A SYSTEM AND A METHOD FOR NON-ORTHOGONAL MULTIPLE ACCESS (NOMA)

Abstract

ABSTRACT A SYSTEM AND A METHOD FOR NON-ORTHOGONAL MULTIPLE ACCESS (NOMA) The present disclosure discloses a system and a method for a Non-Orthogonal Multiple Access (NOMA). The system (100) comprises a network communication module (102) ensuring simultaneous signal transmission and reception with power level differentiation, a power allocation module (104) optimizing signal integrity based on channel conditions, a deep learning-based signal decoding module 106 using denoising autoencoders to enhance signal separation accuracy, a demodulator module (108) compatible with modulation schemes for error reduction, a Bit Error Rate (BER) calculation module (110) for real-time monitoring, a denoising AutoEncoder (AE) detector module (112) for noise reduction, a channel estimation module (114) for resource distribution optimization, a superimposed signal management module (116) for efficient transmission, and an error minimization feedback loop module (118) for adaptive system optimization. This system (100) aims to minimize errors and enhance communication efficiency in wireless networks through advanced signal processing techniques. Figure 1

Specification

Description:FIELD
The present disclosure generally relates to the field of decoding signals. More particularly, the present disclosure relates to a system and a method for Non-Orthogonal Multiple Access (NOMA).
DEFINITIONS
As used in the present disclosure, the following terms are generally intended to have the meaning as set forth below, except to the extent that the context in which they are used indicates otherwise.
The terms "Bit Error Rate (BER)" refer to the overall performance and reliability of the wireless communication system.
The terms "ReLu" refer to an activation function used in artificial neural networks and deep learning models.
The above definitions are in addition to those expressed in the art.
BACKGROUND
The background information herein below relates to the present disclosure but is not necessarily prior art.
Traditional NOMA systems have historically relied on the conventional Successive Interference Cancellation (SIC) decoding method to extract user equipment information. As the number of users equipment increases, concerns have been raised about the scalability and performance of the SIC decoding method in practical scenarios. Furthermore, the precise Channel State Information (CSI) required for optimized power allocation based on varying channel conditions is not always readily available in real-world operating environments.
Despite their benefits, traditional methods face several limitations. The foremost issue associated with traditional methods is traditional NOMA systems pertain to the limitations of the conventional SIC decoding method as the number of user equipment grows. Additionally, the reliance on perfect Channel State Information (CSI) for optimized power allocation based on varying channel conditions presents a significant technical problem. Ensuring the availability of perfect CSI proves to be a challenging task in real-world operating environments, raising concerns about the robustness and reliability of power allocation in NOMA systems.
There is, therefore felt a need for a system and a method for Non-Orthogonal Multiple Access (NOMA) that alleviates the aforementioned drawbacks.
OBJECTS
Some of the objects of the present disclosure, which at least one embodiment herein satisfies, are as follows:
It is an object of the present disclosure to ameliorate one or more problems of the prior art or to at least provide a useful alternative.
An object of the present disclosure is to provide a system and a method for Non-Orthogonal Multiple Access (NOMA).
Another object of the present disclosure is to provide a system that dynamically optimizes signal integrity and reduces inter-user interference based on channel conditions.
Still another object of the present disclosure is to provide a system that deploys a deep learning-based signal decoding module with denoising autoencoders to enhance signal separation accuracy and minimize Bit Error Rate (BER).
Yet another object of the present disclosure is to provide a system with real-time monitoring to enhance data accuracy for each user's equipment.
Still another object of the present disclosure is to provide a system that optimizes and minimizes error rates.
Yet another object of the present disclosure is to provide a system that ensures accurate signal recovery in noisy environments.
Still another object of the present disclosure is to provide a system for optimal resource distribution among user equipment.
Yet another object of the present disclosure is to provide a system that establishes a superimposed signal management module for efficient signal transmission and separation.
Still another object of the present disclosure is to provide a system with an error-minimization feedback loop for continuous monitoring and adjustment of system parameters to ensure minimal error rates.
Other objects and advantages of the present disclosure will be more apparent from the following description, which is not intended to limit the scope of the present disclosure.
SUMMARY
The present disclosure introduces a system and a method for Non-Orthogonal Multiple Access (NOMA) communication. The system comprises a network communication module, a power allocation module, a deep learning-based signal decoding module, a demodulator module, a Bit Error Rate (BER) calculation module, a denoising autoencoder (AE) detector module, a channel estimation module, a superimposed signal management module, and an error minimization feedback loop module.
