, the first indication of the event the probability of occurrence of which is to be predicted by the first node 111. The event is configured to be indicative of the performance of at feast a part of the communications system 100. The second node 112 is also configured to perform the receiving of Action 302, e.g,, by means of a receiving unit 1002 within the second node 112, configured to, receive the another indication from the first node 111. The another indication is configured to indicate the probabiiity of occurrence of the event configured to be determined over the second time period, as configured to be determined by the first node 111. The another indication is configured to be based on the probabiiity of survivai overtime of the event, configured to be defined by the first variabie, as configured to be determined by the first node 111 , via reliability modelling.

In some embodiments, the probability of occurrence may be configured to be indicated as being determined at the level of at least one of: a) the cell 131 configured to operate in the communications system 100, and the plurality of cells 130 configured to operate in the communications system 100 within a selected area.

In some embodiments, with the proviso that the event is configured to be an indicator of performance of the communications system 100 exceeding or being lower than the first threshold, the first indication may be further configured to indicate the first threshold. The another indication may be configured to be based on the first indication configured to be sent.

In some embodiments, the sending may be further configured to comprise sending the second indication configured to indicate at least one of the following. According to the first option, the second threshold configured to indicate the value of the probability of occurrence of the event that, when exceeded by the probability of occurrence configured to be determined by the first node 111, is to trigger the first node 111 to send the another indication to the second node 112 or to another node 113, 114 configured to be comprised in the communications system 100, The another indication configured to be received may be configured to be based on the second indication configured to be sent. According to the second option, the variables configured to have the possibility to co-vary with the first variable configured to define the event. The another indication may be configured to be based on the second indication configured to be sent. According to the third option, the second indication may be configured to indicate the plurality of cells 130 configured to operate in the communications system 100 within the selected area, at the level of which the probability of occurrence may be to be determined. in some embodiments, the receiving may be configured to be performed based on the probability configured to be determined of the occurrence of the event exceeding the second threshold.

The embodiments herein in the second node 112 may be implemented through one or more processors, such as a processor 1003 in the second node 112 depicted in Figure 10a, togetherwith computer program code for performing the functions and actions of the embodiments herein. A processor, as used herein, may be understood to be a hardware component. The program code mentioned above may aiso be provided as a computer program product, for instance in the form of a data carrier carrying computer program code for performing the embodiments herein when being loaded into the second node 112. One such carrier may be in the form of a CD ROM disc. It is however feasible with other data carriers such as a memory stick. The computer program code may furthermore be provided as pure program code on a server and downloaded to the second node 112.

The second node 112 may further comprise a memory 1004 comprising one or more memory units. The memory 1004 is arranged to be used to store obtained information, store data, configurations, scheduiings, and applications etc. to perform the methods herein when being executed in the second node 112.

In some embodiments, the second node 112 may receive information from, e.g., the first node 111, the third node 113, the fourth node 114, the radio network node 120 and/or the device 140, through a receiving port 1005. In some embodiments, the receiving port 1005 may be, for example, connected to one or more antennas in second node 112. In other embodiments, the second node 112 may receive information from another structure in the communications system 100 through the receiving port 1005. Since the receiving port 1005 may be in communication with the processor 1003, the receiving port 1005 may then send the received information to the processor 1003. The receiving port 1005 may also be configured to receive other information.

The processor 1003 in the second node 112 may be further configured to transmit or send information to e.g., the first node 111, the second node 112, the third node 113, the fourth node 114, the radio network node 120, the device 140, or another structure in the communications system 100 and/or or another structure in the communications system 100, through a sending port 1006, which may be in communication with the processor 1003, and the memory 1004.

Those skilled in the art will also appreciate that the units 1001-1002 described above may refer to a combination of analog and digital circuits, and/or one or more processors configured with software and/or firmware, e.g., stored in memory, that, when executed by the one or more processors such as the processor 1003, perform as described above. One or more of these processors, as well as the other digital hardware, may be included in a single Application-Specific Integrated Circuit (ASIC), or several processors and various digital hardware may be distributed among several separate components, whether individually packaged or assembled into a System-on-a-Chip (SoC). Also, in some embodiments, the different units 1001-1002 described above may be impiemented as one or more applications running on one or more processors such as the processor 1003.

