Control node and a method therein in a network
By integrating Anomaly Detection and Failure Prediction to trigger Failure Testing and generate counter measures, the control node optimizes resource allocation and enhances failure prevention in target systems, addressing inefficiencies in existing protection methods.
Patent Information
- Application Number
- PCT/SE2025/050432
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-05-07
- Publication Date
- 2026-11-12
AI Technical Summary
Existing systems for protecting target systems from malfunctioning and failure rely solely on Anomaly Detection, Failure Prediction, or Failure Testing, leading to inefficiencies, resource exhaustion, and ineffective counter measures due to lack of collaboration between these methods.
A control node integrates Anomaly Detection and Failure Prediction scores to trigger Failure Testing, simulating adversarial actions through a Digital Target System, and generates counter measures to prevent potential failures, optimizing resource allocation and improving protection systems.
The integrated approach enhances resource efficiency and effectiveness in preventing system failures by accurately predicting and addressing potential issues, reducing resource usage and improving system availability.
Smart Images

Figure SE2025050432_12112026_PF_FP_ABST
Abstract
Description
[0001] CONTROL NODE AND A METHOD THEREIN IN A NETWORK
[0002] TECHNICAL FIELD
[0003] Embodiments herein relate to a control node controlling a protection system and a method therein. In some aspects, they relate to performing an action relating to preventive protection of a Target System (TS) in a network.
[0004] BACKGROUND
[0005] A Service-Level Agreement (SLA) e.g., defines the level of service expected by a customer from a supplier, laying out metrics by which that service is measured, and the remedies or penalties, if any, in cases when service levels are not achieved. SLAs may be between companies and external suppliers, but they may also be between two departments within a company.
[0006] Given the fact that maintaining services and availability up and performing as expected in the SLA, protection against failure and malfunctioning of any system have been a hot topic for academia and industry. Availability up when used herein e.g. means when a system provides the minimum expected service. To face such challenge, many works have been published, either to detect abnormal behaviour, failure or crash prediction, or to discover weaknesses in the system on local machines or on the edge for example described in e.g., Maren David Dangut, et al., Application of Deep Reinforcement Learning for Extremely Rare Failure Prediction in Aircraft, https: / / dspace.lib.cranfield.ac.uk / bitstream / handle / 1826 / 17569 / Rare_failure_prediction_in _aircraft_maintenance-2022.pdf?sequence=4; Adaptive Stress Testing: Finding Likely Failure Events with Reinforcement Learning, https: / / arxiv.org / abs / 1811.02188; Xingxing Liu et al., Smart Server Crash Prediction in Cloud Service Data Center, https: / / ieeexplore.ieee.org / document / 9190321.
[0007] In the area of abnormality detection, anomaly detection techniques and algorithms are taking the lead. This has e.g. been described in Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series, Dan Li, Dacheng Chen, Jonathan Goh, and See-Kiong Ng, arXiv:1809.04758v3 [cs.LG] 15 Jan 2019; Multi-head enhanced selfattention network for novelty detection, and Yingying Zhang, Yuxin Gong, Haogang Zhu, Xiao Bai, Wenzhong Tang, Pattern Recognition 107 (2020) 107486; Multivariate Time-series Anomaly Detection via Graph Attention Network, Hang Zhao et al, https: / / arxiv.org / pdf / 2009.02040.pdf.
[0008] Abnormality when used herein e.g., means behaviour that deviates from the norm, and anomaly when used herein e.g., means behaviour that deviates from the norm. These two terms are used interchangeably in this document.
[0009] As for discovering weakness in the system, it is noticeable that testing and trying different ways of damaging a digital representation of the target system are very common approaches to conduct such task. This is performed to avoid applying harmful actions on the target system. Discovering weaknesses in the context of security usually referred to as penetration testing. This is e.g., described in Penetration Testing == POMDP Solving?, Carlos Sarraute et al, https: / / arxiv.org / pdf / 1306.4714.pdf; POMDP + Information-Decay: Incorporating Defender’s Behaviour in Autonomous Penetration Testing, Jonathon Schwartz et al, https: / / ojs.aaai.org / index.php / ICAPS / article / view / 6666 / 6520; Hierarchical reinforcement learning for efficient and effective automated penetration testing of large networks, Mohamed C. Ghanem, et al,https: / / link.springer.com / content / pdf / 10.1007 / s10844-022-00738-0.pdf.
[0010] For Malfunctioning or failure, failure testing or Adaptive Stress Testing has been used. When building a digital representation of a target physical system, digital twin techniques have been used widely. This is e.g. described in Digital Twins for CyberPhysical Systems Security. State of the Art and Outlook, Matthias Eckhart and Andreas Ekelhar, Chapter November 2019, DOI: 10.1007 / 978-3-030-25312-7_14; Digital twins: artificial intelligence and the loT cyber-physical systems in Industry 4.0, Petar Radanliev et al, International Journal of Intelligent Robotics and Applications (2022) 6:171-185, https: / / doi.org / 10.1007 / s41315-021-00180-5; Integration of digital twin and deep learning in cyber-physical systems: towards smart manufacturing, Jay Lee et al, IET Collab. Intell. Manuf., 2020, Vol. 2 Iss. 1, pp. 34-36.
[0011] SUMMARY
[0012] As part of developing embodiments herein, the inventors identified some problems that first will be described.
[0013] In order to have a robust protection system capable of dealing with malfunctioning and failure in a system, e.g., a Target System (TS), several issues need to be addressed. Relying only on Anomaly Detection (AD), and / or Failure Prediction (FP) and / or FailureTesting (FT) without considering collaboration between them, would lead to some gaps in the whole process of protection. For example:
[0014] When relying only on Failure Prediction:
[0015] Advantages:
[0016] - It is possible to predict, even when considering online prediction, a future malfunctioning or failure based on current and / or previous system’s state and then decide possible Counter Measures (CM).
[0017] Drawbacks:
[0018] - A scenario that would lead to that malfunctioning or failure is unknown.
[0019] - It doesn’t involve how the Counter Measures will affect the system and how to deal with its possible new state after taking those counter measures.
[0020] A counter measure is e.g., a measure or action taken to counter or offset another action.
[0021] When relying only on Anomaly Detection:
[0022] Anomaly Detection alone cannot efficiently protect systems given the fact that Anomaly Detection -based protection systems act reactively to possible, maybe not real, problems. Furthermore, taking one or more counter measures based only on Anomaly Detection may affect the Quality of Service (QoS) or Quality of experience (QoE) where some anomalies, i.e., something different from expected, would not harm the system functionalities. A case where this may be applied is e.g., in the case of false positive, for example false alarms due to data distribution drift.
[0023] When relying only on Failure Testing:
[0024] Failure Testing may be handy in assessing the impact of an action on a system given its state and even simulate its future state or states after taking some possible counter measures, which will remedy the case when only Failure Prediction is considered. However, continuous Failure Testing would exhaust the protection system resources. Furthermore:
[0025] - On the one hand, running Failure Testing randomly may help in discovering unknown problems, e.g., exploration, but on the other hand, following this approach excessively would be a waste of time and resources as it would be running when the system is functioning well, and no problem does really exist.- Running Failure Testing for every new state would exhaust the resources of the protection system.
[0026] - Running the Anomaly Detection and Failure Testing models’ learning process without taking into consideration the importance, e.g., the level of abnormality, of a given state or the possible future damage that may occur given that state, would result in a longer and / or low-performing training process of a Failure Testing model and consequently, underperforming protection system.
[0027] An object of embodiments herein is to improve the handling of malfunctioning and failure in a target system.
[0028] According to an aspect of embodiments herein, the object is achieved by a method performed by a control node controlling a protection system. The method is for performing an action relating to preventive protection of a Target System in a network. The control node obtains output data relating to an Anomaly Detection and a Failure Prediction related to the TS. The output data from the AD comprises an anomaly score related to a state of the TS, and the output data from the FP comprises a failure prediction score related to a future state of the TS. The control node runs a Failure Testing for the TS, by interacting with a Digital Target System, DTS, representing the TS. This is to simulate adversarial actions for the TS. The Failure Testing is triggered based on the output data relating to the anomaly score and the failure prediction score. The control node then performs an action relating to preventive protection for the TS, based on the output data of the run Failure Testing.
[0029] According to another aspect of embodiments herein, the object is achieved by a control node adapted to control a protection system. The control node is configured to perform an action related to preventive protection of a Target System, TS, in a network. The control node is further configured to obtain output data related to an Anomaly Detection and a Failure Prediction related to the TS. The output data from the Anomaly Detection is adapted to comprise an anomaly score related to a state of the TS and the output data from the Failure Prediction comprises a failure prediction score related to a future state of the TS. The control node is further configured to run a Failure Test for the TS, by an interaction with a Digital Target System, DTS, adapted to represent the TS. This is to simulate adversarial actions for the TS, which Failure Testing is adapted to be triggered based on the output data related to the anomaly score and the failure predictionscore. The control node is further configured to perform an action related to preventive protection for the TS, based on the output data of the run Failure Testing.
[0030] Thanks to that the control node runs the Failure Testing triggered by and based on the output data relating to the anomaly score output data of the Anomaly Detection and the failure prediction score output data of the Failure Prediction, the control node can perform an action relating to preventive protection for the TS, based on the output data of the run Failure Testing. This results in better resource allocation and protection which in turn results in an improved handling of malfunction and failure in a TS.
[0031] Embodiments herein may provide one or more of the following advantages:
[0032] - A collaborative-preventive protection system that would help with better resource allocation and protection.
