Methods and apparatus for selecting pilot patterns of a channel estimation in a wireless communication system

Abstract

The present disclosure relates to a 5G communication system or a 6G communication system for supporting higher data rates beyond a 4G communication system such as long term evolution (LTE). Disclosed herein is a method for selecting pilot patterns for a channel estimation in a wireless communication system.

Description

METHODS AND APPARATUS FOR SELECTING PILOT PATTERNS OF A CHANNEL ESTIMATION IN A WIRELESS COMMUNICATION SYSTEM

[0001] The present disclosure relates generally to wireless communication systems, and more particularly, to a method and apparatus for selecting pilot patterns of a channel estimation in a wireless communication system.

[0002] Considering the development of wireless communication from generation to generation, the technologies have been developed mainly for services targeting humans, such as voice calls, multimedia services, and data services. Following the commercialization of 5G (5th generation) communication systems, it is expected that the number of connected devices will exponentially grow. Increasingly, these will be connected to communication networks. Examples of connected things may include vehicles, robots, drones, home appliances, displays, smart sensors connected to various infrastructures, construction machines, and factory equipment. Mobile devices are expected to evolve in various form-factors, such as augmented reality glasses, virtual reality headsets, and hologram devices. In order to provide various services by connecting hundreds of billions of devices and things in the 6G (6th generation) era, there have been ongoing efforts to develop improved 6G communication systems. For these reasons, 6G communication systems are referred to as beyond-5G systems.

[0003] 6G communication systems, which are expected to be commercialized around 2030, will have a peak data rate of tera (1,000 giga)-level bit per second (bps) and a radio latency less than 100μsec, and thus will be 50 times as fast as 5G communication systems and have the 1 / 10 radio latency thereof.

[0004] In order to accomplish such a high data rate and an ultra-low latency, it has been considered to implement 6G communication systems in a terahertz (THz) band (for example, 95 gigahertz (GHz) to 3THz bands). It is expected that, due to severer path loss and atmospheric absorption in the terahertz bands than those in mmWave bands introduced in 5G, technologies capable of securing the signal transmission distance (that is, coverage) will become more crucial. It is necessary to develop, as major technologies for securing the coverage, Radio Frequency (RF) elements, antennas, novel waveforms having a better coverage than Orthogonal Frequency Division Multiplexing (OFDM), beamforming and massive Multiple-input Multiple-Output (MIMO), Full Dimensional MIMO (FD-MIMO), array antennas, and multiantenna transmission technologies such as large-scale antennas. In addition, there has been ongoing discussion on new technologies for improving the coverage of terahertz-band signals, such as metamaterial-based lenses and antennas, Orbital Angular Momentum (OAM), and Reconfigurable Intelligent Surface (RIS).

[0005] Moreover, in order to improve the spectral efficiency and the overall network performances, the following technologies have been developed for 6G communication systems: a full-duplex technology for enabling an uplink transmission and a downlink transmission to simultaneously use the same frequency resource at the same time; a network technology for utilizing satellites, High-Altitude Platform Stations (HAPS), and the like in an integrated manner; an improved network structure for supporting mobile base stations and the like and enabling network operation optimization and automation and the like; a dynamic spectrum sharing technology via collision avoidance based on a prediction of spectrum usage; an use of Artificial Intelligence (AI) in wireless communication for improvement of overall network operation by utilizing AI from a designing phase for developing 6G and internalizing end-to-end AI support functions; and a next-generation distributed computing technology for overcoming the limit of UE computing ability through reachable super-high-performance communication and computing resources (such as Mobile Edge Computing (MEC), clouds, and the like) over the network. In addition, through designing new protocols to be used in 6G communication systems, developing mechanisms for implementing a hardware-based security environment and safe use of data, and developing technologies for maintaining privacy, attempts to strengthen the connectivity between devices, optimize the network, promote softwarization of network entities, and increase the openness of wireless communications are continuing.

[0006] It is expected that research and development of 6G communication systems in hyper-connectivity, including person to machine (P2M) as well as machine to machine (M2M), will allow the next hyper-connected experience. Particularly, it is expected that services such as truly immersive eXtended Reality (XR), high-fidelity mobile hologram, and digital replica could be provided through 6G communication systems. In addition, services such as remote surgery for security and reliability enhancement, industrial automation, and emergency response will be provided through the 6G communication system such that the technologies could be applied in various fields such as industry, medical care, automobiles, and home appliances.

[0007] The present disclosure relates to a method and apparatus for selecting pilot patterns of a channel estimation in a wireless communication system.

[0008] According to an aspect of an exemplary embodiment, there is provided a communication method in a wireless communication system.

[0009] Aspects of the present disclosure provide efficient communication methods in a wireless communication system.

[0010] These and other features, aspects, and advantages of embodiments 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 1 illustrates pilot patterns in different scenarios, in accordance with an embodiment of the prior art;

[0012] Figure 2 illustrates a block diagram of a system for selecting pilot patterns for a channel estimation in a wireless communication network, in accordance with an embodiment of the present disclosure;

[0013] Figure 3 illustrates a flowchart for a method of an iterative pilot pattern selection, in accordance with an embodiment of the present disclosure;

[0014] Figure 4 illustrates a flowchart for network architecture for pilot selection, in accordance with an embodiment of the present disclosure;

[0015] Figure 5 illustrates flowcharts for variations in a transform layer, in accordance with an embodiment of the present disclosure.

[0016] Figure 6 illustrates a flowchart for a plurality of decoder connection assemblies, in accordance with an embodiment of the present disclosure.

[0017] Figure 7 illustrates a flowchart for a method for constraining pilot locations, in accordance with an embodiment of the present disclosure.

[0018] Figure 8 illustrates a flowchart of a method of manual adaptation as a post-processing step of constraining pilot location, in accordance with an embodiment of the present disclosure.

[0019] Figure 9 illustrates a flowchart for a method for determining the best pilot pattern using Rx considering reserved control signals, in accordance with an embodiment of the present disclosure.

[0020] Figure 10 illustrates a flowchart for a method for determining the best pilot pattern using Tx considering reserved control signals, in accordance with an embodiment of the present disclosure.

[0021] Figure 11 illustrates a flowchart for a method for deciding channel estimator at Rx, in accordance with an embodiment of the present disclosure.

[0022] Figure 12 illustrates a flowchart for a method for deciding channel estimator at Tx, in accordance with an embodiment of the present disclosure.

[0023] Figure 13 illustrates a flowchart for a method of optimal pilot pattern selection, wherein a UE handles reserved REs and selects its AI-CE model for channel estimation, in accordance with an embodiment of the present disclosure.

[0024] Figure 14 illustrates a flowchart for a method of optimal pilot pattern selection, wherein the UE handles the reserved REs and BS transmits AI-CE model to UE, in accordance with an embodiment of the present disclosure.

[0025] Figure 15 illustrates a flowchart for a method of optimal pilot pattern selection, wherein the BS handles the reserved REs and transmits AI-CE model to UE, in accordance with an embodiment of the present disclosure.

[0026] Figure 16 illustrates a flowchart for a method of optimal pilot pattern selection, wherein the BS handles the reserved REs and UE selects its AI-CE model for channel estimation, in accordance with an embodiment of the present disclosure.

[0027] Figure 17 illustrates a flowchart for a method of a BPP monitoring procedure, in accordance with an embodiment of the present disclosure.

[0028] Figure 18 illustrates a graph for channel estimation as a function of SNR, in accordance with an embodiment of the present disclosure.

[0029] Figure 19 illustrates an exemplary graphical representation for pilot positions with respect to a number of pilots with DS - 1000ns and DoS - 125Hz, in accordance with an embodiment of the present disclosure.

[0030] Figure 20 illustrates an exemplary graphical representation for pilot positions with respect to a number of pilots with DS - 1000ns and DoS - 250Hz, in accordance with an embodiment of the present disclosure.

[0031] Figure 21 illustrates an exemplary graphical representation for pilot positions with respect to a number of pilots with DS - 1000ns and DoS - 500Hz, in accordance with an embodiment of the present disclosure.

[0032] Figure 22 illustrates an exemplary graphical representation for pilot positions with respect to a number of pilots with DS - 10 ns and DoS - 250Hz, in accordance with an embodiment of the present disclosure.

[0033] Figure 23 illustrates an exemplary graphical representation for pilot positions with respect to a number of pilots with DS - 300 ns and DoS - 250Hz, in accordance with an embodiment of the present disclosure.

[0034] Figure 24 illustrates graphs of fixed pilots versus Different channels, in accordance with an embodiment of the present disclosure;

[0035] Figure 25 illustrates a flowchart depicting a method for selecting pilot patterns for a channel estimation in a wireless communication network, in accordance with an embodiment of the present disclosure; and

[0036] Figure 26 illustrates a flowchart depicting a method for deploying pilot patterns for a channel estimation in a wireless communication network, in accordance with an embodiment of the present disclosure.

[0037] Figure 27 illustrates the configuration of a UE in a wireless communication system according to various embodiments.

[0038] Figure 28 illustrates the configuration of a base station or a network entity in a wireless communication system according to various embodiments.

[0039] Further, skilled artisans will appreciate those 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 and 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] This best mode is provided to introduce a selection of concepts, in a simplified format, that are further described in mode for invention. This best mode is neither intended to identify key or essential inventive concepts of the invention nor is it intended for determining the scope of the invention.