Thus, the methods according to the embodiments described herein for the second node 112 may be respectively implemented by means of a computer program 1007 product, comprising instructions, i.e., software code portions, which, when executed on at least one processor 1003, cause the at least one processor 1003 to carry out the actions described herein, as performed by the second node 112. The computer program 1007 product may be stored on a computer-readable storage medium 1000. The computer-readable storage medium 1008, having stored thereon the computer program 1007, may comprise instructions which, when executed on at least one processor 1003, cause the at least one processor 1003 to carry out the actions described herein, as performed by the second node 112. In some embodiments, the computer-readable storage medium 1008 may be a non-transitory computer-readable storage medium, such as a CD ROM disc, or a memory stick. In other embodiments, the computer program 1007 product may be stored on a carrier containing the computer program 1007 just described, wherein the carrier is one of an electronic signal, optical signal, radio signal, or the computer-readable storage medium 1008, as described above.

The second node 112 may comprise a communication interface configured to facilitate, or an interface unit to facilitate, communications between the second node 112 and other nodes or devices, e.g., the first node 111, the third node 113, the fourth node 114, the radio network node 120, the device 140 and/or or another structure in the communications system 100. The interface may, for example, include a transceiver configured to transmit and receive radio signals over an air interlace in accordance with a suitable standard.

In other embodiments, the second node 112 may comprise the following arrangement depicted In Figure 10b. The second node 112 may comprise a processing circuitry 1003, e.g., one or more processors such as the processor 1003, in the second node 112 and the memory 1004. The second node 112 may also comprise a radio circuitry 1000, which may comprise e.g., the receiving port 1005 and the sending port 1006. The processing circuitry 1003 may be configured to, or operable to, perform the method actions according to Figure 3, and/or Figure 4-Hgure 8, in a similar manner as that described In relation to Figure 10a. The radio circuitry 1009 may be configured to set up and maintain at least a wireless connection with the first node 111, the third node 113. the fourth node 114, the radio network node 120, the device 140 and/or or another structure in the communications system 100. Circuitry may be understood herein as a hardware component. Hence, embodiments herein also relate to the second node 112 operative to operate in the communications system 100. The second node 112 may comprise the processing circuitry 1003 and the memory 1004, said memory 1004 containing instructions executable by said processing circuitry 1003. whereby the second node 112 is further operative to perform the actions described herein in re!ation to the second node 112, e.g., in Figure 3, and/or Figure 4- Figure 8.

Figure 11 depicts two different examples in panels a) and b), respectively, of the arrangement that the communications system 100 may comprise to perform the actions according to Figure 4. The communications system 100 is for handiing the prediction of the event. The communications system 100 is configured to comprise the first node 111 and the second node 112 configured to operate in the communications system 100.

The configurations described for the first node 111 and the second node 112, in relation to Figure 11 may be understood to correspond to those described in Figure 9 and Figure 10, respectively, and to be performed, e.g., by means of the corresponding units and arrangements described in Figure 9 and Figure 10, which wiii not be repeated here in its entirety. Only some of the features are described here.

The communications system 100 is further configured, e.g., by means of the sending unit 1001 within the second node 112, configured to, send, by the second node 112 to the first node 111, the first indication of the event the probability of occurrence of which is to be predicted by the first node 111. The event is configured to be indicative of the performance of at least a part of the communications system 100.

The communications system 100 is further configured to, e.g., by means of the obtaining unit 901 within the first node 111, configured to, obtain, by the first node 111 from the second node 112, the first indication.

The communications system 100 is further configured to, e.g., by means of the determining unit 902 within the first node 111, configured to, determine, by the first node 111, the probability of occurrence of the event in the communications system 100 during the first time period. The determining is configured to be based on estimating the probability of survival overtime of the event, configured to be defined by the first variable, via reliability modelling.