[0033] - A better Anomaly Detection, Failure Prediction, Failure Testing and Counter Measure models training based on anomaly, failure prediction and severity scores.
[0034] BRIEF DESCRIPTION OF THE DRAWINGS
[0035] Examples of embodiments herein are described in more detail with reference to attached drawings in which:
[0036] Figure 1 is a schematic block diagram illustrating embodiments of a network.
[0037] Figure 2 is a flowchart depicting an embodiment of a method in a control node.
[0038] Figure 3a is a sequence diagram illustrating an example embodiment of a method herein.
[0039] Figure 3b is a sequence diagram illustrating an example embodiment of a method herein.
[0040] Figure 3c is a sequence diagram illustrating an example embodiment of a method herein.
[0041] Figure 4a is a sequence diagram illustrating an example embodiment of a method herein.
[0042] Figure 4b is a sequence diagram illustrating an example embodiment of a method herein.
[0043] Figure 5 is a sequence diagram illustrating an example embodiment of a method
[0044] herein.Figures 6 a and b are a flowchart illustrating an example embodiment of a method herein.
[0045] Figure 7 is a schematic block diagram illustrating embodiments of a control node.
[0046] Figure 8 schematically illustrates embodiments of a communication system.
[0047] Figure 9 is a generalized block diagram of embodiments of a UE.
[0048] Figure 10 is a generalized block diagram of embodiments of a network node.
[0049] Figure 11 is a generalized block diagram of embodiments of a virtualization environment.
[0050] DETAILED DESCRIPTION
[0051] Embodiments herein, e.g., relate to anyone or more out of: Anomaly detection, failure prediction, failure prevention, malfunctioning, Reinforcement learning, Deep Reinforcement learning, Counter measure, Collaborative system, Protection system, Security and Cloud.
[0052] Embodiments herein provide a control node which controls a protection system, e.g. to monitor and take appropriate preventive actions by using a collaboration between an Anomaly Detection, a Failure Prediction and a Failure Testing. Embodiments herein e.g. provide the following:
[0053] • A collaborative protection system where anomaly scores of states would be used to trigger Failure Testing and the result of this last may be used to:
[0054] - Detect if there is a problem or not.
[0055] - Generate counter measures to face it.
[0056] - Predict the system’s status, including failure, for many steps ahead in the future and generate necessary counter measures for possible failures.
[0057] • An improved Anomaly Detection and Failure Prediction models training through a better data selection for training, validation, and testing of datasets, where the severity of data point, which represents the TS’s state, would be used in data points selection.
[0058] • An improved Failure Testing model training process by considering the abnormality of a given state, such as AD anomalies score, and failure prediction score amongst the coefficients used to select samples during the training of the model.
[0059] Figure 1 is a schematic overview depicting a network 100 wherein embodiments herein may be implemented. The network 100 may be a telecommunications network such as a wireless communications network comprising one or more Radio AccessNetwork (RAN)s, and one or more Core Network (CN)s, such as e.g. a communications network that may use 5G NR but may further use a number of other different technologies, such as, 6G, Wi-Fi, Long Term Evolution (LTE), LTE-Advanced, Wideband Code Division Multiple Access (WCDMA), Global System for Mobile communications / enhanced Data rate for GSM Evolution (GSM / EDGE), Worldwide Interoperability for Microwave Access (WiMax), or Ultra Mobile Broadband (UMB), just to mention a few possible implementations.
[0060] A protection system 101 is operating in the network 100. The Protection system 101 when used herein may e.g. relate to anomaly detection, failure prediction and failure testing modules.
[0061] A control node 110 operates in the network 100 and is controlling the Protection system 101 and processes therein. The control node 110 may e.g. be a control unit, a User Equipment (UE) or a processing unit. The control node 110 may be operating wired or wirelessly from a remote distance or be integrated into e.g., the protection system 101. The control node 110 may be communicating with the Protection system 101, a target system 101 and / or a Digital Target System 103 independently or codependently over the network. The communication may be operated wired or wirelessly from an integrated or remote position.
[0062] A Target system (TS) 102 is operating in the network 110. The word “target” in the TS 102 e.g. refers to the system to be protected. The TS 102 may e.g. relate to a web Server.
[0063] The TS 102 is the system that is to be protected by the control node 110 of the protection system 101 and may be communicating with the Protection system 101, the control node 110 and the Digital target system 103 independently or codependently over the network. The communication may be operated wired or wirelessly from an integrated or remote position.
[0064] A Digital Target System (DTS) 103 operates in the network 100. The DTS 103 is a digital representation of the TS102. The DTS103 may be communicating with the protection system 101, the control node 110 and / or the TS102 independently or codependently over the network. The communication may be operated wired or wirelessly from an integrated or remote position.Methods according to embodiments herein are performed by the control node 110. This node may be a Distributed Node (DN) and functionality, e.g. comprised in a cloud 170.
[0065] Embodiments herein may relate to any one or more out of: Use of Anomaly Detection and Failure Prediction scores to trigger a Failure Testing process and then the Counter Measures generation. Use of Anomaly Detection and Failure Prediction scores in the selection process of samples for Failure Testing model training. Use of severity to select data for Anomaly Detection and Failure Prediction models training.
[0066] When used herein, Anomaly Detection score, AD score, anomaly score and abnormality score may be used interchangeably.
[0067] A number of embodiments will now be described, some of which may be seen as alternatives, while some may be used in combination.
[0068] A method according to embodiments herein will first be described as seen from the view of the control node 110 together with Figure 2.
[0069] Figure 2 shows example embodiments of a method performed by the control node 110 controlling the protection system 101. The method is for performing an action relating to preventive protection of the Target System (TS) 102, in the network 100. The method comprises the following actions, which actions may be taken in any suitable order.
[0070] Action 201. The control node 110 obtains output data relating to an Anomaly Detection and a Failure Prediction related to the TS 102. The output data from the Anomaly Detection comprises an anomaly score related to a state of the TS 102. The output data from the Failure Prediction comprises a failure prediction score related to a future state of the TS 102.
[0071] An anomaly score when used herein e.g. means a score representing how much a behavior is deviated from normal, usual or expected behavior. A failure prediction score when used herein e.g. means a score representing the likelihood of a failure in the future.Action 202. The control node 110 runs a Failure Testing for the TS 102. This is performed by interacting with the Digital Target System (DTS) 103 representing the TS 102 to simulate adversarial actions for the TS 102. An adversarial action when used herein e.g. means an action that may affect a system in a negative way. The Failure Testing is triggered based on the output data relating to the anomaly score and the failure prediction score. This is an advantage since leveraging these two scores would reduce the number of times the failure testing is triggered, which results in reduced resources usage.
[0072] Action 203. The control node 110 performs an action relating to preventive protection for the TS 102, based on the output data of the run Failure Testing. A preventive protection when used herein e.g. means one or a series of actions leading the TS 102 to a required state and / or to avoid a harmful state.
[0073] The action relating to preventive protection for the TS 102 may e.g. further be dropping some requests to reduce resources usage to keep the TS functional.
[0074] Action 204. In some embodiments the control node 110 performs the action relating to preventive protection for the TS 102 by determining whether or not there is a potential failure in the TS 102.
[0075] Action 205. In some embodiments the control node 110 performs the action relating to preventive protection for the TS 102 by, when it is determined to be a potential failure, generating counter measures to prevent the potential failure. This e.g. means that generating an action that may lead the TS 102 to the required state or avoid a potential failure, e.g. by dropping some requests that require an amount of resources which can reduce the TS 102 functioning.
[0076] Action 206. In some embodiments the control node 110 performs the action relating to preventive protection for the TS 102 by predicting the status of the TS 102 for a number of steps ahead in the future and generate necessary counter measures for possible failures. The status may comprise anyone or more out of: failure, abnormality and weakness of the TS 102.In this way by using the methods above, avoiding failure would be more accurate with less amount of resource usages to achieve the same results if collaboration between Anomaly Detection, Failure Prediction and Failure Testing is not considered.
[0077] As already mentioned, the control node 110 controls the protection system 101 to e.g., monitor and take appropriate preventive actions by using the collaboration between the Anomaly Detection, Failure Prediction and Failure Testing in order to maintain services and availability up and to achieve a performance as expected in the SLA.
[0078] Embodiments herein such as the embodiments mentioned above will now be further described and exemplified. The text below is applicable to and may be combined with any suitable embodiment described above.
[0079] Taking a web server as a use case for representing the TS 102, a state at a given point of time may serve as input value for the Anomaly Detection and Failure Prediction. This web server may be represented for example with its resources’ usage and temperature, if applicable. Examples of resources’ usage and resources’ temperature may e.g. relate to any one or more of a Central Processing Unit (CPU) or Graphics Processing Unit (GPU), Random-Access Memory (RAM), storage space, Virtual memory, number of packets, e.g., per protocol, and their average size received in the predefined time units and the number of different IP trying to connect to the web server, etc.
[0080] KPIs may be used to calculate the impact of an adversarial action or a counter measure on the TS 102, and / or when the number of unserved requests in the server’s queue is high, e.g., to minimize resources’ usage or temperature.
[0081] Requests, such as requests to access TS 102, in this example the web server, for a purchase may have different importance, e.g., weights. For example, requests to access the server related to purchase would have more importance than those related to just viewing web pages.
[0082] As actions that may lead to failure, e.g., adversarial actions, a sequence of requests that may exhausts the server’s resources and lead the server to crash may be an example, such as excessive number of requests for simulations, e.g., pricing simulations.
