System and method for optimizing access point selection in a network comprising multi-link devices

Abstract

The present subject matter discloses a method and a system for optimizing access point selection in a network comprising Multi-Link Devices (MLDs). The method includes obtaining a traffic information of the network comprising the MLDs, wherein the traffic information comprises at least one of, application type, contextual factors associated with one or more client devices, contextual factors associated with the MLDs, and channel quality variations in the network. Further, the method includes predicting traffic patterns at one or more access points in the network based on the obtained traffic information of the network. Further, the method includes deciding physical layer parameters and Media Access Control (MAC) layer parameters associated with the one or more access points in the network. Further, the method includes prioritizing one or more data packets in the network based on the predicted traffic patterns.

Description

SYSTEM AND METHOD FOR OPTIMIZING ACCESS POINT SELECTION IN A NETWORK COMPRISING MULTI-LINK DEVICES

[0001] The present disclosure generally relates to the field of communication networks. In particular, the present disclosure relates to a method and a system for optimizing access point selection in a network comprising Multi-Link Devices (MLDs).

[0002] Background description includes information that may be useful in understanding the present disclosure. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication specifically or implicitly referenced is prior art.

[0003] There has been considerable research on the adoption of Multi-Link Operation (MLO) in the latest Wi-Fi standards. MLO implemented via Multi-Link Devices (MLDs) is associated with a low latency and high throughput for data intensive real time applications. The technology majorly finds applications in cloud gaming, wireless Virtual Reality (VR) headsets, 4K and 8K video streaming, metaverse related applications, and the like.

[0004] The related techniques associated with Access Point (AP) selection in a network comprising MLDs focus on a limited set of factors. The real-time factors and parameters associated with AP selection are not considered in the related techniques. The related techniques focus majorly on Received Signal Strength Indicator (RSSI) based access point selection. The RSSI based access point selection has limitations as RSSI is not associated with backhaul information in the network. Further, the related techniques for AP selection and prioritization do not take into account factors such as real time network conditions, AP capabilities, and changes in the network conditions.

[0005] This summary is provided to introduce a selection of concepts in a simplified format that are further described in the detailed description of the disclosure. This summary is not intended to identify essential inventive concepts of the disclosure, nor is it intended to determine the scope of the disclosure.

[0006] According to an embodiment of the present disclosure, a method for optimizing access point selection in a network comprising Multi-Link Devices (MLDs). According to an embodiment of the present disclosure, the method may include obtaining a traffic information of the network comprising the MLDs. According to an embodiment of the present disclosure, the method may include predicting traffic patterns at one or more access points in the network based on the obtained traffic information of the network. According to an embodiment of the present disclosure, the method may include deciding physical layer parameters and Media Access Control (MAC) layer parameters associated with the one or more access points in the network, wherein the decision is based on the predicted traffic patterns. According to an embodiment of the present disclosure, the method may include performing access point selection by selecting the access point with the highest access point score, wherein the access point score is associated with the physical layer parameters and MAC layer parameters.

[0007] According to an embodiment, an electronic device to optimize access point selection in a network comprising Multi-Link Devices (MLDs) is disclosed. According to an embodiment, the electronic device may include memory. According to an embodiment, the electronic device may include at least one processor including processing circuitry, memory storing instructions that, when executed by the at least one processor individually or collectively, cause the electronic device to:. According to an embodiment, the at least one processor may cause the electronic device to obtain a traffic information of the network comprising the MLDs. According to an embodiment, the at least one processor may cause the electronic device to predict traffic patterns at one or more access points in the network based on the obtained traffic information of the network. According to an embodiment, the at least one processor may cause the electronic device to decide physical layer parameters and Media Access Control (MAC) layer parameters associated with the one or more access points in the network, wherein the decision is based on the predicted traffic patterns. According to an embodiment, the at least one processor may cause the electronic device to perform access point selection by selecting the access point with the highest access point score, wherein the access point score is associated with the physical layer parameters and MAC layer parameters.

[0008] One embodiment provides a machine readable medium containing instructions. The instructions, when executed by at least one processor, may cause the at least one processor to perform the method corresponding.

[0009] To further clarify the advantages and features of the present disclosure, a more particular description of the disclosure will be rendered by reference to specific an embodiment thereof, which is illustrated in the appended drawing. It is appreciated that these drawings depict only typical an embodiment of the disclosure and are therefore not to be considered limiting its scope. The disclosure will be described and explained with additional specificity and detail with the accompanying drawings.

[0010] These and other features, aspects, and advantages of the present disclosure will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:

[0011] Figure 1illustrates an environment for the implementation of optimized access point selection in a network comprising Multi-Link Devices (MLDs), according to an embodiment of the present disclosure;

[0012] Figure 2illustrates an exemplary general architecture of a system, according to an embodiment of the present disclosure;

[0013] Figure 3illustrates an exemplary general architecture of a User Equipment (UE), according to an embodiment of the present disclosure;

[0014] Figure 4illustrates an exemplary general architecture of an access point (AP), according to an embodiment of the present disclosure;

[0015] Figure 5illustrates a process flow associated with a parameter negotiation module of the system, according to an embodiment of the present disclosure;

[0016] Figure 6illustrates a process flow associated with a parameter optimization sub-module of the system, according to an embodiment of the present disclosure;

[0017] Figure 7illustrates a schematic diagram associated with an exemplary predicted traffic patterns by an Artificial Intelligence / Machine Learning (AI / ML) traffic pattern prediction module of the UE, according to an embodiment of the present disclosure;

[0018] Figure 8illustrates a schematic diagram associated with parameter negotiation sub-module of the UE, according to an embodiment of the present disclosure;

[0019] Figure 9illustrates a schematic diagram associated with action frame parameters for implementing physical network layer and Machine Access Control (MAC) network layer parameter decision, according to an embodiment of the present disclosure,

[0020] Figure 10illustrates a schematic diagram associated with Information Elements (IE) for Physical network layer and MAC network layer parameter decision, according to an embodiment of the present disclosure;

[0021] Figure 11illustrates an exemplary schematic diagram of a score map based on correlating the predicted traffic patterns with a set of expected physical layer parameters and a set of expected MAC layer parameters in the network, according to an embodiment of the present disclosure;

[0022] Figure 12illustrates a block diagram associated with an access point selection sub-module of the UE, according to an embodiment of the present disclosure;

[0023] Figure 13aillustrates a process flow associated with a data prioritization sub-module of the UE, according to an embodiment of the present disclosure;

[0024] Figure 13billustrates a block diagram associated with the data prioritization sub-module of the UE, according to an embodiment of the present disclosure;

[0025] Figure 14illustrates a schematic diagram associated with mapping one or more data buffers to one or more data packets by the data prioritization sub-module of the UE, according to an embodiment of the present disclosure;

[0026] Figure 15illustrates a schematic diagram associated with prioritization of the one or more data packets by the data prioritization sub-module of the UE, according to an embodiment of the present disclosure;

[0027] Figure 16illustrates a block diagram associated with a communication module of the UE, according to an embodiment of the present disclosure;

[0028] Figure 17illustrates a block diagram associated with a network layer parameter configuration module of the AP, according to an embodiment of the present disclosure;

[0029] Figure 18illustrates a schematic diagram associated with requested Physical network layer and Machine Access Control (MAC) network layer parameter by the UE to be implemented by the network layer parameter configuration module of the AP, according to an embodiment of the present disclosure;

[0030] Figure 19illustrates a block diagram associated with a load analysis module of the AP, according to an embodiment of the present disclosure;

[0031] Figure 20illustrates a schematic diagram for an exemplary signal transmitted by the AP for network load analysis by the load analysis module of the AP, according to an embodiment of the present disclosure;

[0032] Figure 21illustrates an exemplary block diagram for overall process associated with optimizing access point selection in a network comprising MLDs, according to an embodiment of the present disclosure;

[0033] Figure 22aillustrates an exemplary use case scenario associated with absence of network availability at the AP connected to the UE, according to an embodiment of the present disclosure;

[0034] Figure 22billustrates an exemplary use case scenario associated with AP selection among a plurality of APs saved at the UE, according to an embodiment of the present disclosure;

[0035] Figure 22cillustrates an exemplary use case scenario associated with AP selection based on the comparison of backhaul throughput of the APs available for connection with the UE, according to an embodiment of the present disclosure;

[0036] Figure 22dillustrates an exemplary use case scenario associated with selection of a Multi Link Operation (MLO) supported AP based on the comparison of backhaul throughput of the APs available for connection with the UE, according to an embodiment of the present disclosure;

[0037] Figure 22eillustrates an exemplary use case scenario associated with prioritization of data packets from the UE based on the priority of a data packet and data throughput of the APs available for connection with the UE, according to an embodiment of the present disclosure; and

[0038] Figure 23illustrates an exemplary process flow comprising a method for optimizing access point selection in a network comprising MLDs, according to an embodiment of the present disclosure.