The communications system 100 is further configured to, e.g., by means of the sending unit 903 within the first node 111, configured to, send by the first node 111, the another indication to the second node 112 or to the another node 113, 114 configured to be comprised in the communications system 100. The another indication is configured to indicate the probability configured to be determined of occurrence of the event over the second time period. The communications system 100 is further configured to, e.g., by means of the receiving unit 1002 within the second node 112, configured to, receive, by the second node 112, the another indication from the first node 111. in some embodiments, one of the following may apply: a) the first time period may be configured to be the same time period as the second time period, and b) the second time period may be configured to be different than the first time period and have a se!ected level of granularity.

In some embodiments, the probability of occurrence may be configured to be determined at a Ievel of at least one of: a) the cell 131 configured to operate in the communications system 100, and b) the plurality of cells 130 configured to operate in the communications system 100 within the selected area.

In some embodiments, with the proviso that the event is an indicator of performance of the communications system 100 exceeding or being lower than the first threshold, the first indication may be further configured to indicate the first threshold. The determining may be configured to be performed based on the first indication configured to be sent by the second node 112 and configured to be obtained by the first node 111.

In some embodiments, the sending may be further configured to comprise sending the second indication and the obtaining may be further configured to comprise obtaining the second indication. The second indication may be configured to indicate at least one of the following. According to the first option, the second threshold configured to indicate the value of the probability of occurrence of the event that, when exceeded by the probability of occurrence configured to be determined by the first node 111, is to trigger the sending of the another indication, to the second node 112 or to the another node 113, 114. The sending may be configured to be performed based on the second indication configured to be sent by the second node 112 and obtained by the first node 111. According to the second option, the variables configured to have the possibility to co-vary with the first variable configured to define the event. The determining may be configured to be performed based on the second indication configured to be sent by the second node 112 and obtained by the first node 111. According to the third option, the second indication may be configured to indicate the plurality of cells 130 configured to operate in the communications system 100 within the selected area, at the Ievel of which the probability of occurrence is to be determined by the first node 111.

The communications system 100 may be further configured to, e.g., by means of the retrieving unit 904 within the first node 111, configured to, retrieve, by the first node 111, the data from the third node 113 configured to operate in the communications system 100. The data may be configured to comprise the observed data from the components of the communications system 100. The observed data may be configured to be indicative of the event configured to be indicated, The determining may be configured to be performed by analyzing the data configured to be retrieved.

The communications system 100 is further configured to, e,g., by means of the processing unit 905 within the first node 111 , configured to, process, by the first node 111 , the data configured to be retrieved, to align the data with the predictive model configured to be used for the determining by identifying the censoring in the data configured to be retrieved.

In some embodiments, to send may be configured to be performed based on the probability configured to be determined of the occurrence of the event exceeding the second threshold.

When using the word "comprise" or “comprising", it shall be interpreted as non- limiting, i.e. meaning "consist at least of.

The embodiments herein are not iimited to the above described preferred embodiments. Various alternatives, modifications and equivalents may be used. Therefore, the above embodiments should not be taken as limiting the scope of the invention.

Generally, all terms used herein are to be interpreted according to their ordinary meaning in the relevant technical field, unless a different meaning is clearly given and/or is implied from the context in which it is used. All references to a/an/the element, apparatus, component, means, step, etc. are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, step, etc., unless explicitly stated otherwise. The steps of any methods disclosed herein do not have to be performed in the exact order disclosed, unless a step is explicitly described as following or preceding another step and/or where it is implicit that a step must follow or precede another step. Any feature of any of the embodiments disclosed herein may be applied to any other embodiment, wherever appropriate. Likewise, any advantage of any of the embodiments may apply to any other embodiments, and vice versa. Other objectives, features and advantages of the enclosed embodiments will be apparent from the following description.