[0041] According to an embodiment of the present disclosure, disclosed herein is a method for selecting pilot patterns for a channel estimation in a wireless communication network. The method includes receiving, at a receiver (Rx), demodulation reference signals (DMRS) or channel state information (CSI) from a current wireless channel. Further, the method includes determining, based on the estimated channel, a set of pilot patterns through an artificial intelligence (AI) model and applying a masking layer to the set of pilot patterns to exclude resource element (RE) positions reserved for control signals, or signals for other user equipment (UE) in multiple-input-multiple-output (MIMO) scenario. The AI model is trained based on online training or historical channel data and simulation results to enhance accuracy of selection of pilot pattern. Further, the method includes selecting at least one pilot pattern among the set of pilot patterns based on correlating each of the set of pilot patterns and predefined performance parameters. The predefined performance parameters comprise channel estimation error, interference minimization, signal-to-noise ratio (SNR), delay spread (DS), Doppler Spread (DoS), power delay profile (PDP), and Doppler spectrum. The method further includes receiving feedback from a transmitter (Tx) based on transmitting the selected pilot pattern. The feedback indicates compatibility correlation between the selected pilot pattern and a resource allocation of the Tx. The method further includes identifying an optimal pilot pattern by adjusting the selected pilot pattern based on the received feedback from the transmitter for subsequent data transmissions.

[0042] In an embodiment, applying the masking layer includes creating a mask that reflects current allocations of resource elements for control signals, and signals for the other UE in the MIMO scenario.

[0043] In an embodiment, the method includes periodically or on-demand calculating the predefined performance parameters to ensure continued accuracy of the optimal pilot pattern and to account for long term channel variations.

[0044] In an embodiment, the method includes verifying, via the AI model, the optimal pilot pattern to facilitate non-interference of the optimal pilot patterns with wireless network communication.

[0045] In an embodiment, the method includes predicting future channel conditions through a machine learning model and adjusting the pilot patterns based on the predicted future channel conditions.

[0046] In one or more embodiments, a system for selecting pilot patterns for a channel estimation in a wireless communication network. The system includes a memory, and a processor communicatively coupled with the memory. The processor is configured to: receive, at a receiver (Rx), demodulation reference signals (DMRS) or channel state information (CSI) from a current wireless channel; determine, based on the estimated channel, a set of pilot patterns through an artificial intelligence (AI) model; apply a masking layer to the set of pilot patterns to exclude resource element (RE) positions reserved for control signals, or signals for other user equipment (UE) in multiple-input-multiple-output (MIMO) scenario; select, at least one pilot pattern among the set of pilot patterns based on correlating each of the set of pilot patterns and predefined performance parameter; receive a feedback from a transmitter (Tx) based on transmitting the selected pilot pattern, wherein the feedback indicates compatibility correlation between the selected pilot pattern and a resource allocation of the Tx 202; and identify an optimal pilot pattern by adjusting the selected pilot pattern based on the received feedback from the transmitter for subsequent data transmissions.

[0047] In one or more embodiments, a method of deploying pilot patterns in a wireless communication network is disclosed. The method includes identifying, at a transmitter (Tx), a set of resource elements (REs) designated for pilot signal transmission based on a current resource allocation map. Further, the method includes selecting, at the Tx, a pilot pattern based on an optimal pilot pattern reported by a receiver (Rx) to align with identified set of resource elements or sending such information to Rx and Rx selecting a pilot pattern. The set of resource element slots correspond to high-density resource element slots that are chosen to minimize channel estimation error while maintaining compliance with network protocols. The method further includes transmitting the selected pilot pattern between Tx and Rx and configuring, at the Tx, a set of resource element slots to implement pilot pattern and transmit locations of the set of resource element slots in a time-frequency (TM) grid to the Rx. Further, the method includes issuing, from the Tx, an activation command to the receiver to activate the selected pilot pattern. The activation command includes synchronization information to align demodulation process of the receiver with a new pilot pattern. Further, the method includes monitoring, at the Tx / Rx, a real-time channel conditions indicating a predefined performance parameter. The predefined performance parameters comprise signal-to-noise ratio (SNR), delay spread (DS), Doppler Spread (DoS), power delay profile (PDP), and Doppler spectrum. The method further includes assessing, at the Tx, receiver performance parameters indicative of accuracy of channel estimation and interference levels based on feedback from the Rx and deploying, by the Tx, an updated pilot pattern to the Rx.

[0048] In an embodiment, the resource elements designated for pilot signal transmission are identified through an analysis of time and frequency-domain control signal distributions.

[0049] In an embodiment, the method includes performing an interference assessment to ensure the selected pilot pattern minimizes cross-channel interference.

[0050] In an embodiment, the method includes refining, based on current channel data or a historical performance database, the pilot pattern selection process.

[0051] In an embodiment, the method includes scheduling periodically or based on Rx 220 reporting, updates to the pilot pattern based on predicted changes in channel environment.

[0052] In one or more embodiments, a system for deploying pilot patterns for a channel estimation in a wireless communication network. The system includes a memory, and a processor communicatively coupled with the memory. The processor is configured to: identify, at a transmitter (Tx), a set of resource elements (REs) designated for pilot signal transmission based on a current resource allocation maps; select, at the Tx, a pilot pattern based on an optimal pilot pattern reported by a receiver (Rx) to align with identified set of resource elements, or sending such information to Rx and Rx selecting a pilot pattern; transmit the selected pilot pattern between Tx and Rx; configure, at the Tx, a set of resource element slots to implement pilot pattern and transmit locations of the set of resource element slots in a time-frequency (TM) grid to the Rx; issue, from the Tx, an activation command to the receiver to activate the selected pilot pattern; monitor, at the Tx / Rx, a real-time channel conditions indicating a predefined performance parameters; assess, at the Tx, receiver performance parameters indicative of accuracy of channel estimation and interference levels based on feedback from the Rx; and deploy, by the Tx, an updated pilot pattern to the Rx.

[0053] To further clarify the advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawing. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.

[0054] Nowadays, in recent years several broadband wireless technologies have been developed to meet the requirements of the growing number of broadband subscribers for providing better applications and services. A second-generation wireless communication system has been developed to provide voice services while ensuring the mobility of users. A third-generation wireless communication system supports voice services along with a data service. In recent years, a fourth-generation (4G) wireless communication system has been developed to provide high-speed data service to cater to the requirement for high-speed and low-latency data services. However, currently, the fourth generation (4G) or Long-Term Evolution (LTE) wireless communication system suffers from a lack of resources to meet the growing demand for high-speed data services. The problem is solved by the deployment of a fifth-generation wireless communication system to meet the ever-growing demand for high-speed data services. Furthermore, the fifth generation (5G) or New Radio (NR) wireless communication system provides ultra-reliability and supports low latency applications.

[0055] In wireless communication channels, the transmitted signal needs to pass through medium before it is received as a signal on the receiver side. This medium is called a channel. When a signal passes through the channel, the signal is distorted due to noise as well as other signals which are passing through the channel. Hence, the received signal has errors. To address the channel distortion and noise, the channel needs to be estimated and compensated for, at the receiver so that transmitted symbols are recovered. To estimate the channel response, reference signals are transmitted, at predefined locations, called as pilots. Data transmitted at the pilots is known to the receiver, thus a comparison of the original transmitted data and received data may be done. Pilot locations are used to estimate the channel distortion and noise and are needed for channel estimation to obtain the transmitted data.

[0056] It should be understood at the outset that although illustrative implementations of the embodiments of the present disclosure are illustrated below, the present invention 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.

[0057] The term “some”, “one or more embodiment”, “one or more example embodiments”, as used herein is defined as “one, or more than one, or all.” Accordingly, the terms “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 one embodiment, several embodiments, or to all embodiments. Accordingly, the term “some embodiments” is defined as meaning “one embodiment, or more than one embodiment, or all embodiments.”

[0058] The terminology and structure employed herein are for describing, teaching, and illuminating some embodiments and their specific features and elements and do not limit, restrict, or reduce the spirit and scope of the claims or their equivalents.

[0059] More specifically, any terms used herein such as but not limited to “includes,” “comprises”, “has”, “have”, 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 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.”

[0060] 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”, “one or more elements”, “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.”

[0061] The terms “A or B,” “at least one of A or / and B,” or “one or more of A or / and B” used in the various embodiments of the present disclosure include any and all combinations of words enumerated with it. For example, “A or B,” “at least one of A and B,” or “at least one of A or B” means (1) including at least one A, (2) including at least one B, or (3) including both at least one A and at least one B.

[0062] Although the term such as “first” and “second” used in various embodiments of the present disclosure may modify various elements of various embodiments, these terms do not limit the corresponding elements. For example, these terms do not limit an order and / or importance of the corresponding elements. These terms may be used for the purpose of distinguishing one element from another element. For example, a first user device and a second user device all indicate user devices and may indicate different user devices. For example, a first element may be named a second element without departing from the scope of right of various embodiments of the present disclosure, and similarly, a second element may be named a first element.

[0063] The expression “configured to (or set to)” used in various embodiments of the present disclosure may be replaced with “suitable for,” “having the capacity to,” “designed to,” “adapted to,” “made to,” or “capable of” according to the situation. The term “configured to (set to)” does not necessarily mean “specifically designed to” as hardware. Instead, the expression “apparatus configured to ...” may mean that the apparatus is “capable of ... ” along with other devices or parts in a certain situation. For example, “a processor configured to (set to) perform A, B, and C” may be a dedicated processor, for example, an embedded processor, for performing a corresponding operation, or a generic-purpose processor, for example, a Central Processing Unit (CPU) or an application processor (AP), capable of performing a corresponding operation by executing one or more software programs stored in a memory device.

[0064] A term “module” used in the present document may imply a unit including, for example, one of hardware, software, and firmware or a combination of two or more of them. The “module” may be interchangeably used with a term such as a unit, a logic, a logical block, a component, a circuit, and the like. The “module” may be a minimum unit of an integrally constituted component or may be a part thereof. The “module” may be a minimum unit for performing one or more functions or may be a part thereof. The “module” may be mechanically or electrically implemented. For example, the “module” of the present disclosure may include at least one of an Application-Specific Integrated Circuit (ASIC) chip, a Field-Programmable Gate Arrays (FPGAs), and a programmable-logic device, which are known or will be developed, and which perform certain operations.