The network communication module is configured to facilitate wireless communication between multiple user equipment and a base station, wherein the network communication module enables simultaneous transmission and reception of superimposed signals from multiple user equipment using shared frequency and time resources, with signal separation achieved through the assignment of differentiated power levels assigned to each user equipment.
The power allocation module is configured to dynamically allocate power to the user equipment's based on their respective channel conditions characterized by ensuring that user equipment with weaker channel gains is assigned higher power levels, optimizing signal integrity and system efficiency while minimizing inter-user interference.
The deep learning-based signal decoding module is configured to employ neural networks, including particularly denoising autoencoders (AE), for each user equipment to recover their respective signals from a superimposed transmission, and further configured to mitigate channel noise and interference, thereby enhancing signal separation accuracy and minimizing Bit Error Rate (BER).
The demodulator module is configured to demodulate the received signals after decoding, characterized by compatibility with multiple modulation schemes (BPSK, QPSK), and further reduce any residual errors in the recovered signals by means of error correction techniques, thereby improving data accuracy for each user.
The Bit Error Rate (BER) calculation module is configured to monitor and calculate the Bit Error Rate (BER) for each user equipment in real-time, characterized by interaction with the deep learning decoder and power allocation modules, providing feedback for adaptive system optimization to ensure minimized error rates.
The denoising Autoencoders (AE) detector module is configured to decode and denoise each user equipment's signal using a specific AE designed to separate the user equipment's signal from the superimposed NOMA transmission and further configured to reduce channel noise, mitigate interference, and enable accurate signal recovery for each user equipment in a scalable and computationally efficient manner.
The channel estimation module is configured to estimate the channel conditions the real-time analysis of channel gains characterizes each user equipment to provide input to the power allocation module, ensuring optimal resource distribution among user equipment.
The superimposed signal management module is configured to combine and transmit the signals of multiple user equipment using different power levels based on their channel conditions and is characterized by its ability to handle multiple user equipment transmissions efficiently in a shared spectrum while ensuring that signal separation at the receiver is maintained.
The error minimization feedback loop module is configured to continuously monitor the system's Bit Error Rate (BER) and adjust the power allocation and the deep learning-based decoder parameters in real-time, and further configured to adapt to changing channel conditions and user requirements to achieve minimal error rates across multiple user equipment's.
In an embodiment, the network communication module prioritizes users with higher channel quality by allowing for higher data rates while ensuring users with weaker channel conditions maintain reliable communication with increased power levels, as managed by the power allocation module.
In an embodiment, the power allocation module is further designed to adjust the power levels of users dynamically based on real-time feedback from the Bit Error Rate (BER) Calculation Module, ensuring optimal power distribution to minimize BER across all users.
In an embodiment, the deep learning-based signal decoding module is trained using supervised learning methods to enhance the accuracy of signal recovery by adapting to the specific channel conditions of each user, thereby improving decoding efficiency.
In an embodiment, the deep learning-based signal decoding module is further designed to operate using unsupervised learning techniques in real-time to continuously improve signal separation accuracy and reduce Bit Error Rate (BER) without prior training data.
In an embodiment, the demodulator module is further designed to utilize adaptive modulation schemes based on the quality of the recovered signal, switching between modulation schemes (BPSK, QPSK, etc.) to maximize data throughput and maintain accuracy.
In an embodiment, the Bit Error Rate (BER) Calculation Module is further designed to provide real-time adjustments to the deep learning-based signal decoding module, thereby improving system performance by dynamically updating the decoding process based on current BER values.
In an embodiment, the denoising AutoEncoder (AE) detector module includes a neural network model that is optimized for different noise profiles and interference levels, further enhancing its ability to recover signals from noisy environments.
In an embodiment, the channel estimation module is further designed to utilize machine learning algorithms for predictive modelling of future channel conditions, allowing the power allocation module to preemptively adjust power levels to maintain optimal communication efficiency.