[0039] Further, skilled artisans will appreciate that elements in the drawings are illustrated for simplicity and may not have necessarily been drawn to scale. For example, the flow charts illustrate the method in terms of the most prominent steps involved to help to improve understanding of aspects of the present disclosure. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the drawings with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.

[0040] It should be understood at the outset that although illustrative implementations of the embodiments of the present disclosure are illustrated below, the present disclosure may be implemented using any number of techniques, whether currently known or in existence. The present disclosure should in no way be limited to the illustrative implementations, drawings, and techniques illustrated below, including the exemplary design and implementation illustrated and described herein, but may be modified within the scope of the appended claims along with their full scope of equivalents.

[0041] The term "some" as used herein is defined as "none, or one, or more than one, or all." Accordingly, the terms "none," "one," "more than one," "more than one, but not all" or "all" would all fall under the definition of "some." The term "some embodiments" may refer to no embodiments, to one embodiment or to several embodiments or to all embodiments. Accordingly, the term "some embodiments" is defined as meaning "no embodiment, or one embodiment, or more than one embodiment, or all embodiments."

[0042] The terminology and structure employed herein is for describing, teaching, and illuminating some embodiments and their specific features and elements and does not limit, restrict, or reduce the spirit and scope of the claims or their equivalents.

[0043] More specifically, any terms used herein such as but not limited to "includes," "comprises," "has," "consists," and grammatical variants thereof do NOT specify an exact limitation or restriction and certainly do NOT exclude the possible addition of one or more features or elements, unless otherwise stated, and furthermore must NOT be taken to exclude the possible removal of one or more of the listed features and elements, unless otherwise stated with the limiting language "MUST comprise" or "NEEDS TO include."

[0044] Whether or not a certain feature or element was limited to being used only once, either way, it may still be referred to as "one or more features" or "one or more elements" or "at least one feature" or "at least one element." Furthermore, the use of the terms "one or more" or "at least one" feature or element does NOT preclude there being none of that feature or element, unless otherwise specified by limiting language such as "there NEEDS to be one or more . . ." or "one or more element is REQUIRED."

[0045] Unless otherwise defined, all terms, and especially any technical and / or scientific terms, used herein may be taken to have the same meaning as commonly understood by one having ordinary skill in the art.

[0046] Embodiments of the present disclosure will be described below in detail with reference to the accompanying drawings.

[0047] According to an embodiment, the present disclosure discloses a method and a system for optimizing access point selection in a network comprising MLDs.

[0048] As used herein, Multi-Link Devices (MLDs) are associated with the implementation of multi-link operation (MLO) in a communication network. MLO enables stations (STAs) and User Equipments (UEs) to simultaneously send and receive data across different channels on different frequency bands (e.g. 2.4GHz, 5GHz, 6GHz). The frequency bands herein include a plurality of channels. For example, a 2.4 GHz frequency band may include channel 1 to channel 13 for MLO based communication.

[0049] The detailed methodology of the disclosure is explained in the following paragraphs.

[0050] Figure 1illustrates the environment for the implementation of optimized access point selection in a network comprising MLDs, according to an embodiment of the present disclosure.

[0051] According to an embodiment, a plurality of Station (STA) 106 illustrated as STA 1, STA 2, STA 3, and STA 4 in Figure 1 are present in the network. The STA may also correspond to a UE in the embodiment. In an example, the STA or UE 106 may be a laptop computer, a desktop computer, a Personal Computer (PC), a notebook, a smartphone, a tablet, a smartwatch, a smart television or any device capable of accessing or connecting to a communication network. The Figure further illustrates Access Points (APs) 108 as Access Point 1 and Access Point 2 in the network. In an example, the APs 108 may be present in an MLD and may support MLO. In an example, the APs 108 may be a non-MLO AP. In the embodiment, the APs 108 may be connected to an Internet Service Provider (ISP) infrastructure 102. In an example, the ISP infrastructure may correspond to a Core Network (CN) in a wireless communication network (e.g. 5G).

[0052] In an embodiment, backhaul capabilities 110 and multi-link device capabilities 112 are used by the STA 106 to optimize the access point selection in the network. The backhaul capabilities may be provided by a CN entity to the APs 108 with MLD support. The implementation of the embodiment as provided by the present disclosure is associated with better access point selection in a network comprising MLDs and the APs 108 with MLO support. The problem associated with reliance on RSSI for AP selection is addressed and the present disclosure, in an embodiment, utilizes the backhaul capabilities 110 and multi-link device capabilities 112 in a method for optimized AP selection in a network comprising MLDs.

[0053] A detailed methodology for optimizing access point selection in a network comprising Multi-Link Devices (MLDs) is explained in the following paragraphs of the disclosure.

[0054] Figure 2illustrates an exemplary general architecture of a system, according to an embodiment of the present disclosure.

[0055] The system 200 may include but is not limited to, at least one processor 202 (may alternatively be referred to as "the processor 202"), memory 204, modules 206, and data 208. The modules 206 and the memory 204 may be coupled to the processor 202.

[0056] The processor 202 may be a single processing unit or several units, all of which could include multiple computing units. The processor 202 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and / or any devices that manipulate signals based on operational instructions. Among other capabilities, the processor 202 is adapted to fetch and execute computer-readable instructions and data stored in the memory 204.

[0057] The memory 204 may include any computer-readable medium known in the art including, for example, volatile memory, such as static random-access memory (SRAM) and dynamic random-access memory (DRAM), and / or non-volatile memory, such as read-only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes. The memory 204 may alternatively be referred to as the database 204 in the present disclosure, within the scope of the disclosure.

[0058] The modules 206, amongst other things, may include routines, programs, objects, components, data structures, etc., which perform particular tasks or implement data types. The modules 206 may also be implemented as, signal processor(s), state machine(s), logic circuitries, and / or any other device or component that manipulates signals based on operational instructions.

[0059] Further, the modules 206 can be implemented in hardware, instructions executed by a processing unit, or by a combination thereof. The processor 202 may comprise a computer, a processor, a state machine, a logic array, or any other suitable devices capable of processing instructions. The processing unit may be a general-purpose processor (e.g., processor 202) which executes instructions to cause the general-purpose processor to perform the required tasks or, the processing unit can be dedicated to performing the required functions. In an embodiment of the present disclosure, the modules 206 may be machine-readable instructions (software) which, when executed by the processor 202 / processing unit, perform any of the described functionalities / methods, as discussed throughout the present disclosure.

[0060] In an embodiment, module 206 may include a parameter negotiation module 210 and a parameter optimization sub-module 212. The parameter negotiation module 210 and a parameter optimization sub-module 212 may be in communication with each other. The data 208 serves, amongst other things, as a repository for storing data processed, received, and generated by one or more of the modules 206. Further, Figure 5 and Figure 6 provide a detailed description of each of the modules 206.