[0065] 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.

[0066] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein.

[0067] As is traditional in the field, embodiments may be described and illustrated in terms of modules that carry out a described function or functions. These modules, which may be referred to herein as units or blocks or the like, or may include blocks or units, are physically implemented by analog or digital circuits such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, or the like, and may optionally be driven by firmware and software. The circuits may, for example, be embodied in one or more semiconductor chips, or on substrate supports such as printed circuit boards and the like. The circuits constituting a block may be implemented by dedicated hardware, by a processor (e.g., one or more programmed microprocessors and associated circuitry), or by a combination of dedicated hardware to perform some functions of the block and a processor to perform other functions of the block. Each block of the embodiments may be physically separated into two or more interacting and discrete blocks without departing from the scope of the invention. Likewise, the blocks of the embodiments may be physically combined into more complex blocks without departing from the scope of the invention.

[0068] The accompanying drawings are used to help easily understand various technical features and it should be understood that the embodiments presented herein are not limited by the accompanying drawings. As such, the present disclosure should be construed to extend to any alterations, equivalents, and substitutes in addition to those which are particularly set out in the accompanying drawings. Although the terms first, second, third, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are generally only used to distinguish one element from another.

[0069] Embodiments of the present disclosure will be described below in detail with reference to the accompanying drawings.

[0070] The objective of the present disclosure is to provide a deep learning-based feature selection approach to select the appropriate pilot locations, which is more appropriate for complex-valued numbers, as is the case with wireless communications. Further, a masking-based approach is disclosed so that the DL-based algorithm does not pick the locations that are reserved as a priority for other control signals. Moreover, procedures for switching among AI channel estimators for UE along with a practical approach for selecting the minimum number of pilots required for channel estimation. Furthermore, an extension of a CAE by incorporating a transform layer, such that it can extended for the usage of complex numbers, which is the case with channel coefficients.

[0071] For the sake of clarity, the first digit of a reference numeral of each component of the present disclosure is indicative of the Figure number, in which the corresponding component is shown. For example, reference numerals starting with digit “1” are shown at least in Figure 1. Similarly, reference numerals starting with digit “2” are shown at least in Figure 2.

[0072] Figure 1 illustrates pilot patterns in different scenarios, in accordance with an embodiment of the prior art.

[0073] In wireless communication systems like 4G LTE and 5G NR, an orthogonal frequency-division multiplexing (OFDM) modulation scheme may be employed to address frequency-selective fading in the channel. The channel estimation is done using demodulation reference signals (DMRS), also known as pilots, whose value and locations are known to both the transmitter and receiver. The locations at which the pilots are placed (pilot pattern) are chosen from a set of predefined patterns as specified by the 3rd generation partnership project (3GPP). The pilot patterns used for 4G and 5G are uniformly distributed, precisely, the diamond structure(case A) for 4G and the parallel structure(case B) for the 5G.

[0074] As illustrated in Figure 1, pilot patterns are optimized for conventional channel estimators such as least squares-based channel estimators and minimum mean square error (MMSE) based channel estimators. The goal is to identify the locations in the time-frequency (TF) grid that are more informative so that they can be used as pilots. The pilots in diamond and parallel structures(case A and B) are being used in the case of LTE and NR respectively.

[0075] The channel estimators used for 4G and 5G communications systems are least squares-based channel estimators and MMSE, which are conventional channel estimators. In one perspective, more advanced DL based channel estimators such as ChannelNet have been proposed for better channel estimation and are more favorable to be used in upcoming 6G technologies. The diamond and parallel shaped pilot patterns(case A and B) used in 4G and 5G are optimized for conventional channel estimators.

[0076] The conventional pilot patterns used for wireless communication are not optimal for the emerging channel estimation techniques, mainly deep learning-based approaches. The pilot patterns that are more optimal for such techniques may provide random patterns(case C) and can interfere with other positions that are reserved for other control signals.

[0077] Therefore, in view of the above-mentioned problems, it is advantageous to provide an improved system and method that can overcome the above-mentioned problems and limitations associated with selecting a near optimal pilot pattern(case C) with practical constraints.

[0078] In wireless communication systems like 4G LTE and 5G NR, the employment of an orthogonal frequency-division multiplexing (OFDM) modulation scheme addresses frequency-selective fading in the channel. The transmitted signal in a communication system undergoes channel distortion before being received. Addressing the channel distortion and recover the transmitted symbols requires channel estimation and compensation at the receiver. The channel estimation is done using demodulation reference signals (DMRS), also known as pilots, whose value and locations are known to both the transmitter and receiver. The locations at which the pilots are placed (pilot pattern) are chosen from a set of predefined patterns as specified by the 3rdgeneration partnership project (3GPP). The pilot patterns used for 4G and 5G are uniformly distributed, precisely, the diamond structure for 4G and the parallel structure for the 5G. The abovementioned patterns are optimized for conventional channel estimators such as least squares-based channel estimators and minimum mean square error (MMSE) based channel estimators.

[0079] In the OFDM system, the received signal is distorted by the channel. The received signal at the ithsubcarrier and jthsymbol may be represented as equation (1) illustrated below:

[0080]

[0081] Here, Hi,j, Xi,jand Ni,jcorresponds to the channel coefficient, transmitted signal, and noise at the ithsubcarrier and the jthsymbol, respectively. To compensate for the distortions introduced in the received signal, there is a need to estimate the channel coefficients of the entire TF grid, . Using the pilots known to both transmitter and receiver, the channel coefficients at the pilot locations, , are first estimated, which are then used to estimate the complete channel response of the TF grid, . For better performance, estimated should be close to actual H, so that there are minimum errors while decoding the transmitted signal. Considering the channel estimator is represented by fCE(.), then for a fixed number of pilots, K, we need to minimize the error in the following expression (2) illustrated below:

[0082]

[0083] Figure 2 illustrates a block diagram of a system 200 for selecting pilot patterns for a channel estimation in a wireless communication network, in accordance with an embodiment of the present disclosure.

[0084] In an embodiment, the system 200 may be implemented on a device or a user device at a transmitting end or at a receiving end in the wireless communication network. The transmitting end may have a transmitter (Tx) 202 and the receiving end may have a receiver (Rx) 220. The Tx 202 may be communicatively coupled to the Rx 220 over a network 218 through a communication interface 216. In an embodiment, the Tx 202 or the Rx 220 may be configured to perform operations of the system 200 in the wireless communication network. The system 200 may include a processor 204, a display 206, a memory 208, which may belong to the Tx 202 or Rx 220 and may form a part of the Tx 202 or Rx 220. In an embodiment, the system 200 may be installed on the Tx 202, e.g., smart phone, tablet, laptop, computer, or other smart electronic devices that the user may be carrying.

[0085] The memory 208 may include an operating system 210, and a database 212 to store data. Further, the Tx 202 may include an Artificial Intelligence (AI) module 214 may be configured to perform the steps of the present disclosure using the data stored in the database 212. In an embodiment, each of the AI module 214 may be implemented as a hardware unit, a software unit, or a combination thereof. The AI module 214 may be outside the memory 208, within the memory 208, or a combination thereof.

[0086] The processor 204 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 204 may be configured to fetch and execute computer-readable instructions and data stored in the memory 208 and / or modules 214. At this time, the processor 204 may be a general-purpose processor, such as a central processing unit (CPU), an application processor (AP), or the like, and an AI-dedicated processor such as a neural processing unit (NPU). The processor 204 may control the processing of input data in accordance with a predefined operating rule or artificial intelligence (AI) model stored in the non-volatile memory and the volatile memory, i.e., the memory 208. The predefined operating rule or artificial intelligence model is provided through training or learning. Further, the processor 204 may be operatively coupled to each of the memory, the I / O Interface. The processor 204 may be configured to process, execute, or perform a plurality of operations described herein.

[0087] The memory 208 may include any non-transitory 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 208 is communicatively coupled with the processor to store processing instructions for completing the process. Further, the memory 208 may include the operating system 210 for performing one or more tasks of the system, as performed by a generic operating system 210 in a computing domain. The memory 208 is operable to store instructions executable by the processor 204.

[0088] In some embodiments, the Tx 202 may include a set of instructions that can be executed to cause the processor 204 of the Tx 202 to perform any one or more of the methods disclosed. The Tx 202 may operate as a standalone device or may be connected, e.g., using a network, to other computer systems or peripheral devices.

[0089] In a networked deployment, the Tx 202 may operate in the capacity of a server or as a client user computer in a server-client user network environment, or as a peer system in a peer-to-peer (or distributed) network environment. The Tx 202 can also be implemented as or incorporated across various devices, such as a personal computer (PC), a tablet PC, a personal digital assistant (PDA), a mobile device, a palmtop computer, a laptop computer, a desktop computer, a communications device, a wireless telephone, a land-line telephone, a web appliance, a network router, switch or bridge, or any other machine capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by that machine. Further, while a single Tx 202 is illustrated, the term “system” shall also be taken to include any collection of systems or sub-systems that individually or jointly execute a set, or multiple sets, of instructions to perform one or more computer functions.

[0090] As discussed, the Tx 202 may include the processor 204, e.g., a central processing unit (CPU), a graphics processing unit (GPU), or both. The processor 204 may be a component in a variety of systems. For example, the processor 204 may be part of a standard personal computer or a workstation. The processor 204 may be one or more general processors, digital signal processors, application-specific integrated circuits, field-programmable gate arrays, servers, networks, digital circuits, analog circuits, combinations thereof, or other now known or later developed devices for analyzing and processing data. The processor 204 may implement a software program, such as code generated manually (i.e., programmed).

