Detection of conflicts between cognitive functions

Abstract

Systems, methods, apparatuses, and computer program products for detecting conflicts between cognitive functions based on key performance metrics. The method may include detecting, by a conflict monitoring cognitive function, that a performance indicator exceeds a first boundary based on first radio access network information, the first radio access network information indicating a first parameter of a radio access network associated with the first cognitive function at a first time, detecting, by the conflict monitoring cognitive function, that the performance indicator exceeds a second boundary based on second radio access network information indicating a second parameter of the radio access network associated with the first cognitive function at a second time, the second parameter being different from the first parameter, a conflict of the first cognitive function and the at least one second cognitive function is detected by the conflict monitoring cognitive function, and a severity of the conflict is determined based on the performance indicator exceeding the second boundary.

Description

[0001] Related applications This patent application claims priority to Finnish Patent Application No. 20236245, filed on 7 November 2023, which is incorporated herein by reference as if reproduced in its entirety. Technical Field

[0002] Some example embodiments may generally relate to mobile or wireless telecommunications systems, such as Long Term Evolution (LTE) or 5G radio access technologies or New Radio (NR) access technologies, or other+ systems. For example, some example embodiments may relate to apparatus, systems, and / or methods for detecting conflicts between cognitive functions. Background Technology

[0003] Examples of mobile or wireless telecommunications systems can include Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access Network (UTRAN), LTE Evolution of UTRAN (E-UTRAN), LTE-Advanced (LTE-A), MulteFire, LTE-A Pro, Open Radio Access Network (O-RAN), fifth-generation (5G) radio access technology or NR access technology, and / or sixth-generation (6G) radio access technology. 5G and 6G wireless systems refer to next-generation (NG) radio systems and network architectures. 5G and 6G network technologies are primarily based on NR technology, but 5G / 6G (or NG) networks can also be built on top of E-UTRAN radio. O-RAN can be defined according to the O-RAN Consortium's O-RAN specifications. It is estimated that NR can provide bit rates of 10-20 Gbit / s or higher and can at least support enhanced mobile broadband (eMBB) and ultra-reliable low-latency communications (URLLC) as well as massive machine-type communications (mMTC). NR is expected to provide ultra-broadband and ultra-robust, low-latency connectivity, as well as massive network connectivity to support the Internet of Things (IoT).

[0004] A radio access network has parameters that can be controlled by a controller or network control function. The radio access network can be connected to various cognitive functions that work with the controller or network control function to control the parameters of the radio access network based on key performance indicators (KPIs). Conflicts between these cognitive functions may lead to a degraded performance of these KPIs. However, other factors, such as network conditions, may also cause a degraded KPI. Therefore, it is sometimes difficult to determine whether the degraded KPI is due to conflict—that is, conflict between the cognitive functions—or another factor. Summary of the Invention

[0005] Example embodiments may relate to an apparatus. The apparatus may include at least one processor and at least one memory storing instructions. When executed by the at least one processor, the instructions may cause the apparatus to at least perform the following actions: detecting a performance metric exceeding a first boundary based on first radio access network information, the first radio access network information indicating a first parameter of the radio access network associated with the first cognitive function at a first time; detecting a performance metric exceeding a second boundary based on second radio access network information, the second radio access network information indicating a second parameter of the radio access network associated with the first cognitive function at a second time, the second parameter being different from the first parameter; detecting a conflict between the first cognitive function and at least one second cognitive function; and determining the severity of the conflict based on the performance metric exceeding the second boundary.

[0006] Another example embodiment may relate to an apparatus. The apparatus may include at least one processor and at least one memory storing instructions. When executed by the at least one processor, the instructions may cause the apparatus to at least perform the following actions: the controller obtains an indication that a performance metric exceeds a first boundary, the performance metric being related to a radio access network and associated with a first cognitive function; the controller transmits information related to the performance metric exceeding the boundary and a request for parameter modification to the first cognitive function; the controller obtains an indication of a conflict between the first cognitive function and at least one second cognitive function and the severity of the conflict; and the controller executes a conflict mitigation procedure based on the conflict.

[0007] Example embodiments may relate to a method. This method may include: a conflict monitoring cognitive function detecting performance metrics exceeding a first boundary based on first radio access network information, the first radio access network information indicating a first parameter of the radio access network associated with the first cognitive function at a first time; the conflict monitoring cognitive function detecting performance metrics exceeding a second boundary based on second radio access network information, the second radio access network information indicating a second parameter of the radio access network associated with the first cognitive function at a second time, the second parameter being different from the first parameter; the conflict monitoring cognitive function detecting a conflict between the first cognitive function and at least one second cognitive function; and determining the severity of the conflict based on the performance metrics exceeding the second boundary.

[0008] Another example embodiment may involve a method. This method may include a controller obtaining an indication that a performance metric exceeds a first boundary, the performance metric being related to a radio access network and associated with a first cognitive function; the controller transmitting information related to the performance metric exceeding the boundary and a request for parameter modification to the first cognitive function; the controller obtaining an indication of a conflict between the first cognitive function and at least one second cognitive function and the severity of the conflict; and the controller executing a conflict mitigation procedure based on the conflict.

[0009] Another example embodiment may relate to an apparatus. This apparatus may include components for detecting, by a conflict monitoring cognitive function, a performance metric exceeding a first boundary based on first radio access network information, the first radio access network information indicating a first parameter of a radio access network associated with the first cognitive function at a first time; components for detecting, by the conflict monitoring cognitive function, a performance metric exceeding a second boundary based on second radio access network information, the second radio access network information indicating a second parameter of a radio access network associated with the first cognitive function at a second time, the second parameter being different from the first parameter; components for detecting, by the conflict monitoring cognitive function, a conflict between the first cognitive function and at least one second cognitive function; and components for determining the severity of the conflict based on the performance metric exceeding the second boundary.

[0010] Another example embodiment may relate to an apparatus. This apparatus may include components for obtaining an indication by a controller that a performance metric exceeds a first boundary, the performance metric being related to a radio access network and associated with a first cognitive function; components for transmitting information related to the performance metric exceeding the boundary and a request for parameter modification from the controller to the first cognitive function; components for obtaining an indication by the controller of a conflict between the first cognitive function and at least one second cognitive function and the severity of the conflict; and components for executing a conflict mitigation procedure by the controller based on the conflict.

[0011] Another example embodiment may relate to an apparatus including circuitry configured to perform a method. The method may include detecting, by a conflict detection cognitive function, a performance metric exceeding a first boundary based on first radio access network information, the first radio access network information indicating a first parameter of a radio access network associated with the first cognitive function at a first time; detecting, by the conflict detection cognitive function, a performance metric exceeding a second boundary based on second radio access network information, the second radio access network information indicating a second parameter of a radio access network associated with the first cognitive function at a second time, the second parameter being different from the first parameter; detecting a conflict between the first cognitive function and at least one second cognitive function; and determining the severity of the conflict based on the performance metric exceeding the second boundary.