As used herein, the expression “at least one of:” followed by a list of alternatives separated by commas, and wherein the last alternative is preceded by the “and” term, may be understood to mean that only one of the list of alternatives may apply, more than one of the list of alternatives may apply or all of the list of alternatives may apply. This expression may be understood to be equivalent to the expression “at least one of:” followed by a list of alternatives separated by commas, and wherein the last alternative is preceded by the “or” term.

Any of the terms processor and circuitry may be understood herein as a hardware component. As used herein, the expression “in some embodiments” has been used to indicate that the features of the embodiment described may be combined with any other embodiment or exampie disclosed herein.

As used herein, the expression “in some examples” has been used to indicate that the features of the example described may be combined with any other embodiment or exampie disclosed herein.

REFERENCES

1. US20200084087A1 (INTELLIGENT ANOMALY DETECTION AND ROOT CAUSE ANALYSIS IN MOBILE NETWORKS)

2. US20200213202A1 (SYSTEM AND METHOD FOR PREDICTING KEY PERFORMANCE INDICATOR (KP!) IN A TELECOMMUNICATION NETWORK)

3. Approximating the Sum of Independent Non-Identical Binomial Random Variables by Liu et. Al. (2018), The R Journal Vo!. 10/1, July 2018; https://journaI.rpproject.org/archive/2018/RJ-2018-011/RJ-2018-011.pdf

4. US6735549B2 (Predictive Maintenance Display System)

5. Field-Failure Predictions Based on Failure-Time Data with Dynamic Covariate information by Hong et. Ai (2013), Technometrics, VOL. 55, NO. 2

6. Big data and reliability applications: The complexity dimension by Hong et. Al. (2018), JOURNAL OF QUALITY TECHNOLOGY, VOL. 50, NO. 2, 135 - 149

7. Two Birds with One Network: Unifying Failure Event Prediction and TIme-to~failure Modeling by Aggarwai et. AL, (2018); DOI Bookmark:10.1109/BIgData.2018.8622431

8. Long Short-Term Memory Network for Remaining Useful Life Estimation by Zheng et. AL, (2017), IEEE International Conference on Prognostics and Health Management, 2017,

9. https://patentsjustla.com/patent/9439092 (detection of component fault at cell towers- anomaly detection using heat signature and aerial device)

10. https://patents.justia,com/inventor/Iev-bregman (root cause analysis with fault management system)

11. https://patents.justia.com/patent/9645899 System, method, and computer program for managing fault recovery in network function virtualization (NFV) based networks

12. https://patents.justia.com/inventor/claudio-meruIla (checks mutual reachability, reducing time not predicting)

13. https://patentsjustia.com/inventor/andrea-pinnola (Fault location in telecommunications networks using bayesian networks)

14. ( https://patents.goog!e.com/patent/US9716633B2/en alarm prediction in telecom network 15. https://patents.google.com/patent/EP0972252A1/en (System and method for telecommunications system fault diagnostics.

16. SYSTEMS AND METHODS FOR NETWORK PERFORMANCE FORECASTING https://patents.googie.com/patent/US9439081?oq=telecom+ network÷KPiH-simulation 17. Handbook of Survival Analysis, edited by Klein, van Houwelingen, Ibrahim and Scheike (2014)

18. Event History Modeling: A Guide for Social Scientists (Analytical Methods for Social Research) by Janet M. Box-Sfeffensmeier (Author)

19. Survival Analysis Techniques for Censored & Truncated Data BY JOHN P MOBS KLEIN 20. Cox, D. R.; Oakes, D. (1984). Analysis of Survival Data. New York: Chapman & Hall.

21. Modeling Survival Data: Extending the Cox Mode! BY TERRY M. THERNEAU AND PATRICIA M. GRAMBSCH

Claims

CLAIMS:

1 . A method, performed by a first node (111 ), the method being for handling a prediction of an event, the first node (111 ) operating in a communications system (100), the method comprising:

- obtaining (201), from a second node (112) operating in the communications system (100), a first indication of an event the probability of occurrence of which is to be predicted by the first node (111), the event being indicative of a performance of at least a part of the communications system (100), - determining (204) the probability of occurrence of the event in the communications system (100) during a first time period, the determining (204) being based on estimating a probability of survival over time of the event, defined by a first variable, via reliability modelling, and

- sending (205) another indication to the second node (112) or to another node (113, 114) comprised in the communications system (100), the another indication indicating the determined probability of occurrence of the event over a second time period.

