Communication apparatus and method for mitigating network faults

Abstract

A processor of a communication apparatus is configured to: receive, from a network element (NE), an alarm message comprising information indicating network faults that have occurred in the NE; identify whether a combination of the network faults that have occurred in the NE is included in a look up table (LUT) comprising one or more actions for mitigating each combination of predefined network faults; according to identification that the combination of the network faults is not included in the LUT, identify a plurality of actions for mitigating the combination of the network faults on the basis of a trained artificial intelligence model; and transmit, to the NE, a configuration change request message comprising information about at least one action from among the plurality of actions for mitigating the combination of the network faults.

Description

Communication device and method for mitigating network failures

[0001] The following descriptions relate to communication devices and methods for mitigating network faults.

[0002] When a network fault occurs, the NE (network element) may send a message to the SMO (service management and orchestration) (or NMS (network management system)) to notify of the occurrence of the network fault. The SMO (or NMS) may send information to the NE about an action to mitigate (or resolve) the network fault.

[0003] The information described above may be provided as related art for the purpose of aiding understanding of the present disclosure. No claim or determination is made as to whether any of the foregoing may be applied as prior art related to the present disclosure.

[0004] A communication device is provided. The communication device may include a communication circuit. The communication device may include a memory that stores instructions and includes one or more storage media. The communication device may include at least one processor that includes a processing circuit. When the instructions are executed individually or collectively by the at least one processor, the communication device may cause the communication device to receive an alarm message from the NE (network element) that includes information indicating network faults that occurred in the NE. When the instructions are executed individually or collectively by the at least one processor, the communication device may cause the communication device to identify whether the combination of network faults that occurred in the NE is included in a look-up table (LUT) that includes one or more actions to mitigate each of the predefined combinations of network faults. When the above instructions are executed individually or collectively by the at least one processor, the communication device may be caused to identify a plurality of actions to mitigate the combination of network failures based on a trained artificial intelligence model, upon identification that the combination of network failures is not included in the LUT. When the above instructions are executed individually or collectively by the at least one processor, the communication device may be caused to transmit a configuration change request message to the NE, the message including information on at least one of the plurality of actions to mitigate the combination of network failures.

[0005] A method performed by a communication device is provided. The method may include the operation of receiving an alarm message from a network element (NE) that includes information indicating network faults that occurred in the NE. The method may include the operation of identifying whether a combination of network faults that occurred in the NE is included in a look-up table (LUT) that includes one or more actions for mitigating each of the predefined combinations of network faults. The method may include the operation of identifying a plurality of actions for mitigating the combination of network faults based on a trained artificial intelligence model, upon the identification that the combination of network faults is not included in the LUT. The method may include the operation of transmitting a configuration change request message to the NE that includes information regarding at least one of the plurality of actions for mitigating the combination of network faults.

[0006] In relation to the description of the drawings, the same or similar reference numerals may be used for identical or similar components.

[0007] Figure 1 illustrates an example of a communication system.

[0008] Figure 2 illustrates the components of a communication device.

[0009] Figure 3 illustrates an example of a rule-based mitigation system for mitigating network failures.

[0010] Figure 4 is a flowchart illustrating the operations of a communication device to mitigate network failures.

[0011] FIG. 5a is a flowchart illustrating the operations of a communication device to mitigate network failures based on a learned artificial intelligence model.

[0012] FIG. 5b is a flowchart illustrating the operations of a communication device to mitigate network failures.

[0013] FIG. 6 illustrates signaling between a network element (NE), a communication device, and an operation support system (OSS) to mitigate network failures.

[0014] Figure 7 illustrates signaling between devices for distributing actions for a combination of network failures in a communication system.

[0015] The terms used in this disclosure are used merely to describe specific embodiments and are not intended to limit the scope of other embodiments. A singular expression may include a plural expression unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as generally understood by those skilled in the art described in this disclosure. Terms used in this disclosure that are defined in a general dictionary may be interpreted as having the same or similar meaning as they have in the context of the relevant technology, and are not to be interpreted in an ideal or overly formal sense unless explicitly defined in this disclosure. In some cases, even terms defined in this disclosure are not to be interpreted to exclude the embodiments of this disclosure.

[0016] In the various embodiments of the present disclosure described below, a hardware-based approach is described as an example. However, since the various embodiments of the present disclosure include techniques using both hardware and software, the various embodiments of the present disclosure do not exclude a software-based approach.

[0017] Terms referring to signals used in the following description (e.g., packet, message, signal, information, signaling), terms referring to resources (e.g., section, symbol, slot, subframe, radio frame, subcarrier, RE (resource element), RB (resource block), BWP (bandwidth part), occasion)), terms for operation states (e.g., step, operation, procedure)), terms referring to data (e.g., packet, message, user stream, information, bit, symbol, codeword)), terms referring to channels, terms referring to network entities (DU (distributed unit), RU (radio unit), CU (central unit), CU-CP (control plane), CU-UP (user plane), O-DU (O-RAN (open radio access network) DU), O-RU (O-RAN RU), O-CU (O-RAN CU), Terms such as O-CU-UP (O-RAN CU-CP), O-CU-CP (O-RAN CU-CP), and terms referring to components of the device are examples provided for convenience of explanation. Accordingly, the present disclosure is not limited to the terms described below, and other terms having equivalent technical meanings may be used. Furthermore, terms such as '...part', '...device', '...object', '...body' used below may refer to at least one shape structure or a unit that processes a function.

[0018] Additionally, in this disclosure, expressions of "greater than" or "less than" may be used to determine whether a specific condition is satisfied or fulfilled; however, this is merely for the purpose of expressing an example and does not exclude descriptions of "greater than" or "less than." Conditions described as "greater than" may be replaced with "greater than," conditions described as "less than" may be replaced with "less than," and conditions described as "greater than and less than" may be replaced with "greater than and less than." Furthermore, "A" to "B" below refer to at least one of elements from A (including A) to B (including B). Below, "C" and / or "D" refers to including at least one of "C" or "D," i.e., {"C", "D", "C" and "D"}.

[0019] This disclosure describes various embodiments using terms used in some communication standards (e.g., 3GPP (3rd Generation Partnership Project), ETSI (European Telecommunications Standards Institute), xRAN (extensible radio access network), O-RAN (open-radio access network), but these are merely illustrative examples. Various embodiments of this disclosure can be easily modified and applied to other communication systems.

[0020] Figure 1 illustrates an example of a communication system.

[0021] The network architecture of the communication system exemplified in FIG. 1 may include a service management and orchestration (SMO) (110), a non-real time (non-RT) radio access network intelligent controller (RIC) (111), a near-RT RIC (120), a central unit-control plane (CU-CP) (130), a central unit-user plane (CU-UP) (140), a distributed unit (DU) (150), and a radio unit (RU) (160).

[0022] In one embodiment, the SMO (110) may be responsible for RAN management among various management domains (e.g., RAN (radio access network) management, core management, transport management, E2E (end-to-end) slice management) in the service provider's network. For RAN management, the SMO (110) may provide RAN optimization using an FCAPS (fault, configuration, accounting, performance, security) interface and a non-real-time RIC (111). The SMO (110) may be referred to as a network management system (NMS) or other terms having an equivalent technical / functional meaning.

[0023] In one embodiment, the SMO (110) may provide a function for managing network faults occurring in a network element (NE). Network faults may occur in the NE of a communication system. For example, network faults may be caused by hardware failure, software error, problems with network configuration, or external factors. Since network faults can cause service interruption or performance degradation, the SMO (110) may provide a fault management process to resolve and / or mitigate network faults. For example, the SMO (110) may provide an action to resolve (and / or mitigate) network faults reported by the NE. Actions to resolve (and / or mitigate) network faults may vary, such as hardware replacement, changing the configuration of the NE, or software upgrades. For example, the SMO (110) can send a message (e.g., a remote procedure call (RPC)) to the NE that has experienced a network failure, indicating an action (e.g., a change in configuration) to resolve (and / or mitigate) the network failure. For example, the SMO (110) can display an action to resolve (and / or mitigate) the network failure on a display so that an operator (or engineer) can select an action to resolve (and / or mitigate) the network failure.

[0024] In one embodiment, a non-real-time RIC (111) is implemented within an SMO (110) and can communicate with a near-real-time RIC (120) via an A1 interface. Policy management services, enrichment information services, and machine learning (ML) model management services may be provided via the A1 interface. The non-real-time RIC (111) can drive content delivered via the A1 interface.