[0012] Another example embodiment may relate to an apparatus including circuitry configured to perform a method. The method may include: a controller acquiring an indication that a performance metric exceeds a first boundary, the performance metric being related to a radio access network and associated with a first cognitive function; the controller transmitting information related to the performance metric exceeding the boundary and a request for parameter modification to the first cognitive function; the controller acquiring information about a conflict between the first cognitive function and at least one second cognitive function and the severity of the conflict; and the controller executing a conflict mitigation procedure based on the conflict.

[0013] Another example embodiment may relate to a non-transitory computer-readable medium including program instructions stored thereon, which, when executed by a device, cause the device to perform at least a method. The method may include detecting, by a conflict detection cognitive function, a performance metric exceeding a first boundary based on first radio access network information, the first radio access network information indicating a first parameter of a radio access network associated with the first cognitive function at a first time; detecting, by the conflict detection cognitive function, a performance metric exceeding a second boundary based on second radio access network information, the second radio access network information indicating a second parameter of a radio access network associated with the first cognitive function at a second time, the second parameter being different from the first parameter; detecting a conflict between the first cognitive function and at least one second cognitive function; and determining the severity of the conflict based on the performance metric exceeding the second boundary.

[0014] Another example embodiment may relate to a non-transitory computer-readable medium including program instructions stored thereon, which, when executed by a device, cause the device to perform a method. The method may include: a controller obtaining an indication that a performance metric exceeds a first boundary, the performance metric being related to a radio access network and associated with a first cognitive function; the controller transmitting information related to the performance metric exceeding the boundary and a request for parameter modification to the first cognitive function; the controller obtaining an indication of a conflict between the first cognitive function and at least one second cognitive function and the severity of the conflict; and the controller executing a conflict mitigation procedure based on the conflict.

[0015] Another example embodiment may relate to a computer program including instructions that, when executed by a device, cause the device to perform a method. The method may include detecting, by a conflict detection cognitive function, a performance metric exceeding a first boundary based on first radio access network information, the first radio access network information indicating a first parameter of a radio access network associated with the first cognitive function at a first time; detecting, by the conflict detection cognitive function, a performance metric exceeding a second boundary based on second radio access network information, the second radio access network information indicating a second parameter of a radio access network associated with the first cognitive function at a second time, the second parameter being different from the first parameter; detecting a conflict between the first cognitive function and at least one second cognitive function; and determining the severity of the conflict based on the performance metric exceeding the second boundary.

[0016] Another example embodiment may relate to a computer program that includes instructions, which, when executed by a device, cause the device to perform a method. The method may include a controller acquiring an indication that a performance metric exceeds a first boundary, the performance metric being related to a radio access network and associated with a first cognitive function; the controller transmitting information related to the performance metric exceeding the boundary and a request for parameter modification to the first cognitive function; the controller acquiring an indication of a conflict between the first cognitive function and at least one second cognitive function and the severity of the conflict; and the controller executing a conflict mitigation procedure based on the conflict. Attached Figure Description

[0017] To correctly understand the exemplary embodiments, reference should be made to the accompanying drawings, in which: Figure 1 An example block diagram is shown, which represents the Radio Access Network (RAN), Cognitive Function (CF), and Network Control Function (NCF).

[0018] Figure 2A An example configuration conflict is shown; Figure 2B An example of interdependent KPI conflict is shown; Figure 2C An example of an unknown coupling conflict is shown; Figure 3 An example signal flow diagram according to certain example embodiments is shown.

[0019] Figure 4 Another example signal flow diagram according to certain example embodiments is shown.

[0020] Figure 5 Another example signal flow diagram according to certain example embodiments is shown.

[0021] Figure 6 An example flowchart of a method is shown according to certain example embodiments.

[0022] Figure 7 Another example flowchart, which is a flowchart of a method, is shown according to some example embodiments.

[0023] Figure 8 A set of apparatuses according to certain example embodiments is shown. Detailed Implementation

[0024] It will be readily understood that components of certain example embodiments, as generally described and illustrated in the accompanying drawings, can be arranged and designed in a wide variety of different configurations. The following is a detailed description of some example embodiments of systems, methods, apparatuses, and computer program products for detecting conflicts between cognitive functions based on key performance indicators.

[0025] The features, structures, or characteristics of the exemplary embodiments described throughout this specification can be combined in any suitable manner in one or more exemplary embodiments. For example, the phrases "some embodiments," "exemplary embodiments," "some embodiments," or other similar language used throughout this specification refer to specific features, structures, or characteristics described in connection with embodiments that can be included in at least one embodiment. Therefore, the phrases "some embodiments," "exemplary embodiments," "some embodiments," "other embodiments," or other similar language appearing throughout this specification do not necessarily refer to the same set of embodiments, and the described features, structures, or characteristics can be combined in any suitable manner in one or more exemplary embodiments. Furthermore, the terms "base station," "cell," "node," "gNB," "network," or other similar language used throughout this specification are used interchangeably.

[0026] As used herein, "at least one of the following: " and "at least one of " and similar wording, where a list of two or more elements is connected by "and" or "or", means at least any one of these elements, or at least any two or more of these elements, or at least all of these elements.

[0027] Figure 1 Example block diagrams of Radio Access Network (RAN) 100, Cognitive Function (CF) 200, and Network Control Function (NCF) 300 are shown. RAN 100 may be a set of network nodes (e.g., Advanced Node B and NR Node B) providing radio access services. Radio access services may have key performance indicators (KPIs) 'Y', control parameters 'p', and network characteristics / states 'X'. Examples of KPIs may include download and upload bit rates and radio link failures. Examples of control parameters may include antenna tilt, cell-specific offset, and trigger time. Examples of network characteristics and states may include node states (e.g., on, off, standby), node connectivity, number of connected UEs, etc. The overall network environment 'T' can be determined by the given parameters and the KPIs of the network characteristics / states.

[0028] RAN 100, CF 200, and NCF 300 (also known as controller 300) can be implemented in the same hardware or separate hardware. For example, a network node that is part of RAN 100 may include one or more of CF 200 and / or NCF 300. NCF 300 can be implemented in a single server, processor, processing circuitry, control hardware, multiple processors, multiple servers, etc. The interface between RAN 100, CF 200, and NCF 300 can be a software interface (if implemented on the same hardware) or a hardware interface (if implemented on different hardware), such as a wireless or wired interface. RAN 100 can be an O-RAN with E2 nodes.