[0061] Further, the system in an embodiment may be located at a remote cloud server in the network. The system may be connected to one or more STAs or UEs 106 and one or more APs 108. The APs 108 may be MLO supporting APs situated in MLDs or non-MLO supporting APs in the network. Further, the system 200 may act in tandem with the UE 106 as described in Figure 3 to implement the present disclosure. In an embodiment the modules and sub-modules of the UE 106 may be a part of the system 200. Alternatively, the modules of the system 200 may be a part of the architecture of the UE for implementation of the present disclosure.

[0062] Figure 3illustrates an exemplary general architecture of a User Equipment (UE), according to an embodiment of the present disclosure.

[0063] The UE or STA 106 may include a processor, a memory unit, and a communication interface. The same is not illustrated in the Figure 3 for the sake of brevity and clarity. Figure 3 illustrates the modules 301 in the UE 106 for implementation of a method for optimizing access point selection in a network comprising Multi-Link Devices (MLDs). Further, the term "client device"used in the present disclosure is identical to the terms UE or STA. The term client device may correspond to a UE 106 connected to MLD. The MLD may include one or more APs in the MLD. For example, the MLD may be an AP with support for three frequency bands such as 2.4GHz, 5GHz, and 6GHz.

[0064] As an example, the module(s) 301 may include a program, a subroutine, a portion of a program, a software component, or a hardware component capable of performing a stated task or function. As used herein, the module(s) 301 may be implemented on a hardware component such as a server independently of other modules, or a module can exist with other modules on the same server, or within the same program. The module(s) 301 may be implemented on a hardware component such as processor one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and / or any devices that manipulate signals based on operational instructions. The module(s) 301 when executed by the processor(s) may be configured to perform any of the described functionalities.

[0065] In an embodiment, the module(s) 301 may be implemented using one or more AI modules that may include a plurality of neural network layers. Examples of neural networks include but are not limited to, Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Network (RNN), and Restricted Boltzmann Machine (RBM). Further, 'learning' may be referred to in the disclosure as a method for training a predetermined target device (for example, a robot) using a plurality of learning data to cause, allow, or control the target device to make a determination or prediction. Examples of learning techniques include but are not limited to supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. At least one of a plurality of CNN, DNN, RNN, RMB models and the like may be implemented to thereby achieve execution of the present subject matter's mechanism through an AI model. A function associated with an AI module may be performed through the non-volatile memory, the volatile memory, and the processor. The processor may include one or a plurality of processors. At this time, one or a plurality of processors may be a general-purpose processor, such as a central processing unit (CPU), an application processor (AP), or the like, a graphics-only processing unit such as a graphics processing unit (GPU), a visual processing unit (VPU), and / or an AI-dedicated processor such as a neural processing unit (NPU). One or a plurality of processors control the processing of the input data in accordance with a predefined operating rule or artificial intelligence (AI) model stored in the non-volatile memory and the volatile memory. The predefined operating rule or artificial intelligence model is provided through training or learning.

[0066] The modules 301 may include network traffic information builder module 302. The module 302 may further include service analyzer sub-module 304, and device state analyzer sub-module 306. The modules 301 further include AI / ML traffic pattern prediction module 308. Furthermore, there may be an access point management module 310 including a UE parameter negotiation sub-module 312, access point selection sub-module 314, and a data prioritization sub-module 316. The modules 301 may additionally include a communication module 318 for communication with system 200 and AP 108 in the network. The modules 301 are explained in the subsequent figures in the forthcoming paragraphs of the present disclosure. The UE 106 is configured to optimize the access point selection in a network comprising MLDs, in an embodiment of the present disclosure. The UE 106 obtains traffic information from the network and generates predicted traffic patterns. The predicted traffic patterns are used by the modules of the system 200 and UE 106 to perform the access point selection.

[0067] Further, the network traffic information module 302 may include the service analyzer sub-module 304 and device state analyzer sub-module 306. In the embodiment, the network traffic information module 302 provides traffic information to the AI / ML traffic pattern prediction module 308. The traffic information may include at least one of, application type (e.g., VoWiFi, call, real-time gaming, and video streaming), contextual factors associated with one or more client devices (device type [e.g. mobile, laptop, IoT, wearable], mobility state of device, user preferences), contextual factors associated with the MLDs (e.g., number of active links, link quality of each active link for the STA / UE MLD), and channel quality variations in the network (e.g., channel reciprocity analysis, and channel quality variation).

[0068] In an example, the service analyzer sub-module 304 may obtain network traffic information such as application category, bandwidth of the network, communication protocol used (e.g., User Datagram Protocol (UDP) / Transmission Control Protocol (TCP) / Real-time Transport Protocol (RTP) / Real-time Streaming Protocol (RTSP)), context associated with content on the UE, and the like. Further, in an example, the device state analyzer sub-module 306 may obtain information related to the STA and APs connected in the network, including information related to MLO and associated MLDs. The information may include device screen state (ON / OFF), device type (e.g., mobile, laptop, tablet, wearable smart devices, Internet of Things (IoT) devices), device screen size, maximum video resolution supported by the device, number of active frequency links (e.g., 2.4 GHz, 5 GHz, 6 GHz, 60 GHz, and the like), and channel quality information (e.g., Signal to Noise Ratio (SNR), bit failure rate, and the like).

[0069] Figure 4illustrates an exemplary general architecture of an access point (AP), according to an embodiment of the present disclosure.

[0070] The AP 108 may include a processor, a memory unit, and a communication interface. The same is not illustrated in Figure 4 for the sake of brevity and clarity. Figure 4 illustrates the modules associated with the access points (AP or APs) 108. The modules 401 may include a network layer parameter configuration module 402, a load analysis module 404, and communication module 406. The modules 401 are explained in the subsequent figures in the forthcoming paragraphs of the present disclosure. The APs 108 in the network may be non-MLO AP or an AP present in the MLDs. The access points communicate through one of the probe response frame, beacon frame, or action frames with other APs in the network and the STA or UE 106 in the network. The APs 108 may be further configured to perform load analysis at the APs and optimize the network layer parameters at the APs 108.

[0071] Figure 5illustrates a process flow 500 associated with a parameter negotiation module 210 of the system 200, according to an embodiment of the present disclosure.

[0072] At block 500-1, the process 500 may include transmitting at least one of a beacon frames, a probe response frame, and an action frame containing the predicted traffic patterns and associated data in an extended beacon.

[0073] At block 500-2, to the process 500 may include receiving information on resource allocation for one or more links on the one or more client devices 106 and the MLDs, wherein the resource allocation is based on the predicted traffic patterns and the channel quality variations identified through reciprocity analysis.

[0074] The parameter negotiation module 210 may be configured to perform parameter decision based on the predicted traffic patterns. The term client device may correspond to the UE 106 connected to MLD with one or more APs 108 in the MLD. For example, the MLD may be an AP with support for three frequency bands such as 2.4GHz, 5GHz, and 6GHz. The parameter negotiation module 210 functions in tandem with the UE parameter negotiation sub-module 312 and the working of the parameter negotiation module 210 must be read in conjunction with the working of the UE parameter negotiation sub-module 312.

[0075] The predicted traffic patterns in the network are exemplified in Figure 7 and the same is not reproduced here for the sake of brevity. Further, the UE 106, system 200, and the APs 108 may communicate among one another using the signal such as the beacon frames, a probe response frame, and an action frame. The signal frames may be communicated in the form of an extended beacon in an embodiment.

[0076] Figure 6illustrates a process flow 600 associated with a parameter optimization sub-module 212 of the system 200, according to an embodiment of the present disclosure.

[0077] At block 600-1, the process 600 may include enhancing at least one of an Orthogonal Frequency-Division Multiple Access (OFDMA) transmission, a Multi-user Multi-input Multi Output (MU-MIMO) transmission, a Multi-Link MU-MIMO transmission, and a Radio Unit (RU) allocation for the one or more client devices.

[0078] At block 600-2, the process 600 may include enhancing Signal-to-Noise Ratio (SNR), Modulation and Coding Scheme (MCS) guard interval, MCS modulation technique, and channel width for the one or more access points based on backhaul real throughput, access point buffering capability, operating temperature and predicted traffic patterns for each of the one or more access points.