The present disclosure also envisages a method for a non-orthogonal multiple access. The method comprises the following steps:
• facilitating, by a network communication module, wireless communication between multiple users and a base station, wherein the network communication module enables simultaneous transmission and reception of superimposed signals from multiple users using shared frequency and time resources, with signal separation achieved through the assignment of differentiated power levels assigned to each user;
• dynamically allocating, by a power allocation module, power to users based on their respective channel conditions, characterized by ensuring that users with weaker channel gains are assigned higher power levels, optimizing signal integrity and system efficiency while minimizing inter-user interference;
• employing, a deep learning-based signal decoding module, neural networks, particularly denoising autoencoders (AE), for each user equipment to recover their respective signals from a superimposed transmission, and mitigating channel noise and interference, thereby enhancing signal separation accuracy and minimizing Bit Error Rate (BER);
• demodulating, by a demodulator module, the received signals after decoding, characterized by compatibility with multiple modulation schemes (BPSK, QPSK) and reducing any residual errors in the recovered signals by means of error correction techniques, thereby improving data accuracy for each user.
• monitoring and calculating, by a Bit Error Rate (BER) calculation module, a Bit Error Rate (BER) for each user equipment in real-time, characterized by interaction with the deep learning decoder and power allocation modules, providing feedback for adaptive system optimization to ensure minimized error rates;
• decoding and denoising, by a denoising AutoEncoder (AE) detector module, each user's signal using a specific AE designed to separate the user's signal from the superimposed NOMA transmission, and reducing channel noise, mitigate interference, and enabling accurate signal recovery for each user equipment in a scalable and computationally efficient manner;
• estimating, by a channel estimation module , the channel conditions , of each user, characterized by the real-time analysis of channel gains to provide input to the power allocation module, ensuring optimal resource distribution among users;
• combining and transmitting, by a superimposed signal management module, the signals of multiple users using different power levels based on their channel conditions, characterized by its ability to handle multiple user equipment transmissions efficiently in a shared spectrum while ensuring that signal separation at the receiver is maintained; and
• continuously monitoring, by an error minimization feedback loop module, the system's Bit Error Rate (BER) and adjusting the power allocation and the deep learning-based decoder parameters in real-time, and adapting to changing channel conditions and user equipment requirements to achieve minimal error rates across multiple users.
BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWING
A system and a method for Non-Orthogonal Multiple Access (NOMA) of the present disclosure will now be described with the help of the accompanying drawing, in which:
Figure 1 illustrates a block diagram of a system for Non-Orthogonal Multiple Access (NOMA) in accordance with an embodiment of the present disclosure;
Figures 2A-2B illustrate a flow chart depicting the steps involved in a method for Non-Orthogonal Multiple Access (NOMA) in accordance with an embodiment of the present disclosure;
Figure 3 illustrates a prototype of a system for Non-Orthogonal Multiple Access (NOMA) in accordance with an embodiment of the present disclosure;
Figure 4 illustrates a architectural diagram of a system for Non-Orthogonal Multiple Access (NOMA) in accordance with an embodiment of the present disclosure;
Figure 5 illustrates an experimental setup of a system for Non-Orthogonal Multiple Access (NOMA) in accordance with an embodiment of the present disclosure; and
Figure 6 illustrates a Deep-Learning-based receiver system for Non-Orthogonal Multiple Access (NOMA) in accordance with an embodiment of the present disclosure.
LIST OF REFERENCE NUMERALS
100 - System
102 - Network Communication Module
104 - Power Allocation Module
106 - Deep Learning-Based Signal Decoding Module
108 - Demodulator Module
110 - Bit Error Rate (BER) Calculation Module
112 - Denoising Autoencoder (AE) Detector Module
114 - Channel Estimation Module
116 - Superimposed Signal Management Module
118 - Error Minimization Feedback Loop Module
120 - User Equipment's
DETAILED DESCRIPTION
Embodiments, of the present disclosure, will now be described with reference to the accompanying drawing.
Embodiments are provided so as to thoroughly and fully convey the scope of the present disclosure to the person skilled in the art. Numerous details, are set forth, relating to specific components, and methods, to provide a complete understanding of embodiments of the present disclosure. It will be apparent to the person skilled in the art that the details provided in the embodiments should not be construed to limit the scope of the present disclosure. In some embodiments, well-known processes, well-known apparatus structures, and well-known techniques are not described in detail.
The terminology used, in the present disclosure, is only for the purpose of explaining a particular embodiment and such terminology shall not be considered to limit the scope of the present disclosure. As used in the present disclosure, the forms "a," "an," and "the" may be intended to include the plural forms as well, unless the context clearly suggests otherwise. The terms "including," and "having," are open ended transitional phrases and therefore specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not forbid the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. The particular order of steps disclosed in the method and process of the present disclosure is not to be construed as necessarily requiring their performance as described or illustrated. It is also to be understood that additional or alternative steps may be employed.