[0029] The RAN 100 network reports KPIs, parameters, and network characteristics / status to the CF 200, and the CF 200 communicates with the NCF 300. The CF 200 can suggest changes to RAN 100 parameters to the NCF 200 based on the KPIs and network characteristics / status. The CF 200 can send suggestions to keep the values ​​of one or more KPIs within a range or limit (e.g., between 'a' and 'b', above 'c', or below 'd'). The range or limit can change depending on the RAN's status. For example, if many UEs are connected to RAN 100, it may not be expected that RAN 100 will operate with the same upload and download rate ranges as when fewer UEs are connected to the RAN.

[0030] The NCF 300 can change the parameters of RAN 100 by sending configuration control messages that include parameter changes to RAN 100. RAN 100 can also send network data to the NCF 300. Network data may include KPIs, parameters, network characteristics / status, and other information such as KPIs changing over time and command history.

[0031] Figures 2A to 2C An example of a conflict between CF 200s is shown. Figure 2A An example configuration conflict is illustrated where multiple cognitive CF 200s share the same parameters for different key performance indicators (KPIs). This creates a conflict because each CF 200 will suggest parameter changes to improve its respective associated KPI, and changes to the parameters may adversely affect another KPI associated with another CF 200.

[0032] Figure 2BAn example of a conflicting KPI dependency is illustrated. In a conflicting KPI dependency, CFs control different parameters, but the parameters of one CF affect the KPIs associated with another CF. For example, a first CF1 200 might change the antenna tilt angle of a base station to control the coverage and / or capacity of a first cell. A second CF2 might perform load balancing between the first and second cells. Changes to the coverage and / or capacity of the first cell may affect the load or load balancing between the first and second cells. This type of dependency can be difficult to perceive without a large amount of historical information available for analysis.

[0033] Figure 2C An example of unknown coupling conflict is illustrated. In unknown coupling conflict, changing a parameter alters an unrelated KPI in an unknown way. Because the coupling is unknown and can change over time, depending on how the network state evolves as a function of time, this type of conflict is difficult to predict and detect in systems with a large number of CF 200s. Furthermore, in multi-vendor environments, CF 200s may be designed independently, and conflicts between CF 200s from other vendors may not have been considered in the design of the CF 200s.

[0034] Figure 3 An example signal flow diagram 3000 is shown according to certain example embodiments. Signal flow diagram 3000 illustrates communication between RAN 100, CF 200, controller 300, conflict detection cognitive function (CMCF) 400, and database 500. Flowchart 300 can be an operational example in an Open RAN (O-RAN) near real-time radio access network intelligent controller architecture. RAN100, CF 200, controller 300, and CMCF 400 can each be implemented on separate hardware, or any combination of RAN 100, CF 200, controller 300, and CMCF 400 can be implemented on the same hardware. Although a single CF 200 is shown, it should be understood that multiple CF 200s will be associated with RAN 100 and controller 300 (e.g., ...). Figure 1 (as shown), and each CF 200 will operate in a similar manner. RAN 100, CF 200, controller 300, conflict detection cognitive function (CMCF) 400 and database 500 can be implemented in O-RAN to detect conflicts that may affect KPI performance at E2 nodes of O-RAN.

[0035] NFC 300 can be a near real-time RIC platform function with an E2 interface to RAN 100. CF 200 and CMCF 400 can be implemented in xApp, which is logically located inside or near the real-time RIC system, but outside the near real-time RIC platform function or NFC 300. This means that xApp can run in one cloud location, while the near real-time RIC platform function can run in another cloud location. CF 200 and CMCF 400 can interface with each other via the near real-time RIC application programming interface specified in the O-RAN standard.

[0036] At S3010, RAN 100 can transmit performance data to CMCF 400. The performance data may include information about KPI 'Y', control parameter 'p', and network characteristics / state 'X'. The performance information may include performance information for each KPI monitored by RAN 100 and controlled by CF 200 and controller 300. For example, a single KPI associated with a single CF 200 is shown.

[0037] At S3020, RAN 100 can report network fault status to controller 300. Network fault status can include errors, faults, failures, or related network information. At S3030, RAN reports network data for CF 200, including KPIs and associated parameters and network characteristics / status.

[0038] At S3040, CF 200 can detect suboptimal configurations. Detection of suboptimal configurations can include detecting KPIs exceeding ranges or limits, or abnormal network conditions. CF 200 can determine the recommended update parameter p. and expected KPI Y Update parameter p and expected KPI Y It can be determined based on algorithms (e.g., machine learning algorithms), computations, lookup tables, etc. at CF 200, based on KPIs, parameters, and network features / states.

[0039] At S3050, CF 200 can report the suggested update parameter p to controller 300. and expected KPI Y At S3060, controller 300 can determine whether to accept or reject a suggestion based on network fault status, KPIs, parameters, and network characteristics / status. For example, if the suggestion is unlikely to increase network fault status, controller 300 can determine to accept the suggestion and update parameter p. With update parameter p The commands are transmitted together to RAN 100. Operations S3010-S3060 can be repeated periodically or triggered by an event (such as the detection of a network failure).

[0040] At S3110, CMCF 400 can calculate the limits of the KPIs based on received information related to KPI 'Y', control parameter 'p', and network feature / state 'X'. The received KPI information can be correlated with key performance indicator information collected over a time period (time series). The limits can be probabilistic limits based on the control parameter and network feature / state of the KPIs as they change over time. For example, a limit could be the range of KPIs that contain KPI values ​​90% of the time under specific parameters and network features / states. Limits can be calculated for each KPI in RAN 100.

[0041] At S3120, CMCF 400 can transmit KPI performance data and calculation limit updates to database 500. Database 500 can store KPI performance data and calculation limit updates.

[0042] At S3130, CMCF 400 can receive additional performance data from RAN 100. From the perspective of RAN 100, this operation can be a repetition of operation S3010.

[0043] At S3140, CMCF 400 can query database 500 for the previous limits of KPIs, and database 500 can report the previous limits.

[0044] At S3150, the CMCF 400 can detect anomalies in one or more key performance indicators (KPIs). For example, the CMCF 400 can train a machine learning algorithm using previous limits of the KPIs and can input the time series of the current KPI into the machine learning algorithm to determine if anomalies exist in any KPI. As another example, the CMCF 400 can input historical limits and historical parameters, along with network state / features, into the machine learning algorithm, which outputs predicted limits for the current parameters and network state / features. If the limits of the current KPI's time series are outside the probability window of the predicted limits, the CMCF can determine that an anomaly has occurred. Therefore, the CMCF 400 can detect whether a KPI exceeds its limits based on the limits predicted by the machine learning algorithm.

[0045] At S3160, CMCF 400 can report anomalies (e.g., KPI time series exceeding limits) to controller 300. CMCF 400 can report the KPI and the cause of the detected anomaly (e.g., KPI time series falling below prediction limits).