[0025] In one embodiment, the near-real-time RIC (120) is a logical node for customizing RAN functionality for new services or regional resource optimization. The near-real-time RIC (120) can provide functions such as network intelligence (e.g., policy enforcement, handover optimization), resource assurance (e.g., radio-link management, advanced self-organized-network), and resource control (e.g., load balancing, slicing policy). The near-real-time RIC (120) can be connected to the CU-CP (130), CU-UP (140), and / or DU (150) via an E2 interface. The near-real-time RIC (120) can communicate with the CU-CP (130), CU-UP (140), and / or DU (150).

[0026] In one embodiment, CU-CP (130) and CU-UP (140) can perform upper layer functions of the access network (e.g., RRC (radio resource control), PDCP (packet data convergence protocol), SDAP (service data adaptation protocol)). CU-CP (130) and CU-UP (140) can be connected to DU (150) via an F1 interface. For example, CU-CP (130) can be connected to DU (150) via an F1-c interface. For example, CU-UP (140) can be connected to DU (150) via an F1-u interface. FIG. 1 illustrates CU-CP (130) and CU-UP (140) respectively according to the separation of the control plane and the user plane, but the present disclosure is not limited thereto. In a non-limiting example, CU-CP (130) and CU-UP (140) may be composed of a single CU.

[0027] In one embodiment, the DU (150) and RU (160) may be connected via a fronthaul (FH) interface. The DU (150) and RU (160) may perform lower layer functions of the access network (e.g., RLC (radio link control), MAC (medium access control), PHY (physical)). For example, the DU (150) may perform some functions of RLC, MAC, and PHY (high PHY). For example, the RU (160) may perform some functions of PHY (low PHY). The some functions of PHY performed by the DU (150) and the some functions of PHY performed by the RU (160) may be determined by a function split associated with the fronthaul transmission capacity. In one example, depending on the separation of functions (e.g., option 7-2x category A), the RU (160) can perform inverse fast Fourier transform (iFFT) transformation / cyclic prefix (CP) insertion in the downlink, FFT transformation / CP removal and digital beamforming in the uplink. The DU (150) can perform the remaining PHY functions.

[0028] FIG. 2 illustrates the components of a communication device. In FIG. 2, the communication device (201) may be a service management and orchestration (SMO) (110). However, the operations of the communication device (201) according to the present disclosure may also be applied to devices other than the SMO (110). For example, the communication device (201) may be one of a non-real time (non-RT) radio access network intelligent controller (RIC) (111), a near-RT RIC (120), a central unit-control plane (CU-CP) (130), a central unit-control plane (CU-CP) (140), or a distributed unit (DU) (150).

[0029] Referring to FIG. 2, the communication device (201) may include a processor (210), a memory (220), a transceiver (230), and a display (240). The processor (210), the memory (220), the transceiver (230), and the display (240) may be electrically and / or operably coupled with each other. Operatally coupled hardware components may mean that a direct or indirect connection between the hardware components is established via wired or wireless means so that a second hardware component (e.g., memory (220), communication circuit (230), or display (240)) is controlled by a first hardware component (e.g., processor (210)).

[0030] In one embodiment, the communication device (201) may include a processor (210). The processor (210) may control the operations of the communication device (201). The processor (210) may control the transceiver (230) to transmit and / or receive signals through a wired interface (e.g., A1 interface, O1 interface, E1 interface). The processor (210) may write and read data to and from memory (220). For example, the processor (210) may update a look-up table (LUT) for network failure mitigation stored in memory (220). For example, the processor (210) may identify a specific action from the LUT for network failure mitigation stored in memory (220). The processor (210) may include various processing circuits and / or a plurality of processors. For example, the term “processor” as used herein, including in the claims, may include various processing circuits comprising at least one processor, and one or more of said at least one processor may be configured to perform the various functions described below in a distributed manner, individually and / or collectively. Where “processor,” “at least one processor,” and “one or more processors” are described as being configured to perform various functions as used below, these terms encompass situations where one processor performs some of the cited functions and other processor(s) perform other parts of the cited functions, and situations where one processor can perform all of the cited functions. Additionally, at least one processor may include a combination of processors that perform the enumerated / disclosed various functions in a distributed manner. At least one processor may execute program instructions to achieve or perform the various functions.

[0031] In one embodiment, the communication device (201) may include a memory (220). Within the memory of the communication device (201), one or more instructions representing operations and / or operations performed by the processor (210) of the communication device (201) may be stored. A set of one or more instructions may be referred to as a program, operating system, process, routine, sub-routine, and / or application. Being installed within the communication device (201) may mean that one or more instructions are stored within the memory (220), and that one or more instructions are stored in an executable format by the processor (210) of the communication device (201). The memory (220) may store a look-up table (LUT) that defines mitigation actions for each combination of predefined network failures.

[0032] In one embodiment, the communication device (201) may include a transceiver (230). The transceiver (230) may provide an interface for performing communication with other NEs within the communication system. The transceiver (230) may include a communication circuit for performing communication with other NEs.

[0033] In one embodiment, the communication device (201) may include a display (240). The display (240) may include a display panel, a touch sensor, and / or a processing circuit. For example, the display (240) may be used to display information (e.g., an image, a script, an object, a user interface (UI)) regarding actions to mitigate network failures.

[0034] FIG. 3 illustrates an example of a rule-based mitigation system for mitigating network faults. A communication system comprising a rule-based mitigation system for resolving and / or mitigating network faults exemplified in FIG. 3 may include a communication device (201), a network element (NE) (310), and an operations support system (OSS) (320). The network architecture exemplified in FIG. 3 is merely an example and is not limited thereto. For example, the communication device (201) may be connected directly or indirectly to a plurality of NEs through an interface. For example, the OSS (320) may be connected to a plurality of communication devices.

[0035] In the communication system of FIG. 3, the communication device (201) may be a service management and orchestration (SMO) (110). The SMO (110) may be referred to as an NMS. However, the rule-based mitigation system according to the present disclosure may also be applied to devices other than the SMO (110). For example, the communication device (201) may be one of a non-real time (non-RT) radio access network intelligent controller (RIC) (111), a near-RT RIC (120), a central unit-control plane (CU-CP) (130), a central unit-control plane (CU-CP) (140), or a distributed unit (DU) (150).

[0036] The NE (310) of FIG. 3 may be a subordinate or child NE of the communication device (201). For example, the NE (310) may be one of a base station, DU, RU, CU-CP, CU-UP, CU-CP and CU-UP, near-real-time RIC, router, switch, server, load balancer, NE of a LTE (long term evolution) core network (CN) (e.g., MME (mobility management entity), S-GW (serving-gateway), P-GW (packet data network-gateway)), or NE of an NR (new radio) core network (e.g., AMF (access and mobility management function), SMF (session management function), UPF (user plane function)). However, this is merely an example and the present disclosure is not limited thereto. NE(310) may be a different subordinate NE in addition to the examples described above.

[0037] Referring to FIG. 3, in one embodiment, a communication device (201) may receive (or obtain) a message (301) from the NE (310) that includes information indicating network failures that occurred in the NE (310). The message (301) that includes information indicating network failures may be referred to as an alarm message, an event notification message, a network failure notification message, a network failure report message, or other terms having an equivalent technical / functional meaning.

[0038] In one embodiment, the communication device (201) can identify whether a combination of network failures occurring in the NE (310) is included in a look-up table (LUT). The LUT may be a table that defines an action for each of the predefined combinations of network failures. In one example, the total number of network failures may exceed 1,000. However, this is merely an example, and the total number of network failures may be 1,000 or less. In one example, the LUT may be configured as shown in [Table 1] below.

[0039] Network failure combination mitigation action 1st network failure and 2nd network failure Action 1 1st network failure and 3rd network failure Action 2 2nd network failure and 4th network failure Action 3 4th network failure and 5th network failure Action 4th network failure Action 5th network failure Action 5th

[0040] For example, the capacity (or resource) of the memory (220) of the communication device (201) may be limited. Since the capacity (or resource) of the memory (220) is limited, the LUT may not be able to store mitigation actions for all combinations of predefined network failures. Since the LUT may not be able to store mitigation actions for all combinations of predefined total network failures, combinations of network failures that occurred in the NE (310) may not be included in the LUT.

[0041] In one embodiment, the communication device (201) may transmit a message (303) to the OSS (320) to request a mitigation action for a combination of network failures that occurred in the NE (310), upon identifying that such combination is not included in the LUT. The message (303) transmitted to the OSS (320) may be referred to as a mitigation action request message or other terms having an equivalent technical meaning. The message (303) may include an identifier of the communication device (201), location information of the communication device (201), information about network failures that occurred in the NE (310) (e.g., type of network failure (e.g., link down), severity, time of network failure occurrence, cause of network failure (e.g., loss of connectivity detected on interface ge-0 / 0 / 0), an identifier of the NE (310), and / or location information of the NE (310).