[0083] As hinted above, counter measures may be one or a series of actions to be taken to deal with a current state or avoid undesirable future state of the target system. A counter measure when used herein e.g. means a preventive action or series of actions in order to protect the target system 102, Actions may be active. This means that actions may lead toa change of the system’s state, e.g., by making more memory available or by decreasing CPU usage. Actions may also be passive, which means that actions that do not lead to any change, literally does nothing.
[0084] Continuing with the example where the TS 102 is a web server. In this example counter measure actions may be for example, a sequence of dropping of requests of different or the same importance level. When used herein, a sequence of dropping of requests means for example removing requests from the services queue and their related data from memory. In some embodiments, an action may be to perform automatic memory management. This may be performed by launching garbage collector to free memory space or remove old or all data from the server’s cache. Such actions, would help in anyone or more out of:
[0085] - Avoid the system from crashing.
[0086] - Avoid or deal with the denial of service.
[0087] - Reducing the number of unserved requests.
[0088] - Serving the maximum of highly important requests, yet avoid crashing, which means, maybe dropping some important requests would be the best action to maintain the whole service.
[0089] This is related to and may be combined with Action 203, 205 and 206 mentioned above.
[0090] A number of embodiments will now be described as overcoming the problems mentioned above:
[0091] Consider a preventive approach for the TS 102 based on the collaboration between Anomaly Detection, Failure Prediction and Failure Testing, where the Anomaly Detection outputs a states’ anomaly score, and the Failure Prediction outputs a failure prediction score. A score, when used herein relate to a rated value representing a level on a scale, e.g., a value with a higher or lower anomaly rate and / or a higher or lower failure prediction rate. In some embodiments, the score is a value on a numerical scale. The score may in some embodiments be a Boolean value. These scores would be used to trigger the Failure Testing. On its turn, the Failure Testing would work on the predictive approach to simulate the adversarial actions. This would be performed by the failure testing module. Then, the counter measures evaluator assesses counter measures generated by the counter measures generator. The counter measure or measures may be used to lead the TS states to a desirable state or to avoid an undesirable one. In other words, the countermeasures may prevent a potential failure. This is related to and may be combined with Action 202 mentioned above.
[0092] Such approach makes the protection system 101 always steps ahead against any crash or malfunctioning and consequently, future damage.
[0093] High level architecture of some embodiments:
[0094] Before getting into more details, a summary of the Anomaly Detection, Failure Prediction, Failure Testing and Counter Measure generator roles will be described.
[0095] Anomaly Detection:
[0096] Input: A data point may be represented by the Target System’s 102 State at a given point of time or during a window of time for example.
[0097] Output: Anomaly score that tells how likely this is an abnormal state for that Target system.
[0098] Objective: Tells how abnormal a given state is.
[0099] Failure Prediction:
[0100] Input: A data point may be represented by the Target System’s 102 State at a given point of time or during a window of time for example.
[0101] Output: Anomaly score that tells how likely in the future, given this state, the target system will crash or fail for example.
[0102] Objective: Predict the malfunctioning or failure of a system given its current, past, or combination of states.
[0103] Failure Testing:
[0104] Input: Sequence of states.
[0105] Output: Sequence of episodes, e.g., states, actions and / or rewards.
[0106] Objective: Infer the actions that led the system to its current state and then predict the subsequent actions that would lead that system to failure. These outputs will be used to prepare counter measure to avoid and deal with the failure before it happens.
[0107] Counter Measure generator:
[0108] Input: Failure Testing generated episode’s data.
[0109] Outputs: The actions to be executed in order to improve the TS’s 102 state.Figures 3a, 3b and 3c depicts three parts of an example of a sequence diagram of embodiments herein of the collaborative protection system 101, e.g. comprising Anomaly Detection, Failure Prediction, Failure Testing and Counter Measure. E.g., AF2C, comprising the above-mentioned Anomaly Detection, Failure Prediction, Failure Testing and Counter Measure Collaborative protection system.
[0110] The labels’ in Figures 3a, 3b and 3c are represented as below:
[0111] 1. Target system’s information and state
[0112] 2. Target system’s prepared information and state
[0113] 3. Target system’s information and anomaly score
[0114] 4. Target system’s information and Failure prediction score
[0115] 5. Target System information, anomaly score, failure prediction score
[0116] 6. Failure testing action
[0117] 7. Digital target system new state
[0118] 8. Failure test Report Message
[0119] 9. Failure testing generated state or states
[0120] 10. Anomaly score or scores
[0121] 11. Failure prediction score or scores
[0122] 12. Sequence of Episodes, Anomaly and Failure prediction scores
[0123] 13. Counter measure generator action
[0124] 14. Digital target system’s new state
[0125] 15. Counter measures
[0126] 16. Counter measures evaluation report
[0127] In Figures 3a, 3b and 3c, the TS 102 represents the system to be protected and the DTS 103 module mimics the TS 102, e.g., as a simulator. The Data collection and Preparation (DP) module is for data collection, pre-processing, feature engineering, etc., to be used adequately by other modules, such as the Anomaly Detection and Failure Prediction modules.
[0128] On receiving data from the TS 102, The DP prepares data for the Anomaly Detection and Failure Prediction. Examples of received data herein may be, the TS resources’ usage and temperature. If applicable, other examples of received data may be CPU or GPU type, RAM, stockage space, Virtual memory, number of packets, e.g., per protocol, and their average size received in predefined number of time units and thenumber of different IP addresses trying to connect to the server. In some embodiments, such as when the TS 102 is a web server, a request’s importance, may be applicable as received data.
[0129] Anomaly Detection module: Based on the prepared data coming from the DP, this module e.g., an Al or ML model, may output an anomaly score reflecting how abnormal this prepared data is. The prepared data represents the system’s state, which in its turn may be an indicator of how unusual the current state of the TS is.
[0130] Failure Prediction module: Based on the prepared data coming from the DP, this module, which may be an Al or ML model, outputs a failure prediction score reflecting how likely the system will fail in the future.
[0131] Failure Testing Trigger (FTT): The FTT Triggers the Failure Testing based on the Anomaly Detection and Failure Prediction outputs. This is related to and may be combined with any one or more out of Actions 201, 202 and 203 mentioned above.
[0132] For a given sequence of length L of states s, where L, A, F, atand f are hyperparameters to tune the FTT, where L represents the number of states considered to calculate the triggering score, atcorresponds to a weight given to the anomaly score of state Sj. f correspond to a weight given to the failure prediction score of state st. A and F refer to weight of total anomaly scores and failure prediction scores respectively. FTT calculates the triggering score as follows:
[0133]
[0134] The failure testing will run if:
[0135] The triggering score is greater than a predefined threshold. Then N number of subsequent states, which may be predefined, along with their Anomaly Detection and Failure Prediction scores, will be generated to be used for subsequent steps, e.g., in the Failure Testing, learning process, Or
[0136] If no Failure Testing has been triggered in a predefined number of time units, the FTT may trigger a Failure Testing to run.
[0137] Otherwise, no failure testing will be executed.
[0138] Failure Testing module: This module interacts with the DTS 103 to run a simulation by generating episodes, e.g., actions or series of actions. This may be performed by using a Reinforcement Learning (RL)-agent, to get the expected new statefrom the DTS 103 or to calculate rewards. Examples of calculated rewards may be KPIs values such as number of requests served in a given number of time units.
[0139] Failure test Report Message (FRM): It includes all the information needed to identify a failure test ran for a given TS, such as TS 102 based on a given data. Examples of given data herein may be TS id, timestamp, and id of the received sample of data, failure test episodes and the Anomaly Detection and Failure Prediction scores of each state in these episodes.
[0140] Protection Input Message preparation (PIM): Prepares the input for the Counter measures generator based on:
[0141] Necessary information, such as e.g., the ID of the TS 102 or the received data ID.
[0142] - Anomaly and failure prediction scores related to the received data, e.g., representing the TS’s current and future state, and:
[0143] - The FRM If the failure test took place.
[0144] Afterwards, PIM will send this information as Sequence of Episodes (SEAF) comprising e.g., the Anomaly Detection and Failure Prediction scores to the Counter measure generator.
[0145] The Counter measure generator may generate counter measures to deal with possible failure.
[0146] Counter Measure Evaluator (CME): The CME assesses the counter measures, if needed, related to the received SEAF. Through interacting with DTS 103, the impact of the identified counter measures will be evaluated before sending them to the TS 102 as a Counter measures evaluation report. By doing so, the counter measures ensure effectiveness or efficiency and safety, and they won’t drive the system to an undesirable state. This is related to and may be combined with any one or more out of Actions 202, 203, 204 and 205 mentioned above.
[0147] In the following sections, more details are given on how the method according to some embodiments herein may be running.
[0148] Set up Failure testing:
[0149] Firstly, two types of sequence of states need to be distinguished:
[0150] Sequence of Real States (SRS), which comprises a sequence of real states. When used herein, real states means e.g., detected status of the real TS.Sequence of Expected states (SES), which comprises a sequence of generated states, e.g., generated by the DTS 103. When used herein, generated states means e.g., expected status of the TS.
[0151] The length of these sequences may be predefined parameters. In some embodiments, they may be defined based on allowed test duration. For example, a longer test duration may result in longer sequences.
[0152] A severity score may also be calculated. The severity score may be considered as the level of damage caused to the system given a specific state. For example, considering the case where the TS 102 is a web server, the severity of a given state may be considered as the length of the unserved requests queue during a given window of time. This is related to and may be combined with action 202 mentioned above.
[0153] Running Failure testing:
[0154] There are two phases:
[0155] In the first one, phase 1, the Failure Testing is trying to follow the same path of a presumed crash or malfunctioning, and by interaction with the DTS, it generates adversarial actions for SRS.