[0046] At S3170, controller 300 can transmit a re-optimization request with anomaly information or another indication based on the anomaly to CF 200 (e.g., if the KPI is below the threshold of 10%, the request could be to re-optimize to increase the KPI by 10%).

[0047] At S3180, CF 200 can determine the suggested parameter p. and the predicted KPI Y And the suggested parameter p and the predicted KPI Y Send to controller 300. At S3190, similar to S3160, controller 300 can determine to update parameter p. To update the parameters, and then update the parameter p. It is sent to RAN 100 along with the command to update the parameters.

[0048] At S3200, controller 300 can report a re-optimization to CMCF 400. The report may include information such as that a re-optimization has been performed and that parameter p has been updated. and the predicted KPI Y .

[0049] At S3210, CMCF can query RAN 100 for performance data reports based on the reported re-optimization. RAN 100 can respond with the performance data.

[0050] At S3220, CMCF 400 can query historical limits from database 500, and database 500 can report historical limits to CMCF 400.

[0051] At S3230, similar to S3250, CMCF can detect anomalies in KPIs. If it is the same KPI that was detected as an anomaly in S3150, then the anomaly in the KPI can be determined to be persistent.

[0052] At S3240, if the anomaly in the KPI persists, the CMCF 400 can report a potential conflict to the controller 300. The report may include the first detected anomaly, the second detected anomaly, and the anomalous KPI. The report may also include the last normal time. The last normal time is the last time the KPI returned to normal (or was within the normal range), and a request to report any network failures after the last normal time.

[0053] At S3250, controller 300 can report the actions of CF 200 associated with the abnormal KPI, the actions of CF 200 associated with other KPIs, and network information. Network information may include RAN node information and RAN function information. The report may also include network fault reports after the last normalization time. All actions of all CF 200s associated with other KPIs can be reported. Alternatively, only the actions of selected CF 200s can be reported. CF 200s can be selected based on the probability of conflict. For example, CF 200s associated with KPIs known to potentially conflict with the abnormal KPIs, or CF 200s associated with KPIs that have changed significantly before and after the last normalization time, can be selected.

[0054] In S3260, controller 300 can detect conflicts and their severity based on reported information (e.g., information from RAN 200, information reported by controller 300, and information retrieved from database 500). KPI degradation may be caused by factors other than conflicts in the CF, such as changes in network state. Therefore, CMCF 400 can determine whether the action of another CF 200 not associated with the KPI affected the anomalous KPI, or whether other conditions caused the anomalous KPI. CMCF 400 can also detect conflicts based on other known conflicts. The severity of a conflict can be calculated based on the KPI's time series and prediction boundary. For example, the severity of a conflict can be determined by calculating the distance between the current time series of the anomalous KPI and the midpoint of the prediction boundary. The severity of a conflict can be a value or an indication. For example, severity can be indicated as a value, such as the amount by which the KPI exceeds the tolerance. If the severity is benign (e.g., within the tolerance), the severity can be indicated as an indication.

[0055] In S3270, CMCF 400 can query database 500 for KPI-related tolerances. For example, the database may include KPI-based network failure information and the tolerable range of KPIs or network failures. Database 500 can report KPI-related tolerances to CMCF 400.

[0056] In S3280, CMCF 400 can report conflicts and their severity to controller 300. The report may include KPI-related tolerances, and controller 300 can determine whether the conflict is tolerable based on these tolerances. Alternatively, CMCF 400 can determine if the conflict is within tolerances and therefore not report it. As another alternative, if the conflict is within tolerances, it can be reported with an indication that the conflict is benign. Benign conflicts can be logged (e.g., in database 500 or other storage) for future reference. As described above, known conflicts can be used by controller 300 for conflict detection.

[0057] In S3290, if the conflict cannot be tolerated, controller 300 can initiate a conflict handling and / or mitigation procedure. The conflict handling and mitigation procedure may include determining which CF operations are in conflict (this can be performed at CMCF 400 and reported to controller 300), determining the operations or operational changes used to mitigate the conflict at CF 200 and controller 300 (e.g., determining that the proposed parameter change is not allowed if it might cause KPIs to exceed tolerances), and updating RAN parameters based on the conflict. Controller 300 can then perform the conflict handling and / or mitigation procedure together with RAN 100, CF 200, and CMCF 400. Examples of conflict handling and / or mitigation procedures performed by CMCF 400 may include: identifying the CFs in conflict, determining whether the proposed parameter change will mitigate the conflict between the CFs, and determining whether anomalies still exist in the KPIs after the RAN parameters have been updated.

[0058] Figure 4 Another example signaling flowchart 4000 is shown according to some example embodiments. The signaling flowchart illustrates the signaling between RAN 100, CF 200, controller 300, and database 500. In this example, the controller also operates as CMCF 400. Therefore, in Figure 3 Operations performed by CMCF 400 in Figure 4 The operation is performed by controller 300, and the signal between controller 300 and CMCF 400 is internal communication or information transmission, not shown. For example, operations S4010-S4060 are similar to operations S3010-S3060, except that S4010 and S4060 are between RAN 100 and controller 300 instead of... Figure 3 Between RAN 100 and CMCF 400 as shown. Figure 3 Descriptions of operations similar to those can be reduced or omitted.

[0059] In S4010, RAN 100 can report performance data to controller 300. In S4020, RAN 100 can report network fault status to controller 300. In S4030, RAN can report KPI-related network data to CF 200. In S4040, CF 200 can detect suboptimal configurations and determine recommended update parameters p. And predicting KPI Y In S4050, CF sends the suggested update parameter p to controller 300. And predicting KPI Y In S4060, controller 300 sends an update parameter p to RAN 100. Command to update parameters.

[0060] In S4110, the controller can calculate the boundaries of the KPI. In S4120, the controller can send KPI boundary updates. In S4130, the controller 300 can receive additional network data from RAN 100. In S4140, the controller 300 can query the database 500 for the KPI boundaries, and the database can report the KPI boundaries. In S4150, the controller can detect anomalies in the KPI.

[0061] In S4160, the controller can send a re-optimization request to the CF associated with the KPI that has abnormal information. In S4170, the CF can send a suggested update parameter p. And predicting KPI Y In S4180, controller 300 can send a command to RAN 100 to update parameters. In S4190, controller 300 can query RAN 100 for additional network data, and RAN 100 can report the additional network data.

[0062] In S4200, controller 300 can query database 500 for KPI boundary information, and database 500 can report the KPI boundary information. In S4210, controller 300 can detect anomalies within the same KPI. In S4220, controller 300 can detect conflicts and determine their severity. In S4230, controller 300 can query database 500 for tolerance information related to the KPI, and database 500 can report this tolerance information. The controller can determine whether the conflict is tolerable. In S4240, the controller can determine to execute conflict handling and / or mitigation procedures. Then, controller 300 can execute conflict handling and / or mitigation procedures together with RAN 100 and CF 200.