[0079] The parameter optimization sub-module 212 may be configured to optimize the physical layer parameters and MAC layer parameters for the one or more access points in the network comprising MLDs. The parameter optimization sub-module 212 of the system 200 functions in tandem with the UE parameter negotiation sub-module 312 and the working of the parameter optimization sub-module 212 of the system must be read in conjunction with the working of the UE parameter negotiation sub-module 312. The same is explained in the description of the forthcoming figures and not repeated here for the sake of brevity and clarity.

[0080] Figure 7illustrates a schematic diagram associated with an exemplary predicted traffic patterns by an Artificial Intelligence / Machine Learning (AI / ML) traffic pattern prediction module 308 of the UE 106, according to an embodiment of the present disclosure.

[0081] In an embodiment of the present disclosure, the AI / ML traffic pattern prediction module 308 is configured to receive traffic information 702 from the network traffic information module 302 and channel backhaul information.

[0082] As illustrated in Figure 7, the traffic patterns at one or more access points in the network is predicted by an Artificial Intelligence (AI) model, that resides in the AI / ML traffic pattern prediction module 308, based on the obtained traffic information 702 of the network. In an embodiment, as illustrated in Figure 7, the AI / ML traffic pattern prediction module 308 may obtain traffic information 702 of the network as input data. The traffic information 702 may include information such as application type, device type, screen state, screen resolution, screen size, active links, link quality, and the like. The AI / ML traffic pattern prediction module 308 may predict the priority of the traffic pattern in the network as predicted priority score 704. The traffic pattern may be classified as Extremely High Throughput (EHT), High Throughput (HT), Good Throughput (GT), Low Throughput (LT), and Extremely Low Throughput (ELT) in the embodiment. The AI / ML traffic pattern prediction module 308 further may assign an associated traffic identifier (TID) 706 for each predicted priority score 704. Further in an embodiment, the TID may correspond to TID as zero (0) for EHT, TID as one (1) for HT, TID as two (2) for GT, TID as three (3) for LT, TID as four (4) for ELT.

[0083] In an example, the AI model of the AI / ML traffic pattern prediction module 308 may be trained using a random forest algorithm to predict the traffic patterns in the network. The random forest algorithm builds multiple decision trees and combines their predictions to improve accuracy and reduce overfitting. Each decision tree in the random forest algorithm is trained on a random subset of the training data and a random subset of the features. This random nature of the training data and features helps to remove correlation among the trees and thereby increases the reliability of the prediction by the AI / ML traffic pattern prediction module 308.

[0084] Figure 8illustrates a schematic diagram associated with UE parameter negotiation sub-module 312 of the UE 106, according to an embodiment of the present disclosure.

[0085] In an embodiment of the present disclosure, score map 812 is created for a predicted priority score 704 and corresponding parameters for the physical network layer and Media Access Control (MAC) network layer. An example of the score map 812 is illustrated in Figure 11 for EHT and HT. The score map may associate the predicted traffic pattern and a set of expected optimized parameters for physical layer and MAC layer of the network. Further, the output from the AI / ML traffic pattern prediction module 308 may be applied as an input to the parameter negotiation sub-module 312. Furthermore, the score map 812 may serve as another input to the UE parameter negotiation sub-module 312.

[0086] At block 802, the parameter negotiation sub-module 312 may be configured to decide the physical network layer and MAC network layer parameters for optimizing access point selection in the network comprising MLDs. Next at block 804, the parameter negotiation sub-module 312 is configured to check the actual physical network layer and MAC network layer parameters of the corresponding AP 108.

[0087] Next at block 806, the parameter negotiation sub-module 312 may be configured to compare the decided parameters and the actual parameters for the network layers. Next at block 808, based on the comparison the requirement for parameter enhancement is determined. In an embodiment, there is an absence of a requirement for parameter enhancement, then the parameter negotiation sub-module 312 may trigger the access point selection sub-module 314 to perform the configured function. In an embodiment, at block 810, on determination of the requirement for enhancement of parameters, the parameter negotiation sub-module 312 may be configured to perform parameter enhancement by communicating the parameter enhancement information via the communication module 318 to the APs in the network including MLDs.

[0088] In an embodiment of the present disclosure, the parameter negotiation sub-module 312 may be further configured to decide a Target Wake Time (TWT) with APs 108 available in the network. The TWT is decided to control the UE 106 optimal sleep / wake cycles. In an example, the TWT decision is performed based on predicted traffic patterns at the one or more APs 108. In an example, the TWT decision is performed based on the requirements of an application executed on the UE 106. The TWT decision may be performed to reduce the temperature of the AP 108. The TWT decision may be further associated with improved battery lifecycle of UE 106.

[0089] In an embodiment of the present disclosure, the parameter negotiation sub-module 312 may be further configured to receive real-time network traffic information from an AP 108. In the embodiment, the AP 108 may correspond to an AP selected based on the implementation of an embodiment of the present disclosure. Further, the UE 106 may be configured to adapt the predicted traffic patterns and decision process based on the received real-time network traffic information. In an example, the real-time network traffic information received by the UE 106 from the AP 108 may be used as training data for the AI / ML traffic pattern prediction module 308.

[0090] Figure 9illustrates a schematic diagram associated with action frame parameters for implementing physical network layer and Machine Access Control (MAC) network layer parameter decision, according to an embodiment of the present disclosure.

[0091] In an embodiment, Figure 9 at block 902 illustrates the action frame parameters transmitted by the UE parameter negotiation sub-module 312 of the UE 106 to perform parameter optimization at the AP 108. The AP 108 may be present as one of the access points in an MLD in the network. Further, in the action frame parameters 902 the size of information elements in the action frame may be provided as frame control is of 2 octets, duration is of 2 octets, DA is of 6 octets, SA is of 6 octets, Basic Service Set ID (BSSID) is of 6 octets, sequence control is of 2 octets, category is of 1 octet, action and elements are of variable size as per the embodiment, Frame Check Sequence (FCS) is of 4 octet.

[0092] Furthermore, as illustrated in Figure 9 at block 904, to implement the embodiment of the present disclosure an information element MP-IE may be introduced containing information associated with the enhancement of the physical network layer parameters and MAC network layer parameters of the AP 108. At 906, the information elements in MP-IE are further illustrated as Element ID (EID)=255, length, Element ID extension, MP-IE information. The size for EID, length and element ID extension is 1 octet each. The size for MP-IE information is variable. At 908, the MP-IE is exemplified to include AP parameter information of variable size depending on the embodiment and requirements for parameter decision and parameter enhancement of the physical network layer parameters and MAC network layer parameters. Figure 10 further exemplifies the AP parameter information at 908.

[0093] Figure 10illustrates a schematic diagram associated with Information Elements (IE) for Physical network layer and MAC network layer parameter decision, according to an embodiment of the present disclosure.

[0094] In an embodiment, at 1002 the AP parameter information is of 4 bytes. Further, at 1004 the bits may include information associated with Physical network layer and MAC network layer parameter such as Quadrature Amplitude Modulation (QAM), spatial stream, MLO, multiple-input multiple-output (MIMO), Multi-User MIMO (MU MIMO), Modulation Coding Scheme (MCS) index, OFDMA, TWT, and the like. The bit information as illustrated at 1004 may be represented as the table 1 below:

[0095]

[0096] Figure 11illustrates a schematic diagram of the score map based on correlating the predicted traffic patterns with a set of expected physical layer parameters and a set of expected MAC layer parameters in the network, according to an embodiment of the present disclosure.

[0097] In an embodiment, prior to decision present disclosure may include the AI / ML traffic pattern prediction module 308 generating a score map based on correlating the predicted traffic patterns with a set of expected physical layer parameters and a set of expected MAC layer parameters in the network. The score map is illustrated in Figure 8 at 812 and exemplified in Figure 11 for EHT and HT as predicted traffic pattern. The score map helps in identifying the expected parameters for physical layer and MAC layer of the network at an AP based on the predicted traffic patterns. The score map further helps in deciding and enhancing the parameters for physical layer and MAC layer of the network at an AP.