[0156] In the second one, phase 2, the Failure Testing will try to imagine what would be the states, e.g., SES, of the TS given SRS, which will help in predicting possible future problems and estimate their impacts. This is related to and may be combined with action 202 mentioned above.
[0157] Figures 4a and 4b depicts an RL-based example of a Failure Testing model.
[0158] Figure 4a is a representation of phase 1. In some embodiments Phase 1 is represented as a following phase and may be described as below. When used herein, following phase means, as already mentioned, that the Failure Testing are trying to follow the same path of a presumed crash or malfunctioning
[0159] By using SRS, the Failure Testing, in interaction with the DTS, will execute their corresponding actions and calculate the returned rewards to have a sequence comprising anyone or more out of: real statet, generated actiont, generated statet, generated statetand real rewardt.
[0160] It is easiest to explain the interaction between the Failure Testing and the DTS in phase 1 by an example. Let’s say, on the TS 102 level, that two consecutive states and the reward estimated at the last one, i.e. , real statet-i, real statetand / or real rewardthave been recorded. When having input real statet-i and real statet, as the Failure Testing executes a generated actiontat DTS which in its turn generates a statetand a rewardt. which makes the tuple. A tuple, when described herein e.g., means an ordered sequence of values comprising, e.g., as previously mentioned anyone or more out of: real statet, generated actiont, generated statet, generated rewardtand real rewardt.
[0161] For example, if real states St-i and St of a web server, e.g., TS 102, states are represented by CPU usage rate and memory usage rate. Then the DTS should first exhibit the same state St-i , and the Failure Testing, will generate and execute an actiont, such as a specific number of requests to the DTS, e.g., number of request web page p1 =P1 , number of request web page p2 = P2, etc. A reward may be represented for this example as the KPI values changes between State St-i and State St. In some embodiments, a reward may be the number of unserved requests in the real web server’s queue at a time point t or the difference of unserved requests between the time point t-1 and t. This is related to and may be combined with action 202 mentioned above.
[0162] In this case, the severity score of a given St is the reward calculated for that state. In general, if the difference between real and generated states and / or rewards, e.g., at the same time step, is greater than a predefined threshold. Then this may mean that the Failure Testing, possibly, is unable to track the presumed malfunctioning. To calculate the reliability of the Failure Testing, the difference between the real and generated states and rewards may be used as follows, where a, p and y are tunable coefficients, a refers to state distance’s weight, refers to reward distance’s weight when calculating Step’s reliability and y refers to reward distance’s weight when calculating adjusted reward’s.
[0163] States distancet= Distancejreal statet, generated statet) (2) Rewards distancet= Distancejreal rewar dt, generated rewar dt) (3)
[0164] Step s reliabilityt= a. state distancet+ / 3. rewards ' distancet(4) Adjusted rewardt= generated rewardt— y. rewards ' distancet(5)
[0165] Severity score(Statejt= reward(State)t(6) For an episode of M steps: (7)
[0166]
[0167] Distances may be calculated as Euclidian distance or based on any other formula. This is related to and may be combined with action 202 mentioned above.
[0168] Figure 4b is a representation of phase 2. In some embodiments Phase 2 is represented as an imagining phase and may be described as below: When used herein, imagining phase means, as already mentioned, that the Failure Testing will try to imagine what would be the states, e.g., SES, of the TS 102 given SRS, which will help in predicting possible future problems and estimate their impacts.
[0169] In some embodiments one or more F episodes are generated, which may be a predefined parameter. In each episode the Failure Testing model starts with the SRS corresponding steps then through interaction with DTS, another subsequent state will be generated as exemplified in Figure 4b. For example, if a given episode comprises 1... M real state, then:
[0170] - The first sequence of 1... M steps may be represented as follows:
[0171] stept= [real statet, generated actiont, Adjusted rewardt, real statet+i] Followed by a sequence of 1...Z steps which may be represented as follows: step M+X= [expected state M+X , generated action M+X, expected reward M+X, expected state M+X+I].
[0172] This is related to and may be combined with action 202 mentioned above.
[0173] Prepare and communicate testing results as exemplified in Figures 3a, 3b and 3c:
[0174] By preparing the FRM as a last step, the necessary information is communicated, which information for example comprises:
[0175] Failure Testing’s episodes and their states severity scores.
[0176] Failure Testing’s episodes’ reliability.
[0177] Necessary information to identify the test such as the ID of the TS 102, the ID of the test, datetime, etc.
[0178] The communication may then be performed by sending the FRM to the PIM. This is related to and may be combined with action 202 mentioned above.
[0179] On its turn, PIM:
[0180] Sends the episodes’ expected states, e.g., in the FRM, to Anomaly Detection and Failure Prediction to get their corresponding scores, which is exemplified in Figures 3a, 3b and 3c. Now all states, e.g., the real and expected states have their Anomaly Detection and Failure Prediction and severity scores.
[0181] Prepare and send the SEAF to the Counter measures generator.This is related to and may be combined with action 202 mentioned above.
[0182] Generate and communicate counter measures:
[0183] For each episode in SEAF, the counter measures generator generates counter measures sequence of actions.
[0184] The counter measures generator may be designed as an Al or ML model which gets as input, the episode’s related data and outputs the actions that may change the TS 102 to the desired one as exemplified in Figure 5.
[0185] For example, an input data point may be shaped as a time series, where each timestep may have as dimensions: the states, e.g., statet, statet+i, and the reward. In some embodiments, a developer may consider more, less and / or other dimensions if appropriate.
[0186] As output, the model may generate the sequence of actions to execute in order to reduce, e.g., the sum of rewards noticed in the input. In some embodiments the executed action reduces the mean, the max or all of them, depending on the application.
[0187] The sequence of states and their corresponding generated sequence of counter measure actions would be applied on the DTS 103 to get the impact, e.g., how they did reduce the impact of the problem, of those counter measures.
[0188] Also, the counter measures actions may be evaluated to ensure that they are safe. In some embodiments the Counter Measures Evaluator outputs a counter measure’s evaluation score for each action, e.g., through analyzing the DTS 103 after executing the action.
[0189] The Counter measure’s evaluation score values may be between [0, 1], In some embodiments, the greater the score is, the better. For instance, for a web server business, if a counter measure action drops all requests in the un-served requests queue this would be a very dangerous counter measure as it would violate the SLA. Consequently, it may get a low counter measure’s evaluation score. This is related to and may be combined with any one or more out of actions 203, 204 and 205 mentioned above.
[0190] Figure 5 exemplifies a Counter measures generation and evaluation. The Counter Measure Evaluator may generate a Counter Measure Evaluation Report (CMER). The CMER comprises the counter measures with their corresponding reliability, e.g., the Failure Testing’s episode reliability for the corresponding SEAF’s episode, and the evaluation scores to the TS 102. This report represents the possible impact of the counter measures on the TS 102, such as if they are safe and efficient. Considering the examplewhen the TS 102 is a web server, the counter measures would lead the system to a desired state, e.g., with a given KPI value, and won’t exhaust the system resources or lead it to crash or drop many service requests. This is related to and may be combined with any one or more out of actions 203, 204 and 205 mentioned above.
[0191] Figures 6a and 6b shows a training model of Anomaly Detection, Failure Prediction, Failure Testing and Counter Measure. Embodiments below will explain, how to improve Anomaly Detection, Failure Prediction, Failure Testing and Counter Measure models training processes.
[0192] The content of SEAF, which e.g., comprises the states and their corresponding severity may be used to improve samples selection for RL model training. This may be performed to build training, validation, and testing datasets used to train Anomaly Detection and / or Failure Prediction models and leveraging the Anomaly Detection and Failure Prediction scores.
[0193] The Anomaly Detection and Failure Prediction training process:
[0194] To improve the training process of the Anomaly Detection and Failure Prediction models, the focus is on data points selection to build training, validation, and testing datasets.
[0195] States may be, for example, of high, medium, and low severity, where thresholds to define the level of severity may be tunable, and the number of data points for each level may be tunable as well.
[0196] In case the severity level is also considered in the selection of data points, it will help models in detecting and predicting better. The focus will be more on harmful activities rather than just abnormal states, as for example in the case of Anomaly Detection.
[0197] In some embodiments, a data point selection probability may be considered as a weighted sum of its anomaly score, failure prediction score and severity score as calculated in eq 8, where (p", 3", p" are hyperparameters to be tuned. A given state, (p" refers to the weight given to anomaly detection score,
[0198]
[0199] which refers to the weight given to failure prediction score and p" refers to the weight given to severity score.
[0200] <" "
[0201]
[0202] "
[0203] Such approach may help in focusing more on the objective of such system which is to avoid damages and not only to detect if a state is abnormal or to predict that a problem would occur without assessing how the related counter measures would impact thesystem. This is related to and may be combined with any one or more out of actions 201, 202, 203, 204, 205 and 206 mentioned above.
[0204] The Failure Testing training process:
[0205] Consider the abnormality of a given state amongst the coefficients used to select samples during the training of a RL-based model. For example, in a priority-based experience replay based training process, states with higher abnormality scores should be considered more important than those with low scores, however the importance of the state’s anomaly scores in calculating the final priority score of a sample may be tuned along with other importance coefficients such as Reducible Loss and prioritizing with TD-error. When described herein, a priority-based experience replay based training process may relate to reinforcement learning techniques where more frequent replay transitions with high expected learning progress are based on their temporal-difference (TD) error.