[0063] Figure 5 Another example signaling flowchart 5000 according to some example embodiments is shown. The signaling flowchart illustrates signaling between RAN 100, CF 200, controller 300, and database 500. Database 500 may be a database associated with RAN 100, and therefore may be a RAN database or a memory. In this example, RAN 100 operates as CMCF 400. Therefore, in Figure 3 Operations performed by CMCF 400 in Figure 5 This is performed by RAN 100, and the signaling between RAN 100 and CMCF 400 is internal communication or information transmission, not shown. Figure 3 Descriptions of operations similar to those can be reduced or omitted.

[0064] In S5010, RAN 100 can send network fault status to controller 300. In S5020, RAN 100 can send network data for KPIs to CF 200. In S5030, CF 200 can detect suboptimal configurations and calculate recommended update parameters p. And predicting KPI Y In the S5040, CF 200 can send suggested update parameters p to controller 300. And predicting KPI Y In the S5050, the controller can send commands to the RAN 100 to update parameters.

[0065] In S5110, RAN 100 can calculate the boundaries of its performance information. In S5120, RAN 100 can send KPI-related data and boundaries to database 500. In S5130, after new performance information becomes available at RAN 100, RAN 100 can query boundary information from database 500, and database 500 can report the boundary information. In S5140, RAN 100 can detect anomalies in the KPIs. In S5150, RAN 100 can report the anomaly information to controller 300. In S5160, controller 300 can request re-optimization by CF 200 associated with the anomalous KPI. In S5170, CF 200 can send suggested update parameters p to controller 300. And predicting KPI Y In the S5180, the controller can send commands to RAN 100 to update parameters and also report predicted KPIs (Y) to RAN 100. .

[0066] In S5190, RAN 100 can query boundary information from database 500, and database 500 can report boundary information to RAN 100. In S5200, RAN 100 can detect anomalies in KPIs that were detected as anomalous in S5140.

[0067] In S5210, RAN 100 can report potential conflicts along with the context of boundaries, KPIs, time, and other relevant information. In S5230, controller 300 can process and confirm conflicts. For example, controller 300 can analyze the provided information to determine whether a conflict exists rather than a network failure causing the abnormal KPI. For instance, if the last normal time happens to be before the CF associated with a different KPI takes a configuration action, a conflict can be determined between the CF of the different KPI and the CF of the abnormal KPI.

[0068] In S5240, controller 300 can send conflict information, including the conflicting CF and its past configuration actions and action times. In S5250, RAN 100 can revert configuration changes (e.g., parameter changes) to restore the RAN parameters to the levels before the abnormal KPI was detected, as a first conflict mitigation action when further conflict mitigation or handling is determined and implemented by the controller. In S5260, controller 300 can determine whether the conflict is tolerable and determine the action to handle or mitigate the conflict.

[0069] Figure 6 An example flowchart 6000 is shown, illustrating a method according to certain example embodiments. In the example embodiments, Figure 6 The method can be performed by a network entity or a group of multiple network elements in a 3GPP system, such as LTE or 5G-NR. For example, in an example embodiment, Figure 6 The method can be performed by a server, network node, or other electronic device, and is similar to Figure 8 One of the devices 10 or 20 shown.

[0070] According to certain example embodiments, Figure 6 The method may include: in S610, detecting that a performance indicator exceeds a first boundary by a conflict monitoring cognitive function based on first radio access network information, wherein the first radio access network information indicates a first parameter of the radio access network associated with the first cognitive function at a first time; in S620, detecting that a performance indicator exceeds a second boundary by a conflict monitoring cognitive function based on second radio access network information, wherein the second radio access network information indicates a second parameter of the radio access network associated with the first cognitive function at a second time, wherein the second parameter is different from the first parameter; in S630, detecting a conflict between the first cognitive function and at least one second cognitive function by the conflict monitoring cognitive function; and in S640, determining the severity of the conflict based on the performance indicator exceeding the second boundary.

[0071] Figure 7 An example flowchart 7000 is shown, illustrating another method according to certain example embodiments. In the example embodiments, Figure 7 The method can be performed by a network entity or a group of multiple network elements in a 3GPP system, such as LTE or 5G-NR. For example, in an example embodiment, Figure 7 The method can be executed by the controller or the server, and it is similar to Figure 8 One of the devices 10 or 20 shown.

[0072] According to certain example embodiments, Figure 7The method may include: in S710, the controller obtains an indication that a performance indicator exceeds a first boundary, the performance indicator being related to the radio access network and associated with a first cognitive function; the controller transmits information related to the performance indicator exceeding the boundary and a request for parameter modification to the first cognitive function; in S720, the controller obtains an indication of a conflict between the first cognitive function and at least one second cognitive function and the severity of the conflict; and in S730, the controller executes a conflict mitigation procedure based on the conflict.

[0073] Figure 8 A set of devices 10 and 20 according to certain example embodiments are shown. In some example embodiments, devices 10 and 20 may be elements in or associated with a communication network. For example, device 10 may be a computing device or machine, such as a server or network node, and device 20 may also be a server or network node (i.e., gNB, 5GS, 5G core, 5G RAN, etc.).

[0074] In some example embodiments, devices 10 and 20 may include one or more processors, one or more computer-readable storage media (e.g., memory, storage device, etc.), one or more radio access components (e.g., modem, transceiver, etc.), and / or a user interface. In some example embodiments, devices 10 and 20 may be configured to operate using one or more radio access technologies, such as GSM, LTE, LTE-A, NR, 5G, WLAN, WiFi, NB-IoT, Bluetooth, NFC, MulteFire, O-RAN, 6G, and / or any other radio access technology. It should be noted that those skilled in the art will understand that devices 10 and 20 may include... Figure 8 Components or features not shown in the diagram.

[0075] like Figure 8 As illustrated in the example, devices 10 and 20 may include or be coupled to processors 12 and 22 for processing information and executing instructions or operations. Processors 12 and 22 may be any type of general-purpose or special-purpose processor. In practice, processors 12 and 22 may include one or more of a general-purpose computer, a special-purpose computer, a microprocessor, a digital signal processor (DSP), a field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), and a processor based on a multi-core processor architecture, as an example. Figure 8Single processors 12 and 22 are shown, but multiple processors may be used according to other example embodiments. For example, it should be understood that in some example embodiments, devices 10 and 20 may include two or more processors, which may form a multiprocessor system (e.g., in this case, processor 12 may represent multiple processors), which may support multiprocessing. According to some example embodiments, the multiprocessor system may be tightly coupled or loosely coupled (e.g., to form a computer cluster).