The method according to claim 1 , wherein one of: a. the first time period is the same time period as the second time period, and b. the second time period is different than the first time period and has a selected level of granularity.

3. The method according to any of claims 1-2, wherein the probability of occurrence is determined at a level of at least one of: a. a cell (131) operating in the communications system (100), and b. a plurality of cells (130) operating in the communications system (100) within a selected area. 4. The method according to any of claims 1 -3, wherein with the proviso that the event is an indicator of performance of the communications system (100) exceeding or being lower than a first threshold, the first indication further indicates the first threshold, and wherein the determining (204) is performed based on the obtained first indication.

5. The method according to any of claims 1-4, wherein the obtaining (201) further comprises obtaining a second indication indicating at least one of: a. a second threshold indicating a value of the probability of occurrence of the event that, when exceeded by the probability of occurrence determined by the first node (111), is to trigger the sending (205) of the another indication, to the second node (112) or to the another node (113, 114), and wherein the sending (205) is performed based on the obtained second indication, b. variables having a possibility to co-vary with the first variable defining the event, and wherein the determining (204) is performed based on the obtained second indication, and c. a plurality of cells (130) operating in the communications system (100) within a selected area, at a level of which the probability of occurrence is to be determined. 6. The method according to any of claims 1-5, further comprising:

- retrieving (202) data from a third node (113) operating in the communications system (100), the data comprising observed data from the components of the communications system (100), the observed data being indicative of the indicated event, and wherein the determining (204) is performed by analyzing the retrieved data.

7. The method according to claim 6, further comprising:

- processing (203) the retrieved data to align the data with a predictive model used for the determining (204) by identifying censoring in the retrieved data.

8. The method according to any of claims 1-7, wherein the sending (205) is performed based on the determined probability of the occurrence of the event exceeding a second threshold. 9. A computer program (910), comprising instructions which, when executed on at least one processor (906), cause the at least one processor (906) to carry out the method according to any one of claims 1 to 8.

10. A computer-readable storage medium (911), having stored thereon a computer program (910), comprising instructions which, when executed on at least one processor (906), cause the at least one processor (906) to carry out the method according to any one of claims 1 to 8.

11 . A method, performed by a second node (112), the method being for handling a prediction of an event, the second node (112) operating in a communications system

(100), the method comprising:

- sending (301 ), to a first node (111) operating in the communications system (100), a first indication of an event the probability of occurrence of which is to be predicted by the first node (111), the event being indicative of a performance of at least a part of the communications system (100), and

- receiving (302) another indication from the first node (111), the another indication indicating a determined probability of occurrence of the event over a second time period, as determined by the first node (111 ), the another indication being based on a probability of survival over time of the event, defined by a first variable , as determined by the first node (111) via reliability modelling.

12. The method according to claim 11 , wherein the probability of occurrence is indicated as being determined at a level of at least one of: a. a cell (131) operating in the communications system (100), and b. a plurality of cells (130) operating in the communications system (100) within a selected area.

13. The method according to any of claims 11-12, wherein with the proviso that the event is an indicator of performance of the communications system (100) exceeding or being lower than a first threshold, the first indication further indicates the first threshold, and wherein the another indication is based on the sent first indication.

14. The method according to any of claims 11-13, wherein the sending (301) further comprises sending a second indication indicating at least one of: a. a second threshold indicating a value of the probability of occurrence of the event that, when exceeded by the probability of occurrence determined by the first node (111), is to trigger the first node (111 ) to send the another indication to the second node (112) or to another node (113, 114) comprised in the communications system (100), and wherein the received another indication is based on the sent second indication, b. variables having a possibility to co-vary with the first variable defining the event, and wherein the another indication is based on the sent second indication, and c. a plurality of cells (130) operating in the communications system (100) within a selected area, at a level of which the probability of occurrence is to be determined.