[0098] As illustrated in Figure 11 at 1100-2, for EHT as predicted traffic pattern the expected physical layer parameters and expected MAC layer parameters in the network may include 4096 QAM, 300 MHz bandwidth, symbol duration of 12.8 ㎲, MCS index as 31, spatial streams as 16, Network Allocation Vector (NAV) as 2 and Target Wake Time (TWT) as 10 ms.

[0099] Furthermore at 1100-4, for HT as predicted traffic pattern, the expected physical layer parameters and expected MAC layer parameters in the network may include 1024 QAM, 160 MHz bandwidth, symbol duration of 12.8 ㎲, MCS index as 13, spatial streams as 8, NAV as 2 and TWT as 8 ms. The details provided in the illustration are exemplary and non-limiting to the scope of the present disclosure.

[0100] Figure 12illustrates a block diagram associated with the access point selection sub-module 314 of the UE 106, according to an embodiment of the present disclosure.

[0101] In an embodiment, AP backhaul parameters 1202, UE / STA real-time throughput and link parameters 1204 and information from UE parameter negotiation sub-module 312 may be used by the access point selection sub-module 314 of the UE. The access point selection sub-module 314 may be configured to compute the access point score for APs at 1208. In the embodiment, the access point score of an access point in the network may be computed based on the parameters comprising throughput of a channel, Received Signal Strength Indicator (RSSI), Quadrature amplitude modulation (QAM), Multi Link Operation (MLO), multi-user, multiple input, multiple output (MU-MIMO), Target Wake Time (TWT) Service Period, Modulation Coding Scheme (MCS) rate, band / frequency, channel width, Signal to Noise Ratio (SNR), guard interval, security protocol, spatial stream, and channel utilization. In an embodiment, the access point score may be associated with the parameters for physical layer and MAC layer of the network at an AP.

[0102] Next, at 1210 the access point selection sub-module 314 may be configured to compare the access point score for the connected APs. Further, at 1206, the access point selection sub-module 314 may obtain saved network information such as available APs in the network.

[0103] Next, at 1214 if the access point score for connected AP is higher, then the access point selection sub-module 314 may take no action as illustrated at 1220. Further, on comparison of access point score if an available AP has a better access point score than the access point score of the connected AP then the access point selection sub-module 314 may choose an AP having score better than connected AP score as illustrated at 1212.

[0104] Furthermore, step 1212 may further include prioritizing saved APs if the chosen AP has a higher score than the connected access point. The prioritization of saved APs may be performed by data prioritization sub-module 316 of the UE. The working and functionality of the data prioritization sub-module 316 is explained in Figure 13a to Figure 15.

[0105] Furthermore, at 1216 a decision may be made by the access point selection sub-module 314 to connect to the chosen saved AP if the AP is in a list of saved APs (step 1222). Additionally, the access point selection sub-module 314 may provide indication to a user for a new AP connection if the chosen AP is not in a list of saved APs (step 1218).

[0106] Figure 13aillustrates a process flow associated with a data prioritization sub-module 316 of the UE 106, according to an embodiment of the present disclosure.

[0107] At block 1300a-1, the data prioritization sub-module 316 may be configured to associate one or more data buffers to the one or more access points in the network, wherein the association is based on the access point score of the one or more access points, and wherein the one or more data buffers store the one or more data packets.

[0108] In an embodiment, the access point score computed by the access point selection sub-module 314 may be used by the data prioritization sub-module 316 to associate the one or more data buffers to the one or more access points in the network. The description for Figure 13a to 15 are to be read together to understand the working of the data prioritization sub-module 316. Furthermore, the data prioritization sub-module may be responsible for prioritizing one or more data packets in the network based on the predicted traffic patterns.

[0109] Figure 13billustrates a block diagram associated with the data prioritization sub-module of the UE, according to an embodiment of the present disclosure.

[0110] In an embodiment, the access point selection sub-module 314 may be configured to provide a list of APs 108 with corresponding access point score. The APs 108 may be further associated with multi-link devices (MLDs). As illustrated at 1302b, the data prioritization sub-module 316 may be configured to associate (or map) one or more access points (e.g. AP 1, AP 2, AP 3) with one or more data buffers (EHT, HT, GT, LT, ELT) based on the access point score. The association (or mapping) may be furthermore based on the predicted traffic patterns (and TID).

[0111] In an embodiment, at 1304b the data prioritization sub-module 316 may be configured to activate the data path between the one or more data buffers and the one or more access points 108. Thereafter, the data prioritization sub-module 316 may be connected to the communication module 318 to enable communication with the APs 108 in the network. The process prioritizing one or more data packets in the network based on the predicted traffic patterns is further illustrated for enhancement in Figure 14 and 15.

[0112] Figure 14illustrates a schematic diagram associated with mapping one or more data buffers to one or more data packets by the data prioritization sub-module of the UE, according to an embodiment of the present disclosure.

[0113] In an embodiment of the present disclosure, at 1402 the UE 106 is illustrated to scan for MLDs with associated APs 108. In an embodiment, the UE parameter negotiation sub-module 304 may be configured to perform the scan for MLDs. In an example, the MLD 1 has associated access points AP 1, AP 2, and AP 3. Further, MLD 2 has associated access points AP 4, AP 5, and AP 6 and so on. In an example, the UE 106 may detect n MLDs, with MLD n having an associated access point AP m. Furthermore, the APs in the MLDs may be associated with one or more frequencies of operation such as 2.4 GHz, 5 GHz, 6 GHz, and the like.

[0114] Further at 1403, the access point selection sub-module 314 may be configured to provide the list of MLD APs with corresponding access point score.

[0115] Furthermore at 1404, the data prioritization sub-module 316 may be configured to associate the APs with one or more data buffers based on the predicted traffic patterns. In an example, as illustrated in Figure 14, the AP 2 has predicted traffic patterns as EHT and is associated with EHT related data buffer. Similarly, AP 1 has predicted traffic patterns a HT and is associated with HT related data buffer. In the Figure, the data buffers have associated priority, where EHT data buffer has highest priority, and the ELT data buffer has lowest priority.

[0116] Figure 15illustrates a schematic diagram associated with prioritization of the one or more data packets by the data prioritization sub-module 316 of the UE 106, according to an embodiment of the present disclosure.

[0117] In an embodiment of the present disclosure, the one or more data packets are illustrated at 1502 in Figure 15. In an example, the one or more data packets are illustrated as A, B, C, D, E, and F arranged according to the priority. Data packet A has the highest priority and data packet F has the lowest priority.

[0118] At 1504, the priority buffers may be classified based on the assigned TID and associated traffic pattern. In an example as illustrated in Figure 15, the EHT data buffer with assigned TID as zero receives data packet C. Similarly other data buffers for HT, GT, LT and ELT are illustrated in the Figure 15.

[0119] As illustrated at 1506, the data packets may be provided with a data path in the network comprising MLDs to a plurality of transmit queues. As illustrated at 1508, the transmit queues temporarily may store the data packets prior to the data packet being transmitted to APs 108 in the network.

[0120] The prioritization of the one or more data packets depends on the predicted traffic pattern in the network. The predicted traffic pattern in turn is responsible for assigning the data buffer. The data prioritization sub-module 316 is thereafter responsible for associating (or mapping) the one or more data buffers with one or more access points in the network. In the present disclosure, the emphasis is on the one or more access point supporting MLO and associated with MLDs.

[0121] Figure 16illustrates a block diagram associated with a communication module of the UE, according to an embodiment of the present disclosure.

[0122] In an embodiment of the present disclosure, the communication module 318 may receive inputs from the UE parameter negotiation module 312, the access point selection sub-module 314, and the data prioritization sub-module 316 of the UE 106. The inputs from the UE parameter negotiation module 312 and the access point selection sub-module 314 may be transmitted to the communication module as action frames to be further transmitted to the network and APs 108. Further, the inputs from the data prioritization sub-module 316 may be transmitted to the communication module as data frames to be further transmitted to the network and APs 108.