[0042] In one embodiment, the communication device (201) may receive (or obtain) a message (304) from the OSS (320) containing information about a mitigation action for a combination of network failures that occurred in the NE (310). The message (303) and message (304) may be based on a REST (representation state transfer) protocol.

[0043] In one embodiment, the communication device (201) displays information about mitigation actions obtained from the LUT and / or OSS (320) through the display (240) and can identify mitigation actions based on input from an operator (e.g., a field engineer). The communication device (201) can transmit a message (302) containing information about mitigation actions for a combination of network failures that occurred in the NE (310) to the NE (310).

[0044] A rule-based mitigation system based on combinations of network failures and predefined mitigation actions for those combinations may have problems such as limited adaptability, an inefficient decision-making structure, a lack of contextual awareness, high maintenance requirements, and difficulty scaling. For example, defining mitigation actions for all combinations of network failures may be inefficient, considering limitations such as the memory (220) of the communication device (201). If mitigation actions for all combinations of network failures are not defined within the LUT or OSS (320), the communication device (201) may not be able to resolve and / or mitigate network failures. For example, even if combinations of network failures are defined within the LUT or OSS (320), the mitigation actions may not be able to resolve and / or mitigate network failures as the size and complexity of the network increase. In the following, a communication device and method based on an intelligence mitigation system (IMS) are described to solve the aforementioned problems.

[0045] FIG. 4 is a flowchart illustrating the operations of a communication device for mitigating network failures. The operations of FIG. 4 can be performed by the communication device (201) of FIG. 2. For example, at least some of the operations can be controlled by the processor (210) of the communication device (201). In the following, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed. For example, at least two operations may be performed in parallel.

[0046] In FIG. 4, an intelligence mitigation system (IMS) for mitigating (or resolving) network faults occurring in a network element (NE) is described. The communication device (201) of FIG. 4 may be a service management and orchestration (SMO) (110). However, the intelligence mitigation system according to the present disclosure may also be applied to devices other than the SMO (110). For example, the communication device (201) may be one of a non-real-time (non-RT) radio access network intelligent controller (RIC) (111), a near-RT RIC (120), a central unit-control plane (CU-CP) (130), a central unit-control plane (CU-CP) (140), or a distributed unit (DU) (150).

[0047] The NE of FIG. 4 may be a subordinate or child NE of a communication device (201). For example, the NE (310) may be one of a base station, a DU, a RU, a CU including CU-CP, CU-UP, CU-CP and CU-UP, a near-real-time RIC, a router, a switch, a server, a load balancer, an NE of a LTE (long term evolution) core network (CN) (e.g., MME (mobility management entity), S-GW (serving-gateway), P-GW (packet data network-gateway)), or an NE of an NR (new radio) core network (e.g., AMF (access and mobility management function), SMF (session management function), UPF (user plane function)). However, this is merely an example and the present disclosure is not limited thereto. The NE (310) may be a different subordinate NE in addition to the examples described above.

[0048] Referring to FIG. 4, in operation 401, a communication device (201) according to one embodiment may receive an alarm message from an NE containing information indicating network failures that occurred in the NE. The alarm message may be referred to as a message, an event notification message, a network failure notification message, a network failure report message, or other terms having an equivalent technical / functional meaning. For example, the information indicating network failures may include an identifier of the NE, location information of the NE, time of occurrence of the network failure, cause of the network failure, type of network failure, and / or severity.

[0049] In operation 402, a communication device (201) according to one embodiment can identify whether a combination of network failures that occurred in NE is included in a look-up table (LUT).

[0050] In one embodiment, the LUT may be generated during the initialization phase of the intelligent mitigation system. For example, the communication device (201) may identify some combinations of each of the total network failures based on the frequency of occurrence among the total network failures. For example, the communication device (201) may identify mitigation actions for some of the identified combinations of each of the total network failures based on a document regarding mitigation actions (e.g., in XML (extensible markup language) format). In one example, the document regarding mitigation actions may be provided by an operator. In one example, the LUT may be configured as shown in [Table 2] below.

[0051] LUT 1st state = 11001 1st action 2nd state = 10010 2nd action … … 1st state = 10001 1st action

[0052] In each state of [Table 2], '1' indicates the occurrence of a network failure, and '0' indicates that no network failure has occurred. For example, the first state (e.g., 11001) represents the combination of network failures with the highest frequency. The first state indicates a condition in which the first, second, and fifth network failures have occurred among all (or predefined) network failures (e.g., first network failure, second network failure, third network failure, fourth network failure, fifth network failure). The first action represents an action to resolve and / or mitigate the network failures of the first state. The second state (e.g., 10010) represents the combination of network failures with the second highest frequency. The second state indicates a condition in which the first and fourth network failures have occurred among all (or predefined) network failures. The second action represents an action to resolve and / or mitigate the network failures of the second state. The i-th state (e.g., 10001) represents the combination of network failures with the lowest frequency among a specified number of combinations. The i-th state represents a state in which the first network failure and the fifth network failure have occurred among all (or, predefined) network failures. The i-th action represents an action to resolve and / or mitigate the network failures of the i-th state. i represents the size of the LUT, which is specified by the operator or determined by the capacity (or resource) of the memory (220). In [Table 2], the action for each state is shown as one, but this is merely an example and the present disclosure is not limited thereto. For example, each action may include one or more actions. In one example, the action may consist of multiple actions as shown in [Table 3].

[0053] 1) Execute a request to receive wireless cell configuration information to check the cell configuration information. 2) If all cells are locked, execute a request to receive wireless cell status information. 3) If the alarm is not cleared, execute a request to change wireless cell configuration information.

[0054] In [Table 3], text-based actions are exemplified, but the present disclosure is not limited thereto. For example, an action may be an instruction executable in NE.

[0055] In operation 403, a communication device (201) according to one embodiment may transmit a configuration change request message to the NE containing information indicating an action for a combination of network failures identified based on a LUT. In one example, the configuration change request message may be referred to as a state change request message or other terms having an equivalent technical / functional meaning.

[0056] In one embodiment, the communication device (201) can identify an action corresponding to a combination of network failures from the LUT based on the identification that a combination of network failures occurring in the NE is included in the LUT. The communication device (201) can transmit a configuration change request message to the NE containing information indicating an action corresponding to a combination of network failures. For example, the communication device (201) can transmit a configuration change request message to the NE containing information indicating an action based on the identification that the action corresponding to a combination of network failures is an action that does not require user intervention (e.g., software update, configuration change). In an example that is not limited to, the communication device (201) can display the information through the display (240) without transmitting a configuration change request message based on the identification that the action corresponding to a combination of network failures is an action that requires user intervention (e.g., hardware replacement, physical cable replacement, device reboot).

[0057] In operation 404, a communication device (201) according to one embodiment can identify a plurality of actions corresponding to a combination of network failures occurring in the NE based on a trained artificial intelligence model. The artificial intelligence model may be an artificial intelligence model trained using reinforcement learning (RL). In one example, the trained artificial intelligence model may be a deep Q network (DQN) based on a Markov decision process (MDP). However, this is merely an example and the present disclosure is not limited thereto. The artificial intelligence model may be another artificial intelligence model based on RL. For example, the input data of the artificial intelligence model may be a combination of network failures occurring in the NE and all actions (or some of the all actions). The output data of the artificial intelligence model may be an action value (e.g., Q-value) for each of the all actions (or some of the all actions) for resolving and / or mitigating network failures occurring in the NE. The action value may directly or indirectly represent the probability of resolving and / or mitigating network failures occurring in the NE. In one example, when the status of network failures occurring in NE is '11101', the output of the artificial intelligence model may be as shown in [Table 4] below.

[0058] State Action Value (Q-value) State = 11101 1st Action = 10 2nd Action = 15 … 2nd Action = 7

[0059] In the states of [Table 4], '1' indicates the occurrence of a network failure, and '0' indicates that no network failure will occur. For example, a state (e.g., 11101) is not included in the LUT and represents a state in which the first, second, third, and fifth network failures have occurred among all (or predefined) network failures (e.g., first network failure, second network failure, third network failure, fourth network failure, and fifth network failure). In the example shown in [Table 4], the first action may have a first action value (e.g., 10) for network failures occurring in the NE, the second action may have a second action value (e.g., 15) for network failures occurring in the NE, and the j action may have a j action value (e.g., 7) for network failures occurring in the NE. j represents the total number of actions (or some of the total actions) to mitigate the network failure. For example, the priority of actions can be determined based on the action values ​​for network failures.