[0206] When considering the failure prediction score and the severity scores it may also be a good approach in improving the process of selecting samples for the experience replay. Experience replay, when used herein, is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, et=(st, at, rt, st+1) in a data-set D=e1,---,eN, pooled over many episodes into a replay memory.
[0207] For example, In TD error technique each transition in the replay buffer is assigned a priority pi, and the transitions are sampled based on this priority. To ensure that data points, even with low TD error, are sampled sometimes by the agent, instead of greedy sampling based on TD error, the replay buffer in Prioritized Experience Replay (PER) stochastically samples point based on weight wi, where (a e[0, 1]):
[0208] (9)
[0209]
[0210] And the probability P_i equals to ( e[0, 1 ]):
[0211] p (10) p = — - —
[0212] 1P"
[0213] Instead of prioritization based on the TD error, the agent may focus on samples that have higher reducible TD error, where a measure called Reducible Loss (ReLo) of how much the TD error may be potentially decreased, should be used as the priority pi. Such approach would help the algorithm to avoid repeated sampling points that the agent has been unable to learn from, e.g., noisy or not learnable by the model. The agent mayinstead focus on minimizing error on points that are learnable, and thereby improving sample efficiency.
[0214] ReLo represents the difference between the loss of the data point with respect to the online network L_0 and with respect to the target network L_0tgt. The Reducible Loss (ReLo) may be computed as:
[0215] ReLo = Le- Letgt(1 1 )
[0216] In case the Anomaly Detection, Failure Prediction and / or severity scores would also be used in sampling, along with ReLo for example, and for a given data point, where T, (p, p and p' are parameters to be tuned, T represents ReLo weight. For a given two states Statet, Statet+1, cp and cp' represent weights of Anomaly scores, 3
[0217]
[0218] represent weights of failure prediction scores , and p and p' represent weight of severity scores of these two states respectively:
[0219]
[0220] This is related to and may be combined with action 202 mentioned above.
[0221] Counter Measure generator training process:
[0222] If the sum of Failure Testing’s actions’ corresponding rewards, e.g., of a given episode, is considered as the impact of malfunctioning and the sum of counter measure actions’ rewards, also mentioned as Counter Measure’s rewards, as the impact of counter measures. Then by assuming that the objective is to minimize the impact of the problem, e.g., by minimizing the malfunctioning, the loss may be calculated as follows:
[0223] Counter Measures’s impact = Counter Measure’s reward x Counter Measure’s evaluation score
[0224] Counter Measure model Loss = Counter Measure’s impact - Failure Testing’s impact
[0225] This is related to and may be combined with any one or more out of actions 203, 204 and 205 mentioned above.To perform the method actions above, the control node 110 is adapted to control the protection system 101 and is configured to perform an action related to preventive protection of the TS 102 in the network 100.
[0226] The control node 110 may comprise an arrangement depicted in Figure 7. The control node 110 may comprise an input and output interface 700 configured to communicate in the network 100, e.g., with the Protection system 101, the Target system 102 and Digital Target System 103. The input and output interface 700 may comprise a wireless receiver not shown, and a wireless transmitter not shown.
[0227] The control node is further configured to obtain output data related to an Anomaly Detection and a Failure Prediction related to the TS 102. The output data from the Anomaly Detection is adapted to comprise an anomaly score related to a state of the TS 102 and the output data from the Failure Prediction comprises a failure prediction score related to a future state of the TS 102.
[0228] The control node is further configured to run a Failure Testing for the TS 102, by an interaction with the DTS 103 adapted to represent the TS 102, to simulate adversarial actions for the TS 102. The Failure Testing is adapted to be triggered based on the output data related to the anomaly score and the failure prediction score.
[0229] The control node is further configured to perform an action related to preventive protection for the TS 102, based on the output data of the run Failure Testing.
[0230] The action related to preventive protection may be adapted to relate to leading the TS 102 to a required state and / or to avoid a harmful state.
[0231] The control node 110 may further be configured to perform an action related to preventive protection for the TS 102 by any one or more out of:
[0232] Determine whether or not there is a potential failure in the TS 102,
[0233] when it is determined to be a potential failure, generate counter measures to prevent the potential failure, and / or
[0234] predict the status of the TS 102 adapted to comprise anyone or more out of: failure, abnormality and weakness of the TS 102 for a number of steps ahead in the future and generate necessary counter measures for possible failures.
[0235] Embodiments herein may be implemented through a processor or one or more processors, such as the processor 710 of a processing circuitry in the control node 110 depicted in Figure 7, together with respective computer program code for performing the functions and actions of the embodiments herein. The program code mentioned above may also 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 whenbeing loaded into the control node 110. 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 control node 110.
[0236] The control node 110 may further comprise a memory 720 comprising one or more memory units. The memory 720 comprises instructions executable by the processor in the control node 110. The memory 720 is arranged to be used to store e.g., media functions, indications, tags, information, data, configurations, communication data, and applications to perform the methods herein when being executed in the control node 110.
[0237] In some embodiments, a computer program 730 comprises instructions, which when executed by the at least one processor 710, cause the at least one processor of the control node 110 to perform the actions above.
[0238] In some embodiments, a carrier 740 comprises the computer program 730, wherein the carrier 740 is one of an electronic signal, an optical signal, an electromagnetic signal, a magnetic signal, an electric signal, a radio signal, a microwave signal, or a computer-readable storage medium.
[0239] Those skilled in the art will appreciate that units in the control node 110 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 the control node 110, that when executed by the one or more processors such as the processors described above. One or more of these processors, as well as the other digital hardware, may be included in a single Application-Specific Integrated Circuitry 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).
[0240] Figure 8 shows an example of a communication system QQ100 in accordance with some embodiments.
[0241] In the example, the communication system QQ100 includes a telecommunication network QQ102 that includes an access network QQ104, such as a radio access network (RAN), and a core network QQ106, which includes one or more core network nodes QQ108. The access network QQ104 includes one or more access network nodes, such as network nodes QQ110a and QQ110b (one or more of which may be generally referred to as network nodes QQ110), or any other similar 3rd Generation Partnership Project (3GPP) access nodes or non-3GPP access points. Moreover, as will be appreciated by those of skill in the art, a network node is not necessarily limited to an implementation inwhich a radio portion and a baseband portion are supplied and integrated by a single vendor. Thus, it will be understood that network nodes include disaggregated implementations or portions thereof. For example, in some embodiments, the telecommunication network QQ102 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a node in the telecommunication network QQ102 that supports an ORAN specification (e.g., a specification published by the O-RAN Alliance, or any similar organization) and may operate alone or together with other nodes to implement one or more functionalities of any node in the telecommunication network QQ102, including one or more network nodes QQ110 and / or core network nodes QQ108.
[0242] Examples of an ORAN network node include an open radio unit (0-Rll), an open distributed unit (0-Dll), an open central unit (O-CU), including an O-CU control plane (O-CLI-CP) or an O-CU user plane (O-CU-UP), a RAN intelligent controller (near-real time or non-real time) hosting software or software plug-ins, such as a near-real time control application (e.g., xApp) or a non-real time control application (e.g., rApp), or any combination thereof (the adjective “open” designating support of an ORAN specification). The network node may support a specification by, for example, supporting an interface defined by the ORAN specification, such as an A1, F1, W1, E1, E2, X2, Xn interface, an open fronthaul user plane interface, or an open fronthaul management plane interface. Moreover, an ORAN access node may be a logical node in a physical node. Furthermore, an ORAN network node may be implemented in a virtualization environment (described further below) in which one or more network functions are virtualized. For example, the virtualization environment may include an O-Cloud computing platform orchestrated by a Service Management and Orchestration Framework via an 0-2 interface defined by the O-RAN Alliance or comparable technologies. The network nodes QQ110 facilitate direct or indirect connection of user equipment (UE), such as by connecting UEs QQ112a, QQ112b, QQ112c, and QQ112d (one or more of which may be generally referred to as UEs QQ112) to the core network QQ106 over one or more wireless connections.
[0243] Example wireless communications over a wireless connection include transmitting and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information without the use of wires, cables, or other material conductors. Moreover, in different embodiments, the communication system QQ100 may include any number of wired or wireless networks, network nodes, UEs, and / or any other components or systems that may facilitate or participate in the communication of data and / or signals whether via wired or wireless connections. The communication system QQ100 may include and / or interface with anytype of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.
[0244] The UEs QQ112 may be any of a wide variety of communication devices, including wireless devices arranged, configured, and / or operable to communicate wirelessly with the network nodes QQ110 and other communication devices. Similarly, the network nodes QQ110 are arranged, capable, configured, and / or operable to communicate directly or indirectly with the UEs QQ112 and / or with other network nodes or equipment in the telecommunication network QQ102 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in the telecommunication network QQ102.
[0245] In the depicted example, the core network QQ106 connects the network nodes QQ110 to one or more host computing systems, such as host QQ116. These connections may be direct or indirect via one or more intermediary networks or devices. In other examples, network nodes may be directly coupled to hosts. The core network QQ106 includes one more core network nodes (e.g., core network node QQ108) that are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the UEs, network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node QQ108. Example core network nodes include functions of one or more of a Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (AUSF), Subscription Identifier De-concealing function (SIDF), Unified Data Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).
[0246] The host QQ116 may be under the ownership or control of a service provider other than an operator or provider of the access network QQ104 and / or the telecommunication network QQ102. The host QQ116 may host a variety of applications to provide one or more service. Examples of such applications include live and pre-recorded audio / video content, data collection services such as retrieving and compiling data on various ambient conditions detected by a plurality of UEs, analytics functionality, social media, functions for controlling or otherwise interacting with remote devices, functions for an alarm and surveillance center, or any other such function performed by a server.