[0123] Thereafter, the output from the transmission queue 1602 may be transmitted to decide the physical layer parameters and MAC layer parameters associated with the one or more access points in the network. Further, reception queue 1604 may be configured to receive information from the one or more access points for AP selection and decision.

[0124] Figure 17illustrates a block diagram 1700 associated with a network layer parameter configuration module 402 of the AP 108, according to an embodiment of the present disclosure.

[0125] In an embodiment of the present disclosure, the communication module 406 may receive action frames from the UE (or STA) 106 present in a network comprising MLDs. The communication module 406 may be associated with an AP 108 present in an MLD. The AP 108 may be further configured to extract the physical layer parameters and MAC layer parameters requested by the UE 106 by using an information element (IE) parser. Figure 18 illustrates exemplary parameters associated with the requested physical network layer and MAC network layer parameter by the UE 106.

[0126] At block 1702, the network layer parameter configuration module 402 may be configured to aggregate the requested parameters for Physical and Mac layer from the UE 106 in the network. The requested parameters may be associated with the physical and MAC layer at AP 108. At 1704, the network layer parameter configuration module 402 may be configured to enhance the parameters for Physical and Mac layer for the UE (or UEs) 106 connected to the AP 108. The table 2 below illustrates the aggregated requested parameters from the UE (or STA) 106 in the network.

[0127]

[0128] At 1706, the network layer parameter configuration module 402 may be configured to set parameters for Physical layer for connected STAs or UE from among the UE 106 in the network. The table 3 below illustrates the set parameters for the connected UE 106.

[0129]

[0130] At 1708, the network layer parameter configuration module 402 may be configured to send finalized suggested parameters to all the STAs or UEs 106 in the network via action frames. The block 1708 may be required to complete the parameter decision process between the UE 106 and AP 108 in the network comprising MLDs.

[0131] Figure 18illustrates a schematic diagram associated with requested Physical network layer and Machine Access Control (MAC) network layer parameter by the UE to be implemented by the network layer parameter configuration module of the AP, according to an embodiment of the present disclosure.

[0132] In an embodiment of the present disclosure, an exemplary action frame from a UE 106 in the network received at the AP 108 is illustrated at block 1802 in Figure 18. Further, the AP 108 may be further configured to extract the physical layer parameters and MAC layer parameters requested by the UE 106 by using an information element (IE) parser. In Figure 18 at block 1804, the extracted physical layer parameters and MAC layer parameters requested by the UE 106 are illustrated. The extracted parameters may include MU-MIMO, RU, QAM, MCS, NAV, TWT, and the like.

[0133] Figure 19illustrates a block diagram 1900 associated with a load analysis module of the AP, according to an embodiment of the present disclosure.

[0134] In an embodiment of the present disclosure, the load analysis module 404 of the AP may be configured to obtain backhaul parameters from Internet Service Provider (ISP) 1902. The functionality of components in the load analysis module 404 is explained in the following description. In an embodiment, the Backhaul Parameter Control Unit (BPCU) 1904 may be configured to calculate backhaul parameters, jitter congestion, network congestion, and the like. Further, in an embodiment, the buffer calculator 1906 may aggregate the buffer available in the corresponding UEs 106 for the AP 108.

[0135] Next, in an embodiment, the physical parameter detector 1908 may aggregate parameters like, temperature, resource unit, band support, bandwidth support, and the like. The operations by components 1904, 1906, and 1908 are done in every t interval of time. Further, at 1910, the output from the components 1904. 1906, 1908 may be relied upon by the load analysis module 404 of the AP to build AP load parameters. Thereafter, at 1912, the load analysis module may append the load parameters to one of a probe response frame, or a beacon frame, or an action frame. The operations may be repeated after lapse of a fixed time interval (t) and transmitted to communication module 406 at 1914.

[0136] Figure 20illustrates a schematic diagram for an exemplary signal transmitted by the AP for network load analysis by the load analysis module of the AP, according to an embodiment of the present disclosure.

[0137] In an embodiment of the present disclosure, Figure 20 at 2002 illustrates a signal transmitted by the AP, where the signal may correspond to one of a probe response frame, or a beacon frame, or an action frame. In an example, at 2002 the signal may correspond to a probe response frame with appended AP load parameters.

[0138] At 2004, the Figure 20 illustrates the frame body for the probe response frame. In an embodiment, the probe response frame at 2004 may be configured to include Access Point Internet Reachability Information Element (AP-IR IE). Further, at 2006, the Figure 20 illustrates the AP-IR IE. At, 2008, the Figure 20 illustrates the information of AP-IR IE.

[0139] In an example at 2008 in Figure 20, AP Load parameters may include:

[0140] · Throughput of AP backbone network in Mbps (2 bytes).

[0141] · AP's current operating temperature (1 byte).

[0142] · Backbone network Congestion (1 byte).

[0143] · Buffer capability (1 byte - available in percentage).

[0144] · Number of connected UEs or STAs (1byte).

[0145] · Jitter of backbone network (1byte).

[0146] · Reserved (1byte)

[0147] Figure 21illustrates an exemplary block diagram for the overall process associated with optimizing access point selection in a network comprising MLDs, according to an embodiment of the present disclosure.

[0148] In an embodiment, the UE 106 is in a network comprising MLDs and the figure further illustrates N APs as AP1 2106, AP2 2108..., AP N 2110. The backhaul information is obtained from the network and APs and stored in storage 2104. The storage 2104 may be located in the UE 106 or in the system 200 or may be stored in a remote cloud-based storage. The APs in the figure may be one of non-MLO AP or an MLO supported AP or an AP in an MLD.

[0149] The network traffic information builder module 302 may be configured to obtain traffic information based on factors such as network backhaul information, device state, service analysis information, and the like.

[0150] In an example, the backhaul information may include backhaul AP throughput, buffer capability, backbone network congestion, Jitter, temperature, and the like. Further, the module 302 may rely on information such as the frequency band, channel bandwidth, channel, scattering, fading, power decay.

[0151] Next, the AI / ML traffic pattern prediction module 308 may rely on the obtained traffic information from the network traffic information builder module 302 to predict the traffic patterns in the network and at the APs. Parameters to AI / ML model to predict the upcoming traffic. Further, the UE 106 may obtain the score map 812 from AI / ML model with mapped parameters for physical layer parameters and MAC layer parameters based on the predicted traffic patterns.

[0152] Next, the UE parameter negotiation sub-module 312 may be configured to decide the physical layer parameters and MAC layer parameters with the APs. Further, in the figure dashed lines depict action frames from non-associated APs and solid lines depict action frames from associated APs. At 2112, the APs are illustrated to perform parameter enhancement based on the received action frames.

[0153] Thereafter, the AP selection sub-module 314 may perform access point selection based on the embodiments of the present disclosure. The AP selection sub-module 314 relies upon the backhaul AP load information to determine the throughput in the network for an AP to decide the need for AP selection. The description is non-limiting and must be read with the description provided with other figures and explanations for modules and sub-modules for understanding the scope of the present disclosure.

[0154] Figure 22aillustrates an exemplary use case scenario associated with the absence of network availability at the AP connected to the UE 106, according to an embodiment of the present disclosure.

[0155] The Figure 22a illustrates a scenario where the UE 106 is connected to an AP without internet connection. The present disclosure enables switching to an AP matching the requirements of the UE 106 without delay in the switch. The selection is based on the obtained traffic information of the network and the predicted traffic patterns.

[0156] Figure 22billustrates an exemplary use case scenario associated with AP selection among a plurality of APs saved at the UE 106, according to an embodiment of the present disclosure.