[0060] In operation 405, a communication device (201) according to one embodiment may transmit a setting change request message to NE that includes information indicating at least one of a plurality of actions.

[0061] In one embodiment, the communication device (201) can identify actions that are performed without user intervention (e.g., software updates) among a plurality of actions. The communication device (201) can identify at least one action among the actions based on an action value (e.g., Q-value) for each of the actions performed without user intervention. For example, the communication device (201) can identify the action having the largest action value among the actions (e.g., the second action of [Table 4]). In an example that is not limited, the communication device (201) can display the actions through a display (240) and identify at least one action based on user input (e.g., input from an engineer). The communication device (201) can transmit a configuration change request message containing information about at least one action to the NE.

[0062] FIG. 5a is a flowchart illustrating the operations of a communication device for mitigating network failures based on a learned artificial intelligence model. The operations of FIG. 5a can be performed by the communication device (201) of FIG. 2. For example, at least some of the operations can be controlled by the processor (210) of the communication device (201). In the following, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed. For example, at least two operations may be performed in parallel.

[0063] In FIG. 5a, an intelligence mitigation system (IMS) for mitigating (or resolving) network faults occurring in a network element (NE) is described. The communication device (201) of FIG. 5a may be a service management and orchestration (SMO) (110). However, the intelligence mitigation system according to the present disclosure may also be applied to devices other than the SMO (110). For example, the communication device (201) may be one of a non-real-time (non-RT) radio access network intelligent controller (RIC) (111), a near-RT RIC (120), a central unit-control plane (CU-CP) (130), a central unit-control plane (CU-CP) (140), or a distributed unit (DU) (150).

[0064] The NE of FIG. 5a may be a subordinate or child NE of a communication device (201). For example, the NE (310) may be one of a base station, a DU, a RU, a CU including CU-CP, CU-UP, CU-CP and CU-UP, a near-real-time RIC, a router, a switch, a server, a load balancer, an NE of a long-term evolution (LTE) core network (CN) (e.g., MME (mobility management entity), S-GW (serving-gateway), P-GW (packet data network-gateway)), or an NE of a new radio (NR) core network (e.g., AMF (access and mobility management function), SMF (session management function), UPF (user plane function)). However, this is merely an example and the present disclosure is not limited thereto. The NE (310) may be a different subordinate NE in addition to the examples described above.

[0065] Referring to FIG. 5a, in operation 501, a communication device (201) according to one embodiment can identify an action for a combination of network failures that occurred in NE using a learned artificial intelligence model.

[0066] In one embodiment, the communication device (201) may receive an alarm message from the NE that includes information indicating network failures that occurred in the NE. The alarm message may be referred to as a message, an event notification message, a network failure notification message, a network failure report message, or other terms having an equivalent technical or functional meaning. For example, the information indicating network failures may include an identifier of the NE, location information of the NE, time of occurrence of the network failure, cause of the network failure, type of network failure, and / or severity.

[0067] In one embodiment, the communication device (201) can identify whether a combination of network failures occurring in the NE is included in a look-up table (LUT). Based on the identification that a combination of network failures occurring in the NE is not included in the LUT, the communication device (201) can identify a plurality of actions corresponding to the combination of network failures occurring in the NE using a trained artificial intelligence model. The artificial intelligence model may be an artificial intelligence model trained using reinforcement learning (RL). In one example, the trained artificial intelligence model may be a deep Q network (DQN) based on a Markov decision process (MDP). However, this is merely an example, and the present disclosure is not limited thereto. The artificial intelligence model may be another artificial intelligence model based on RL. For example, the input data of the artificial intelligence model may be a combination of network failures occurring in the NE and all actions (or some of the all actions). The output data of the artificial intelligence model may be an action value (e.g., Q-value) for each of the total actions (or some of the total actions) for resolving and / or mitigating network failures that occurred in the NE. The action value may directly or indirectly represent the probability of resolving and / or mitigating network failures that occurred in the NE. The communication device (201) may identify actions that are performed without user intervention (e.g., software updates) among a plurality of actions. The communication device (201) may identify an action among the actions based on the action value (e.g., Q-value) for each of the actions performed without user intervention. For example, an action may have the largest action value among the actions performed without user intervention.In a non-limiting example, the communication device (201) may display information indicating a plurality of actions and an action value for each of the plurality of actions through a display (240) and identify the actions based on user input (e.g., input by an engineer). In a non-limiting example, the communication device (201) may display information indicating actions performed without user intervention and an action value for each of the actions through a display (240) and identify the actions based on user input (e.g., input by an engineer).

[0068] In operation 502, a communication device (201) according to one embodiment may transmit a configuration change request message containing information about an action to the NE. In one example, the configuration change request message may be referred to as a state change request message or other terms having an equivalent technical / functional meaning.

[0069] In operation 503, a communication device (201) according to one embodiment may receive a message from the NE associated with the mitigation of network failures that occurred in the NE. For example, the message may include information indicating whether each of the network failures that occurred in the NE has been resolved. In one example, the network failures that occurred in the NE (e.g., status = 11101 in [Table 4]) may include a first network failure, a second network failure, a third network failure, and a fifth network failure. The message may include information indicating whether the first network failure has been resolved, whether the second network failure has been resolved, whether the third network failure has been resolved, and whether the fifth network failure has been resolved. However, this is merely an example for illustrative purposes and the present disclosure is not limited thereto.

[0070] In non-limiting examples, the message may be a message indicating that all network failures that occurred in the NE have been resolved. In one example, the message may indicate whether network failures have been resolved with 1 bit. A message indicating that all network failures that occurred in the NE have been resolved may be referred to as an alarm clear message or by other terms having an equivalent technical / functional meaning.

[0071] In non-limiting examples, the message may be a message containing NE's KPIs (key performance indicators) (e.g., network availability, packet loss rate, bandwidth utilization, network latency). A message containing KPIs may be referred to as a performance report message or other terms having an equivalent technical / functional meaning.

[0072] In operation 504, a communication device (201) according to one embodiment can identify whether network failures that occurred in the NE have been mitigated (or resolved).

[0073] In one embodiment, the communication device (201) can identify whether network failures occurring in the NE have been mitigated (or resolved) based on a received message. For example, the communication device (201) can identify whether network failures have been mitigated (or resolved) based on the severity of the network failure. The severity of the network failure may be one of critical, major, minor, or warning. For example, the communication device (201) can identify whether network failures having a critical severity or a major severity among network failures occurring in the NE have been resolved based on a received message. The communication device (201) can identify that network failures have been mitigated based on the identification that network failures having a critical severity or a major severity among network failures occurring in the NE have been resolved. In one example, network failures occurring in the NE (e.g., status = 11101 in [Table 4]) may include a first network failure having critical severity, a second network failure having major severity, a third network failure having minor severity, and a fifth network failure having warning severity. The communication device (201) can identify that network failures occurring in the NE are mitigated when the first network failure and the second network failure having critical or major severity are resolved. In another example, the communication device (201) can identify that network failures occurring in the NE are not mitigated when the first network failure or the second network failure having critical or major severity is not resolved. However, this is merely an example and the present disclosure is not limited thereto. The severity criteria for identifying whether network failures are mitigated may be determined differently from the example described above.

[0074] In a non-limiting example, a message received from the NE may be an alarm release message indicating that all network failures that occurred in the NE have been resolved. In response to receiving the message, the communication device (201) may identify that network failures that occurred in the NE have been mitigated (or resolved).

[0075] In a non-limiting example, a message received from the NE may be a message containing the NE's KPIs (e.g., network availability, packet loss rate, bandwidth utilization, network latency). The communication device (201) may identify whether network failures occurring in the NE have been mitigated (or resolved) based on the message. For example, the communication device (201) may display the NE's KPIs through a display (240) and identify whether network failures occurring in the NE have been mitigated (or resolved) based on user input (e.g., engineer input).

[0076] In one embodiment, the communication device (201) can update the weights of the artificial intelligence model by providing negative feedback to the artificial intelligence model upon identifying that network failures occurring in the NE have not been mitigated (or resolved). After providing the negative feedback, the communication device (201) can perform operations 501 to 503.