[0091] As mentioned above, the Tx 202 may include the memory 208, such as a memory 208 that can communicate via a bus. The memory 208 may include, but is not limited to, computer-readable storage media such as various types of volatile and non-volatile storage media, including, but not limited to, random access memory, read-only memory, programmable read-only memory, electrically programmable read-only memory, electrically erasable read-only memory, flash memory, magnetic tape or disk, optical media and the like. In one example, memory 208 includes a cache or random-access memory for the processor 204. In alternative examples, the memory 208 is separate from the processor 204, such as a cache memory of a processor, the system memory, or other memory. The memory 208 may be an external storage device or database for storing data. The memory 208 is operable to store instructions 206 executable by the processor 204. The functions, acts or tasks illustrated in the figures or described may be performed by the programmed processor 204 for executing the instructions 206 stored in the memory 208. The functions, acts or tasks are independent of the particular type of instructions set, storage media, processor or processing strategy and may be performed by software, hardware, integrated circuits, firmware, micro-code and the like, operating alone or in combination. Likewise, processing strategies may include multiprocessing, multitasking, parallel processing and the like.

[0092] As shown, the Tx 202 may or may not further include the display 206, such as a liquid crystal display (LCD), an organic light-emitting diode (OLED), a flat panel display, a solid-state display, a cathode ray tube (CRT), a projector, a printer or other now known or later developed display device for outputting determined information. The display 206 may act as an interface for the user to see the functioning of the processor 204, or specifically as an interface with the software stored in the memory 208.

[0093] The present invention contemplates a computer-readable medium that includes memory 208 having executable instructions responsive to a propagated signal so that a device connected to the network 218 can communicate voice, video, audio, images, or any other data over the network 218. Further, the instructions 208 may be transmitted or received over the network 218 via the communication interface or port 120. The communication interface 120 may be a part of the processor 204 or maybe a separate component. The communication interface 120 may be created in software or maybe a physical connection in hardware. The communication interface 120 may be configured to connect with the network 218, external media, the display 210, or any other components in Tx 202, or combinations thereof. The connection with the network 218 may be a physical connection, such as a wired Ethernet connection or may be established wirelessly as discussed later. Likewise, the additional connections with other components of the Tx 202 may be physical or may be established wirelessly.

[0094] The network 218 may include wired networks, wireless networks, Ethernet AVB networks, or combinations thereof. The wireless network may be a cellular telephone network, an 802.11, 802.16, 802.20, 802.1Q or WiMax network. Further, the network 218 may be a public network, such as the Internet, a private network, such as an intranet, or combinations thereof, and may utilize a variety of networking protocols now available or later developed including, but not limited to, TCP / IP based networking protocols. The Tx 202 may not be limited to operation with any particular standards and protocols. For example, standards for Internet and other packet-switched network transmissions (e.g., TCP / IP, UDP / IP, HTML, and HTTP) may be used.

[0095] In an embodiment, the system 200, by the processor 204, may be employed for selecting pilot patterns for a channel estimation in the wireless communication network.

[0096] The processor 204 may be configured to receive, at the Rx 220, demodulation reference signals (DMRS) or channel state information (CSI) from a current wireless channel. Further, the processor 204 may be configured to determine, based on the estimated channel, a set of pilot patterns through the AI model 214. The AI model 214 may be trained based on online training or historical channel data and simulation results to enhance the accuracy of the selection of the pilot pattern.

[0097] The processor 204 may be configured to apply a masking layer to the set of pilot patterns to exclude resource element (RE) positions reserved for control signals or signals for other UE in multiple-input-multiple-output (MIMO) scenario.

[0098] Further, the processor 204 may be configured to select at least one pilot pattern among the set of pilot patterns based on correlating each of the set of pilot patterns and predefined performance parameters. In an embodiment, the predefined performance parameters comprise channel estimation error, interference minimization, signal-to-noise ratio (SNR), delay spread (DS), Doppler Spread (DoS), power delay profile (PDP), and Doppler spectrum.

[0099] The processor 204 may be configured to receive feedback from a transmitter (Tx) 202 based on transmitting the selected pilot pattern. The feedback indicates a compatibility correlation between the selected pilot pattern and a resource allocation for the Tx 202. The processor 204 may be configured to identify an optimal pilot pattern by adjusting the selected pilot pattern based on the received feedback from the transmitter for subsequent data transmissions.

[0100] In an embodiment, processor 204, may be configured to create a mask to apply the masking layer, that reflects current allocations of resource elements for control signals, and signals for the other UE in the MIMO scenario.

[0101] In an embodiment, the processor 204 may be configured to periodically or on-demand calculate the predefined performance parameters to ensure continued accuracy of the optimal pilot pattern and to account for long term channel variations. In an embodiment, the processor 204 may be configured to verify, via the AI model 214, the optimal pilot pattern to facilitate non-interference of the optimal pilot patterns with wireless network communication.

[0102] In an embodiment, the processor 204 may be configured to predict future channel conditions through a machine learning model and adjusting the pilot patterns based on the predicted future channel conditions. In an embodiment, the system 200, by the processor 204, may be employed for deploying pilot patterns in a wireless communication network.

[0103] The processor 204 may be configured to identify, at the Tx 202, the set of REs designated for pilot signal transmission based on a current resource allocation maps.

[0104] The processor 204 may be configured to select, at the Tx 202, a pilot pattern based on an optimal pilot pattern reported by the Rx 220 to align with the identified set of resource elements, or sending such information to the Rx 220 and the Rx 220 selecting a pilot pattern.

[0105] Further, the processor 204 may be configured to transmit the selected pilot pattern between the Tx 202 and the Rx 220. Further, the processor 204 may configure, at the Tx 202, a set of resource element slots to implement pilot pattern and transmit locations of the set of resource element slots in a time-frequency (TM) grid to the Rx 220.

[0106] Further, the processor 204 may be configured to issue, from the Tx 202, an activation command to the receiver to activate the selected pilot pattern. Further, the processor 204 may be configured to monitor, at the Tx 202 / Rx 220 202 / 220, a real-time channel conditions indicating a predefined performance parameters.

[0107] The processor 204 may be further configured to assess, at the Tx 202, receiver performance parameters indicative of the accuracy of channel estimation and interference levels based on feedback from the Rx 220. The processor 204 may be further configured to deploy, by the Tx 202, an updated pilot pattern to the Rx 220.

[0108] In an embodiment, the resource elements designated for pilot signal transmission are identified through an analysis of time and frequency-domain control signal distributions. In an embodiment, the processor 204 may be further configured to perform an interference assessment to ensure the selected pilot pattern minimizes cross-channel interference. In an embodiment, the processor 204 may be further configured to refine, based on current channel data or a historical performance database, the pilot pattern selection process. In an embodiment, the processor 204 may be further configured to schedule periodically or based on the Rx 220 reporting, updates to the pilot pattern based on predicted changes in the channel environment.

[0109] Figure 3 illustrates a flowchart depicting a method 300 of an iterative pilot pattern selection, in accordance with an embodiment of the present disclosure.

[0110] The method 300 depicts the iterative pilot pattern selection, wherein the goal is to determine pilot positions for a given set of channel parameters such as a delay spread (DS), a Doppler spread (DoS), a power delay profile (PDP), an SNR, and a Doppler spectrum, etc.

[0111] At step 302, the method 300 includes selecting K (number of nodes to be chosen by selector layer) to 1 and pilot locations are to be an empty set. At step 304, the ideal channel data or channel data with very SNR is obtained for a given set of channel parameters. At step 306, the K and the channel data are used to train a neural network for pilot pattern selection. The number of nodes to be selected at the selector layer, K is determined.

[0112] At Step 308, determine whether there are any repetitions in the selected K locations or if the channel estimations error is below a threshold. At step 310, if no repetitions are determined, update the pilot positions as chosen by the selector layer and at step 312 increment K by 1 and repeat from step 302. In case, if repetitions are determined, then at step 306, conclude the process and use the pilot locations as chosen in step 306.

[0113] In an embodiment, the iterative method for determining a number of pilots and pilot patterns, described previously may be very time-consuming in practical scenarios. Apart from the iterative method, other methods for choosing K and pilot pattern may include, modelling number of pilots, which may further include:

[0114] In one exemplary embodiment, a number of pilots K may be modelled to be an estimate of joint function such as illustrated in equation (3) below:

[0115]

[0116] or a combination of separate functions such as illustrated in equation (4) below:

[0117]

[0118] In another exemplary embodiment, the iterative search may be followed around a K estimate, reducing latency compared to starting from K=1.

[0119] A lookup table approach based on channel parameters may be used, such as the Delay spread, the Doppler, and the SNR, etc.

[0120] Figure 4 illustrates a schematic workflow depicting a network architecture 400 for pilot selection, in accordance with an embodiment of the present disclosure.

[0121] The network architecture 400 is used for the selection of the pilot. Firstly, a channel with m subcarrier frequency tones and n symbols is converted to a m X n X 2 real-valued vector by concatenating a real and imaginary parts depth-wise. Further, a transform layer 402 then converts the m X n X 2 vector into a m X n X 1 vector using 1 X 1 convolutional filters. The m X n X 1 vector is then flattened to form a 1D vector of size m*n. Moreover, a selector layer 404 then picks K nodes from the previous m*n nodes, which will be used for pilots. Furthermore, a decoder 406 estimates the channel (m X n X 2) from these K pilot nodes. The network is trained by minimizing an error between an actual channel and an estimated channel.

[0122] Figure 5 illustrates different variations of an architecture of the transform layer 402, in accordance with an embodiment of the present disclosure.

[0123] In an embodiment, the transform layer 402, irrespective of any variation, 1 X 1 convolutional filters are utilized, because during testing, only pilots are available and corresponding neighboring values may not be available. Further, the number of layers that may be used for the transform layer 402 is not limited. Hence, there may be multiple variations in the transform layer 402.