[0247] As a whole, the communication system QQ100 of Figure 8 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication systemmay be configured to operate according to predefined rules or procedures, such as specific standards that include, but are not limited to: Global System for Mobile Communications (GSM); Universal Mobile Telecommunications System (UMTS); Long Term Evolution (LTE), and / or other suitable 2G, 3G, 4G, 5G standards, or any applicable future generation standard (e.g., 6G); wireless local area network (WLAN) standards, such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards (WiFi); and / or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (WiMax), Bluetooth, Z-Wave, Near Field Communication (NFC) ZigBee, LiFi, and / or any low-power wide-area network (LPWAN) standards such as LoRa and Sigfox.
[0248] In some examples, the telecommunication network QQ102 is a cellular network that implements 3GPP standardized features. Accordingly, the telecommunications network QQ102 may support network slicing to provide different logical networks to different devices that are connected to the telecommunication network QQ102. For example, the telecommunications network QQ102 may provide Ultra Reliable Low Latency Communication (URLLC) services to some UEs, while providing Enhanced Mobile Broadband (eMBB) services to other UEs, and / or Massive Machine Type Communication (mMTC) / Massive loT services to yet further UEs.
[0249] In some examples, the UEs QQ112 are configured to transmit and / or receive information without direct human interaction. For instance, a UE may be designed to transmit information to the access network QQ104 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network QQ104. Additionally, a UE may be configured for operating in single- or multi-RAT or multi-standard mode. For example, a UE may operate with any one or combination of Wi-Fi, NR (New Radio) and LTE, i.e. being configured for multi-radio dual connectivity (MR-DC), such as E-UTRAN (Evolved-UMTS Terrestrial Radio Access Network) New Radio - Dual Connectivity (EN-DC).
[0250] In the example, the hub QQ114 communicates with the access network QQ104 to facilitate indirect communication between one or more UEs (e.g., UE QQ112c and / or QQ112d) and network nodes (e.g., network node QQ110b). In some examples, the hub QQ114 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub QQ114 may be a broadband router enabling access to the core network QQ106 for the UEs. As another example, the hub QQ114 may be a controller that sends commands or instructions to one or more actuators in the UEs. Commands or instructions may bereceived from the UEs, network nodes QQ110, or by executable code, script, process, or other instructions in the hub QQ114. As another example, the hub QQ114 may be a data collector that acts as temporary storage for UE data and, in some embodiments, may perform analysis or other processing of the data. As another example, the hub QQ114 may be a content source. For example, for a UE that is a VR device, display, loudspeaker, or other media delivery device, the hub QQ114 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub QQ114 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub QQ114 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy loT devices.
[0251] The hub QQ114 may have a constant / persistent or intermittent connection to the network node QQ110b. The hub QQ114 may also allow for a different communication scheme and / or schedule between the hub QQ114 and UEs (e.g., UE QQ112c and / or QQ112d), and between the hub QQ114 and the core network QQ106. In other examples, the hub QQ114 is connected to the core network QQ106 and / or one or more UEs via a wired connection. Moreover, the hub QQ114 may be configured to connect to an M2M service provider over the access network QQ104 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes QQ110 while still connected via the hub QQ114 via a wired or wireless connection. In some embodiments, the hub QQ114 may be a dedicated hub - that is, a hub whose primary function is to route communications to / from the UEs from / to the network node QQ110b. In other embodiments, the hub QQ114 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node QQ110b, but which is additionally capable of operating as a communication start and / or end point for certain data channels.
[0252] Figure 9 shows a UE QQ200 in accordance with some embodiments. The UE QQ200 presents additional details of some embodiments of the UE QQ112 of Figure 8. As used herein, a UE refers to a device capable, configured, arranged and / or operable to communicate wirelessly with network nodes such as e.g the control node 110 and / or other UEs. Examples of a UE include, but are not limited to, a smart phone, mobile phone, cell phone, voice over IP (VoIP) phone, wireless local loop phone, desktop computer, personal digital assistant (PDA), wireless cameras, gaming console or device, music storage / playback device, wearable terminal device, wireless endpoint, mobile station,tablet, laptop, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), an Augmented Reality (AR) or Virtual Reality (VR) device, wireless customer-premise equipment (CPE), vehicle, vehicle-mounted or vehicle embedded / integrated wireless device, etc. Other examples include any UE identified by the 3rd Generation Partnership Project (3GPP), including a narrow band internet of things (NB-loT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.
[0253] A UE may support device-to-device (D2D) communication, for example by implementing a 3GPP standard for sidelink communication, Dedicated Short-Range Communication (DSRC), vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), or vehicle-to-everything (V2X). In other examples, a UE may not necessarily have a user in the sense of a human user who owns and / or operates the relevant device. Instead, a UE may represent a device that is intended for sale to, or operation by, a human user but which may not, or which may not initially, be associated with a specific human user (e.g., a smart sprinkler controller). Alternatively, a UE may represent a device that is not intended for sale to, or operation by, an end user but which may be associated with or operated for the benefit of a user (e.g., a smart power meter).
[0254] The UE QQ200 includes processing circuitry QQ202 that is operatively coupled via a bus QQ204 to an input / output interface QQ206, a power source QQ208, a memory QQ210, a communication interface QQ212, and / or any other component, or any combination thereof. Certain UEs may utilize all or a subset of the components shown in Figure 9. The level of integration between the components may vary from one UE to another UE. Further, certain UEs may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.
[0255] The processing circuitry QQ202 is configured to process instructions and data and may be configured to implement any sequential state machine operative to execute instructions stored as machine-readable computer programs in the memory QQ210. The processing circuitry QQ202 may be implemented as one or more hardware-implemented state machines (e.g., in discrete logic, field-programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), etc.); programmable logic together with appropriate firmware; one or more stored computer programs, general-purpose processors, such as a microprocessor or digital signal processor (DSP), together with appropriate software; or any combination of the above. For example, the processing circuitry QQ202 may include multiple central processing units (CPUs).
[0256] In the example, the input / output interface QQ206 may be configured to provide an interface or interfaces to an input device, output device, or one or more input and / oroutput devices. Examples of an output device include a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smartcard, another output device, or any combination thereof. An input device may allow a user to capture information into the UE QQ200. Examples of an input device include a touch-sensitive or presence-sensitive display, a camera (e.g., a digital camera, a digital video camera, a web camera, etc.), a microphone, a sensor, a mouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smartcard, and the like. The presence-sensitive display may include a capacitive or resistive touch sensor to sense input from a user. A sensor may be, for instance, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, a biometric sensor, etc., or any combination thereof. An output device may use the same type of interface port as an input device. For example, a Universal Serial Bus (USB) port may be used to provide an input device and an output device.
[0257] In some embodiments, the power source QQ208 is structured as a battery or battery pack. Other types of power sources, such as an external power source (e.g., an electricity outlet), photovoltaic device, or power cell, may be used. The power source QQ208 may further include power circuitry for delivering power from the power source QQ208 itself, and / or an external power source, to the various parts of the UE QQ200 via input circuitry or an interface such as an electrical power cable. Delivering power may be, for example, for charging of the power source QQ208. Power circuitry may perform any formatting, converting, or other modification to the power from the power source QQ208 to make the power suitable for the respective components of the UE QQ200 to which power is supplied.
[0258] The memory QQ210 may be or be configured to include memory such as random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, and so forth. In one example, the memory QQ210 includes one or more application programs QQ214, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data QQ216. The memory QQ210 may store, for use by the UE QQ200, any of a variety of various operating systems or combinations of operating systems.
[0259] The memory QQ210 may be configured to include a number of physical drive units, such as redundant array of independent disks (RAID), flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, high-density digital versatiledisc (HD-DVD) optical disc drive, internal hard disk drive, Blu-Ray optical disc drive, holographic digital data storage (HDDS) optical disc drive, external mini-dual in-line memory module (DIMM), synchronous dynamic random access memory (SDRAM), external micro-DIMM SDRAM, smartcard memory such as tamper resistant module in the form of a universal integrated circuit card (IIICC) including one or more subscriber identity modules (SIMs), such as a IISIM and / or ISIM, other memory, or any combination thereof. The IIICC may for example be an embedded IIICC (elllCC), integrated IIICC (illlCC) or a removable IIICC commonly known as ‘SIM card.’ The memory QQ210 may allow the UE QQ200 to access instructions, application programs and the like, stored on transitory or non-transitory memory media, to off-load data, or to upload data. An article of manufacture, such as one utilizing a communication system may be tangibly embodied as or in the memory QQ210, which may be or comprise a device-readable storage medium.
[0260] The processing circuitry QQ202 may be configured to communicate with an access network or other network using the communication interface QQ212. The communication interface QQ212 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna QQ222. The communication interface QQ212 may include one or more transceivers used to communicate, such as by communicating with one or more remote transceivers of another device capable of wireless communication (e.g., another UE or a network node in an access network). Each transceiver may include a transmitter QQ218 and / or a receiver QQ220 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter QQ218 and receiver QQ220 may be coupled to one or more antennas (e.g., antenna QQ222) and may share circuit components, software or firmware, or alternatively be implemented separately.
[0261] In the illustrated embodiment, communication functions of the communication interface QQ212 may include cellular communication, Wi-Fi communication, LPWAN communication, data communication, voice communication, multimedia communication, short-range communications such as Bluetooth, near-field communication, location-based communication such as the use of the global positioning system (GPS) to determine a location, another like communication function, or any combination thereof.