[0077] In operation 505, a communication device (201) according to one embodiment may update mapping information between network failures and actions that mitigate (or resolve) network failures in a look-up table (LUT) based on the identification that network failures occurring in the NE have been mitigated. By updating the mapping information in the LUT, the communication device (201) may provide the NE with actions to mitigate (or resolve) network failures based on the LUT when the network failures occur again. Additionally, the communication device (201) may update the weights of an artificial intelligence model by providing positive feedback to the artificial intelligence model based on the identification that network failures occurring in the NE have been mitigated (or resolved).

[0078] In operation 506, a communication device (201) according to one embodiment may transmit mapping information between network failures occurring in the NE and actions that mitigate (or resolve) the network failures occurring in the NE to an OSS (operations support system) (320). The OSS (320) may be connected to other communication devices in addition to the communication device (201). By transmitting the mapping information to the OSS (320), the communication device (201) may enable the OSS (320) to distribute the mapping information to other communication devices as well. The distribution of the mapping information is described in FIG. 7.

[0079] FIG. 5b is a flowchart illustrating the operations of a communication device for mitigating network failures. The operations of FIG. 5b can be performed by the communication device (201) of FIG. 2. For example, at least some of the operations can be controlled by the processor (210) of the communication device (201). In the following, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed. For example, at least two operations may be performed in parallel.

[0080] In FIG. 5b, an intelligence mitigation system (IMS) for mitigating (or resolving) network faults occurring in a network element (NE) is described. The communication device (201) of FIG. 5a may be a service management and orchestration (SMO) (110). However, the intelligence mitigation system according to the present disclosure may also be applied to devices other than the SMO (110). For example, the communication device (201) may be one of a non-real-time (non-RT) radio access network intelligent controller (RIC) (111), a near-RT RIC (120), a central unit-control plane (CU-CP) (130), a central unit-control plane (CU-CP) (140), or a distributed unit (DU) (150).

[0081] The NE of FIG. 5b may be a subordinate (or child) NE of a communication device (201). For example, the NE (310) may be one of a base station, a DU, a RU, a CU including CU-CP, CU-UP, CU-CP and CU-UP, a near-real-time RIC, a router, a switch, a server, a load balancer, an NE of a LTE (long term evolution) core network (CN) (e.g., MME (mobility management entity), S-GW (serving-gateway), P-GW (packet data network-gateway)), or an NE of an NR (new radio) core network (e.g., AMF (access and mobility management function), SMF (session management function), UPF (user plane function)). However, this is merely an example and the present disclosure is not limited thereto. The NE (310) may be a different subordinate NE in addition to the examples described above.

[0082] For example, a look-up table (LUT) can be created during the initialization phase of an intelligent mitigation system and updated by performing mitigation actions based on a learned artificial intelligence model. However, since network conditions change, even if actions stored in the LUT are performed for network failures, network failures may not be mitigated (or resolved). In FIG. 5b, operations of a communication device (201) to resolve such a situation are described. After the operations according to FIG. 5b are performed, the communication device (201) can perform the operations described in FIG. 5a.

[0083] Referring to FIG. 5b, in operation 511, a communication device (201) according to one embodiment can identify an action for a combination of network failures that occurred in the NE based on a LUT.

[0084] In one embodiment, the communication device (201) may receive an alarm message from the NE that includes information indicating network failures that occurred in the NE. The alarm message may be referred to as a message, an event notification message, a network failure notification message, a network failure report message, or other terms having an equivalent technical or functional meaning. For example, the information indicating network failures may include an identifier of the NE, location information of the NE, time of occurrence of the network failure, cause of the network failure, type of network failure, and / or severity.

[0085] In one embodiment, the communication device (201) can identify whether a combination of network failures that occurred in the NE is included in a look-up table (LUT). Based on the identification that a combination of network failures that occurred in the NE is included in the LUT, the communication device (201) can identify an action corresponding to the combination of network failures from the LUT.

[0086] In operation 512, a communication device (201) according to one embodiment may transmit a configuration change request message containing information about an action to the NE. In one example, the configuration change request message may be referred to as a state change request message or other terms having an equivalent technical / functional meaning.

[0087] In operation 513, a communication device (201) according to one embodiment may receive a message from the NE associated with the mitigation of network failures. For example, the message may include information indicating whether each of the network failures that occurred in the NE has been resolved. In an example that is not limited, the message may be a message indicating that all network failures that occurred in the NE have been resolved. A message indicating that all network failures that occurred in the NE have been resolved may be referred to as an alarm clear message or other terms having an equivalent technical / functional meaning. In an example that is not limited, the message may be a message containing key performance indicators (KPIs) of the NE (e.g., network availability, packet loss rate, bandwidth utilization, network latency). A message containing KPIs may be referred to as a performance report message or other terms having an equivalent technical / functional meaning.

[0088] In operation 514, a communication device (201) according to one embodiment may remove mapping information between a combination of network failures and an action performed to mitigate network failures from the LUT, based on the identification that network failures occurring in the NE have not been mitigated.

[0089] In one embodiment, the communication device (201) can identify whether network failures occurring in the NE have been mitigated (or resolved) based on a received message. For example, the communication device (201) can identify whether network failures have been mitigated (or resolved) based on the severity of the network failure. The severity of the network failure may be one of critical, major, minor, or warning. For example, the communication device (201) can identify whether network failures having a critical severity or a major severity among network failures occurring in the NE have been resolved based on a received message. The communication device (201) can identify that network failures have been mitigated based on the identification that network failures having a critical severity or a major severity among network failures occurring in the NE have been resolved. In one example, network failures occurring in the NE (e.g., status = 11101 in [Table 4]) may include a first network failure having critical severity, a second network failure having major severity, a third network failure having minor severity, and a fifth network failure having warning severity. The communication device (201) can identify that network failures occurring in the NE are mitigated when the first network failure and the second network failure having critical or major severity are resolved. In another example, the communication device (201) can identify that network failures occurring in the NE are not mitigated when the first network failure or the second network failure having critical or major severity is not resolved. However, this is merely an example and the present disclosure is not limited thereto. The severity criteria for identifying whether network failures are mitigated may be determined differently from the example described above.

[0090] In a non-limiting example, a message received from the NE may be an alarm release message indicating that all network failures that occurred in the NE have been resolved. In response to receiving the message, the communication device (201) may identify that network failures that occurred in the NE have been mitigated (or resolved).

[0091] In a non-limiting example, a message received from the NE may be a message containing the NE's KPIs (e.g., network availability, packet loss rate, bandwidth utilization, network latency). The communication device (201) may identify whether network failures occurring in the NE have been mitigated (or resolved) based on the message. For example, the communication device (201) may display the NE's KPIs through a display (240) and identify whether network failures occurring in the NE have been mitigated (or resolved) based on user input (e.g., engineer input).

[0092] In one embodiment, the communication device (201) can update the weights of the artificial intelligence model by providing negative feedback to the artificial intelligence model upon identifying that network failures occurring in the NE have not been mitigated (or resolved). The communication device (201) can remove mapping information between combinations of network failures and actions performed to mitigate network failures from the LUT upon identifying that network failures occurring in the NE have not been mitigated (or resolved). After removing the mapping information from the LUT, the communication device (201) can perform the operations described in FIG. 5a.

[0093] FIG. 6 illustrates signaling between a network element (NE), a communication device, and an operation support system (OSS) to mitigate network failures.

[0094] In FIG. 6, an intelligence mitigation system (IMS) for mitigating (or resolving) network faults occurring in a network element (NE) (310) is described. The communication device (201) of FIG. 6 may be a service management and orchestration (SMO) (110). However, the intelligence mitigation system according to the present disclosure may also be applied to devices other than the SMO (110). For example, the communication device (201) may be one of a non-real-time (non-RT) radio access network intelligent controller (RIC) (111), a near-RT RIC (120), a central unit-control plane (CU-CP) (130), a central unit-control plane (CU-CP) (140), or a distributed unit (DU) (150).

[0095] The NE (310) of FIG. 6 may be a subordinate or child NE of the communication device (201). For example, the NE (310) may be one of a base station, DU, RU, CU including CU-CP, CU-UP, CU-CP and CU-UP, near-real-time RIC, router, switch, server, load balancer, NE of a long-term evolution (LTE) core network (CN) (e.g., MME (mobility management entity), S-GW (serving-gateway), P-GW (packet data network-gateway)), or NE of a new radio (NR) core network (e.g., AMF (access and mobility management function), SMF (session management function), UPF (user plane function)). However, this is merely an example and the present disclosure is not limited thereto. NE(310) may be a different subordinate NE in addition to the examples described above.