15. The method according to any of claims 11-14, wherein the receiving (302) is performed based on the determined probability of the occurrence of the event exceeding a second threshold.

16. A computer program (1007), comprising instructions which, when executed on at least one processor (1003), cause the at least one processor (1003) to carry out the method according to any one of claims 11 to 15. 17. A computer-readable storage medium (1007), having stored thereon a computer program (1007), comprising instructions which, when executed on at least one processor (1003), cause the at least one processor (1003) to carry out the method according to any one of claims 11 to 15. 18. A method, performed by a communications system (100), the method being for handling a prediction of an event, the communications system (100) comprising a first node (111) and a second node (112) operating in a communications system (100), the method comprising:

- sending (401 , 301), by the second node (112) to the first node (111), a first indication of an event the probability of occurrence of which is to be predicted by the first node (111), the event being indicative of a performance of at least a part of the communications system (100),

- obtaining (402, 201 ), by the first node (111) from the second node (112), the first indication, - determining (405, 204), by the first node (111 ), the probability of occurrence of the event in the communications system (100) during a first time period, the determining (405, 204) being based on estimating a probability of survival over time of the event, defined by a first variable, via reliability modelling,

- sending (406, 205) by the first node (111), another indication to the second node (112) or to another node (113, 114) comprised in the communications system (100), the another indication indicating the determined probability of occurrence of the event over a second time period, and

- receiving (407, 302), by the second node (112), the another indication from the first node (111).

19. The method according to claim 18, wherein one of: a. the first time period is the same time period as the second time period, and b. the second time period is different than the first time period and has a selected level of granularity.

20. The method according to any of claims 18-19, wherein the probability of occurrence is determined by the first node (111 ) at a level of at least one of: a. a cell (131) operating in the communications system (100), and b. a plurality of cells (130) operating in the communications system (100) within a selected area.

21. The method according to any of claims 18-20, wherein with the proviso that the event is an indicator of performance of the communications system (100) exceeding or being lower than a first threshold, the first indication further indicates the first threshold, and wherein the determining (405, 204) is performed based on the first indication sent by the second node (112) and obtained by the first node (111).

22. The method according to any of claims 18-21 , wherein the sending (401 , 301 ) further comprises sending a second indication and the obtaining (402, 201) further comprises obtaining the second indication, the second indication indicating at least one of: a. a second threshold indicating a value of the probability of occurrence of the event that, when exceeded by the probability of occurrence determined by the first node (111), is to trigger the sending (406, 205) of the another indication, to the second node (112) or to the another node (113, 114), and wherein the sending (406, 205) is performed based on the obtained second indication, b. variables having a possibility to co-vary with the first variable defining the event, and wherein the determining (405, 204) is performed based on the obtained second indication, and c. a plurality of cells (130) operating in the communications system (100) within a selected area, at a level of which the probability of occurrence is to be determined. 23. The method according to any of claims 18-22, further comprising:

- retrieving (403, 202), by the first node (111), data from a third node (113) operating in the communications system (100), the data comprising observed data from the components of the communications system (100), the observed data being indicative of the indicated event, and wherein the determining (405, 204) is performed by analyzing the retrieved data.

24. The method according to claim 23, further comprising: - processing (404, 203), by the first node (111), the retrieved data to align the data with a predictive model used for the determining (405, 204) by identifying censoring in the retrieved data.

25. The method according to any of claims 18-24, wherein the sending (406, 205) is performed based on the determined probability of the occurrence of the event exceeding a second threshold.