[0124] In an embodiment, a variation 1 comprises a single layer which further includes only 1 layer with only 1 filter of size 1 X 1 X 2, resulting in an output of size m X n X 1. Further, a variation 2 comprises two layers, which further include, a first layer has A filters of size 1 X 1 X 2 and a second layer has 1 filter of size 1 X 1 X A, resulting in an output of size m X n X 1. In an exemplary embodiment, A may be any natural number. Further, a variation 3 comprises a plurality of layers wherein a first layer’s filter size should be 1 X 1 X 2, and a last layer should incorporate only 1 filter of size 1 X 1 X G, where G corresponds to the depth of the signal in last but one layer, resulting in an output of size m X n X 1. In an embodiment, there may be any number of intermediate layers, for which the only constraint is to have only 1 X 1 filter.

[0125] Figure 6 illustrates schematic workflows depicting a plurality of decoder connection assemblies, in accordance with an embodiment of the present disclosure.

[0126] Case A in Figure 6 depicts a general decoder 406 architecture converting K pilots to estimated time-frequency grid. Case B in Figure 6 depicts decoders 406 with fully connected layers, wherein, a K channel coefficient as obtained from the selector layer is used as an input. Further, a single or multiple fully connected layers may be used such that the last layer consists of m*n*2 output nodes, which are then reshaped to a m X n X 2. The resulting m X n X 2 vector is then an estimated channel coefficient of a TF grid. Moreover, Case C in Figure 6 depicts a decoder 406 based on an NN channel estimator. In this case, the final m X n X 2 vector is further processed through convolutional filters to obtain the estimated channel coefficients of the TF grid.

[0127] As discussed earlier, in conjunction with Figure 3, the training mechanism of the neural network for pilot selection may be further explained. The input to the neural network is the channel coefficients of the complete TF grid H. Further, let K be the number of pilots, wherein, {pi|1≤i≤K}, corresponds to selected pilot locations as selected at the selector layer and Hpcorresponds to the channel coefficients at these pilot locations. Moreover, consider the decoder block is represented by fDec(.) which is learned using the decoder network. Then, for a fixed number of pilots, K, the network is required to be trained to minimize the error illustrated in equation (5) below:

[0128]

[0129] Further, an error metric is also generated in correspondence to the training mechanism, wherein, a complete TF grid H may not be available in a practical system scenario. Further, let Hmmsebe a channel estimated through a conventional MMSE channel estimator, wherein the error metric is illustrated in equation (6) below:

[0130]

[0131] Figure 7 illustrates a schematic workflow depicting a method 700 for constraining pilot locations, in accordance with an embodiment of the present disclosure.

[0132] The method 700 may be implemented at the Rx 220 for constraining the pilot locations such that the pilot locations may not interfere with the locations of other control signals. The method 700 may be a deep learning-based approach that may choose the pilot locations from anywhere in the TF grid, however, there may be some locations that are already reserved for other control signals such as a PT-RS, etc. Also, in the case of a MIMO, the selection of pilot locations may be controlled. In an embodiment, at least three approaches may be provided for restriction of the pilot locations while selecting pilots during training, which may include but are not limited to a masking layer 702, a regularization term and a manual adaptation as a post-processing step.

[0133] The masking layer 702 may be applied at different phases during the process in two stages. A first stage may be the masking layer 702 in between layers of the selector 404 and the decoder 406. A second stage may be the masking of the input for data pre-processing. The first stage and the second stage may be described in greater detail in the following paragraphs.

[0134] The first stage may include the masking layer 702 to be inserted after the selector layer 404, which nullifies the effect of the chosen pilot in the reconstruction of the channel using the decoder layer 406. Let H correspond to the channel coefficients of the entire TF grid, which is used as input to the network. Let {pi|1≤i≤K} corresponds to the selected pilot locations as selected at the selector layer 404, and the pilots HP. Let, Hkmpcorrespond to the channel coefficients at the pilot locations which are selected after the masking layer 702 by removing the pilots corresponding to pre-reserved locations in Hp. Further, considering the decoder block may be represented by fDec(.) is learned using the decoder 406, then for a fixed number of pilots, K, the network needs to be trained to minimize the error illustrated in equation (7) below.

[0135]

[0136] The second stage may include the masking layer 702 for the pre-processing of input is disclosed. In the second stage, the pre-reserved locations input signal is nullified while training the network, thus removing the information present at reserved resource elements (REs). Let H correspond to the channel coefficients of the entire TF grid. First, the channel coefficients at the pre-reserved locations are nullified to obtain Hm. Then, this Hmmay be used as the input to the network, illustrated in equation (8) below.

[0137]

[0138] Let {pi|1≤i≤K} corresponds to the selected pilot locations as selected at the selector layer 404 and Hmpcorresponds to the channel coefficients at these pilot locations. Consider the decoder block is represented by fDec(.) is learned using the decoder 406. Then, for a fixed number of pilots, K, the network needs to be trained to minimize the error , illustrated in equation (9) below.

[0139]

[0140] The second approach may include the regularization term. In this approach, a cost function is redefined to penalize the network when selecting the pilots at reserved RE locations during training. Let H correspond to the channel coefficients of the entire TF grid. Let {pi|1≤i≤K} corresponds to pilot locations and Hmpcorresponds to their channel coefficients. Let P be the pilot matrix such that, illustrated in equation (10) below:

[0141]

[0142] Let {m} be the set of reserved REs and M be reserved matrix such that, illustrated in equation (11) below:

[0143]

[0144] Then, for a fixed number of pilots, K, the network needs to be trained to minimize the error illustrated in equation (12) below:

[0145]

[0146] Figure 8 illustrates a flowchart depicting a method 800 of manual adaptation as a post-processing step of constraining pilot location, in accordance with an embodiment of the present disclosure.

[0147] The method 800 depicting the manual adaptation flow as a post-processing step corresponds to the third approach for restriction of the pilot locations while selecting pilots during training.

[0148] At step 802, the pilot locations {pi|1≤i≤K} may be obtained by running a default algorithm (network architecture 400) without any constraints. At step 804, the method 800 may determine whether any of the pilot locations are interfering with the reserved locations {m}, a manual adjustment of their positions is done so that the selected pilot locations and reserved pilot locations are disjoint sets. Further, let {si|1≤i≤K} corresponds to the final required pilot locations, illustrated in equation (13) below:

[0149]

[0150] In one case, the method 800 may determine that the pilot pattern may be interfering with the reserved REs. In this case, the method 800 may proceed to step 806 to apply manual adaptation. In an embodiment, the manual adaptation approach is useful with a pre-trained model, so that model training need not be done on the fly. In case, the manual adaptation is required to adjust the pilot locations to restrict them to either a few symbols or a few subcarrier tones. The manual adaptation may be done by forcing the locations which are sparsely populated in a symbol or subcarrier tone using nearest neighbour method. In an embodiment, the manual adaptation approach helps in scaling the proposed solution to MIMO channel estimation. In another case, the method 800 may determine that the pilot pattern may not be interfering with the reserved REs. In this case, the method 800 may proceed to step 808 to obtain a final pilot pattern.

[0151] In an embodiment, a decision for a pilot pattern selection may be made by both the Tx 202 and the Rx 220. The pilot pattern selection also includes information exchange between the Tx 202 and the Rx 220 that may be required to make a decision on the pilot pattern in case some information needs to be exchanged with the other side, i.e., either the Tx 202 or the Rx 220. For example, the restricted pilot locations are known to the Tx 202, and if the Tx 202 is selecting the final pilot pattern, then the Tx 202 may need to send the pilot location information to the Rx 220.

[0152] Figure 9 illustrates a flowchart depicting a method 900 for determining a best pilot pattern (BPP) using the Rx 220 considering reserved control signals, in accordance with an embodiment of the present disclosure.

[0153] The method 900 includes a determination of the final BPP by using the masking layer 702 at the Rx 220. In an embodiment, no pilots are chosen at locations that are reserved for other control signals such as phase tracking reference signal (PTRS). In an embodiment, the masking layer 702 may be used for avoiding conflicts between the pilot pattern locations and the reserved REs locations.

[0154] Further, the Tx 202 may need to provide information to the Rx 220 regarding the reserved REs {m} through a radio resource control (RRC) or a synchronization channel (SCH). Moreover, the reserved RE information may be used by the Rx 220 during the training process. This may make sure that the pilot pattern {t} obtained through the training and the reserved REs {m} are disjoint sets. The Rx 220 may then transmit the best pilot {t} pattern (BPP) to the Tx 202 for further scheduling.

[0155] In an embodiment, the Rx 220 may be configured to determine the BPP through the regularization term approach. As discussed earlier, the method 900, the Tx 202 may need to provide information to the Rx 220 regarding reserved REs {m} through the RRC or the SCH. Then, the reserved RE information may be used by the Rx 220 in the cost function during the training process. This will make sure that the pilot pattern {t} obtained through the training and the reserved REs {m} are disjoint sets. The Rx 220 may then report its best pilot {t} pattern to the Tx 202 for further scheduling.

[0156] In an embodiment, the Rx 220 may be configured to perform the manual adaptation. The Rx 220 may choose the pilot pattern {pi|1≤i≤K}, corresponding to the selected pilot locations as selected at the selector layer. The Tx 202 may provide information to the Rx 220 regarding reserved REs {m} through the RRC or the SCH. Further, the Rx 220 may compute a final pilot pattern {s} through manual adaptation as mentioned in method 900.

[0157] In an embodiment, sets {s} and {m} being disjointed may ensure there are no conflicts present. Finally, the Rx 220 may report the best pilot pattern {s} to the Tx 202 for further scheduling.

[0158] Figure 10 illustrates a flowchart depicting a method 1000 for determining the BPP using the Tx 202 considering reserved control signals, in accordance with an embodiment of the present disclosure.

