EP4740387A1

EP4740387A1 - System and method for auto-tuning network configuration

Info

Publication number: EP4740387A1
Application number: EP24839045.2A
Authority: EP
Inventors: Sandeep Bisht; Prashant Pandey; Ravindra Yadav; Aayush Bhatnagar; Anurag Sinha; Ezaj Ansari
Original assignee: Jio Platforms Ltd
Current assignee: Jio Platforms Ltd
Priority date: 2023-07-08
Filing date: 2024-06-11
Publication date: 2026-05-13
Also published as: WO2025012929A1

Abstract

The present disclosure relates to a method and a system for configuration auto-tuning in a network system. The method encompasses fetching, by a fetching unit [206] via a service communication proxy - performance Artificial Intelligence (SCP-pAI) [306], the set of network statistics from the SCP [110] at predetermined intervals, wherein the set of network statistics is determined at the SCP [110]; analysing, by an analysis unit [208] using a trained SCP-pAI [306], the determined set of network statistics to determine an optimal network system configuration for prevailing network conditions; comparing, by a comparator [210], the determined optimal network system configuration with a current network system configuration; and in case of a mismatch between the determined optimal network system configuration and the current network system configuration, automatically adjusting, by an adjusting unit [212], the network system configuration based on the comparison.

Description

SYSTEM AND METHOD FOR AUTO-TUNING NETWORK CONFIGURATION

FIEED OF THE DISCEOSURE

[0001] The present disclosure relates generally to the field of wireless communication systems. More particularly, the present disclosure relates to methods and systems for auto-tuning network configuration.

BACKGROUND

[0002] The following description of related art is intended to provide background information pertaining to the field of the disclosure. This section may include certain aspects of the art that may be related to various features of the present disclosure. However, it should be appreciated that this section be used only to enhance the understanding of the reader with respect to the present disclosure, and not as admissions of prior art.

[0003] Wireless communication technology has rapidly evolved over the past few decades, with each generation bringing significant improvements and advancements. The first generation of wireless communication technology was based on analog technology and offered only voice services. However, with the advent of the second-generation (2G) technology, digital communication and data services became possible, and text messaging was introduced. 3G technology marked the introduction of high-speed internet access, mobile video calling, and location-based services. The fourth-generation (4G) technology revolutionized wireless communication with faster data speeds, better network coverage, and improved security. Currently, the fifth-generation (5G) technology is being deployed, promising even faster data speeds, low latency, and the ability to connect multiple devices simultaneously. With each generation, wireless communication technology has become more advanced, sophisticated, and capable of delivering more services to its users.

[0004] Existing techniques in network management and configuration tuning faces several challenges. One of the primary issues is the lack of adaptability in existing systems, which are not equipped to automatically adjust to sudden changes in network conditions such as increased Round-trip Time (RTT), congestion, and packet drop ratios. Existing systems are typically optimized for normal operating conditions and fail to adapt when anomalies occur. Consequently, network administrators are required to manually re-tune the system configurations to adapt to the new conditions, a process that is time-consuming, labour-intensive, and prone to human error. Additionally, existing systems often lack effective mechanisms for continuously monitoring network performance metrics in real time, limiting their ability to detect and respond to changes promptly. Many existing techniques use static configuration parameters that do not account for the dynamic nature of network conditions, leading to suboptimal performance and inefficiencies. Furthermore, existing systems typically do not employ artificial intelligence to anticipate network changes and adjust configurations proactively. Managing and optimizing network configurations can be complex, especially in large-scale networks, and prior art solutions may not provide intuitive tools or interfaces for simplifying this process. Lastly, effective re-tuning of network configurations often requires in-depth knowledge and expertise, which may not be readily available in all organizations.

[0005] The proposed system aims to solve these problems by providing a more adaptive, automated, and efficient approach to network configuration management, minimizing the impact of network disruptions on performance and reducing the reliance on manual intervention.

OBJECTS OF THE INVENTION

[0006] Some of the objects of the present disclosure, which at least one embodiment disclosed herein satisfies are listed herein below.

[0007] It is an object of the present disclosure to provide a method and system for auto-tuning network configuration.

[0008] It is another object of the present disclosure to provide a method and system for auto-tuning network configuration that enables the network system to adapt automatically to changes in network conditions such as Round-trip Time (RTT), congestion, and packet drop ratios, ensuring optimal performance even during disruptions.

[0009] It is another object of the present disclosure to provide a method and system for auto-tuning network configuration that reduces the need for manual reconfiguration by network administrators, thereby saving time and reducing the potential for human error.

[0010] It is another object of the present disclosure to provide a method and system for auto-tuning network configuration that incorporates mechanisms for continuous real-time monitoring of network performance metrics, allowing for timely detection and response to changes in network conditions.

[0011] It is another object of the present disclosure to provide a method and system for auto-tuning network configuration that employs dynamic configuration parameters that adjust according to the current network conditions, ensuring more efficient and effective network performance.

[0012] It is another object of the present disclosure to provide a method and system for auto-tuning network configuration that leverages artificial intelligence to anticipate changes in network conditions and proactively adjust configurations accordingly.

[0013] It is another object of the present disclosure to provide a method and system for auto-tuning network configuration that provides intuitive tools or interfaces for managing and optimizing network configurations, making it easier to handle even in large-scale networks.

[0014] It is yet another object of the present disclosure to provide a method and system for autotuning network configuration that minimizes the reliance on in-depth technical knowledge or expertise for re-tuning network configurations, making the system more accessible to a broader range of users.

SUMMARY

[0015] This section is provided to introduce certain aspects of the present disclosure in a simplified form that are further described below in the detailed description. This summary is not intended to identify the key features or the scope of the claimed subject matter.

[0016] An aspect of the present disclosure is related to a method for configuration auto-tuning in a network system. The method includes fetching, by a fetching unit via the SCP-pAI, the set of network statistics from the SCP at predetermined intervals, wherein the set of network statistics is determined at the SCP [110], The method further includes analysing, by an analysis unit using a trained SCP-pAI, the determined set of network statistics to determine an optimal network system configuration for prevailing network conditions. The method further includes comparing, by a comparator, the determined optimal network system configuration with a current system configuration. Thereafter, in case of a mismatch between the determined optimal network system configuration and the current network system configuration, the method further includes automatically adjusting, by an adjusting unit, the network system configuration based on the comparison.