[0157] The Figure 22b illustrates a scenario where the UE 106 is initially connected to a low backhaul network. The present disclosure enables the UE 106 to switch to a saved AP 108 with better backhaul performance. The present disclosure allows optimized AP selection among the saved APs 108 based on the predicted traffic patterns and access point score.

[0158] Figure 22cillustrates an exemplary use case scenario associated with AP selection based on the comparison of the backhaul throughput of the APs available for connection with the UE 106, according to an embodiment of the present disclosure.

[0159] The Figure 22c illustrates a scenario where a UE 106 is connected to an AP 108 with low backhaul. The implementation of present disclosure provides the UE 106 with list of APs available in the network with better backhaul performance. The present disclosure allows optimized AP selection among the available APs 108 based on the predicted traffic patterns and access point score.

[0160] Figure 22dillustrates an exemplary use case scenario associated with selection of a Multi-Link Operation (MLO) supported AP based on the comparison of backhaul throughput of the APs available for connection with the UE 106, according to an embodiment of the present disclosure.

[0161] The Figure 22d illustrates a scenario with two STAs 106 depicted as STA1 and STA2 in the figure. STA1 is MLO supported and is initially connected to a Non-MLO AP. Further STA2 is also MLO supported and initially connected to a dual-band AP.

[0162] The scenario illustrates a situation where the non-MLO AP connected to STA1 is associated with a low backhaul network. The implementation of the present disclosure provides STA1 with an available AP with a better backhaul network. In Figure 22d, a tri-band MLO AP is available with a better backhaul network.

[0163] The scenario further illustrates a situation where the dual band AP connected with STA2 is associated with low backhaul network. The tri-band MLO AP is in the list of saved AP at STA2. The implementation of the present disclosure provides STA2 with saved AP with better backhaul network. In figure a tri-band MLO AP is in the list of saved AP at STA2 and has a better backhaul network.

[0164] Figure 22eillustrates an exemplary use case scenario associated with prioritization of data packets from the UE 106based on the priority of a data packet and data throughput of the APs available for connection with the UE, according to an embodiment of the present disclosure.

[0165] The Figure 22e illustrates a scenario where an MLO supported UE is connected to a non-MLO AP-1 and MLO supported AP-2. The implementation of the present disclosure allows UE to prioritize data packets to the connected APs based on the priority of data packets.

[0166] Figure illustrates a scenario where the EHT data packets of UE are handled by MLO supported AP-2 and LT data packets of UE are handled by non-MLO AP-1. The data packets may be assigned to the APs based on the access point score and the predicted traffic patterns.

[0167] Figure 23illustrates a process flow comprising a method for optimizing access point selection in a network comprising MLDs, according to an embodiment of the present disclosure.

[0168] The method 2300 may be a computer-implemented method executed, for example, by the system 200, the UE 106, and the APs 108 and the modules 206, 301, and 401. For the sake of brevity, the constructional and operational features of the system 200, UE 106, and APs 108 that are already explained in the description of Figure 1 to Figure 22e are not explained in detail in the description of Figure 23.

[0169] At step 2302, the method 2300 may include obtaining a traffic information of the network comprising the MLDs.

[0170] At step 2304, the method 2300 may include predicting traffic patterns at one or more access points in the network based on the obtained traffic information of the network.

[0171] At step 2306, the method 2300 may include deciding physical layer parameters and Media Access Control (MAC) layer parameters associated with the one or more access points in the network, wherein the decision is based on the predicted traffic patterns.

[0172] At step 2308, the method 2300 may include performing access point selection by selecting the access point with the highest access point score, wherein the access point score is associated with the physical layer parameters and MAC layer parameters.

[0173] While the above-discussed steps in Figure 23 are shown and described in a particular sequence, the steps may occur in variations to the sequence in accordance with an embodiment. Further, a detailed description related to the various steps of Figure 23 is already covered in the description related to Figures 1-22e and is omitted herein for the sake of brevity.

[0174] The present disclosure provides the following advantages:

[0175] The disclosure relates to optimized access point selection and ensures access point selection based on backhaul network of the access point. The present disclosure provides faster data transfers and reduced latency.

[0176] The optimized access point selection ensures seamless connectivity, reduced buffering, and improved overall quality of service.

[0177] The present disclosure prioritizes data packets based on the predicted traffic patterns and access point score. This ensures handling of data packets based on the associated priority and better services to the user of the UE.

[0178] The present disclosure assesses the network condition based on factors related to backhaul information, UE information and analysis of the services running on the UE. This results in better selection of access points, particularly in a network with MLDs.

[0179] The present disclosure is further associated with better battery performance in power constrained UE such as mobile phones, laptops, IoT devices, and the like connected to the network.

[0180] While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.

[0181] The drawings and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not limited to the manner described herein.

[0182] Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts necessarily need to be performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples. Numerous variations, whether explicitly given in the specification or not, such as differences in structure, dimension, and use of material, are possible. The scope of embodiments is at least as broad as given by the following claims.

[0183] Benefits, other advantages, and solutions to problems have been described above with regard to specific embodiments. However, the benefits, advantages, solutions to problems, and any component(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential feature or component of any or all the claims.

[0184] According to an embodiment of the present disclosure, the traffic information of the network may comprise at least one of type of application running on a client device, type of the client device, screen state of the client device, mobility of the client device, screen size of the client device, maximal video resolution supported by the client device, user preference on the client device, number of active links on the MLDs, quality of active links on the MLDs, channel reciprocity analysis, and channel quality variation.

[0185] According to an embodiment of the present disclosure, the deciding the physical layer parameters and the MAC layer parameters may comprise transmitting at least one of a beacon frame, a probe response frame, and an action frame containing the predicted traffic patterns and associated data in an extended beacon. According to an embodiment of the present disclosure, the deciding the physical layer parameters and the MAC layer parameters may comprise receiving information on resource allocation for one or more links on the one or more client devices and the MLDs, wherein the resource allocation is based on the predicted traffic patterns and the channel quality variations identified through reciprocity analysis.

[0186] According to an embodiment of the present disclosure, the method may comprise enhancing at least one of an Orthogonal Frequency-Division Multiple Access (OFDMA) transmission, a Multi-user Multi-input Multi Output (MU-MIMO) transmission, a Multi-Link MU-MIMO transmission, and a Radio Unit (RU) allocation for the one or more client devices. According to an embodiment of the present disclosure, the method may comprise enhancing Signal-to-Noise Ratio (SNR), Modulation and Coding Scheme (MCS) guard interval, MCS modulation technique, and channel width for the one or more access points based on backhaul real throughput, access point buffering capability, operating temperature and predicted traffic patterns for each of the one or more access points.

[0187] According to an embodiment of the present disclosure, the traffic patterns at one or more access points in the network may be predicted by an Artificial Intelligence (AI) model based on the obtained traffic information of the network.

[0188] According to an embodiment of the present disclosure, prior to decision the method may comprise generating a score map based on correlating the predicted traffic patterns with a set of expected physical layer parameters and a set of expected MAC layer parameters in the network.

[0189] According to an embodiment of the present disclosure, the method may comprise prioritizing one or more data packets in the network based on the predicted traffic patterns.

[0190] According to an embodiment of the present disclosure, prioritizing the one or more data packets in the network may comprise associating one or more data buffers to the one or more access points in the network, wherein the association is based on the access point score of the one or more access points, and wherein the one or more data buffers store the one or more data packets.

[0191] According to an embodiment of the present disclosure, the access point score of an access point in the network may be computed based on the parameters comprising throughput of a channel, Received Signal Strength Indicator (RSSI), Quadrature amplitude modulation (QAM), Multi Link Operation (MLO), multi-user, multiple input, multiple output (MU-MIMO), Target Wake Time (TWT) Service Period, Modulation Coding Scheme (MCS) rate, band / frequency, channel width, Signal to Noise Ratio (SNR), guard interval, security protocol, spatial stream, and channel utilization.