[0159] The method 1000 depicts a determination of a final BPP through the manual adaptation at the Tx 202. It may be noted that the manual adaptation needs to be done as a post-processing step as mentioned in the method 800 while conflicts present between the pilot pattern and the reserved REs. The manual adaptation may be performed on the best pilot pattern {pi|1≤i≤K} reported by the Rx 220 to the Tx 202, at step 1002.

[0160] At step 1004, the Tx 202 may prepare a set of reserved REs {m}, which may contain other control signals for the same Rx 220, or DMRS and control signals for the other Rx 220, where the Tx 202 may not allow to schedule DMRS for the Rx 220. Let {si|1≤i≤K} corresponds to the final required pilot locations, illustrated in equation (14) below:

[0161]

[0162] Further, the sets {s} and {m} being disjointed may ensure there are no conflicts present. At step 1006, the Tx 202 may decide the final pilot pattern, i.e., the BPP through the manual adaptation. Successively, at step 1008, the Tx 202 may report a final pilot pattern {s}, i.e., the BPP, to the Rx 220 for further usage.

[0163] Figure 11 illustrates a flowchart depicting a method 1100 for deciding channel estimator at the Rx 220, in accordance with an embodiment of the present disclosure.

[0164] The method 1100 may be implemented on an algorithm to obtain the BPP through a decoder architecture, channel conditions, or number of pilots (K).

[0165] In an embodiment, the decoder architecture may be used as the channel estimator by the Rx 220 for decoding the transmitted signals. Thus, in the case of multiple channel estimator’s scenario, the BPP may also change with respect to each channel estimator. In an embodiment, during the pilot pattern changes, an associated channel estimator (AI-CE) model needs to be used by the Rx 220 for channel estimation for proper decoding.

[0166] In an embodiment, a best fit AI-CE model selection may be determined through a following algorithm. Let {pi|1≤i≤K}, be the current BPP and K be the number of pilots. Let {Pilot patterns, AI-CE models} be the set of BPPs under different channel conditions and their associated channel estimator models. Then given K, {sj,CEj} maybe the chosen with same number of pilots K such that, illustrated in equation (15) below:

[0167]

[0168] At last, the best fit channel estimator CEjmay be chosen such that, illustrated in equation (16) below:

[0169]

[0170] The method 1100 may be used in downlink / uplink (DL / UL) scenarios. At step 1102, the Rx 220 may be configured to select the final BPP. Further, at step 1104, the Rx 220 may fetches a set of pilot patterns and models from the memory 208. The Rx 220 may a set of {Pilot patterns, AI-CE models} available in the memory 208. In an embodiment, under the current channel conditions, the Rx 220 may obtain the BPP and then select the AI-CE model from the memory 208 through the best fit AI-CE model selection. At step 1106, the Rx 220 may decide channel estimation based on the AI-CE model selection. Further, the AI-CE model present in the memory 208 may be used directly, thus reducing latency.

[0171] Figure 12 illustrates a flowchart depicting a method 1200 for deciding channel estimator at the Tx 202, in accordance with an embodiment of the present disclosure.

[0172] The method 1200 depicts the channel estimator decided by the Tx 202. In an embodiment, the Tx 202 may act as a base station (BS) and the Rx 220 may act as a user equipment (UE) and hereinafter may be used interchangeably.

[0173] The method 1200 may be helpful in case of the DL scenario, in which the BS may store a larger set of {Pilot patterns, AI-CE models} in the memory 208 than the UE. In an embodiment, under the current channel conditions, the BS may use the BPP for the UE. At step 1202, the UE, i.e., Rx 220, may transmit a request containing report of the BPP.

[0174] Further, at steps 1204-1206, the BS may select the AI-CE model from the memory 208 through the best fit AI-CE model selection. At step 1208, the BS may be configured to transmit the AI-CE model to the UE through the RRC or the SCH channel. The AI-CE model may be used for the channel estimation by the UE. In an embodiment, the number of AI-CE models stored may be very large, and channel accuracy may be improved by selecting the best possible model.

[0175] Figure 13 illustrates a flowchart depicting a method 1300 of optimal pilot pattern selection, wherein the UE utilizes reserved REs and selects the AI-CE model for channel estimation, in accordance with an embodiment of the present disclosure.

[0176] In an embodiment, the deployment procedure of signal flow between the BS and the UE may be performed in at least five different scenarios. Figures 13-16 describe the at least five different scenarios.

[0177] At step 1302, the UE may attach a standard pilot pattern. At step 1304, the BS sends high density RE slot for the UE. In an embodiment, during attach or a pilot pattern monitor, using a conventional pilot pattern, the BS sends a large number of known symbols in a slot to the UE. The high-density RE slot may be used by the UE for an ideal H estimation for the current channel conditions. At step 1306, the UE may compute the best pilot pattern. In an embodiment, the BPP may be computed using the methods 900-1200 mentioned earlier.

[0178] At step 1308, the method 1300 may determine whether the pilot pattern is conflicting with the reserved REs. In an embodiment, to resolve any conflicts between the pilot pattern and the reserved REs, the UE may use the masking layer 702, the regularization term, or the manual adaptation approaches to obtain the final pilot pattern. In one case, the method 1300 may determine that the pilot pattern is conflicting with the reserved REs. In this case, the UE may modify the BPP to avoid overlap with the reserved RE locations and corresponding to one of the AI-CE models from the memory 208, at step 1310. In another case, the method 1300 may determine that the pilot pattern is not conflicting with the reserved REs. In this case, the UE may transmit the BPP to the BS, at step 1312.

[0179] In an embodiment, the UE also selects one of the AI-CE models from its memory as the channel estimator using the method 1000. At step 1314, the BS may signal the final BPP pattern to be used for data transmission to the UE. The UE may start using the final pilot pattern for the DMRS reception and use the final pilot pattern for further scheduling. In an embodiment, the UE may use the final pilot pattern till the next pilot pattern monitors timing.

[0180] Figure 14 illustrates a flowchart depicting a method 1400 of optimal pilot pattern selection, wherein the UE handles the reserved REs and the BS transmits the AI-CE model for the channel estimation to the UE, in accordance with an embodiment of the present disclosure. Figure 14 is described in conjunction with Figures 1-13.

[0181] In an embodiment, the steps 1302 to 1312 as discussed above in conjunction with Figure 13 remain same for the implementation of the method 1400.

[0182] At step 1402, the BS selects one of the AI-CE models from the memory 208 as a channel estimator using the method 1300 and transmits the selected AI-CE model to the UE. At step 1404, the UE may download the transmitted AI-CE model for the channel estimation. Successively, the step 1314 of the method 1300 remain same for the method 1400.

[0183] Figure 15 illustrates a flowchart depicting a method 1500 of optimal pilot pattern selection, wherein the BS handles the reserved REs and transmits the AI-CE model to the UE, in accordance with an embodiment of the present disclosure.

[0184] In one embodiment, the steps 1302 to 1306 and step 1312 as discussed above in conjunction with Figure 13 remain same for the implementation of the method 1500. At step 1502, the BS modifies the BPP to avoid overlap with reserved RE locations, if any. Further, the steps 1402 to 1404 as discussed above in conjunction with Figure 14 remain same for the implementation of the method 1500. Successively, the step 1314 of the method 1300 remain same for the method 1500 and omitted herein for the sake of brevity.

[0185] Figure 16 illustrates a flowchart depicting a method 1600 of optimal pilot pattern selection, wherein the BS handles the reserved REs and the UE selects the AI-CE model, in accordance with an embodiment of the present disclosure.

[0186] In one embodiment, the steps 1302 to 1304 as discussed above in conjunction with Figure 13 remain same for the implementation of the method 1500. At step 1602, the UE may compute the BPP and use one of the AI-CE models from the memory 208. Further, the steps 1312, 1502, and 1314 may remain same as discussed in conjunction with methods 1300 and 1500 respectively.

[0187] As discussed earlier, a fifth scenario may be discussed in conjunction with Figures 13-16. In an embodiment, the fifth scenario may extend over to the current 3GPP standards. In this scenario, a set of pilot patterns is restricted to 3GPP supported by the conventional DMRS patterns. The UE computes the BPP {pi|1≤i≤K} using the methods as mentioned above in conjunction with Figures 13-16. Further, a final pilot pattern {si|1≤i≤K} is computed as illustrated in equation (17) below:

[0188]

[0189] The UE may send the information on the final pilot pattern to the BS. In an embodiment, the BS, based on the UE feedback, may select parameters such as the DMRS frequency density and the number of symbols with the DMRS during transmission in a slot. In this scenario, the UE may use the standard channel estimators such as the Linear Minimum Mean Square Error (LMMSE), and Least Square Error (LSE).

[0190] In an exemplary embodiment, the pilot patterns may be required to be known by the BS and the UE so that the pilot patterns may be used for channel estimation to ensure the proper working of the wireless communication systems. In an embodiment, when either of the Tx 202 / Rx 220 may decide to select a new pilot pattern. The selected new pilot pattern may be reported to the other side of the wireless communication system. In an embodiment, the procedures related to the selection of pilot patterns between BS and UE may be based on dimensions, such as BPP reporting, i.e., how the information of pilot patterns is to be shared between the BS and the UE. Two procedures for pilot pattern information transfer include index based BPP reporting, and bit map based BPP reporting. Further, another dimension such as BPP monitoring, i.e., how frequently the pilot pattern information exchange should happen. In an embodiment, the frequency of pilot pattern exchange may be decided by the Tx 202 or the Rx 220.