[0096] Referring to FIG. 6, in operation 601, a communication device (201) according to one embodiment may receive an alarm message from the NE (310) containing information indicating network failures that occurred in the NE. The alarm message may be referred to as a message, an event notification message, a network failure notification message, a network failure report message, or other terms having an equivalent technical / functional meaning. For example, the information indicating network failures may include an identifier of the NE, location information of the NE, time of occurrence of the network failure, cause of the network failure, type of network failure, and / or severity.

[0097] In operation 602, a communication device (201) according to one embodiment can identify an action for a combination of network failures that occurred in the NE (310) using a trained artificial intelligence model.

[0098] In one embodiment, the communication device (201) can identify whether a combination of network failures that occurred in the NE is included in the LUT (look up table).

[0099] For example, the LUT can be generated during the initialization phase of the intelligent mitigation system. For example, the communication device (201) can identify some combinations of each of the total network failures based on the frequency of occurrence among the total network failures. For example, the communication device (201) can identify mitigation actions for some of the identified combinations of each of the total network failures based on a document regarding mitigation actions (e.g., in XML (extensible markup language) format). In one example, the document regarding mitigation actions may be provided by an operator.

[0100] For example, the LUT can be updated during the step of performing a mitigation action based on a learned artificial intelligence model. The description of the operation in which the LUT is updated can be applied in the same way as the description of operation 505 in FIG. 5a.

[0101] In one embodiment, the communication device (201) can identify a plurality of actions corresponding to a combination of network failures occurring in the NE using a trained artificial intelligence model, based on the identification that a combination of network failures occurring in the NE is not included in the LUT. The artificial intelligence model may be an artificial intelligence model trained using reinforcement learning (RL). In one example, the trained artificial intelligence model may be a deep Q network (DQN) based on a Markov decision process (MDP). However, this is merely an example and the present disclosure is not limited thereto. The artificial intelligence model may be another artificial intelligence model based on RL. For example, the input data of the artificial intelligence model may be a combination of network failures occurring in the NE and all actions (or some of all actions). The output data of the artificial intelligence model may be an action value (e.g., Q-value) for each of the all actions (or some of all actions) for resolving and / or mitigating network failures occurring in the NE. The action value may directly or indirectly represent the probability of resolving and / or mitigating network failures that occurred in the NE. The communication device (201) may identify actions that are performed without user intervention (e.g., software updates) among a plurality of actions. The communication device (201) may identify an action among the actions based on an action value (e.g., Q-value) for each action performed without user intervention. For example, an action may have the largest action value among the actions performed without user intervention. In an example that is not limited, the communication device (201) may display information indicating a plurality of actions and an action value for each of the plurality of actions through a display (240) and identify an action based on user input (e.g., input from an engineer).In a non-limiting example, the communication device (201) displays information through the display (240) indicating actions performed without user intervention and the action value of each of said actions, and can identify the actions based on user input (e.g., input from an engineer).

[0102] In operation 603, a communication device (201) according to one embodiment may transmit a configuration change request message to NE that includes information about at least one action. In one example, the configuration change request message may be referred to as a state change request message or other terms having an equivalent technical / functional meaning.

[0103] In operation 604, a communication device (201) according to one embodiment may receive a message from the NE associated with the mitigation of network failures. For example, the message may include information indicating whether each of the network failures that occurred in the NE has been resolved. In an example that is not limited, the message may be a message indicating that all network failures that occurred in the NE have been resolved. A message indicating that all network failures that occurred in the NE have been resolved may be referred to as an alarm clear message or other terms having an equivalent technical / functional meaning. In an example that is not limited, the message may be a message containing key performance indicators (KPIs) of the NE (e.g., network availability, packet loss rate, bandwidth utilization, network latency). A message containing KPIs may be referred to as a performance report message or other terms having an equivalent technical / functional meaning.

[0104] In operation 605, a communication device (201) according to one embodiment may transmit a report message containing mapping information between a combination of network failures and an action to an OSS (operations support system) (320) upon identification that network failures occurring in the NE have been mitigated (or resolved) by an action identified based on a learned artificial intelligence model. The OSS (320) may be connected to other communication devices in addition to the communication device (201). By transmitting the mapping information to the OSS (320), the communication device (201) may enable the OSS (320) to distribute the mapping information to other communication devices as well. The distribution of the mapping information is described in FIG. 7.

[0105] Figure 7 illustrates signaling between devices for distributing actions for a combination of network failures in a communication system.

[0106] Referring to FIG. 7, the communication system may include an operations support system (OSS) (320), a communication device (201), a communication device (710), and a communication device (720). The OSS (320) may be connected directly or indirectly to the communication device (201), the communication device (710), and the communication device (720) through an interface. Each of the communication device (201), the communication device (710), and the communication device (720) may be connected to one or more network elements (NE) through an interface. However, the network architecture illustrated in FIG. 7 is merely an example and the present disclosure is not limited thereto. For example, the OSS (320) may be connected to fewer than three communication device(s). In another example, the OSS (320) may be connected to four or more communication device(s).

[0107] In FIG. 7, the communication device (201), the communication device (710), and the communication device (720) may be a service management and orchestration (SMO) (110). However, the present disclosure is not limited thereto. Each of the communication device (201), the communication device (710), and the communication device (720) may be one of a non-real time (non-RT) radio access network intelligent controller (RIC) (111), a near-RT RIC (120), a central unit-control plane (CU-CP) (130), a central unit-control plane (CU-CP) (140), or a distributed unit (DU) (150).

[0108] In the example illustrated in FIG. 7, the communication device (201) and the communication device (710) are based on the intelligent mitigation system (IMS) described in FIG. 4 through 6, and the communication device (720) may be based on the rule-based mitigation system described in FIG. 3.

[0109] For example, the communication device (201) can identify an action for a combination of network failures that occurred in the first NE (network element) using a trained artificial intelligence model based on the identification that the combination of network failures that occurred in the first NE is not included in the look-up table (LUT). The communication device (201) can send a configuration change request message to the first NE that includes an action to mitigate and / or resolve the network failures that occurred in the first NE. The communication device (201) can receive (or obtain) a message from the first NE indicating whether the network failures that occurred in the first NE have been mitigated and / or resolved by the action. Based on the message received from the first NE, the communication device (201) can identify that the network failures have been mitigated (or resolved) by an action identified based on the trained artificial intelligence model. The communication device (201) can update the mapping information between the combination of network failures and the action in the LUT based on the identification that the network failures that occurred in the first NE have been alleviated. The communication device (201) can transmit a report message (701) containing the mapping information between the combination of network failures and the action to the OSS (320) based on the identification that the network failures that occurred in the first NE have been alleviated.

[0110] For example, the OSS (320) may receive (or obtain) a message (703) from the communication device (710) requesting a mitigation action for a combination of network failures that occurred in the second NE connected to the communication device (710). The combination of network failures that occurred in the second NE may correspond to a combination of network failures that occurred in the first NE connected to the communication device (201). The OSS (320) may transmit a message (704) containing mapping information obtained from the communication device (201) to the communication device (710). The communication device (710) may update the LUT based on the mapping information obtained from the OSS (320). The communication device (710) may mitigate (or resolve) the network failures that occurred in the second NE by transmitting a configuration change request message to the second NE containing information about an action identified based on the mapping information.

[0111] For example, the OSS (320) may obtain a message (705) from the communication device (720) requesting a mitigation action for a combination of network failures that occurred in a third NE connected to the communication device (720). The combination of network failures that occurred in the third NE may correspond to a combination of network failures that occurred in a first NE connected to the communication device (201). The OSS (320) may transmit a message (706) containing mapping information obtained from the communication device (201) to the communication device (720). The communication device (720) may update the LUT based on the mapping information obtained from the OSS (320). The communication device (720) may mitigate (or resolve) the network failures that occurred in the third NE by transmitting a configuration change request message to the third NE containing information about an action identified based on the mapping information.

[0112] As described above, mitigation actions for combinations of network failures obtained by a communication device (201) based on an intelligent mitigation system can be distributed to other communication devices (e.g., communication device (710) and communication device (720)) by an OSS (320), which is a superior or parent NE of the communication device (201). Accordingly, the intelligent mitigation system according to the present disclosure can have quick adaptability by providing optimal mitigation actions according to the network environment. In addition, the intelligent mitigation system according to the present disclosure can have an efficient decision-making structure by utilizing a learned artificial intelligence model. Furthermore, the intelligent mitigation system according to the present disclosure can have contextual awareness by having the artificial intelligence model learn the context of network problems, such as interdependencies between NEs. In addition, the intelligent mitigation system according to the present disclosure can have a low maintenance requirement by reducing operator intervention. In addition, the intelligent mitigation system according to the present disclosure can have easer scaling by using an artificial intelligence model to identify mitigation actions as the size and complexity of the network increase.