[0262] Communications may be implemented in according to one or more communication protocols and / or standards, such as IEEE 802.11, Code Division Multiplexing Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMax, Ethernet, transmission control protocol / internet protocol (TCP / IP),synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QIIIC, Hypertext Transfer Protocol (HTTP), and so forth.
[0263] Regardless of the type of sensor, a UE may provide an output of data captured by its sensors, through its communication interface QQ212, via a wireless connection to a network node. Data captured by sensors of a UE can be communicated through a wireless connection to a network node via another UE. The output may be periodic (e.g., once every 15 minutes if it reports the sensed temperature), random (e.g., to even out the load from reporting from several sensors), in response to a triggering event (e.g., when moisture is detected an alert is sent), in response to a request (e.g., a user initiated request), or a continuous stream (e.g., a live video feed of a patient).
[0264] As another example, a UE comprises an actuator, a motor, or a switch, related to a communication interface configured to receive wireless input from a network node via a wireless connection. In response to the received wireless input the states of the actuator, the motor, or the switch may change. For example, the UE may comprise a motor that adjusts the control surfaces or rotors of a drone in flight according to the received input or to a robotic arm performing a medical procedure according to the received input.
[0265] A UE, when in the form of an Internet of Things (loT) device, may be a device for use in one or more application domains, these domains comprising, but not limited to, city wearable technology, extended industrial application and healthcare. Non-limiting examples of such an loT device are a device which is or which is embedded in: a connected refrigerator or freezer, a TV, a connected lighting device, an electricity meter, a robot vacuum cleaner, a voice controlled smart speaker, a home security camera, a motion detector, a thermostat, a smoke detector, a door / window sensor, a flood / moisture sensor, an electrical door lock, a connected doorbell, an air conditioning system like a heat pump, an autonomous vehicle, a surveillance system, a weather monitoring device, a vehicle parking monitoring device, an electric vehicle charging station, a smartwatch, a fitness tracker, a wearable for tactile augmentation or sensory enhancement, a water sprinkler, an animal- or item-tracking device, a sensor for monitoring a plant or animal, an industrial robot, an Unmanned Aerial Vehicle (UAV), and any kind of medical device, like a heart rate monitor or a remote controlled surgical robot. A UE in the form of an loT device comprises circuitry and / or software in dependence of the intended application of the loT device in addition to other components as described in relation to the UE QQ200 shown in Figure 9.
[0266] As yet another specific example, in an loT scenario, a UE may represent a machine or other device that performs monitoring and / or measurements, and transmits the resultsof such monitoring and / or measurements to another UE and / or a network node. The UE may in this case be an M2M device, which may in a 3GPP context be referred to as an MTC device. As one particular example, the UE may implement the 3GPP NB-loT standard. In other scenarios, a UE may represent a vehicle, such as a car, a bus, a truck, a ship and an airplane, or other equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation.
[0267] In practice, any number of UEs may be used together with respect to a single use case. For example, a first UE might be or be integrated in a drone and provide the drone’s speed information (obtained through a speed sensor) to a second UE that is a remote controller operating the drone. When the user makes changes from the remote controller, the first UE may adjust the throttle on the drone (e.g. by controlling an actuator) to increase or decrease the drone’s speed. The first and / or the second UE can also include more than one of the functionalities described above. For example, a UE might comprise the sensor and the actuator, and handle communication of data for both the speed sensor and the actuators.
[0268] Figure 10 shows a network node QQ300 in accordance with some embodiments. As used herein, network node refers to equipment capable, configured, arranged and / or operable to communicate directly or indirectly with a UE and / or with other network nodes or equipment, in a telecommunication network. Examples of network nodes include, but are not limited to, access points (APs) (e.g., radio access points), base stations (BSs) (e.g., radio base stations, Node Bs, evolved Node Bs (eNBs) and NR NodeBs (gNBs)), O-RAN nodes or components of an O-RAN node (e.g., O-RU, O-DU, O-CU).
[0269] Base stations may be categorized based on the amount of coverage they provide (or, stated differently, their transmit power level) and so, depending on the provided amount of coverage, may be referred to as femto base stations, pico base stations, micro base stations, or macro base stations. A base station may be a relay node or a relay donor node controlling a relay. A network node may also include one or more (or all) parts of a distributed radio base station such as centralized digital units, distributed units (e.g., in an O-RAN access node) and / or remote radio units (RRUs), sometimes referred to as Remote Radio Heads (RRHs). Such remote radio units may or may not be integrated with an antenna as an antenna integrated radio. Parts of a distributed radio base station may also be referred to as nodes in a distributed antenna system (DAS).
[0270] Other examples of network nodes include multiple transmission point (multi-TRP) 5G access nodes, multi-standard radio (MSR) equipment such as MSR BSs, networkcontrollers such as radio network controllers (RNCs) or base station controllers (BSCs), base transceiver stations (BTSs), transmission points, transmission nodes, multi-cel l / multicast coordination entities (MCEs), Operation and Maintenance (O&M) nodes, Operations Support System (OSS) nodes, Self-Organizing Network (SON) nodes, positioning nodes (e.g., Evolved Serving Mobile Location Centers (E-SMLCs)), and / or Minimization of Drive Tests (MDTs).
[0271] The network node QQ300 includes a processing circuitry QQ302, a memory QQ304, a communication interface QQ306, and a power source QQ308. The network node QQ300 may be composed of multiple physically separate components (e.g., a NodeB component and a RNC component, or a BTS component and a BSC component, etc.), which may each have their own respective components. In certain scenarios in which the network node QQ300 comprises multiple separate components (e.g., BTS and BSC components), one or more of the separate components may be shared among several network nodes. For example, a single RNC may control multiple NodeBs. In such a scenario, each unique NodeB and RNC pair, may in some instances be considered a single separate network node. In some embodiments, the network node QQ300 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memory QQ304 for different RATs) and some components may be reused (e.g., a same antenna QQ310 may be shared by different RATs). The network node QQ300 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node QQ300, for example GSM, WCDMA, LTE, NR, WiFi, Zigbee, Z-wave, LoRaWAN, Radio Frequency Identification (RFID) or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within network node QQ300.
[0272] The processing circuitry QQ302 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and / or encoded logic operable to provide, either alone or in conjunction with other network node QQ300 components, such as the memory QQ304, to provide network node QQ300 functionality.
[0273] In some embodiments, the processing circuitry QQ302 includes a system on a chip (SOC). In some embodiments, the processing circuitry QQ302 includes one or more of radio frequency (RF) transceiver circuitry QQ312 and baseband processing circuitryQQ314. In some embodiments, the radio frequency (RF) transceiver circuitry QQ312 and the baseband processing circuitry QQ314 may be on separate chips (or sets of chips), boards, or units, such as radio units and digital units. In alternative embodiments, part or all of RF transceiver circuitry QQ312 and baseband processing circuitry QQ314 may be on the same chip or set of chips, boards, or units.
[0274] The memory QQ304 may comprise any form of volatile or non-volatile computer-readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD)), and / or any other volatile or non-volatile, non-transitory device-readable and / or computer-executable memory devices that store information, data, and / or instructions that may be used by the processing circuitry QQ302. The memory QQ304 may store any suitable instructions, data, or information, including a computer program, software, an application including one or more of logic, rules, code, tables, and / or other instructions capable of being executed by the processing circuitry QQ302 and utilized by the network node QQ300. The memory QQ304 may be used to store any calculations made by the processing circuitry QQ302 and / or any data received via the communication interface QQ306. In some embodiments, the processing circuitry QQ302 and memory QQ304 is integrated.
[0275] The communication interface QQ306 is used in wired or wireless communication of signaling and / or data between a network node, access network, and / or UE. As illustrated, the communication interface QQ306 comprises port(s) / terminal(s) QQ316 to send and receive data, for example to and from a network over a wired connection. The communication interface QQ306 also includes radio front-end circuitry QQ318 that may be coupled to, or in certain embodiments a part of, the antenna QQ310. Radio front-end circuitry QQ318 comprises filters QQ320 and amplifiers QQ322. The radio front-end circuitry QQ318 may be connected to an antenna QQ310 and processing circuitry QQ302. The radio front-end circuitry may be configured to condition signals communicated between antenna QQ310 and processing circuitry QQ302. The radio front-end circuitry QQ318 may receive digital data that is to be sent out to other network nodes or UEs via a wireless connection. The radio front-end circuitry QQ318 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of filters QQ320 and / or amplifiers QQ322. The radio signal may then be transmitted via the antenna QQ310. Similarly, when receiving data, the antenna QQ310may collect radio signals which are then converted into digital data by the radio front-end circuitry QQ318. The digital data may be passed to the processing circuitry QQ302. In other embodiments, the communication interface may comprise different components and / or different combinations of components.
[0276] In certain alternative embodiments, the network node QQ300 does not include separate radio front-end circuitry QQ318, instead, the processing circuitry QQ302 includes radio front-end circuitry and is connected to the antenna QQ310. Similarly, in some embodiments, all or some of the RF transceiver circuitry QQ312 is part of the communication interface QQ306. In still other embodiments, the communication interface QQ306 includes one or more ports or terminals QQ316, the radio front-end circuitry QQ318, and the RF transceiver circuitry QQ312, as part of a radio unit (not shown), and the communication interface QQ306 communicates with the baseband processing circuitry QQ314, which is part of a digital unit (not shown).
[0277] The antenna QQ310 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna QQ310 may be coupled to the radio front-end circuitry QQ318 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna QQ310 is separate from the network node QQ300 and connectable to the network node QQ300 through an interface or port.