[0017] In an aspect, the network statistics comprises at least one of Round-trip Time (RTT), internet control message protocol (ICMP) ping packet drop ratio, and available bandwidth.

[0018] In an aspect, the method comprises displaying, by a display unit, a network system configuration recommendation.

[0019] In an aspect, if the network system configuration recommendation is provided, an administrator is alerted, enabling consent-based tuning of the network system configuration.

[0020] In an aspect, the network system configuration comprises any or a combination of transmission control protocol (TCP)-related kernel parameters, application-related timeouts, and TCP connection counts.

[0021] In an aspect, the network system configuration recommendation provided to the administrator details differences between the current network system configuration and the optimal network system configuration, facilitating informed decision-making.

[0022] In an aspect, the method comprises training, by a training unit, the SCP-pAI with a set of network conditions against a set of respective network system configurations and corresponding set of Key Performance Indicator (KPI) outcomes.

[0023] In an aspect, the set of network conditions corresponds to at least one of values of RTT, packet drop ratios, and different TCP connection counts.

[0024] In an aspect, the SCP-pAI uses stored historical network statistics in conjunction with current statistics to predict optimal network system configuration.

[0025] Another aspect of the present disclosure provides a system for configuration auto-tuning in a network system. The system includes a fetching unit configured to fetch, via the service communication proxy - performance Artificial Intelligence (SCP-pAI), the set of network statistics from the SCP at predetermined intervals, wherein the set of network statistics is determined at the SCP [110], The system further includes an analysis unit configured to analyse, using a trained SCP-pAI, the determined set of network statistics to determine an optimal network system configuration for prevailing network conditions. The method further includes a comparator configured to compare the determined optimal network system configuration with a current network system configuration. Thereafter, in case of a mismatch between the determined optimal network system configuration and the current network system configuration, the system further includes an adjusting unit configured to automatically adjust the network system configuration based on the comparison.

[0026] Another aspect of the present disclosure provides a user equipment (UE) for configuration auto-tuning in a network system. The UE comprises a receiving unit configured to receive network system configuration recommendation. The UE further comprises a display unit configured to display the network system configuration recommendation. The UE further comprises the receiving unit configured to receive user input for the displayed network system configuration recommendation. The UE further comprises a transmitting unit configured to transmit the network system configuration recommendation.

[0027] Yet another aspect of the present disclosure provides a non-transitory computer-readable storage medium storing instruction for configuration auto-tuning in a network system, the storage medium comprising executable code which, when executed by one or more units of a system, causes: a fetching unit to fetch, via a the service communication proxy- performance artificial intelligence (SCP-pAI), the set of network statistics from the SCP at predetermined intervals, wherein the set of network statistics is determined at the SCP; an analysis unit to analyse, using the a trained SCP-pAI, the determined set of network statistics to determine an optimal network system configuration for prevailing network conditions; a comparator to compare the determined optimal network system configuration with a current network system configuration; and an adjusting unit to automatically adjust the network system configuration based on the comparison in case of a mismatch between the determined optimal network system configuration and the current network system configuration.

BRIEF DESCRIPTION OF DRAWINGS

[0028] The accompanying drawings, which are incorporated herein, and constitute a part of this disclosure, illustrate exemplary embodiments of the disclosed methods and systems in which like reference numerals refer to the same parts throughout the different drawings. Components in the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the present disclosure. Some drawings may indicate the components using block diagrams and may not represent the internal circuitry of each component. It will be appreciated by those skilled in the art that disclosure of such drawings includes disclosure of electrical components, electronic components or circuitry commonly used to implement such components.

[0029] FIG. 1 illustrates an exemplary block diagram representation of 5th generation core (5GC) network architecture.

[0030] FIG.2 illustrates an exemplary block diagram of a system for configuration auto-tuning in a network system, in accordance with exemplary embodiments of the present disclosure.

[0031] FIG. 3 illustrates an exemplary block diagram of an architecture for implementation of a system for configuration auto-tuning in a network system, in accordance with exemplary implementations of the present disclosure.

[0032] FIG. 4 illustrates an exemplary method flow diagram indicating the process for configuration auto-tuning in a network system, in accordance with exemplary embodiments of the present disclosure is shown.

[0033] FIG. 5 illustrates an exemplary block diagram of a computing device upon which an embodiment of the present disclosure may be implemented.

[0034] FIG. 6 illustrates an exemplary block diagram of a user equipment (UE) for configuration auto-tuning in a network system, in accordance with exemplary implementations of the present disclosure.

[0035] The foregoing shall be more apparent from the following more detailed description of the disclosure.

DESCRIPTION

[0036] In the following description, for the purposes of explanation, various specific details are set forth in order to provide a thorough understanding of embodiments of the present disclosure. It will be apparent, however, that embodiments of the present disclosure may be practiced without these specific details. Several features described hereafter can each be used independently of one another or with any combination of other features. An individual feature may not address any of the problems discussed above or might address only some of the problems discussed above. Some of the problems discussed above might not be fully addressed by any of the features described herein. Example embodiments of the present disclosure are described below, as illustrated in various drawings in which like reference numerals refer to the same parts throughout the different drawings.

[0037] The ensuing description provides exemplary embodiments only, and is not intended to limit the scope, applicability, or configuration of the disclosure. Rather, the ensuing description of the exemplary embodiments will provide those skilled in the art with an enabling description for implementing an exemplary embodiment. It should be understood that various changes may be made in the function and arrangement of elements without departing from the spirit and scope of the disclosure as set forth.

[0038] It should be noted that the terms "mobile device", "user equipment", "user device", “communication device”, “device” and similar terms are used interchangeably for the purpose of describing the invention. These terms are not intended to limit the scope of the invention or imply any specific functionality or limitations on the described embodiments. The use of these terms is solely for convenience and clarity of description. The invention is not limited to any particular type of device or equipment, and it should be understood that other equivalent terms or variations thereof may be used interchangeably without departing from the scope of the invention as defined herein.

[0039] Specific details are given in the following description to provide a thorough understanding of the embodiments. However, it will be understood by one of ordinary skill in the art that the embodiments may be practiced without these specific details. For example, circuits, systems, networks, processes, and other components may be shown as components in block diagram form in order not to obscure the embodiments in unnecessary detail. In other instances, well-known circuits, processes, algorithms, structures, and techniques may be shown without unnecessary detail in order to avoid obscuring the embodiments.