[0076] Processors 12 and 22 can perform functions associated with the operation of devices 10 and 20, including, as some examples, precoding of antenna gain / phase parameters, encoding and decoding of individual bits forming communication messages, information formatting, and overall control of devices 10 and 20, including... Figure 1-7 The process and examples are shown in the figure.

[0077] Devices 10 and 20 may further include or be coupled to memories 14 and 24 (internal or external), which may be coupled to processors 12 and 24 respectively, for storing information and instructions executable by processors 12 and 24. Memories 14 and 24 may be one or more memories and are of any type suitable for the local application environment, and may be implemented using any suitable volatile or non-volatile data storage technology, such as semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory and / or removable memory. For example, memories 14 and 24 may consist of random access memory (RAM), read-only memory (ROM), static storage devices (e.g., disks or optical discs), hard disk drives (HDDs), or any other type of non-transitory machine or computer-readable medium, in any combination. Instructions stored in memories 14 and 24 may include program instructions or computer program code that, when executed by processors 12 and 22, enable devices 10 and 20 to perform the tasks described herein.

[0078] In some example embodiments, devices 10 and 20 may further include or be coupled to (internal or external) a drive or port configured to receive and read external computer-readable storage media (e.g., optical disc, USB drive, flash drive, or any other storage media). For example, the external computer-readable storage media may store computer programs or software executable by processors 12 and 22 and / or devices 10 and 20 to perform actions in... Figures 1 to 7 Any methods and examples shown in the document.

[0079] In some example embodiments, devices 10 and 20 may further include or be coupled to one or more antennas 15 and 25 for receiving downlink signals and for transmission from devices 10 and 20 via UL. Devices 10 and 20 may also include transceivers 18 and 28 configured to transmit and receive information. Transceivers 18 and 28 may also include a wireless interface (e.g., a modem) coupled to antennas 15 and 25. The wireless interface may correspond to a variety of radio access technologies, including one or more of GSM, LTE, LTE-A, 5G, NR, WLAN, NB-IoT, Bluetooth, BT-LE, NFC, RFID, UWB, O-RAN, etc. The wireless interface may include other components, such as filters, converters (e.g., digital-to-analog converters, etc.), symbol demappers, signal shaping components, inverse fast Fourier transform (IFFT) modules, etc., for processing symbols carried by the downlink or UL, such as OFDMA symbols.

[0080] For example, transceivers 18 and 28 may be configured to modulate information onto a carrier waveform for transmission by antennas 15 and 25, and demodulate information received via antennas 15 and 25 for further processing by other elements of device 10 and device 20. In other example embodiments, transceivers 18 and 28 may be able to directly transmit and receive signals or data. Additionally or alternatively, in some example embodiments, device 10 may include input and / or output devices (I / O devices). In some example embodiments, device 10 and device 20 may also include a user interface, such as a graphical user interface or a touchscreen.

[0081] In some example embodiments, memories 14 and 34 store software modules that provide functionality when executed by processors 12 and 22. These modules may include, for example, an operating system that provides operating system functionality for devices 10 and 20. The memories may also store one or more functional modules, such as applications or programs, to provide additional functionality for devices 10 and 20. Components of devices 10 and 20 may be implemented using hardware or any suitable combination of hardware and software. According to some example embodiments, devices 10 and 20 may optionally be configured to communicate with each other (in any combination) via a wireless or wired communication link 70 according to any radio access technology (e.g., NR).

[0082] According to some example embodiments, processors 12 and 22, and memories 14 and 24, may be included in or formed part of processing or control circuitry. Additionally, in some example embodiments, transceivers 18 and 28 may be included in or formed part of transceiver circuitry.

[0083] Certain example embodiments described herein provide several technical improvements, enhancements, and / or advantages. In some example embodiments, conflicts between cognitive functions can be detected with significantly lower operating costs (in terms of computation time and energy usage) than previously possible. Furthermore, conflicts that would not have been detected previously can be detected and mitigated.

[0084] A computer program product may include one or more computer-executable components that, when the program runs, are configured to perform some example embodiments. The one or more computer-executable components may be at least one piece of software code or a portion thereof. Modifications and configurations required to implement the functionality of certain example embodiments may be executed as routines, which may be implemented as added or updated software routines. These software routines may be downloaded to the device.

[0085] As an example, software or computer program code, or portions thereof, may be in the form of source code, object code, or some intermediate form, and may be stored in some carrier, distribution medium, or computer-readable medium, which may be any entity or device capable of carrying the program. Such carriers may include, for example, recording media, computer memory, read-only memory, photoelectric and / or electrical carrier signals, telecommunication signals, and software distribution packages. Depending on the required processing power, the computer program may execute in a single electronic digital computer or may be distributed among multiple computers. Computer-readable media or computer-readable storage media may be non-transitory media.

[0086] For example, in some exemplary embodiments, the device 10 may be controlled by the memory 14 and the processor 12 to: detect, by the conflict monitoring cognitive function, a performance metric exceeding a first boundary based on first radio access network information, the first radio access network information indicating a first parameter of the radio access network associated with the first cognitive function at a first time; detect, by the conflict monitoring cognitive function, a performance metric exceeding a second boundary based on second radio access network information, the second radio access network information indicating a second parameter of the radio access network associated with the first cognitive function at a second time, the second parameter being different from the first parameter; detect, by the conflict monitoring cognitive function, a conflict between the first cognitive function and at least one second cognitive function; and determine the severity of the conflict based on the performance metric exceeding the second boundary.

[0087] In other example embodiments, the device 20 may be controlled by the memory 14 and the processor 12 to: obtain an indication that a performance metric exceeds a first boundary, the performance metric being related to the radio access network and associated with a first cognitive function; transmit information related to the performance metric exceeding the boundary and a request to modify parameters of the first cognitive function; obtain an indication of a conflict between the first cognitive function and at least one second cognitive function and the severity of the conflict; and execute a conflict mitigation procedure based on the conflict.

[0088] In other example embodiments, the function may be performed by hardware or circuitry included in the device (e.g., device 10 or device 20), for example by using an application-specific integrated circuit (ASIC), a programmable gate array (PGA), a field-programmable gate array (FPGA), or any other combination of hardware and software. In yet another example embodiment, the function may be implemented as a signal, i.e., a non-tangible component carried by an electromagnetic signal downloaded from the Internet or other networks.

[0089] Some example embodiments may relate to an apparatus comprising: means for detecting, by a conflict monitoring cognitive function, a performance metric exceeding a first boundary based on first radio access network information, the first radio access network information indicating a first parameter of a radio access network associated with the first cognitive function at a first time; means for detecting, by the conflict monitoring cognitive function, a performance metric exceeding a second boundary based on second radio access network information, the second radio access network information indicating a second parameter of a radio access network associated with the first cognitive function at a second time, the second parameter being different from the first parameter; means for detecting, by the conflict monitoring cognitive function, a conflict between the first cognitive function and at least one second cognitive function; and means for determining the severity of the conflict based on the performance metric exceeding the second boundary.