26. A first node (111), for handling a prediction of an event, the first node (111) being configured to operate in a communications system (100), the first node (111) being further configured to:

- obtain, from a second node (112) configured to operate in the communications system (100), a first indication of an event the probability of occurrence of which is to be predicted by the first node (111), the event being configured to be indicative of a performance of at least a part of the communications system (100), - determine the probability of occurrence of the event in the communications system

(100) during a first time period, the determining being configured to be based on estimating a probability of survival over time of the event, configured to be defined by a first variable, via reliability modelling, and

- send another indication to the second node (112) or to another node (113, 114) configured to be comprised in the communications system (100), the another indication being configured to indicate the probability of occurrence of the event configured to be determined over a second time period.

27. The first node (111) according to claim 26, wherein one of: a. the first time period is configured to be the same time period as the second time period, and b. the second time period is configured to be different than the first time period and has a selected level of granularity.

28. The first node (111) according to any of claims 26-27, wherein the probability of occurrence is configured to be determined at a level of at least one of: a. a cell (131) configured to operate in the communications system (100), and b. a plurality of cells (130) configured to operate in the communications system (100) within a selected area.

29. The first node (111) according to any of claims 26-28, wherein with the proviso that the event is an indicator of performance of the communications system (100) exceeding or being lower than a first threshold, the first indication is further configured to indicate the first threshold, and wherein the determining is configured to be performed based on the first indication configured to be obtained.

30. The first node (111) according to any of claims 26-29, wherein to obtain is further configured to comprise obtaining a second indication configured to indicate at least one of: a. a second threshold configured to indicate a value of the probability of occurrence of the event that, when exceeded by the probability of occurrence configured to be determined by the first node (111 ), is to trigger the sending of the another indication, to the second node (112) or to the another node (113, 114), and wherein the sending is configured to be performed based on the second indication configured to be obtained, b. variables configured to have a possibility to co-vary with the first variable configured to define the event, and wherein the determining is configured to be performed based on the second indication configured to be obtained, and c. a plurality of cells (130) configured to operate in the communications system (100) within a selected area, at a level of which the probability of occurrence is to be determined.

31 . The first node (111) according to any of claims 26-30, further configured to:

- retrieve data from a third node (113) configured to operate in the communications system (100), the data being configured to comprise observed data from the components of the communications system (100), the observed data being configured to be indicative of the event configured to be indicated, and wherein the determining is configured to be performed by analyzing the data configured to be retrieved.

32. The first node (111) according to claim 31 , being further configured to: - process the data configured to be retrieved, to align the data with a predictive model configured to be used for the determining by identifying censoring in the data configured to be retrieved.

33. The first node (111) according to any of claims 26-32, wherein to send is configured to be performed based on the probability configured to be determined of the occurrence of the event exceeding a second threshold.

34. A second node (112), for handling a prediction of an event, the second node (112) being configured to operate in a communications system (100), the second node (112) being further configured to:

- send, to a first node (111) configured to operate in the communications system (100), a first indication of an event the probability of occurrence of which is to be predicted by the first node (111), the event being configured to be indicative of a performance of at least a part of the communications system (100), and

- receive another indication from the first node (111 ), the another indication being configured to indicate a probability of occurrence of the event configured to be determined over a second time period, as configured to be determined by the first node (111 ), the another indication being configured to be based on a probability of survival over time of the event, configured to be defined by a first variable as configured to be determined by the first node (111 ), via reliability modelling.

35. The second node (112) according to claim 34, wherein the probability of occurrence is configured to be indicated as being determined at a level of at least one of: a. a cell (131) configured to operate in the communications system (100), and b. a plurality of cells (130) configured to operate in the communications system

(100) within a selected area.

36. The second node (112) according to any of claims 34-35, wherein with the proviso that the event is configured to be an indicator of performance of the communications system (100) exceeding or being lower than a first threshold, the first indication is further configured to indicate the first threshold, and wherein the another indication is configured to be based on the first indication configured to be sent.