[0040] Also, it is noted that individual embodiments may be described as a process which is depicted as a flowchart, a flow diagram, a data flow diagram, a structure diagram, or a block diagram. Although a flowchart may describe the operations as a sequential process, many of the operations can be performed in parallel or concurrently. In addition, the order of the operations may be re-arranged. A process is terminated when its operations are completed but could have additional steps not included in a figure.

[0041] The word “exemplary” and/or “demonstrative” is used herein to mean serving as an example, instance, or illustration. For the avoidance of doubt, the subject matter disclosed herein is not limited by such examples. In addition, any aspect or design described herein as “exemplary” and/or “demonstrative” is not necessarily to be construed as preferred or advantageous over other aspects or designs, nor is it meant to preclude equivalent exemplary structures and techniques known to those of ordinary skill in the art. Furthermore, to the extent that the terms “includes,” “has,” “contains,” and other similar words are used in either the detailed description or the claims, such terms are intended to be inclusive — in a manner similar to the term “comprising” as an open transition word — without precluding any additional or other elements.

[0042] As used herein, an “electronic device”, or “portable electronic device”, or “user device” or “communication device” or “user equipment” or “device” refers to any electrical, electronic, electromechanical and computing device. The user device is capable of receiving and/or transmitting one or parameters, performing function/s, communicating with other user devices and transmitting data to the other user devices. The user equipment may have a processor, a display, a memory, a battery and an input-means such as a hard keypad and/or a soft keypad. The user equipment may be capable of operating on any radio access technology including but not limited to IP-enabled communication, Zig Bee, Bluetooth, Bluetooth Low Energy, Near Field Communication, Z-Wave, Wi-Fi, Wi-Fi direct, etc. For instance, the user equipment may include, but not limited to, a mobile phone, smartphone, virtual reality (VR) devices, augmented reality (AR) devices, laptop, a general-purpose computer, desktop, personal digital assistant, tablet computer, mainframe computer, or any other device as may be obvious to a person skilled in the art for implementation of the features of the present disclosure.

[0043] Further, the user device may also comprise a “processor” or “processing unit” includes processing unit, wherein processor refers to any logic circuitry for processing instructions. The processor may be a general-purpose processor, a special purpose processor, a conventional processor, a digital signal processor, a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits, Field Programmable Gate Array circuits, any other type of integrated circuits, etc. The processor may perform signal coding data processing, input/output processing, and/or any other functionality that enables the working of the system according to the present disclosure. More specifically, the processor is a hardware processor.

[0044] As portable electronic devices and wireless technologies continue to improve and grow in popularity, the advancing wireless technologies for data transfer are also expected to evolve and replace the older generations of technologies. In the field of wireless data communications, the dynamic advancement of various generations of cellular technology are also seen. The development, in this respect, has been incremental in the order of second generation (2G), third generation (3G), fourth generation (4G), and now fifth generation (5G), and more such generations are expected to continue in the forthcoming time.

[0045] Radio Access Technology (RAT) refers to the technology used by mobile devices/ user equipment (UE) to connect to a cellular network. It refers to the specific protocol and standards that govern the way devices communicate with base stations, which are responsible for providing the wireless connection. Further, each RAT has its own set of protocols and standards for communication, which define the frequency bands, modulation techniques, and other parameters used for transmitting and receiving data. Examples of RATs include GSM (Global System for Mobile Communications), CDMA (Code Division Multiple Access), UMTS (Universal Mobile Telecommunications System), LTE (Long-Term Evolution), and 5G. The choice of RAT depends on a variety of factors, including the network infrastructure, the available spectrum, and the mobile device's/device's capabilities. Mobile devices often support multiple RATs, allowing them to connect to different types of networks and provide optimal performance based on the available network resources.

[0046] The present disclosure aims to overcome the above-mentioned and other existing problems in this field of technology by introducing a method and system for auto-tuning of network configuration. The method involves training a Service Communication Proxy - Performance Artificial Intelligence (SCP-pAI) with various network conditions and corresponding network configurations, along with the resulting Key Performance Indicator (KPI) outcomes. This training enables the SCP-pAI to predict optimal network configurations based on current network conditions such as Round-trip Time (RTT), congestion, and packet drop ratios. The method includes determining network statistics via a Service Communication Proxy (SCP) and fetching these statistics at predetermined intervals using the SCP-pAI. By analyzing the fetched network statistics, the SCP-pAI determines the optimal network configuration for the prevailing network conditions. If there is a mismatch between the current network configuration and the determined optimal configuration, the system automatically adjusts the network configuration based on the comparison. This automated process reduces the need for manual re-tuning (such as auto tuning) by network administrators, saving time and effort. The system also enhances real-time monitoring of network performance metrics, allowing for prompt detection and response to changes in network conditions.

[0047] It would be appreciated by the person skilled in the art that by employing dynamic configuration parameters and predictive algorithms, the SCP-pAI ensures that the network configuration remains optimized even in the face of network disruptions or changes.

[0048] Hereinafter, exemplary embodiments of the present disclosure will be described with reference to the accompanying drawings.

[0049] FIG. 1 illustrates an exemplary block diagram representation of 5th generation core (5GC) network architecture, in accordance with exemplary embodiment of the present disclosure. As shown in FIG. 1, the 5GC network architecture [100] includes a user equipment (UE) [102], a radio access network (RAN) [104], an access and mobility management function (AMF) [106], a Session Management Function (SMF) [108], a Service Communication Proxy (SCP) [110], an Authentication Server Function (AUSF) [112], a Network Slice Specific Authentication and Authorization Function (NSSAAF) [114], a Network Slice Selection Function (NSSF) [116], a Network Exposure Function (NEF) [118], a Network Repository Function (NRF) [120], a Policy Control Function (PCF) [122], a Unified Data Management (UDM) [124], an application function (AF) [126], a User Plane Function (UPF) [128], a data network (DN) [130], wherein all the components are assumed to be connected to each other in a manner as obvious to the person skilled in the art for implementing features of the present disclosure.

[0050] Radio Access Network (RAN) [104] is the part of a mobile telecommunications system that connects User Equipment (UE) [102] to the core network (CN) and provides access to different types of networks (e.g., 5G, LTE). It consists of radio base stations and the radio access technologies that enable wireless communication.

[0051] Access and Mobility Management Function (AMF) [106] is a 5G core network function responsible for managing access and mobility aspects, such as UE registration, connection, and reachability. It also handles mobility management procedures like handovers and paging. [0052] Session Management Function (SMF) [108] is a 5G core network function responsible for managing session-related aspects, such as establishing, modifying, and releasing sessions. It coordinates with the User Plane Function (UPF) for data forwarding and handles IP address allocation and QoS enforcement.