[0090] Other example embodiments may relate to an apparatus including components for obtaining an indication by a controller that a performance metric exceeds a first boundary, the performance metric being related to a radio access network and associated with a first cognitive function; transmitting information related to the performance metric exceeding the boundary and a request for parameter modification from the controller to the first cognitive function; components for obtaining an indication by the controller of a conflict between the first cognitive function and at least one second cognitive function and the severity of the conflict; and components for executing a conflict mitigation procedure by the controller based on the conflict.

[0091] According to certain example embodiments, an apparatus such as a node, device, or corresponding component may be configured as a circuit, computer, or microprocessor (such as a single-chip computer element) or chipset, which includes at least a memory providing storage capacity for arithmetic operations and an arithmetic processor for performing arithmetic operations.

[0092] According to some example embodiments, an apparatus includes at least one processor and at least one memory storing instructions. When executed by the at least one processor, the instructions cause the apparatus to: detect a performance metric exceeding a first boundary based on first radio access network information, the first radio access network information indicating a first parameter of a radio access network associated with a first cognitive function at a first time; detect a performance metric exceeding a second boundary based on second radio access network information, the second radio access network information indicating a second parameter of a radio access network associated with the first cognitive function at a second time, the second parameter being different from the first parameter; detect a conflict between the first cognitive function and at least one second cognitive function; and determine the severity of the conflict based on the performance metric exceeding the second boundary.

[0093] In an example embodiment of the device, the instructions further instruct the device to: query a database by the conflict monitoring cognitive function to obtain first boundary information of performance indicators; receive the first boundary information from the database by the conflict monitoring cognitive function; and determine the first boundary by the conflict monitoring cognitive function based on the first boundary information.

[0094] In an example embodiment of the device, the first boundary is determined using a machine learning algorithm.

[0095] In an example embodiment of the device, the instructions further instruct the device to: query a database for tolerances of performance metrics by the conflict monitoring cognitive function; and receive tolerance information from the database by the conflict monitoring cognitive function, wherein the detection of conflicts and the determination of the severity of conflicts are based on the tolerance information.

[0096] In an example embodiment of the device, the instructions further instruct the device to: transmit a report indicating that a performance metric exceeds a first boundary; and obtain second radio access network information indicating a second parameter based on the transmitted report.

[0097] In an example embodiment of the device, the instructions further cause the device to perform a conflict mitigation procedure based on the conflict.

[0098] In an example embodiment of the device, the detection of a conflict between a first cognitive function and at least one second cognitive function is also based on network information.

[0099] In an example embodiment of the device, the detection of a conflict between a first cognitive function and at least one second cognitive function is also based on normal time, where normal time is the time during which the performance metric is determined to be within the normal range.

[0100] In an example embodiment of the device, the conflict between the first cognitive function and at least one second cognitive function is determined using a machine learning algorithm.

[0101] In an example embodiment of the device, the conflict between the first cognitive function and at least one second cognitive function is determined based on the action at at least one second cognitive function.

[0102] According to some example embodiments, an apparatus includes at least one processor and at least one memory storing instructions. When executed by the at least one processor, the instructions cause the apparatus to: obtain an indication that a performance metric exceeds a first boundary, the performance metric being related to a radio access network and associated with a first cognitive function; transmit information related to the performance metric exceeding the boundary and a request for parameter modification to the first cognitive function; obtain an indication of a conflict between the first cognitive function and at least one second cognitive function and the severity of the conflict; and execute a conflict mitigation procedure based on the conflict.

[0103] In an example embodiment of the device, indications of performance metrics exceeding a first boundary, as well as indications of conflicts between a first cognitive function and a second cognitive function, and the severity of those conflicts, are obtained from the conflict monitoring cognitive function.

[0104] In an example embodiment of the device, the instructions further instruct the device to: receive updated parameters from a first cognitive function; and transmit the updated parameters to a radio access network.

[0105] In an example embodiment of the device, the instructions further cause the device to: transmit updated parameters to the conflict monitoring cognitive function by the controller; receive indications of potential conflicts by the controller; and report information related to the operation of the first cognitive function, at least one second cognitive function, and the radio access network by the controller.

[0106] It will be readily understood by those skilled in the art that the present invention as described above can be practiced with procedures of a different order and / or with hardware elements in a configuration different from the disclosed configuration. Therefore, although the invention has been described based on these exemplary embodiments, it will be apparent to those skilled in the art that certain modifications, variations, and alternative constructions will be readily apparent while remaining within the spirit and scope of the exemplary embodiments. While the above embodiments relate to 5G NR and LTE technologies, they can also be applied to any other existing or future 3GPP technologies, such as LTE-advanced and / or fourth-generation (4G) technologies.

[0107] Partial Glossary 3GPP Third Generation Partnership Project 5G (Fifth Generation) 5GCN 5G Core Network BS base station DL downlink eNB Enhanced Node B gNB 5G or next-generation node B LTE Long Term Evolution NM Network Manager NR New Radio UE User Equipment NCF Network Control Function CF cognitive function CMCF Conflict Detection Cognitive Function DB database KPIs (Key Performance Indicators) RAN (Radio Access Network) O-RAN Open Radio Access Network

Claims

1. A method comprising: The conflict monitoring cognitive function detects that the performance index exceeds the first boundary based on the first radio access network information, and the first radio access network information indicates the first parameter of the radio access network associated with the first cognitive function at the first time. The conflict monitoring cognitive function detects that the performance index exceeds a second boundary based on the second radio access network information. The second radio access network information indicates a second parameter of the radio access network associated with the first cognitive function at a second time, and the second parameter is different from the first parameter. The conflict monitoring cognitive function detects a conflict between the first cognitive function and at least one second cognitive function; as well as The severity of the conflict is determined by the conflict monitoring and cognitive function based on the performance index exceeding the second boundary.

2. The method according to claim 1, further comprising: The conflict monitoring and cognitive function queries the database for the first boundary information of the performance indicators; The conflict monitoring and cognitive function receives the first boundary information from the database; as well as The conflict monitoring and cognitive function determines the first boundary based on the first boundary information.

3. The method of claim 2, wherein the first boundary is determined using a machine learning algorithm.

4. The method according to any one of claims 1-3, further comprising: The conflict monitoring and cognitive function queries the database for the tolerance of the performance indicators; as well as The conflict monitoring and cognitive function receives the tolerance information from the database. The detection of the conflict and the determination of the severity of the conflict are based on the tolerance information.