[0278] The antenna QQ310, communication interface QQ306, and / or the processing circuitry QQ302 may be configured to perform any receiving operations and / or certain obtaining operations described herein as being performed by the network node. Any information, data and / or signals may be received from a UE, another network node and / or any other network equipment. Similarly, the antenna QQ310, the communication interface QQ306, and / or the processing circuitry QQ302 may be configured to perform any transmitting operations described herein as being performed by the network node. Any information, data and / or signals may be transmitted to a UE, another network node and / or any other network equipment.
[0279] The power source QQ308 provides power to the various components of network node QQ300 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source QQ308 may further comprise, or be coupled to, power management circuitry to supply the components of the network node QQ300 with power for performing the functionality described herein. For example, the network node QQ300 may be connectable to an external power source (e.g., the power grid, an electricity outlet) via an input circuitry or interface such as anelectrical cable, whereby the external power source supplies power to power circuitry of the power source QQ308. As a further example, the power source QQ308 may comprise a source of power in the form of a battery or battery pack which is connected to, or integrated in, power circuitry. The battery may provide backup power should the external power source fail.
[0280] Embodiments of the network node QQ300 may include additional components beyond those shown in Figure 10 for providing certain aspects of the network node’s functionality, including any of the functionality described herein and / or any functionality necessary to support the subject matter described herein. For example, the network node QQ300 may include user interface equipment to allow input of information into the network node QQ300 and to allow output of information from the network node QQ300. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node QQ300. In some embodiments providing a core network node, such as core network node 108 of Figure 8, some components, such as the radio front-end circuitry QQ318 and the RF transceiver circuitry QQ312 may be omitted.
[0281] Figure 11 is a block diagram illustrating a virtualization environment QQ400 in which functions implemented by some embodiments may be virtualized. In the present context, virtualizing means creating virtual versions of apparatuses or devices which may include virtualizing hardware platforms, storage devices and networking resources. As used herein, virtualization can be applied to any device described herein, or components thereof, and relates to an implementation in which at least a portion of the functionality is implemented as one or more virtual components. Some or all of the functions described herein may be implemented as virtual components executed by one or more virtual machines (VMs) implemented in one or more virtual environments QQ400 hosted by one or more of hardware nodes, such as a hardware computing device that operates as a network node, UE, core network node, or host. Further, in embodiments in which the virtual node does not require radio connectivity (e.g., a core network node or host), then the node may be entirely virtualized. In some embodiments, the virtualization environment QQ400 includes components defined by the O-RAN Alliance, such as an O-Cloud environment orchestrated by a Service Management and Orchestration Framework via an 0-2 interface. Virtualization may facilitate distributed implementations of a network node, UE, core network node, or host.Applications QQ402 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment 0400 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.
[0282] Hardware QQ404 includes processing circuitry, memory that stores software and / or instructions executable by hardware processing circuitry, and / or other hardware devices as described herein, such as a network interface, input / output interface, and so forth. Software may be executed by the processing circuitry to instantiate one or more virtualization layers QQ406 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VMs QQ408a and QQ408b (one or more of which may be generally referred to as VMs QQ408), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. The virtualization layer QQ406 may present a virtual operating platform that appears like networking hardware to the VMs QQ408.
[0283] The VMs QQ408 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by a corresponding virtualization layer QQ406. Different embodiments of the instance of a virtual appliance QQ402 may be implemented on one or more of VMs QQ408, and the implementations may be made in different ways. Virtualization of the hardware is in some contexts referred to as network function virtualization (NFV). NFV may be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches, and physical storage, which can be located in data centers, and customer premise equipment.
[0284] In the context of NFV, a VM QQ408 may be a software implementation of a physical machine that runs programs as if they were executing on a physical, non-virtualized machine. Each of the VMs QQ408, and that part of hardware QQ404 that executes that VM, be it hardware dedicated to that VM and / or hardware shared by that VM with others of the VMs, forms separate virtual network elements. Still in the context of NFV, a virtual network function is responsible for handling specific network functions that run in one or more VMs QQ408 on top of the hardware QQ404 and corresponds to the application QQ402.
[0285] Hardware QQ404 may be implemented in a standalone network node with generic or specific components. Hardware QQ404 may implement some functions via virtualization. Alternatively, hardware QQ404 may be part of a larger cluster of hardware (e.g. such as in a data center or CPE) where many hardware nodes work together and are managed via management and orchestration QQ410, which, among others, overseeslifecycle management of applications QQ402. In some embodiments, hardware QQ404 is coupled to one or more radio units that each include one or more transmitters and one or more receivers that may be coupled to one or more antennas. Radio units may communicate directly with other hardware nodes via one or more appropriate network interfaces and may be used in combination with the virtual components to provide a virtual node with radio capabilities, such as a radio access node or a base station. In some embodiments, some signaling can be provided with the use of a control system QQ412 which may alternatively be used for communication between hardware nodes and radio units.
[0286] Although the computing devices described herein (e.g., UEs, network nodes) may include the illustrated combination of hardware components, other embodiments may comprise computing devices with different combinations of components. It is to be understood that these computing devices may comprise any suitable combination of hardware and / or software needed to perform the tasks, features, functions and methods disclosed herein. Determining, calculating, obtaining or similar operations described herein may be performed by processing circuitry, which may process information by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination. Moreover, while components are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, computing devices may comprise multiple different physical components that make up a single illustrated component, and functionality may be partitioned between separate components. For example, a communication interface may be configured to include any of the components described herein, and / or the functionality of the components may be partitioned between the processing circuitry and the communication interface. In another example, non-computationally intensive functions of any of such components may be implemented in software or firmware and computationally intensive functions may be implemented in hardware.
[0287] In certain embodiments, some or all of the functionality described herein may be provided by processing circuitry executing instructions stored on in memory, which in certain embodiments may be a computer program product in the form of a non-transitory computer-readable storage medium. In alternative embodiments, some or all of the functionality may be provided by the processing circuitry without executing instructions stored on a separate or discrete device-readable storage medium, such as in a hard-wiredmanner. In any of those particular embodiments, whether executing instructions stored on a non-transitory computer-readable storage medium or not, the processing circuitry can be configured to perform the described functionality. The benefits provided by such functionality are not limited to the processing circuitry alone or to other components of the computing device, but are enjoyed by the computing device as a whole, and / or by end users and a wireless network generally.
[0288] When using the word "comprise" or “comprising” it shall be interpreted as nonlimiting, i.e. meaning "consist at least of".
[0289] The embodiments herein are not limited to the preferred embodiments described above. Various alternatives, modifications and equivalents may be used.
Claims
CLAIMS1. A method performed by a control node (110) controlling a protection system (101), which method is for performing an action relating to preventive protection of a Target System, TS, (102), in a network (100), the method comprising:obtaining (201) output data relating to an Anomaly Detection, and a Failure Prediction related to the TS (102), wherein the output data from the Anomaly Detection comprises an anomaly score related to a state of the TS (102), and the output data from the Failure Prediction comprises a failure prediction score_related to a future state of the TS (102),running (202) a Failure Testing for the TS (102), by interacting with a Digital Target System, DTS, (103) representing the TS (102) to simulate adversarial actions for the TS (102), which Failure Testing is triggered based on the output data relating to the anomaly score and the failure prediction score, performing (203) an action relating to preventive protection for the TS (102), based on the output data of the run Failure Testing.
2. The method according to claim 1, wherein the action relating to preventive protection comprises leading the TS (102) to a required state and / or to avoid a harmful state.
3. The method according to any of the claims 1-2, wherein the performing (203) an action relating to preventive protection for the TS (102) comprises any one or more out of:determining (204) whether or not there is a potential failure in the TS (102),when it is determined to be a potential failure, generating (205) counter measures to prevent the potential failure, and / orpredicting (206) the status of the TS (102) comprising anyone or more out of: failure, abnormality and weakness of the TS (102) for a number of steps ahead in the future and generating necessary counter measures for possible failures.
4. A computer program (730) comprising instructions, which when executed by a processor (710), causes the processor (710) to perform actions according to any of the claims 1-3.
5. A carrier (740) comprising the computer program (730) of claim 4, wherein the carrier (740) is one of an electronic signal, an optical signal, an electromagnetic signal, a magnetic signal, an electric signal, a radio signal, a microwave signal, or a computer-readable storage medium.
6. A control node (110) adapted to control a protection system (101), which control node (110) is configured to perform an action related to preventive protection of a Target System, TS, (102), in a network (100), the control node (110) further being configured to:obtain output data related to an Anomaly Detection and a Failure Prediction related to the TS (102), wherein the output data from the Anomaly Detection is adapted to comprise an anomaly score related to a state of the TS (102) and the output data from the Failure Prediction comprises a failure prediction score related to a future state of the TS (102),run a Failure Test for the TS (102), by an interaction with a Digital Target System, DTS, (103) adapted to represent the TS (102), to simulate adversarial actions for the TS (102), which Failure Testing is adapted to be triggered based on the output data related to the anomaly score and the failure prediction score, perform an action related to preventive protection for the TS (102), based on the output data of the run Failure Testing.
7. The control node (110) according to claim 6, wherein the action related to preventive protection is adapted to relate to leading the TS (102) to a required state and / or to avoid a harmful state.
8. The control node (110) according to any of the claims 6-7, further is configured to perform an action related to preventive protection for the TS (102) by any one or more out of:determine whether or not there is a potential failure in the TS (102), when it is determined to be a potential failure, generate counter measures to prevent the potential failure, and / orpredict the status of the TS (102) adapted to comprise anyone or more out of: failure, abnormality and weakness of the TS (102) for a number of steps ahead in the future and generate necessary counter measures for possible failures.