[0053] Service Communication Proxy (SCP) [110] is a network function in the 5G core that facilitates communication between other network functions by providing a secure and efficient messaging service. It acts as a mediator for service-based interfaces.

[0054] Authentication Server Function (AUSF) [112] is a network function in the 5G core responsible for authenticating UEs during registration and providing security services. It generates and verifies authentication vectors and tokens.

[0055] Network Slice Specific Authentication and Authorization Function (NSSAAF) [114] is a network function that provides authentication and authorization services specific to network slices. It ensures that UEs can access only the slices for which they are authorized.

[0056] Network Slice Selection Function (NSSF) [116] is a network function responsible for selecting the appropriate network slice for a UE based on factors such as subscription, requested services, and network policies.

[0057] Network Exposure Function (NEF) [118] is a network function that exposes capabilities and services of the 5G network to external applications, enabling integration with third-party services and applications.

[0058] Network Repository Function (NRF) [120] is a network function that acts as a central repository for information about available network functions and services. It facilitates the discovery and dynamic registration of network functions.

[0059] Policy Control Function (PCF) [122] is a network function responsible for policy control decisions, such as QoS, charging, and access control, based on subscriber information and network policies. [0060] Unified Data Management (UDM) [124] is a network function that centralizes the management of subscriber data, including authentication, authorization, and subscription information.

[0061] Application Function (AF) [126] is a network function that represents external applications interfacing with the 5G core network to access network capabilities and services.

[0062] User Plane Function (UPF) [128] is a network function responsible for handling user data traffic, including packet routing, forwarding, and QoS enforcement.

[0063] Data Network (DN) [130] represents external networks or services that users connect to through the mobile network, such as the internet or enterprise networks.

[0064] Referring to FIG. 2, an exemplary block diagram of a system [200] for configuration autotuning in a network system, in accordance with the exemplary implementations of the present disclosure. The system [200] comprises a training unit [202] a fetching unit [206], an analysis unit [208], a comparator [210], an adjusting unit [212] and a display unit [214], Also, all of the components/ units of the system [200] are assumed to be connected to each other unless otherwise indicated below. Also, in FIG. 2 only a few units are shown, however, the system [200] may comprise multiple such units or the system [200] may comprise any such numbers of said units, as required to implement the features of the present disclosure. Further, in an implementation, the system [200] may be present at a network level to implement the features of the present disclosure. In an implementation, the system [200] may reside in a server, a network entity, a SCP [110], or an SCP-pAI [306] as disclosed in FIG. 3. The system [200] may reside entirely within the SCP- pAI [306], or certain modules of the system [200] may be integrated into the SCP-pAI [306], For instance, the training unit [202] must be part of the SCP-pAI [306] for training the artificial intelligence model with various network conditions and their respective optimal configurations. Other components may also reside within the SCP-pAI [306] to ensure seamless data processing and configuration adjustments

[0065] The system [200] includes a training unit [202] configured to train the SCP-pAI with a set of network conditions against a set of respective network system configurations and corresponding set of Key Performance Indicator (KPI) outcomes. The training may include providing the SCP- pAI with historical set of network statistics in conjunction with set of current statistics to predict optimal network system configuration. The historical network statistics may include the set of network conditions against the set of respective network system configurations and corresponding set of Key Performance Indicator (KPI) outcomes. The set of network conditions may include at least one of Round-trip Time (RTT), packet drop ratios, and congestion levels. The SCP-pAI may further be trained with the network system configurations that were applied during those conditions, such as TCP-related kernel parameters, application-related timeouts, and TCP connection counts. Additionally, the SCP-pAI may further be trained on KPI outcomes that were achieved with the specific network conditions and configurations. The training enables the SCP- pAI to establish a relationship between network conditions, system configurations, and their impact on KPI outcomes. Thus, the SCP-pAI enables predicting the optimal network system configuration for any given set of prevailing network conditions for achieving best possible KPI outcomes.

[0066] The SCP [110] may be configured to determine a set of network statistics. The set of network statistics may include metrics comprising but not limited only to Round-trip Time (RTT), available bandwidth, congestion levels, and ICMP ping packet drop ratios. The SCP [110] may continuously monitor the set of network statistics at regular intervals to ensure real-time data is available for the SCP-pAI to analyze and determine the optimal network system configuration for the prevailing conditions, ensuring that the network system remains optimized and performs efficiently despite any changes in network characteristics.

[0067] The system [200] further includes the fetching unit [206] communicatively coupled to the SCP [110], The fetching unit [206] is configured to fetch, via the SCP-pAI, the set of network statistics from the SCP [110] at predetermined intervals, wherein the set of network statistics is determined at the SCP [110], The fetching unit [206] operates at the predetermined intervals. The predefined intervals may be set according to operator's policy, thereby ensuring that the SCP-pAI receives real-time information associated with the network conditions. The set of predefined intervals may be configurable by a user, or operator etc.

[0068] The system [200] further includes the analysis unit [208] communicatively coupled to the fetching unit [206], The analysis unit [208] is configured to analyse, using the trained SCP-pAI, the determined set of network statistics to determine an optimal network system configuration for prevailing network conditions. The trained SCP-pAI is used to evaluate the current network statistics. The analysis unit [208] determines the optimal network system configuration that is expected to yield the best Key Performance Indicator (KPI) outcomes under the current network conditions. The optimal network system configuration may then use by the system [200] to adjust the network settings automatically.

[0069] The system [200] further includes the comparator [210] communicatively coupled to the analysis unit [208], The comparator [210] is configured to compare the determined optimal network system configuration with a current network system configuration to identify any discrepancies between the two. The comparison facilitates in ensuring that the network system operates at its best possible performance. When the analysis unit [208] determines the optimal configuration based on the analysis of current network statistics, the comparator [210] checks this against the network's existing configuration. If there is a mismatch, indicating that the current configuration is not optimal for the prevailing network conditions, the system [200] can take corrective action to adjust the configuration.