[0113] The technical problems to be solved in this disclosure are not limited to those mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art to which this disclosure pertains.

[0114] A communication device as described above may include a communication circuit. The communication device may include a memory that stores instructions and includes one or more storage media. The communication device may include at least one processor that includes a processing circuit. When the instructions are executed individually or collectively by the at least one processor, the communication device may cause the communication device to receive an alarm message from the NE (network element) containing information indicating network faults that occurred in the NE. When the instructions are executed individually or collectively by the at least one processor, the communication device may cause the communication device to identify whether the combination of network faults that occurred in the NE is included in a look-up table (LUT) containing one or more actions for mitigating each of the predefined combinations of network faults. When the above instructions are executed individually or collectively by the at least one processor, the communication device may be caused to identify a plurality of actions to mitigate the combination of network failures based on a trained artificial intelligence model, upon identification that the combination of network failures is not included in the LUT. When the above instructions are executed individually or collectively by the at least one processor, the communication device may be caused to transmit a configuration change request message to the NE, the message including information on at least one of the plurality of actions to mitigate the combination of network failures.

[0115] For example, when the instructions are executed individually or collectively by the at least one processor, the communication device may cause the communication device to receive a message from the NE indicating whether the network failures have been resolved by the at least one action. When the instructions are executed individually or collectively by the at least one processor, the communication device may cause the communication device to identify, based on the message, whether at least one network failure having a critical or major severity among the network failures has been resolved. When the instructions are executed individually or collectively by the at least one processor, the communication device may cause the communication device to update mapping information between the combination of network failures and the at least one action in the LUT based on the identification that the at least one network failure having the critical or major severity among the network failures has been resolved by the at least one action.

[0116] For example, when the above instructions are executed individually or collectively by the at least one processor, the communication device may cause the OSS (operations support system) to transmit a report message containing mapping information regarding the combination of the network failures and the at least one action.

[0117] For example, when the instructions are executed individually or collectively by the at least one processor, the communication device may be prompted to identify whether a network failure having a minor or warning severity among the network failures has been resolved after transmitting the configuration change request message. When the instructions are executed individually or collectively by the at least one processor, the communication device may be prompted to identify an action to resolve the network failure having a minor or warning severity using the learned artificial intelligence model, based on the identification that the network failure having a minor or warning severity has not been resolved. When the above instructions are executed individually or collectively by the at least one processor, the communication device may cause the action for resolving the network failure having the severity of the minor or the warning to be added to the mapping information. For example, when the above instructions are executed individually or collectively by the at least one processor, the communication device may cause the communication device to receive a message from an OSS (operations support system) containing mapping information between a combination of second network failures and actions for mitigating the combination of second network failures. When the above instructions are executed individually or collectively by the at least one processor, the mapping information regarding the combination of second network failures and the actions for mitigating the combination of second network failures may be updated in the LUT.

[0118] For example, the severity of each of the above network failures can correspond to one of critical, major, minor, or warning.

[0119] When the above instructions are executed individually or collectively by the at least one processor, the communication device may cause the communication device to receive a message from the NE that includes a key performance indicator (KPI) of the NE. When the above instructions are executed individually or collectively by the at least one processor, the communication device may cause the communication device to identify whether the network failures have been mitigated based on the KPI. When the above instructions are executed individually or collectively by the at least one processor, the communication device may cause the communication device to update the mapping information between the combination of the network failures and the at least one action in the LUT according to the identification that the network failures have been mitigated. When the above instructions are executed individually or collectively by the at least one processor, the communication device may cause the communication device to transmit the mapping information between the combination of the network failures and the at least one action to an operations support system (OSS).

[0120] For example, the communication device may further include a display. When the instructions are executed individually or collectively by the at least one processor, the communication device may cause the plurality of actions identified based on the learned artificial intelligence model to be displayed on the display based on priority. When the instructions are executed individually or collectively by the at least one processor, the communication device may cause the at least one action among the plurality of actions to be identified based on user input.

[0121] For example, when the instructions are executed individually or collectively by the at least one processor, the communication device may cause the communication device to identify actions performed without user intervention among the plurality of actions identified based on the learned artificial intelligence model. When the instructions are executed individually or collectively by the at least one processor, the communication device may cause the communication device to identify the at least one action among the actions performed without user intervention based on the priority of the actions performed without user intervention.

[0122] For example, when the instructions are executed individually or collectively by the at least one processor, the communication device may cause the NE to transmit a second configuration change request message containing information about an action corresponding to the combination of network failures based on the LUT, upon identification that the combination of network failures is included in the LUT. When the instructions are executed individually or collectively by the at least one processor, the communication device may cause the NE to receive, in response to the second configuration change request message, a message containing information indicating whether the network failures have been mitigated by the action identified based on the LUT. When the instructions are executed individually or collectively by the at least one processor, the communication device may cause the NE to remove mapping information between the combination of network failures and the action from the LUT, upon identification that the network failures have not been mitigated based on the message.

[0123] For example, the communication device may be SMO (service management and orchestration). The learned artificial intelligence model may be trained based on DQN (deep Q-network).

[0124] A method performed by a communication device as described above may include the operation of receiving an alarm message from a network element (NE) containing information indicating network faults that occurred in the NE. The method may include the operation of identifying whether a combination of network faults that occurred in the NE is included in a look-up table (LUT) containing one or more actions for mitigating each of the predefined combinations of network faults. The method may include the operation of identifying a plurality of actions for mitigating the combination of network faults based on a trained artificial intelligence model, upon the identification that the combination of network faults is not included in the LUT. The method may include the operation of transmitting a configuration change request message to the NE containing information about at least one of the plurality of actions for mitigating the combination of network faults.

[0125] For example, the method may include receiving a message from the NE indicating whether the network failures have been resolved by the at least one action. The method may include identifying, based on the message, whether at least one network failure having a critical or major severity among the network failures has been resolved. The method may include updating mapping information between the combination of network failures and the at least one action in the LUT, based on the identification that the at least one network failure having the critical or major severity among the network failures has been resolved by the at least one action.

[0126] For example, the above method may include the operation of transmitting a report message containing mapping information for a combination of the network failures and at least one action to an OSS (operations support system).

[0127] For example, the above method may include an operation of identifying whether a network failure having a minor or warning severity among the network failures has been resolved after transmitting the configuration change request message. The above method may include an operation of identifying an action to resolve the network failure having a minor or warning severity using the learned artificial intelligence model based on the identification that the network failure having a minor or warning severity has not been resolved. The above method may include an operation of adding the action to resolve the network failure having a minor or warning severity to the mapping information.

[0128] For example, the above method may include the operation of receiving a message from an OSS (operations support system) containing mapping information between a combination of second network failures and actions for mitigating the combination of second network failures. The above method may include the operation of updating the mapping information regarding the combination of second network failures and the actions for mitigating the combination of second network failures in the LUT.

[0129] For example, the severity of each of the above network failures can correspond to one of critical, major, minor, or warning.

[0130] For example, the above method may include the operation of receiving a message from the NE that includes a key performance indicator (KPI) of the NE. The above method may include the operation of identifying whether the network failures have been mitigated based on the KPI. The above method may include the operation of updating mapping information between the combination of the network failures and the at least one action in the LUT based on the identification that the network failures have been mitigated. The above method may include the operation of transmitting the mapping information between the combination of the network failures and the at least one action to an operations support system (OSS).

[0131] For example, the above method may include an operation of displaying the plurality of actions identified based on the learned artificial intelligence model through the display based on priority. The above method may include an operation of identifying at least one action among the plurality of actions based on user input.

[0132] For example, the above method may include an operation of identifying actions performed without user intervention among the plurality of actions identified based on the learned artificial intelligence model. The above method may include an operation of identifying at least one action among the actions performed without user intervention based on the priority of the actions performed without user intervention.

[0133] For example, the method may include the operation of transmitting a second configuration change request message to the NE, which includes information about an action corresponding to the combination of network failures based on the LUT, upon identification that the combination of network failures is included in the LUT. The method may include the operation of receiving from the NE, in response to the second configuration change request message, a message including information indicating whether the network failures have been mitigated by the action identified based on the LUT. The method may include the operation of removing mapping information between the combination of network failures and the action from the LUT, upon identification that the network failures have not been mitigated based on the message.