5. The method according to any one of claims 1-4, further comprising: The conflict monitoring cognitive function transmits a report indicating that the performance metric exceeds the first boundary; The conflict monitoring cognitive function obtains second radio access network information indicating the second parameter based on the transmitted report.

6. The method according to any one of claims 1-5, further comprising: The conflict monitoring and cognitive function executes conflict mitigation procedures based on the conflict.

7. The method according to any one of claims 1-6, wherein the detection of the conflict between the first cognitive function and the at least one second cognitive function is further based on network information.

8. The method of claim 7, wherein the detection of the conflict between the first cognitive function and the at least one second cognitive function is further based on normal time, wherein normal time is the time during which the performance metric is determined to be within the normal range.

9. The method of claim 7, wherein detecting the conflict between the first cognitive function and the at least one second cognitive function comprises detecting the conflict of the first cognitive function using a machine learning algorithm.

10. The method of claim 7, wherein detecting the conflict between the first cognitive function and the at least one second cognitive function further comprises detecting the conflict between the first cognitive function and the at least one second cognitive function based on an action at the at least one second cognitive function.

11. A method comprising: The controller obtains an indication that a performance metric exceeds a first boundary, the performance metric being related to the radio access network and associated with a first cognitive function; The controller transmits information related to the performance metric exceeding the boundary and a request to modify the parameters to the first cognitive function; The controller obtains an indication of the conflict between the first cognitive function and at least one second cognitive function, as well as the severity of the conflict. as well as The controller executes a conflict mitigation procedure based on the conflict.

12. The method of claim 11, wherein the indication that the performance metric exceeds the first boundary, the indication of the conflict between the first cognitive function and the second cognitive function, and the severity of the conflict are obtained from the conflict monitoring cognitive function.

13. The method according to claim 11 or 12, further comprising: The controller receives updated parameters from the first cognitive function; as well as The updated parameters are transmitted from the controller to the radio access network.

14. The method of claim 13, further comprising: The updated parameters are transmitted from the controller to the conflict monitoring and cognitive function; The controller receives an indication of a potential conflict; as well as The controller reports information related to the operation of the first cognitive function, the at least one second cognitive function, and the radio access network.

15. An apparatus comprising: Conflict monitoring cognitive functions include: A component for detecting performance indicators exceeding a first boundary based on first radio access network information, wherein the first radio access network information indicates a first parameter of the radio access network associated with the first cognitive function at a first time. Components for detecting performance indicators exceeding a second boundary based on second radio access network information, wherein the second radio access network information indicates a second parameter of the radio access network associated with the first cognitive function at a second time, and the second parameter is different from the first parameter; A component for detecting a conflict between the first cognitive function and at least one second cognitive function; and Components for determining the severity of the conflict based on the performance metric exceeding the second boundary.

16. The apparatus of claim 15, wherein the conflict monitoring and cognitive function further comprises: A component used to query the database for the first boundary information of the performance metric; A component for receiving the first boundary information from the database; as well as A component used to determine the first boundary based on the first boundary information.

17. The apparatus of claim 16, wherein the first boundary is determined using a machine learning algorithm.

18. The apparatus according to any one of claims 15-17, wherein the conflict monitoring and cognitive function further comprises: A component used to query the database for the tolerance of the performance metric; as well as A component for receiving the tolerance information from the database; as well as The component for detecting the conflict between the first cognitive function and at least one second cognitive function includes a component for detecting the conflict based on the tolerance information, and the component for determining the severity of the conflict includes a component for determining the severity of the conflict based on the tolerance information.

19. The apparatus according to any one of claims 15-18, wherein the conflict monitoring and cognitive function further comprises: Components for transmitting reports indicating that the performance metric exceeds the first boundary; as well as A component for obtaining second radio access network information indicating the second parameter based on the report transmitted.

20. The apparatus according to any one of claims 15-19, wherein the conflict monitoring and cognitive function further comprises: Execute conflict mitigation procedures based on the aforementioned conflict.

21. The method of claims 15-20, wherein the component for detecting the conflict between the first cognitive function and the at least one second cognitive function includes a component for detecting the conflict between the first cognitive function and the at least one second cognitive function based on network information.

22. The method of claim 21, wherein the component for detecting the conflict between the first cognitive function and the at least one second cognitive function includes a component for detecting the conflict between the first cognitive function and the at least one second cognitive function based on a normal time, wherein the normal time is the time during which the performance metric is determined to be within a normal range.

23. The apparatus of claim 21, wherein the component for detecting the conflict between the first cognitive function and the at least one second cognitive function includes a component for detecting the conflict between the first cognitive function and the at least one second cognitive function using a machine learning algorithm.

24. The apparatus of claim 21, wherein the component for detecting the conflict between the first cognitive function and the at least one second cognitive function includes a component for detecting the conflict between the first cognitive function and the at least one second cognitive function based on an action at the at least one second cognitive function.

25. A controller, comprising: Components for obtaining an indication that a performance metric exceeds a first boundary, the performance metric being related to a radio access network and associated with a first cognitive function; Components for transmitting information related to the performance metric exceeding the boundary to the first cognitive function and for requesting parameter modification; Components for obtaining an indication of the conflict between the first cognitive function and at least one second cognitive function, and the severity of the conflict; as well as A component for performing conflict mitigation procedures based on the conflict.

26. The controller of claim 25, wherein the indication that the performance metric exceeds the first boundary, the indication of the conflict between the first cognitive function and the second cognitive function, and the severity of the conflict are obtained from the conflict monitoring cognitive function.

27. The controller according to claim 25 or 26, further comprising: A component for receiving updated parameters from the first cognitive function; as well as Components for transmitting the updated parameters to the radio access network.

28. The method of claim 27, further comprising: Components for transmitting the updated parameters to the conflict monitoring cognitive function; A component used to transmit an indication of a potential collision received; as well as Components for transmitting reports related to the operation of the first cognitive function, the at least one second cognitive function, and the radio access network.

29. An apparatus comprising: At least one processor; as well as At least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to perform the method according to any one of claims 1-10.

30. A controller, comprising: At least one processor; as well as At least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to perform the method according to any one of claims 11-14.

31. A computer program comprising instructions, wherein when executed by at least one processor of a device, the computer program causes the device to perform the method according to any one of claims 1-10.

32. A computer program comprising instructions, wherein, when executed by at least one processor of a controller, the computer program causes the controller to perform the method according to any one of claims 11-15.

33. A computer-readable medium comprising instructions that, when executed by at least one processor of a device, cause the device to perform the method according to any one of claims 1-10.

34. A computer-readable medium comprising instructions that, when executed by at least one processor of a controller, cause the controller to perform the method according to any one of claims 11-15.

Images