[0070] The system [200] further includes the adjusting unit [212] communicatively coupled to the comparator [210], In case of a mismatch between the determined optimal network system configuration and the current network system configuration, the adjusting unit [212] is configured to automatically adjust the network system configuration based on the comparison. The adjustment process involves modifying the network settings to align with the optimal configuration determined by the analysis unit [208] . The adjusting unit [212] receives instructions from the SCP- pAI regarding the necessary changes and implements them through a secure interface such as an application programming interface (API). The implementations occur across various network functions (NFs), including both the one or more NF consumers and the one or more NF producers, as well as the one or more SCP instances [110], The adjusting unit [212] thus ensures that the network system operates under the most favourable conditions for its current state. The automated adjustment process minimizes the impact of network disruptions on KPIs and reduces the need for manual intervention by network administrators, thereby saving time and resources based on the instructions received from the SCP-pAI.

[0071] The system [200] includes the display unit [214] communicatively coupled to the adjusting unit [212], The display unit [214] is configured to display a network system configuration recommendation once it is provided by the SCP-pAI. The recommendation may include the optimal network system configuration determined by the analysis unit [208] based on the current network conditions. When the recommendation is displayed, subsequently an administrator may be alerted. The generated alert may enable consent-based tuning of the network system configuration. The consent-based tuning of the network system configuration allows for a manual override or approval of the proposed changes, ensuring that any adjustments are made with full awareness and control. The network system configuration recommendation may include includes details on various parameters such as TCP -related kernel parameters, application-related timeouts, and TCP connection counts. It also outlines the differences between the current network system configuration and the optimal network system configuration, facilitating informed decisionmaking by the administrator. Thus, ensures transparency and control in the auto-tuning process, allowing administrators to make educated decisions based on the recommendations provided by the system.

[0072] Referring to FIG. 3, an exemplary block diagram of a system architecture [300] for outlier detection and alternate route suggestion is shown, in accordance with the exemplary implementations of the present disclosure. The system architecture [300] comprises one or more network function (NF) Consumers [302], one or more network function (NF) Producers [304], SCP-pAI [306], and one or more SCP instances [110], Also, all of the components/units of the system architecture [300] are assumed to be connected to each other unless otherwise indicated below. Also, in FIG. 3 only a few units are shown, however, the system architecture [300] may comprise multiple such units or the system architecture [300] may comprise any such numbers of said units, as required to implement the features of the present disclosure.

[0073] The SCP-pAI [306] includes a training unit [202] configured to train the SCP-pAI [306] with a set of network conditions against a set of respective network system configurations and corresponding set of Key Performance Indicator (KPI) outcomes. The set of network conditions corresponds to at least one of values of RTT, packet drop ratios, and different TCP connection counts. For example, it might be trained with RTT values ranging from a few nanoseconds to several milliseconds. Similarly, packet drop ratios could vary from near zero in optimal conditions to higher percentages during congestion events. The SCP-pAI [306] may correlate the variables with various system configurations like TCP kernel tweaks (e.g., window size adjustments), application timeout settings (longer timeouts during high latency periods), and dynamic adjustments to TCP connection counts to maintain throughput. Training also includes the performance outcomes, measured in KPIs such as throughput, error rate, and service downtime for evaluating the effectiveness of different configurations.

[0074] At regular time intervals, one or more instances of the SCP [110] receive data from the NF Consumers [302] and/or the NF Producers [304] to determine the set of network statistics. The set of network statistics includes, but not limited only to at least one of Round-trip Time (RTT), internet control message protocol (ICMP) ping packet drop ratio, and available bandwidth. The one or more SCP instances [110] may determine the set of network statistics after a predefined interval of time (such as an hour, every day). For example, the one or more SCP instances [110] might detect that RTT has increased from 5 milliseconds to 20 milliseconds and that packet drop ratio has gone from 0% to 2% due to a sudden network issue. The collection frequency, whether hourly or daily, is determined by the network operator’s policy to ensure timely data retrieval.

[0075] The SCP-pAI [306] may periodically fetch, using the fetching unit [206], the determined set of network data from the one or more SCP instance [110] or the one or more NF producers according to the intervals specified by the operator's policy. For example, every 15 minutes, the SCP-pAI [306] retrieves the latest statistics on RTT and packet drop rates. The fetched set of network data is stored in a storage unit. The storage acts as a repository of real-time data that facilitates in building a historical database that the SCP-pAI [306] can reference to detect trends and predict future network conditions.

[0076] Thereafter, the analysis unit [208] of the SCP-pAI [306] analyses, using the trained SCP- pAI [306], the determined set of network statistics to determine an optimal network system configuration for prevailing network conditions. The system further includes utilizing the SCP- pAI [306] to predict system configurations that will yield the best KPI outcomes by learning from various network conditions and their impacts on network performance. For example, if the current RTT is significantly higher than usual, the SCP-pAI [306] might determine that increasing the TCP acknowledgment timeout will prevent premature retransmissions, thus adapting to the slower network speed without flooding the network with unnecessary traffic.

[0077] The SCP-pAI [306] utilizes artificial intelligence to synthesize the information and proactively adjust the network's system configuration. The dynamic configuration is essential in situations where network conditions fluctuate rapidly, ensuring minimal disruption to network performance and maintaining high KPI standards.

[0078] The SCP-pAI [306] comprises the comparator [210], The comparator [210] compares the current network system configuration against the determined optimal network system configuration and in case of a mismatch between the determined optimal network system configuration and the current network system configuration, the adjusting unit [212], which may also be part of the SCP-pAI [306] initiates automatic configuration adjustments. The adjustments ensure the network system aligns with the optimal conditions, thereby enhancing network efficiency and performance in response to changing network dynamics.

[0079] Upon computing the optimal configurations, the SCP-pAI [306] identifies specific targets within the network where the adjustments should be implemented. Once the targets are identified and the adjustments are specified, the SCP-pAI [306] may communicates these changes through a secure API to the respective NF Consumers, Producers, and SCP instances. After the adjustments are distributed, each NF Consumer, NF Producer, and SCP instance [110] implements the received configurations. This implementation may be monitored and managed by respective local controllers or management systems that ensure the changes are applied correctly and efficiently. Additionally, the effects of these adjustments on network performance are monitored, and feedback is sent back to the SCP-pAI [306], where the feedback of its decisions are used to refine its future configuration predictions and adjustments. The system continues to monitor network conditions and performance KPIs. The SCP-pAI [306] uses the ongoing data to further refine and adjust configurations dynamically, maintaining an optimal network state responsive to any changes or emerging issues.