[0134] For example, the communication device may be SMO (service management and orchestration). The learned artificial intelligence model may be trained based on DQN (deep Q-network).

[0135] The effects obtainable from the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art to which the present disclosure belongs.

[0136] Any of the embodiments described above may be combined with any other embodiment (or combination of embodiments) unless otherwise explicitly stated. The foregoing description of one or more embodiments is for illustrative and explanatory purposes only, and is not intended to limit or exhaust the scope of the embodiments in the exact form disclosed. Modifications and variations are possible in light of the foregoing teachings or may be obtained from the practice of various embodiments.

[0137] Methods according to the claims or embodiments described in the specification of the present disclosure may be implemented in the form of hardware, software, or a combination of hardware and software.

[0138] When implemented in software, a computer-readable storage medium (e.g., a non-transient computer-readable storage medium) storing one or more programs (software modules) may be provided. One or more programs stored in the computer-readable storage medium are configured for execution by one or more processors within an electronic device. One or more programs include instructions that cause the electronic device to execute methods according to the claims or embodiments described in the specification of this disclosure. The one or more programs may be provided as a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or distributed online (e.g., download or upload) through an application store (e.g., Play Store™) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0139] Such programs (software modules, software) may be stored in random access memory, non-volatile memory including flash memory, read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic disc storage devices, compact disc-ROM (CD-ROM), digital versatile discs (DVDs), or other forms of optical storage devices, magnetic cassettes. Alternatively, they may be stored in memory composed of some or all of these. Additionally, each constituent memory may include multiple units.

[0140] Additionally, the program may be stored on an attachable storage device that can be accessed via a communication network such as the Internet, Intranet, LAN (local area network), WAN (wide area network), or SAN (storage area network), or a combination thereof. Such a storage device may be connected to a device performing an embodiment of the present disclosure through an external port. Additionally, a separate storage device on a communication network may be connected to a device performing an embodiment of the present disclosure.

[0141] In the specific embodiments of the present disclosure described above, the components included in the disclosure are expressed in a singular or plural form according to the specific embodiments presented. However, the singular or plural expression is selected to suit the situation presented for convenience of explanation, and the present disclosure is not limited to singular or plural components; even if a component is expressed in the plural form, it may be composed of a singular form, and even if a component is expressed in the singular form, it may be composed of a plural form.

[0142] According to the embodiments, one or more of the aforementioned components or operations may be omitted, or one or more other components or operations may be added. Generally or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the plurality of components in the same or similar manner as those performed by the corresponding component among the plurality of components prior to the integration. According to the embodiments, operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0143] Meanwhile, although specific embodiments have been described in the detailed description of the present disclosure, it is understood that various modifications are possible within the scope of the present disclosure.

Claims

1. In a communication device, Communication circuit; Memory for storing instructions and including one or more storage media; and It includes at least one processor comprising a processing circuit, and When the above instructions are executed individually or collectively by the at least one processor, the communication device, Receive an alarm message from the NE (network element) containing information indicating network faults that occurred in the NE, and Identifying whether a combination of network failures occurring in the NE is included in a look-up table (LUT) containing one or more actions for mitigating each combination of predefined network failures, and Based on the identification that the combination of the above network failures is not included in the LUT, a plurality of actions to mitigate the combination of the above network failures are identified based on a trained artificial intelligence model, and Causing to transmit to the NE a configuration change request message containing information about at least one of the plurality of actions for mitigating the combination of the above network failures, Communication device.

2. In Paragraph 1, When the above instructions are executed individually or collectively by the at least one processor, the communication device, Receive a message from the NE indicating whether the above network failures have been resolved by the at least one action, and Based on the above message, identify whether at least one network failure having a critical or major severity among the above network failures has been resolved, and Causing to update mapping information between the combination of network failures and the at least one action in the LUT, based on the identification that the at least one network failure having the critical or major severity is resolved by the at least one action. Communication device.

3. In Paragraph 2, When the above instructions are executed individually or collectively by the at least one processor, the communication device, Causing to transmit to an OSS (operations support system) a report message containing mapping information for the combination of the above network failures and the above at least one action, Communication device.

4. In Paragraph 2, When the above instructions are executed individually or collectively by the at least one processor, the communication device, After transmitting the above configuration change request message, identify whether a network failure among the above network failures having a minor or warning severity has been resolved, and Based on the identification that the network failure having the severity of the minor or the warning has not been resolved, the learned artificial intelligence model is used to identify an action to resolve the network failure having the severity of the minor or the warning, and Causing to add the action to the mapping information to resolve the network failure having the severity of the above minor or above warning, Communication device.

5. In Paragraph 1, When the above instructions are executed individually or collectively by the at least one processor, the communication device, A message containing mapping information between a combination of second network failures and actions to mitigate the combination of second network failures is received from an OSS (operations support system), and Causing the mapping information for the combination of the second network failures and the actions for mitigating the combination of the second network failures to be updated in the LUT, Communication device.

6. In Paragraph 1, When the above instructions are executed individually or collectively by the at least one processor, the communication device, Receive a message from the NE that includes the KPI (key performance indicator) of the NE, and Based on the above KPIs, identify whether the above network failures have been mitigated, and Based on the identification that the above network failures have been alleviated, mapping information between the combination of the above network failures and the at least one action is updated in the LUT, and Causing the OSS (operations support system) to transmit the mapping information between the combination of the above network failures and the above at least one action, Communication device.

7. In Paragraph 1, The above communication device further includes a display, and When the above instructions are executed individually or collectively by the at least one processor, the communication device, The plurality of actions identified based on the above-mentioned learned artificial intelligence model are displayed through the above-mentioned display based on priority, and Causing to identify at least one action among the plurality of actions based on user input, Communication device.

8. In Paragraph 1, When the above instructions are executed individually or collectively by the at least one processor, the communication device, Identifying actions performed without user intervention among the plurality of actions identified based on the above-mentioned learned artificial intelligence model, and Causing to identify at least one action among the actions performed without user intervention, based on the priority of the actions performed without user intervention. Communication device.

9. In Paragraph 1, When the above instructions are executed individually or collectively by the at least one processor, the communication device, Based on the identification that the combination of the above network failures is included in the LUT, a second configuration change request message including information on an action corresponding to the combination of the above network failures based on the LUT is transmitted to the NE, and In response to the second configuration change request message, receive from the NE a message containing information indicating whether the network failures have been mitigated by the action identified based on the LUT, and Causing to remove mapping information between the combination of the network failures and the action from the LUT, based on the identification that the network failures have not been mitigated based on the above message, Communication device.

10. In Paragraph 1, The above communication device is SMO (service management and orchestration), and The above-mentioned trained artificial intelligence model is trained based on DQN (deep Q-network), Communication device.

11. In a method performed by a communication device, An operation of receiving an alarm message from the NE (network element) containing information indicating network faults that occurred in the NE; An operation to identify whether a combination of network failures occurring in the NE is included in a look-up table (LUT) comprising one or more actions for mitigating each combination of predefined network failures; An operation to identify a plurality of actions to mitigate the combination of network failures based on a trained artificial intelligence model, upon identification that the combination of the network failures is not included in the LUT; and The method includes the operation of transmitting a configuration change request message to the NE, the message including information regarding at least one of the plurality of actions for mitigating the combination of the above network failures. method.

12. In Paragraph 11, The operation of receiving a message from the NE indicating whether the above network failures have been resolved by the at least one action; Based on the above message, an operation to identify whether at least one network failure having a critical or major severity among the network failures has been resolved; and Further including the operation of updating mapping information between the combination of network failures and the at least one action in the LUT, upon identification that the at least one network failure having the critical or major severity is resolved by the at least one action. method.

13. In Paragraph 12, The operation further includes transmitting a report message to an OSS (operations support system) that includes mapping information for the combination of the above network failures and the above at least one action. method.

14. In Paragraph 12, After transmitting the above-mentioned configuration change request message, an operation to identify whether a network failure having a minor or warning severity among the above-mentioned network failures has been resolved; An action to identify an action to resolve the network failure having the severity of the minor or the warning using the learned artificial intelligence model, based on the identification that the network failure having the severity of the minor or the warning has not been resolved; and Further including the action of adding to the mapping information the action for resolving the network failure having the severity of the above minor or the above warning, method.

15. In Paragraph 11, The operation of receiving a message from an OSS (operations support system) containing mapping information between a combination of second network failures and actions to mitigate the combination of second network failures; and The method further includes the operation of updating the mapping information for the combination of the second network failures and the actions for mitigating the combination of the second network failures in the LUT. method.

Images