[0192] According to an embodiment of the present disclosure, the traffic information of the network may comprise at least one of type of application running on a client device, type of the client device, screen state of the client device, mobility of the client device, screen size of the client device, maximal video resolution supported by the client device, user preference on the client device, number of active links on the MLDs, quality of active links on the MLDs, channel reciprocity analysis, and channel quality variation.

[0193] According to an embodiment, to decide the physical layer parameters and the MAC layer parameters, at least one processor may cause the electronic device to transmit at least one of a beacon frames, a probe response frame, and an action frame containing the predicted traffic patterns and associated data in an extended beacon. According to an embodiment, to decide the physical layer parameters and the MAC layer parameters, at least one processor may cause the electronic device to receive information on resource allocation for one or more links on the one or more client devices and the MLDs, wherein the resource allocation is based on the predicted traffic patterns and the channel quality variations identified through reciprocity analysis.

[0194] According to an embodiment, at least one processor may cause the electronic device to enhance at least one of an Orthogonal Frequency-Division Multiple Access (OFDMA) transmission, a Multi-user Multi-input Multi Output (MU-MIMO) transmission, a Multi-Link MU-MIMO transmission, and a Radio Unit (RU) allocation for the one or more client devices. According to an embodiment, at least one processor further cause the electronic device to enhance Signal-to-Noise Ratio (SNR), Modulation and Coding Scheme (MCS) guard interval, MCS modulation technique, and channel width for the one or more access points based on backhaul real throughput, access point buffering capability, operating temperature and predicted traffic patterns for each of the one or more access points.

[0195] According to an embodiment, the traffic patterns at one or more access points in the network is predicted by an Artificial Intelligence (AI) model based on the obtained traffic information of the network.

[0196] According to an embodiment, at least one processor may cause the electronic device to prioritize one or more data packets in the network based on the predicted traffic patterns.

[0197] According to an embodiment, prior to decision at least one processor may cause the electronic device to generate a score map based on correlating the predicted traffic patterns with a set of expected physical layer parameters and a set of expected MAC layer parameters in the network.

[0198] According to an embodiment, to prioritize the one or more data packets in the network, at least one processor may cause the electronic device to associate one or more data buffers to the one or more access points in the network, wherein the association is based on the access point score of the one or more access points, and wherein the one or more data buffers store the one or more data packets.

[0199] According to an embodiment, the access point score of an access point in the network may be computed based on the parameters comprising throughput of a channel, Received Signal Strength Indicator (RSSI), Quadrature amplitude modulation (QAM), Multi Link Operation (MLO), multi-user, multiple input, multiple output (MU-MIMO), Target Wake Time (TWT) Service Period, Modulation Coding Scheme (MCS) rate, band / frequency, channel width, Signal to Noise Ratio (SNR), guard interval, security protocol, spatial stream, and channel utilization.

[0200] Thus, there is a need to provide a methodology to overcome the above-mentioned issues in the conventional techniques.

Claims

1.A method for optimizing access point selection in a network comprising Multi-Link Devices (MLDs), the method comprising:obtaining a traffic information of the network comprising the MLDs;predicting traffic patterns at one or more access points in the network based on the obtained traffic information of the network;deciding physical layer parameters and Media Access Control (MAC) layer parameters associated with the one or more access points in the network, wherein the decision is based on the predicted traffic patterns; andperforming access point selection by selecting the access point with the highest access point score, wherein the access point score is associated with the physical layer parameters and MAC layer parameters.2.The method as claimed in claim 1, wherein the traffic information of the network comprises at least one of type of application running on a client device, type of the client device, screen state of the client device, mobility of the client device, screen size of the client device, maximal video resolution supported by the client device, user preference on the client device, number of active links on the MLDs, quality of active links on the MLDs, channel reciprocity analysis, and channel quality variation.3.The method any one of claims 1 to 2, wherein the deciding the physical layer parameters and the MAC layer parameters comprises:transmitting at least one of a beacon frame, a probe response frame, and an action frame containing the predicted traffic patterns and associated data in an extended beacon; andreceiving information on resource allocation for one or more links on the one or more client devices and the MLDs, wherein the resource allocation is based on the predicted traffic patterns and the channel quality variations identified through reciprocity analysis.4.The method any one of claims 1 to 3, the method further comprises:enhancing at least one of an Orthogonal Frequency-Division Multiple Access (OFDMA) transmission, a Multi-user Multi-input Multi Output (MU-MIMO) transmission, a Multi-Link MU-MIMO transmission, and a Radio Unit (RU) allocation for the one or more client devices; andenhancing Signal-to-Noise Ratio (SNR), Modulation and Coding Scheme (MCS) guard interval, MCS modulation technique, and channel width for the one or more access points based on backhaul real throughput, access point buffering capability, operating temperature and predicted traffic patterns for each of the one or more access points.5.The method any one of claims 1 to 4, wherein the traffic patterns at one or more access points in the network is predicted by an Artificial Intelligence (AI) model based on the obtained traffic information of the network.6.The method any one of claims 1 to 5, wherein prior to the decision the method further comprises:generating a score map based on correlating the predicted traffic patterns with a set of expected physical layer parameters and a set of expected MAC layer parameters in the network.7.The method any one of claims 1 to 6, the method further comprises:prioritizing one or more data packets in the network based on the predicted traffic patterns.8.The method as claimed in claim 7, wherein prioritizing the one or more data packets in the network comprises:associating one or more data buffers to the one or more access points in the network, wherein the association is based on the access point score of the one or more access points, and wherein the one or more data buffers store the one or more data packets.9.An electronic device to optimize access point selection in a network comprising Multi-Link Devices (MLDs), the system comprising:memory;at least one processor including processing circuitry, memory storing instructions that, when executed by the at least one processor individually or collectively, cause the electronic device to:obtain a traffic information of the network comprising the MLDs;predict traffic patterns at one or more access points in the network based on the obtained traffic information of the network;decide physical layer parameters and Media Access Control (MAC) layer parameters associated with the one or more access points in the network, wherein the decision is based on the predicted traffic patterns; andperform access point selection by selecting the access point with the highest access point score, wherein the access point score is associated with the physical layer parameters and MAC layer parameters.10.The electronic device as claimed in claim 9, wherein the traffic information of the network comprises at least one of type of application running on a client device, type of the client device, screen state of the client device, mobility of the client device, screen size of the client device, maximal video resolution supported by the client device, user preference on the client device, number of active links on the MLDs, quality of active links on the MLDs, channel reciprocity analysis, and channel quality variation.11.The electronic device any one of claims 9 to 10, wherein to decide the physical layer parameters and the MAC layer parameters, at least one processor cause the electronic device to:transmit at least one of a beacon frame, a probe response frame, and an action frame containing the predicted traffic patterns and associated data in an extended beacon; andreceive information on resource allocation for one or more links on the one or more client devices and the MLDs, wherein the resource allocation is based on the predicted traffic patterns and the channel quality variations identified through reciprocity analysis.12.The electronic device any one of claims 9 to 11, at least one processor further cause the electronic device to:enhance at least one of an Orthogonal Frequency-Division Multiple Access (OFDMA) transmission, a Multi-user Multi-input Multi Output (MU-MIMO) transmission, a Multi-Link MU-MIMO transmission, and a Radio Unit (RU) allocation for the one or more client devices; andenhance Signal-to-Noise Ratio (SNR), Modulation and Coding Scheme (MCS) guard interval, MCS modulation technique, and channel width for the one or more access points based on backhaul real throughput, access point buffering capability, operating temperature and predicted traffic patterns for each of the one or more access points.13.The electronic device as claimed in claim 9 to 12, at least one processor further cause the electronic device to:prioritize one or more data packets in the network based on the predicted traffic patterns.14.The electronic device any one of claims 9 to 13, wherein prior to the decision at least one processor further cause the electronic device to:generate a score map based on correlating the predicted traffic patterns with a set of expected physical layer parameters and a set of expected MAC layer parameters in the network.15.A machine readable medium containing instructions, wherein the instructions, when executed by at least one processor, cause the at least one processor to perform the method of any one of claims 1 to 8.

Images