[0080] Referring to FIG. 4, an exemplary method flow diagram [400], for configuration autotuning in a network system, in accordance with exemplary embodiments of the present disclosure is shown. In an implementation, the method [400] is performed by the system [200], the system architecture [300], or the SCP pAI [306], As shown in FIG. 4, the method [400] starts at step [402],

[0081] Furthermore, at step [404] the method [400] comprises fetching, by a fetching unit [206] via the SCP-pAI [306], the set of network statistics from the SCP [110] at predetermined intervals. The fetching unit [206] operates at the predetermined intervals. The predefined intervals may be set according to operator's policy, thereby ensuring that the SCP-pAI [306] receives real-time information associated with the network conditions. The set of predefined intervals may be configurable by a user, or operator etc. The SCP [110] may be configured to determine a set of network statistics. The set of network statistics may include metrics comprising but not limited only to Round-trip Time (RTT), available bandwidth, congestion levels, and ICMP ping packet drop ratios. The SCP [110] may continuously monitor the set of network statistics at regular intervals to ensure real-time data is available for the SCP-pAI [306] to analyze and determine the optimal network system configuration for the prevailing conditions, ensuring that the network system remains optimized and performs efficiently despite any changes in network characteristics. [0082] Next, at step [406], the method [400] comprises analysing, by an analysis unit [208] using the trained SCP-pAI [306], the determined set of network statistics to determine an optimal network system configuration for prevailing network conditions. The trained SCP-pAI [306] is used to evaluate the current network statistics. The analysis unit [208] determines the optimal network system configuration that is expected to yield the best Key Performance Indicator (KPI) outcomes under the current network conditions. The optimal network system configuration may then used by the system [200] to adjust the network settings automatically.

[0083] Now, at step [408], the method [400] comprises comparing, by a comparator [210], the determined optimal network system configuration with a current network system configuration. The comparison facilitates in ensuring that the network system operates at its best possible performance. When the analysis unit [208] determines the optimal configuration based on the analysis of current network statistics, the comparator [210] checks this against the network's existing configuration. If there is a mismatch, indicating that the current configuration is not optimal for the prevailing network conditions, the system [200] can take corrective action to adjust the configuration.

[0084] Thereafter, in case of a mismatch between the determined optimal network system configuration and the current network system configuration, at step [410], the method [400] encompasses automatically adjusting, by an adjusting unit [212], the network system configuration based on the comparison. The adjustment process involves modifying the network settings to align with the optimal configuration determined by the analysis unit [208], The adjusting unit [212] receives instructions from the SCP-pAI [306] regarding the necessary changes and implements them through a secure API, ensuring that the network system operates under the most favourable conditions for its current state . The automated adjustment process minimizes the impact of network disruptions on KPIs and reduces the need for manual intervention by network administrators, thereby saving time and resources.

[0085] The method [400] comprises training, by the training unit [202], a service communication proxy - performance Artificial Intelligence (SCP-pAI) [306] with a set of network conditions against a set of respective network system configurations and corresponding set of Key Performance Indicator (KPI) outcomes. The training may include providing the SCP-pAI [306] with historical set of network statistics in conjunction with set of current statistics to predict optimal network system configuration. The historical network statistics may include the set of network conditions against the set of respective network system configurations and corresponding set of Key Performance Indicator (KPI) outcomes. The set of network conditions may include at least one of Round-trip Time (RTT), packet drop ratios, and congestion levels. The SCP-pAI [306] may further be trained with the network system configurations that were applied during those conditions, such as TCP-related kernel parameters, application-related timeouts, and TCP connection counts. Additionally, the SCP-pAI [306] may further be trained on KPI outcomes that were achieved with the specific network conditions and configurations. The training enables the SCP-pAI [306] to establish a relationship between network conditions, system configurations, and their impact on KPI outcomes. Thus, the SCP-pAI [306] enables predicting the optimal network system configuration for any given set of prevailing network conditions for achieving best possible KPI outcomes.

[0086] The method further includes displaying, by the display unit [214], a network system configuration recommendation once it is provided by the SCP-pAI [306], The recommendation may include the optimal network system configuration determined by the analysis unit [208] based on the current network conditions. When the recommendation is displayed, subsequently an administrator may be alerted. The generated alert may enable consentbased tuning of the network system configuration. The consent-based tuning of the network system configuration allows for a manual override or approval of the proposed changes, ensuring that any adjustments are made with full awareness and control. The network system configuration recommendation may include includes details on various parameters such as TCP -related kernel parameters, application-related timeouts, and TCP connection counts. It also outlines the differences between the current network system configuration and the optimal network system configuration, facilitating informed decision-making by the administrator. Thus, ensures transparency and control in the auto-tuning process, allowing administrators to make educated decisions based on the recommendations provided by the system.

[0087] The method terminates at step [412],

[0088] As is evident from the above, the present disclosure provides a technically advanced solution by reducing the impact on network KPI when there is a network characteristic (RTT, Congestion, Packet drop, etc) due to failure at few IP layer element or few physical layer element and reduction in manual efforts required for re-tuning configuration which saves time and cost. [0089] FIG. 5 illustrates an exemplary block diagram of a computer system [500] upon which an embodiment of the present disclosure may be implemented. In an implementation, the computing device implements the method for auto-tuning network configuration using the system [200] . In another implementation, the computing device itself implements the method for auto-tuning network configuration in 5G core (5GC) network by using one or more units configured within the computing device, wherein said one or more units are capable of implementing the features as disclosed in the present disclosure.

[0090] The computer system [500] encompasses a wide range of electronic devices capable of processing data and performing computations. Examples of computer system [500] include, but are not limited only to, personal computers, laptops, tablets, smartphones, user equipment (UE), servers, and embedded systems. The devices may operate independently or as part of a network and can perform a variety of tasks such as data storage, retrieval, and analysis. Additionally, computer system [500] may include peripheral devices, such as monitors, keyboards, and printers, as well as integrated components within larger electronic systems, showcasing their versatility in various technological applications.