[0191] In an embodiment, the index-based BPP reporting is useful when there are a small number of predetermined pilot patterns, which are shared / known to both the Tx 202 and the Rx 220. In an embodiment, only an index number of the pilot pattern may be shared at any time for the BPP reporting. For instance, let K be the number of the pilot locations and mn be the time-frequency grid size, then total possible pilot patterns will be . Thus, the number of bits needed for the BPP reporting would be log2 . In an embodiment, the BPP reporting may have a lower scheduling overhead.

[0192] In another embodiment, in the bitmap based BPP reporting, a bit map of the full time-frequency (TF) grid with the pilot locations set as 1 may be shared for the BPP reporting, making the number of bits needed to be mn. Further, there is no limit on the number of possible pilot patterns. In an embodiment, a higher scheduling overhead compared to index-based reporting may be presented by the BPP reporting.

[0193] Figure 17 illustrates a flowchart depicting method 1700 of the BPP monitoring procedure, in accordance with an embodiment of the present disclosure.

[0194] The method 1700 depicts a Tx 202-based periodic BPP monitoring as well as the UE-based BPP monitoring. In an embodiment, the Tx 202 may configure the Rx 220 through the RRC for the high-density RE slot to be received with a certain periodicity. The Rx 220 may calculate the BPP from the ideal H and the channel conditions and then report to the Tx 202. Further, the UE may be configured to monitor the channel conditions and request the BS to configure the high-density RE slot based on certain triggers, for example, a mobility condition change for the UE, the SNR change, a movement from indoor to outdoor or vice-versa.

[0195] At step 1702, the BS 202 may configure 1 bit resource for the BPP to the UE. At step 1704, the UE responds with a request for the BPP computation. In an embodiments, the steps 1702-1704 may happen in case of the UE based BPP monitoring. At step 1706, the BS 202 schedules high density RE slot. Further, at step 1708, the UE may compute the BPP. Further, at step 1710, the UE responds to the BS 202 by reporting the BPP to the BS 202. At step 1712, the BS 202 may send an activation command for the new pilot pattern to the UE.

[0196] Figure 18 illustrates a graph 1800 for channel estimation as a function of SNR, in accordance with an embodiment of the present disclosure.

[0197] The simulation setup includes a Channel - CDL-A, DS - 1000 ns, DoS - 150 Hz, Number of RBs - 2 - 24 rows, and Number of Slots - 1 - 14 columns. Further, the Performance of the proposed algorithm is much better than using the conventional pilot pattern with an AI-based channel estimator (ChannelNet). The Channel estimation error observed is close to the Ideal LMMSE scenario, which uses ideal second-order statistics and represents the lower bound of error. Even with reduced pilot pattern, the proposed algorithm performs better, indicating more REs may be used for data transmission increasing throughput.

[0198] Figure 19 illustrates a graph 1900 for pilot positions with respect to a number of pilots with DS - 1000ns and DoS - 125Hz, in accordance with an embodiment of the present disclosure. Figure 20 illustrates a graph 2000 for pilot positions with respect to a number of pilots with DS - 1000ns and DoS - 250Hz, in accordance with an embodiment of the present disclosure. Figure 21 illustrates a graph 2100 for pilot positions with respect to a number of pilots with DS - 1000ns and DoS - 500Hz, in accordance with an embodiment of the present disclosure. Figure 22 illustrates a graph 2200 for pilot positions with respect to a number of pilots with DS - 10 ns and DoS - 250Hz, in accordance with an embodiment of the present disclosure. Figure 23 illustrates a graph 2300 for pilot positions with respect to a number of pilots with DS - 300 ns and DoS - 250Hz, in accordance with an embodiment of the present disclosure. For the sake of brevity, Figure 18 to Figure 22 have been explained together.

[0199] In an embodiment, for the higher DS, the channel characteristics vary fast in a frequency domain (vertical), and for the higher DoS, the channel characteristics vary fast in the time domain (Horizontal). The pilots picked by the proposed method are in alignment with the expectations mentioned above. For higher DoS and lower DS, the pilots are more densely populated in the horizontal direction, as seen with the DS 10 ns and DoS 250 HZ. For lower DoS and higher DS, the pilots are more densely populated in the vertical direction, as seen with the DS 1000 ns and the DoS 125 Hz. When both the DS and the DoS are higher, the pilots are spread across in both directions. When the channel is more static (DS or DoS being very low), repetitions are observed in the pilots picked for pilot number less than the conventional systems itself, which means that adding more pilots may not have much of an impact. When the channel is fast-varying, it is observed that there are no repetitions indicating there are still positions used which can still improve the channel estimate.

[0200] Figure 24 illustrates graphs 2400 of Fixed pilots versus Different channels, in accordance with an embodiment of the present disclosure. In most cases, the pilot structure is evident. Only for the 1000 ns and 500 Hz, the pattern is not clear, which indicates these pilots may not be sufficient for reconstructing the channel effectively. But as the number of pilots is increased from 10 to 12, the structure is slowly becoming evident as seen below.

[0201] Figure 25 illustrates a flowchart depicting a method 2500 for selecting pilot patterns for a channel estimation in a wireless communication network, in accordance with an embodiment of the present disclosure.

[0202] At step 2502, the method 2500 includes receiving, at a receiver (Rx) 220, demodulation reference signals (DMRS) or channel state information (CSI) from a current wireless channel.

[0203] At step 2504, the method 2500 includes determining, based on the estimated channel, a set of pilot patterns through the AI model 214. At step 2506, the method 2500 includes applying the masking layer 702 to the set of pilot patterns to exclude resource element (RE) positions reserved for control signals, or signals for other user equipment (UE) in multiple-input-multiple-output (MIMO) scenario. The AI model is trained based on online training or historical channel data and simulation results to enhance accuracy of selection of pilot pattern.

[0204] At step 2508, the method 2500 includes selecting at least one pilot pattern among the set of pilot patterns based on correlating each of the set of pilot patterns and predefined performance parameters. The predefined performance parameters comprise channel estimation error, interference minimization, signal-to-noise ratio (SNR), delay spread (DS), Doppler Spread (DoS), power delay profile (PDP), and Doppler spectrum.

[0205] At step 2510, the method 2500 includes receiving feedback from the Tx 202 based on transmitting the selected pilot pattern. The feedback indicates compatibility correlation between the selected pilot pattern and a resource allocation of the Tx 202. At step 2512, the method 2500 includes identifying an optimal pilot pattern by adjusting the selected pilot pattern based on the received feedback from the transmitter for subsequent data transmissions.

[0206] In an embodiment, the method 2500 includes applying the masking layer includes creating a mask that reflects current allocations of resource elements for control signals, and signals for the other UE in the MIMO scenario. In an embodiment, the method 2500 includes periodically or on-demand calculating the predefined performance parameters to ensure continued accuracy of the optimal pilot pattern and to account for long term channel variations.

[0207] In an embodiment, the method 2500 includes verifying, via the AI model, the optimal pilot pattern to facilitate non-interference of the optimal pilot patterns with wireless network communication. In an embodiment, the method 2500 includes predicting future channel conditions through a machine learning model and adjusting the pilot patterns based on the predicted future channel conditions.

[0208] Figure 26 illustrates a flowchart depicting a method 2600 for deploying pilot patterns for a channel estimation in the wireless communication network, in accordance with an embodiment of the present disclosure

[0209] At step 2602, the method 2600 includes identifying, at the Tx 202 a set of resource elements (REs) designated for pilot signal transmission based on a current resource allocation map. At step 2604, the method 2600 includes selecting, at the Tx 202, a pilot pattern based on an optimal pilot pattern reported by the Rx 220 to align with identified set of resource elements or sending such information to Rx 220 and Rx 220 selecting a pilot pattern. The set of resource element slots correspond to high-density resource element slots that are chosen to minimize channel estimation error while maintaining compliance with network protocols.

[0210] At step 2606, the method 2600 includes transmitting the selected pilot pattern between Tx 202 and Rx 220. At step 2608, the method 2600 includes configuring, at the Tx 202, a set of resource element slots to implement pilot pattern and transmit locations of the set of resource element slots in a time-frequency (TM) grid to the Rx 220.

[0211] At step 2610, the method 2600 includes issuing, from the Tx 202, an activation command to the receiver to activate the selected pilot pattern. The activation command includes synchronization information to align demodulation process of the receiver with a new pilot pattern. At step 2612, the method 2600 includes monitoring, at the Tx 202 / Rx 220, a real-time channel conditions indicating a predefined performance parameter. The predefined performance parameters comprise signal-to-noise ratio (SNR), delay spread (DS), Doppler Spread (DoS), power delay profile (PDP), and Doppler spectrum. At step 2614, the method 2600 includes assessing, at the Tx 202, receiver performance parameters indicative of accuracy of channel estimation and interference levels based on feedback from the Rx 220. At step 2616, the method 2600 includes deploying, by the Tx 202, an updated pilot pattern to the Rx 220.

[0212] In an embodiment, the resource elements designated for pilot signal transmission are identified through an analysis of time and frequency-domain control signal distributions.

[0213] In an embodiment, the method 2600 includes performing an interference assessment to ensure the selected pilot pattern minimizes cross-channel interference. In an embodiment, the method 2600 includes refining, based on current channel data or a historical performance database, the pilot pattern selection process. In an embodiment, the method 2600 includes scheduling periodically or based on Rx 220 reporting, updates to the pilot pattern based on predicted changes in channel environment.

[0214] Figure 27 is a block diagram of an internal configuration of a UE, according to an embodiment. Furthermore, the UE of Figure 27 corresponds to the transmitter (Tx) or the receiver (Rx) of Figure 2.

[0215] As shown in Figure 27, the UE according to an embodiment may include a transceiver 2710, a memory 2720, and a processor 2730. The transceiver 2710, the memory 2720, and the processor 2730 of the UE may operate according to a communication method of the UE described above. However, the components of the UE are not limited thereto. For example, the UE may include more or fewer components than those described above. In addition, the processor 2730, the transceiver 2710, and the memory 2720 may be implemented as a single chip. Also, the processor 2730 may include at least one processor.