37. The second node (112) according to any of claims 34-36, wherein the sending is further configured to comprise sending a second indication configured to indicate at least one of: a. a second threshold configured to indicate a value of the probability of occurrence of the event that, when exceeded by the probability of occurrence configured to be determined by the first node (111 ), is to trigger the first node (111) to send the another indication to the second node (112) or to another node (113, 114) configured to be comprised in the communications system (100), and wherein the another indication configured to be received is configured to be based on the second indication configured to be sent, b. variables configured to have a possibility to co-vary with the first variable configured to define the event, and wherein the another indication is configured to be based on the second indication configured to be sent, and c. a plurality of cells (130) configured to operate in the communications system (100) within a selected area, at a level of which the probability of occurrence is to be determined.

38. The second node (112) according to any of claims 34-37, wherein the receiving is configured to be performed based on the probability configured to be determined of the occurrence of the event exceeding a second threshold. 39. A communications system (100), for handling a prediction of an event, the communications system (100) being configured to comprise a first node (111) and a second node (112) configured to operate in a communications system (100), the communications system (100) being further configured to:

- send, by the second node (112) to the first node (111), a first indication of an event the probability of occurrence of which is to be predicted by the first node (111 ), the event being configured to be indicative of a performance of at least a part of the communications system (100),

- obtain, by the first node (111 ) from the second node (112), the first indication,

- determine, by the first node (111 ), the probability of occurrence of the event in the communications system (100) during a first time period, the determining being configured to be based on estimating a probability of survival over time of the event, configured to be defined by a first variable, via reliability modelling,

- send by the first node (111 ), another indication to the second node (112) or to another node (113, 114) configured to be comprised in the communications system (100), the another indication being configured to indicate the probability configured to be determined of occurrence of the event over a second time period, and

- receive, by the second node 112, the another indication from the first node (111).

40. The communications system (100) according to claim 39, wherein one of: a. the first time period is configured to be the same time period as the second time period, and b. the second time period is configured to be different than the first time period and has a selected level of granularity. 41. The communications system (100) according to any of claims 39-40, wherein the probability of occurrence is configured to be determined by the first node (111 ) at a level of at least one of: a. a cell (131) configured to operate in the communications system (100), and b. a plurality of cells (130) configured to operate in the communications system (100) within a selected area.

42. The communications system (100) according to any of claims 39-41 , wherein with the proviso that the event is an indicator of performance of the communications system (100) exceeding or being lower than a first threshold, the first indication is further indicate the first threshold, and wherein the determining is configured to be performed based on the first indication configured to be sent by the second node (112) and configured to be obtained by the first node (111).

43. The communications system (100) according to any of claims 39-42, wherein the sending is further configured to comprise sending a second indication and the obtaining is further configured to comprise obtaining the second indication, the second indication being further configured to indicate at least one of: a. a second threshold configured to indicate a value of the probability of occurrence of the event that, when exceeded by the probability of occurrence configured to be determined by the first node (111 ), is to trigger the sending of the another indication, to the second node (112) or to the another node (113, 114), and wherein the sending is configured to be performed based on the second indication configured to be sent by the second node (112) and obtained by the first node (111 ), b. variables configured to have a possibility to co-vary with the first variable configured to define the event, and wherein the determining is configured to be performed based on the second indication configured to be sent by the second node (112) and obtained by the first node (111), and c. a plurality of cells (130) configured to operate in the communications system (100) within a selected area, at a level of which the probability of occurrence is to be determined by the first node (111).

44. The communications system (100) according to any of claims 39-43, being further configured to:

- retrieve, by the first node (111), data from a third node (113) configured to operate in the communications system (100), the data being configured to comprise observed data from the components of the communications system (100), the observed data being configured to be indicative of the event configured to be indicated, and wherein the determining is configured to be performed by analyzing the data configured to be retrieved.

45. The communications system (100) according to claim 44, being further configured to:

- process, by the first node (111), the data configured to be retrieved to align the data with a predictive model configured to be used for the determining by identifying censoring in the data configured to be retrieved.

46. The communications system (100) according to any of claims 39-45, wherein the sending is configured to be performed based on the probability configured to be determined of the occurrence of the event exceeding a second threshold.