[0091] The computer system [500] may include a bus [502] or other communication mechanism for communicating information, and a processor [504] coupled with bus [502] for processing information. The processor [504] may be, for example, a general-purpose microprocessor. The computer system [500] may also include a main memory [506], such as a random-access memory (RAM), or other dynamic storage device, coupled to the bus [502] for storing information and instructions to be executed by the processor [504], The main memory [506] also may be used for storing temporary variables or other intermediate information during execution of the instructions to be executed by the processor [504], Such instructions, when stored in non-transitory storage media accessible to the processor [504], render the computer system [500] into a special-purpose machine that is customized to perform the operations specified in the instructions. The computer system [500] further includes a read only memory (ROM) [508] or other static storage device coupled to the bus [502] for storing static information and instructions for the processor [504],

[0092] A storage device [510], such as a magnetic disk, optical disk, or solid-state drive is provided and coupled to the bus [502] for storing information and instructions. The computer system [500] may be coupled via the bus [502] to a display [512], such as a cathode ray tube (CRT), for displaying information to a computer user. An input device [514], including alphanumeric and other keys, may be coupled to the bus [502] for communicating information and command selections to the processor [504], Another type of user input device may be a cursor control [516], such as a mouse, a trackball, or cursor direction keys, for communicating direction information and command selections to the processor [504], and for controlling cursor movement on the display [512], This input device typically has two degrees of freedom in two axes, a first axis (e.g., x) and a second axis (e.g., y), that allow the device to specify positions in a plane.

[0093] The computer system [500] may implement the techniques described herein using customized hard-wired logic, one or more Application-Specific Integrated Circuits (ASICs) or Field Programmable Gate Arrays (FPGAs), firmware and/or program logic which in combination with the computer system [500] causes or programs the computer system [500] to be a specialpurpose machine. According to one embodiment, the techniques herein are performed by the computer system [500] in response to the processor [504] executing one or more sequences of one or more instructions contained in the main memory [506], Such instructions may be read into the main memory [506] from another storage medium, such as the storage device [510], Execution of the sequences of instructions contained in the main memory [506] causes the processor [504] to perform the process steps described herein. In alternative embodiments, hard-wired circuitry may be used in place of or in combination with software instructions.

[0094] The computer system [500] also may include a communication interface [518] coupled to the bus [502], The communication interface [518] provides a two-way data communication coupling to a network link [520] that is connected to a local network [522], For example, the communication interface [518] may be an integrated services digital network (ISDN) card, cable modem, satellite modem, or a modem to provide a data communication connection to a corresponding type of telephone line . As another example, the communication interface [518] may be a local area network (LAN) card to provide a data communication connection to a compatible LAN. Wireless links may also be implemented. In any such implementation, the communication interface [518] sends and receives electrical, electromagnetic or optical signals that carry digital data streams representing various types of information.

[0095] The computer system [500] can send messages and receive data, including program code, through the network(s), the network link [520] and the communication interface 518. In the Internet example, a server [530] might transmit a requested code for an application program through the Internet [528], the Internet Service Provider (ISP) [526], the local network [522] and the communication interface [518], The received code may be executed by the processor [504] as it is received, and/or stored in the storage device [510], or other non-volatile storage for later execution.

[0096] FIG. 6 illustrates an exemplary block diagram [600] of a user equipment (UE) for configuration auto-tuning in a network system, in accordance with exemplary implementations of the present disclosure.

[0097] The user equipment (UE) [102] for configuration auto-tuning in a network system comprises a receiving unit [602] configured to receive network system configuration recommendations. The UE [102] further comprises a display unit [604] configured to display the network system configuration recommendation. The UE [102] further comprises the receiving unit [602] configured to receive user input for the displayed network system configuration recommendation. The user input is at least a command or a consent for the displayed network system configuration recommendation. The UE [102] further comprises a transmitting unit [606] configured to transmit the network system configuration recommendation.

[0098] In an embodiment, the UE [102] is associated with an administrator.

[0099] In an embodiment, the service communication proxy performance Artificial Intelligence SCP-pAI [306] is incorporated in the UE [102],

[0100] The network system configuration recommendation is generated based on performing steps of: fetching, by the fetching unit [206] via a service communication proxy - performance Artificial Intelligence (SCP-pAI) [306], the set of network statistics from the SCP [110] at predetermined intervals, wherein the set of network statistics is determined at the SCP [110]; analysing, by the analysis unit [208] using the trained SCP-pAI [306], the determined set of network statistics to determine an optimal network system configuration for prevailing network conditions; comparing, by the comparator [210], the determined optimal network system configuration with a current network system configuration; and in case of a mismatch between the determined optimal network system configuration and the current network system configuration, automatically adjusting, by the adjusting unit [212], the network system configuration based on the comparison.

[0101] Another aspect of the present disclosure provides a user equipment (UE) for configuration auto-tuning in a network system. The UE comprises a receiving unit configured to receive network system configuration recommendation. The UE further comprises a display unit configured to display the network system configuration recommendation. The UE further comprises the receiving unit configured to receive user input for the displayed network system configuration recommendation. The UE further comprises a transmitting unit configured to transmit the network system configuration recommendation.

[0102] According to an aspect of the present disclosure, a non-transitory computer-readable storage medium storing instruction for configuration auto-tuning in a network system is disclosed. The storage medium comprising executable code which, when executed by one or more units of a system, causes: a fetching unit to fetch, via a the service communication proxy- performance artificial intelligence (SCP-pAI), the set of network statistics from the SCP at predetermined intervals, wherein the set of network statistics is determined at the SCP; an analysis unit to analyse, using the a trained SCP-pAI, the determined set of network statistics to determine an optimal network system configuration for prevailing network conditions; a comparator to compare the determined optimal network system configuration with a current network system configuration; and an adjusting unit to automatically adjust the network system configuration based on the comparison in case of a mismatch between the determined optimal network system configuration and the current network system configuration.

[0103] The present disclosure aims to overcome the existing problems in this field of technology by introducing a method and system for auto-tuning of network configuration. The method involves training a Service Communication Proxy - Performance Artificial Intelligence (SCP-pAI) with various network conditions and corresponding network configurations, along with the resulting Key Performance Indicator (KPI) outcomes. The training enables the SCP-pAI to predict optimal network configurations based on current network conditions such as Round-trip Time (RTT), congestion, and packet drop ratios. The method includes determining network statistics via a Service Communication Proxy (SCP) and fetching these statistics at predetermined intervals using the SCP-pAI. By analysing the fetched network statistics, the SCP-pAI determines the optimal network configuration for the prevailing network conditions. If there is a mismatch between the current network configuration and the determined optimal configuration, the system automatically adjusts the network configuration based on the comparison. This automated process reduces the need for manual re-tuning by network administrators, saving time and effort. The system also enhances real-time monitoring of network performance metrics, allowing for prompt detection and response to changes in network conditions. [0104] Further, in accordance with the present disclosure, it is to be acknowledged that the functionality described for the various components/units can be implemented interchangeably. While specific embodiments may disclose a particular functionality of these units for clarity, it is recognized that various configurations and combinations thereof are within the scope of the disclosure. The functionality of specific units, as disclosed in the disclosure, should not be construed as limiting the scope of the present disclosure. Consequently, alternative arrangements and substitutions of units, provided they achieve the intended functionality described herein, are considered to be encompassed within the scope of the present disclosure. [0105] While considerable emphasis has been placed herein on the disclosed embodiments, it will be appreciated that many embodiments can be made and that many changes can be made to the embodiments without departing from the principles of the present disclosure. These and other changes in the embodiments of the present disclosure will be apparent to those skilled in the art, whereby it is to be understood that the foregoing descriptive matter to be implemented is illustrative and non-limiting.