[0216] The transceiver 2710 collectively refers to a UE receiver and a UE transmitter, and may transmit / receive a signal to / from a base station or a network entity. The signal transmitted or received to or from the base station or a network entity may include control information and data. The transceiver 2710 may include a RF transmitter for up-converting and amplifying a frequency of a transmitted signal, and a RF receiver for amplifying low-noise and down-converting a frequency of a received signal. However, this is only an example of the transceiver 2710 and components of the transceiver 2710 are not limited to the RF transmitter and the RF receiver.

[0217] Also, the transceiver 2710 may receive and output, to the processor 2730, a signal through a wireless channel, and transmit a signal output from the processor 2730 through the wireless channel.

[0218] The memory 2720 may store a program and data required for operations of the UE. Also, the memory 2720 may store control information or data included in a signal obtained by the UE. The memory 2720 may be a storage medium, such as read-only memory (ROM), random access memory (RAM), a hard disk, a CD-ROM, and a DVD, or a combination of storage media.

[0219] The processor 2730 may control a series of processes such that the UE operates as described above. For example, the transceiver 2710 may receive a data signal including a control signal transmitted by the base station or the network entity, and the processor 2730 may determine a result of receiving the control signal and the data signal transmitted by the base station or the network entity.

[0220] Figure 28 is a block diagram of an internal configuration of a base station or a network entity, according to an embodiment. Furthermore, the base station or the network entity of the Figure 28 corresponds to the transmitter (Tx) or the receiver (Rx) of the Figure 2.

[0221] As shown in Figure 28, the base station or the network entity according to an embodiment may include a transceiver 2810, a memory 2820, and a processor 2830. The transceiver 2810, the memory 2820, and the processor 2830 of the base station or the network entity may operate according to a communication method of the base station or the network entity described above. However, the components of the base station or the network entity are not limited thereto. For example, the base station or the network entity may include more or fewer components than those described above. In addition, the processor 2830, the transceiver 2810, and the memory 2820 may be implemented as a single chip. Also, the processor 2830 may include at least one processor.

[0222] The transceiver 2810 collectively refers to the base station(or the network entity receiver) and a base station(or the network entity) transmitter, and may transmit / receive a signal to / from a terminal or a network entity or a base station. The signal transmitted or received to or from the terminal or a network entity or the base station may include control information and data. The transceiver 2810 may include a RF transmitter for up-converting and amplifying a frequency of a transmitted signal, and a RF receiver for amplifying low-noise and down-converting a frequency of a received signal. However, this is only an example of the transceiver 2810 and components of the transceiver 2810 are not limited to the RF transmitter and the RF receiver.

[0223] Also, the transceiver 2810 may receive and output, to the processor 2830, a signal through a wireless channel, and transmit a signal output from the processor 2830 through the wireless channel.

[0224] The memory 2820 may store a program and data required for operations of the base station or the network entity. Also, the memory 2820 may store control information or data included in a signal obtained by the base station or the network entity. The memory 2820 may be a storage medium, such as read-only memory (ROM), random access memory (RAM), a hard disk, a CD-ROM, and a DVD, or a combination of storage media.

[0225] The processor 2830 may control a series of processes such that the base station or the network entity operates as described above. For example, the transceiver 2810 may receive a data signal including a control signal transmitted by the terminal or the network entity or the base station, and the processor 2830 may determine a result of receiving the control signal and the data signal transmitted by the terminal or the network entity or the base station.

[0226] Although specific units / modules have been illustrated in the figure and described above, it should be understood that the system may include other hardware modules or software modules or combinations as may be required for performing various functions.

[0227] The various embodiments described above are provided by way of illustration only and should not be construed to limit the scope of the disclosure. Various modifications and changes may be made to the principles described herein without following the example embodiments and applications illustrated and described herein, and without departing from the spirit and scope of the disclosure.

[0228] Those skilled in the art will appreciate that the operations described herein in the present disclosure may be carried out in other specific ways than those set forth herein without departing from essential characteristics of the present invention. The above-described embodiments are therefore to be construed in all aspects as illustrative and not restrictive. The scope of the invention should be determined by the appended claims, not by the above description, and all changes coming within the meaning of the appended claims are intended to be embraced therein.

[0229] 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.

[0230] 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.

[0231] 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.

Claims

1.A method for selecting pilot patterns for a channel estimation in a wireless communication system, the method comprising:receiving, at a receiver (Rx), demodulation reference signals (DMRS) or channel state information (CSI) from a current wireless channel;determining, based on the estimated channel, a set of pilot patterns through an artificial intelligence (AI) model;applying, a masking layer to the set of pilot patterns to exclude resource element (RE) positions reserved for control signals, or signals for other user equipment (UE) in multiple-input-multiple-output (MIMO) scenario;selecting, at least one pilot pattern among the set of pilot patterns based on correlating each of the set of pilot patterns and predefined performance parameter;receiving, a feedback from a transmitter (Tx) based on transmitting the selected pilot pattern, wherein the feedback indicates compatibility correlation between the selected pilot pattern and a resource allocation of the Tx; andidentifying, an optimal pilot pattern by adjusting the selected pilot pattern based on the received feedback from the transmitter for subsequent data transmissions.2.The method of claim 1, wherein the predefined performance parameters comprise channel estimation error, interference minimization, signal-to-noise ratio (SNR), delay spread (DS), Doppler Spread (DoS), power delay profile (PDP), and Doppler spectrum.3.The method of claim 1, wherein applying the masking layer comprises:creating a mask that reflects current allocations of resource elements for control signals, and signals for the other UE in the MIMO scenario.4.The method of claim 1, comprising:periodically or on-demand calculating the predefined performance parameters to ensure continued accuracy of the optimal pilot pattern and to account for long term channel variations.5.The method of claim 1, wherein the AI model is trained based on online training or historical channel data and simulation results to enhance accuracy of selection of pilot pattern.6.The method of claim 1, comprising:verifying, via the AI model, the optimal pilot pattern to facilitate non-interference of the optimal pilot patterns with wireless network communication.7.An apparatus for selecting pilot patterns for a channel estimation in a wireless communication system, comprising:a memory; anda processor communicatively coupled with the memory, wherein the processor is configured to:receive, at a receiver (Rx), demodulation reference signals (DMRS) or channel state information (CSI) from a current wireless channel;determine, based on the estimated channel, a set of pilot patterns through an artificial intelligence (AI) model;apply a masking layer to the set of pilot patterns to exclude resource element (RE) positions reserved for control signals, or signals for other user equipment (UE) in multiple-input-multiple-output (MIMO) scenario;select, at least one pilot pattern among the set of pilot patterns based on correlating each of the set of pilot patterns and predefined performance parameter;receive a feedback from a transmitter (Tx) based on transmitting the selected pilot pattern, wherein the feedback indicates compatibility correlation between the selected pilot pattern and a resource allocation of the Tx; andidentify an optimal pilot pattern by adjusting the selected pilot pattern based on the received feedback from the transmitter for subsequent data transmissions.8.A method of deploying pilot patterns in a wireless communication network, the method comprising:identifying, at a transmitter (Tx), a set of resource elements (REs) designated for pilot signal transmission based on a current resource allocation maps;selecting, at the Tx a pilot pattern based on an optimal pilot pattern reported by a receiver (Rx) to align with identified set of resource elements, or sending such information to the Rx and the Rx selecting a pilot pattern;transmitting, the selected pilot pattern between the Tx and the Rx;configuring, at the Tx, a set of resource element slots to implement pilot pattern and transmit locations of the set of resource element slots in a time-frequency (TM) grid to the Rx ;issuing, from the Tx, an activation command to the receiver to activate the selected pilot pattern;monitoring, at the Tx / Rx, a real-time channel conditions indicating a predefined performance parameters;assessing, at the Tx, receiver performance parameters indicative of accuracy of channel estimation and interference levels based on feedback from the Rx; anddeploying, by the Tx, an updated pilot pattern to the Rx.9.The method of claim 8, wherein the resource elements designated for pilot signal transmission are identified through an analysis of time and frequency-domain control signal distributions.10.The method of claim 8, comprising:performing an interference assessment to ensure that the selected pilot pattern minimizes cross-channel interference.11.The method of claim 8, wherein the set of resource element slots correspond to high-density resource element slots that are chosen to minimize channel estimation error while maintaining compliance with network protocols.12.The method of claim 8, comprising:refining, based on current channel data or a historical performance database, the pilot pattern selection process.13.The method of claim 8, wherein the activation command includes synchronization information to align demodulation process of the receiver with a new pilot pattern.14.The method of claim 8, comprising:scheduling periodically or based on Rx reporting, updates to the pilot pattern based on predicted changes in channel environment.15.An apparatus for deploying pilot patterns for a channel estimation in a wireless communication system, comprising:a memory; anda processor communicatively coupled with the memory, wherein the processor is configured to:identify, at a transmitter (Tx), a set of resource elements (REs) designated for pilot signal transmission based on a current resource allocation maps;select, at the Tx, a pilot pattern based on an optimal pilot pattern reported by a receiver (Rx) to align with identified set of resource elements, or sending such information to Rx and Rx selecting a pilot pattern;transmit the selected pilot pattern between Tx and Rx;configure, at the Tx, a set of resource element slots to implement pilot pattern and transmit locations of the set of resource element slots in a time-frequency (TM) grid to the Rx ;issue, from the Tx, an activation command to the receiver to activate the selected pilot pattern;monitor, at the Tx / Rx, a real-time channel conditions indicating a predefined performance parameters;assess, at the Tx, receiver performance parameters indicative of accuracy of channel estimation and interference levels based on feedback from the Rx; anddeploy, by the Tx , an updated pilot pattern to the Rx.

Images