Claims

I/We Claim:

1. A method [400] for configuration auto-tuning in a network system, the method comprising: fetching, by a fetching unit [206] via a service communication proxy - performance Artificial Intelligence (SCP-pAI) [306], a set of network statistics from the SCP [110] at predetermined intervals, wherein the set of network statistics is determined at the SCP [110]; analysing, by an analysis unit [208] using a trained SCP-pAI [306], the determined set of network statistics to determine an optimal network system configuration for prevailing network conditions; comparing, by a comparator [210], the determined optimal network system configuration with a current network system configuration; and in case of a mismatch between the determined optimal network system configuration and the current network system configuration, automatically adjusting, by an adjusting unit [212], the network system configuration based on the comparison.

2. The method as claimed in claim 1, wherein the set of network statistics comprises at least one of Round-trip Time (RTT), internet control message protocol (ICMP) ping packet drop ratio, and available bandwidth.

3. The method as claimed in claim 1, wherein the method comprises displaying, via a display unit [214], a network system configuration recommendation.

4. The method as claimed in claim 3, wherein if the network system configuration recommendation is provided, an administrator is alerted, enabling consent-based tuning of the network system configuration.

5. The method as claimed in claim 3, wherein the network system configuration comprises any or a combination of transmission control protocol (TCP)-related kernel parameters, application-related timeouts, and TCP connection counts.

6. The method as claimed in claim 4, wherein the network system configuration recommendation provided to the administrator details differences between the current network system configuration and the optimal network system configuration, facilitating informed decision-making.

7. The method as claimed in claim 1, wherein the method comprises training, by a training unit [202], the SCP-pAI [306] with a set of network conditions against a set of respective network system configurations and corresponding set of Key Performance Indicator (KPI) outcomes.

8. The method as claimed in claim 7, wherein the set of network conditions corresponds to at least one of values of RTT, packet drop ratios, and different TCP connection counts.

9. The method as claimed in claim 1, wherein the SCP-pAI [306] uses stored historical set of network statistics in conjunction with current statistics to predict optimal network system configuration.

10. A system [200] for configuration auto-tuning in a network system, the system comprises: a fetching unit [206] configured to fetch, via a service communication proxy - performance Artificial Intelligence (SCP-pAI) [306], a set of network statistics from the SCP at predetermined intervals, wherein the set of network statistics is determined at the SCP [110]; an analysis unit [208] configured to analyse, using a trained SCP-pAI [306], the determined set of network statistics to determine an optimal network system configuration for prevailing network conditions; a comparator [210] configured to compare the determined optimal network system configuration with a current network system configuration; and in case of a mismatch between the determined optimal network system configuration and the current network system configuration, an adjusting unit [212] is configured to automatically adjust the network system configuration based on the comparison.

11. The system as claimed in claim 10, wherein the set of network statistics comprises at least one of Round-trip Time (RTT), internet control message protocol (ICMP) ping packet drop ratio, and available bandwidth.

12. The system as claimed in claim 10, wherein the system comprises a display unit [214] configured to display a network system configuration recommendation.

13. The system as claimed in claim 12, wherein if the network system configuration recommendation is provided, an administrator is alerted, enabling consent-based tuning of the network system configuration.

14. The system as claimed in claim 12, wherein the network system configuration comprises any or a combination of transmission control protocol (TCP)-related kernel parameters, application-related timeouts, and TCP connection counts.

15. The system as claimed in claim 13, wherein the network system configuration recommendation provided to the administrator details differences between the current network system configuration and the optimal network system configuration, facilitating informed decision-making.

16. The system as claimed in claim 10, wherein the system comprises a training unit [202] configured to train the SCP-pAI [306] with a set of network conditions against a set of respective network system configurations and corresponding set of Key Performance Indicator (KPI) outcomes.

17. The system as claimed in claim 16, wherein the set of network conditions corresponds to at least one of values of RTT, packet drop ratios, and different TCP connection counts.

18. The system as claimed in claim 10, wherein the SCP-pAI [306] uses stored historical set of network statistics in conjunction with current statistics to predict optimal network system configuration.

19. A user equipment (UE) [102] for configuration auto-tuning in a network system, said UE [102] comprising: a receiving unit [602] configured to receive network system configuration recommendation; a display unit [604] configured to display the network system configuration recommendation; the receiving unit [602] configured to receive user input for the displayed network system configuration recommendation; and a transmitting unit [606] configured to transmit the network system configuration recommendation .

20. The UE [102] as claimed in claim 19, wherein the UE [102] is associated with an administrator.

21. The UE [102] as claimed in claim 19, wherein the user input is at least a command or a consent.

22. The UE [102] as claimed in claim 19, wherein a service communication proxy - performance Artificial Intelligence SCP-pAI [304] is incorporated in the UE [102],

23. The UE [102] as claimed in claim 19, wherein the network system configuration recommendation is received based on steps performed by claim 1.

24. A non-transitory computer-readable storage medium storing instruction for configuration autotuning in a network system, the storage medium comprising executable code which, when executed by one or more units of a system, causes: a fetching unit [206] to fetch, via a service communication proxy - performance artificial intelligence (SCP-pAI) [306], a set of network statistics from the SCP at predetermined intervals, wherein the set of network statistics is determined at the SCP [110]; an analysis unit [208] to analyse, using a trained SCP-pAI [306], the determined set of network statistics to determine an optimal network system configuration for prevailing network conditions; a comparator [210] to compare the determined optimal network system configuration with a current network system configuration; and an adjusting unit [212] to automatically adjust the network system configuration based on the comparison in case of a mismatch between the determined optimal network system configuration and the current network system configuration.