When an element is referred to as being "engaged to," "connected to," or "coupled to" another element, it may be directly engaged, connected, or coupled to the other element. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed elements.
Traditional systems have historically used the Successive Interference Cancellation (SIC) decoding method to extract user equipment information. However, as the number of users increases, concerns have been raised about the scalability and performance of this method in practical scenarios. Additionally, the reliance on precise Channel State Information (CSI) for optimized power allocation based on varying channel conditions is not always feasible in real-world operating environments.
The limitations of traditional methods are evident, particularly in terms of the scalability and performance of SIC decoding as the number of users grows, as well as the challenge of obtaining and maintaining accurate CSI for power allocation in NOMA systems. These issues raise concerns about the robustness and reliability of power allocation in NOMA systems.
To address the issues of the existing systems and methods, the present disclosure envisages a system (hereinafter referred to as "system 100") for a Non-Orthogonal Multiple Access (NOMA) a method (hereinafter referred to as "method 200") for Non-Orthogonal Multiple Access (NOMA). The system 100 will now be described with reference to Figure 1 and the method 200 will be described with reference to Figure 2A-2B.
Referring to Figure 1, the system 100 comprises a network communication module 102, a power allocation module 104, a deep learning-based signal decoding module 106, a demodulator module 108, a Bit Error Rate (BER) calculation module 110, a denoising autoencoder (AE) detector module 112, a channel estimation module 114, a superimposed signal management module 116, and an error minimization feedback loop module 118.
The network communication module 102 is configured to facilitate wireless communication between multiple user equipment and a base station, wherein the network communication module 102 enables simultaneous transmission and reception of superimposed signals from multiple user equipment using shared frequency and time resources, with signal separation achieved through the assignment of differentiated power levels assigned to each user equipment.
In an embodiment, the network communication module 102 prioritizes user equipment with higher channel quality by allowing for higher data rates while ensuring user equipment with weaker channel conditions maintains reliable communication with increased power levels, as managed by the power allocation module 104.
The power allocation module 104 is configured to dynamically allocate power to the user equipment based on their respective channel conditions , characterized by ensuring that user equipment with weaker channel gains is assigned higher power levels, optimizing signal integrity and system efficiency while minimizing inter-user interference.
In an embodiment, the power allocation module 104 is further designed to adjust the power levels of user equipment dynamically based on real-time feedback from the Bit Error Rate (BER) Calculation Module 110, ensuring optimal power distribution to minimize BER across all user equipment.
The deep learning-based signal decoding module 106 is configured to employ neural networks, including particularly denoising autoencoders (AE), for each user equipment to recover their respective signals from a superimposed transmission, and further configured to mitigate channel noise and interference, thereby enhancing signal separation accuracy and minimizing Bit Error Rate (BER).
In an embodiment, the deep learning-based signal decoding module 106 is trained using supervised learning methods to enhance the accuracy of signal recovery by adapting to the specific channel conditions of each user equipment, thereby improving decoding efficiency.
In an embodiment, the deep learning-based signal decoding module 106 is further designed to operate using unsupervised learning techniques in real-time to continuously improve signal separation accuracy and reduce Bit Error Rate (BER) without prior training data.
The demodulator module 108 is configured to demodulate the received signals after decoding, characterized by compatibility with multiple modulation schemes (BPSK, QPSK), and further reduces any residual errors in the recovered signals by means of error correction techniques, thereby improving data accuracy for each user equipment.
In an embodiment, the demodulator 108 module is further designed to utilize adaptive modulation schemes based on the quality of the recovered signal, switching between modulation schemes (BPSK, QPSK, etc.) to maximize data throughput and maintain accuracy.
The Bit Error Rate (BER) calculation module 110 is configured to monitor and calculate the Bit Error Rate (BER) for each user equipment in real-time, characterized by interaction with the deep learning decoder and power allocation module 104, providing feedback for adaptive system optimization to ensure minimized error rates.
In an embodiment, the Bit Error Rate (BER) calculation module 110 is further designed to provide real-time adjustments to the deep learning-based signal decoding module 106, thereby improving system performance by dynamically updating the decoding process based on current BER values.
The denoising AutoEncoder (AE) detector module 112 is configured to decode and denoise each user equipment's signal using a specific AE designed to separate the user equipment's signal from the superimposed NOMA transmission and further configured to reduce channel noise, mitigate interference, and enable accurate signal recovery for each user equipment in a scalable and computationally efficient manner.
In an embodiment, the denoising AutoEncoder (AE) detector module 112 includes a neural network model that is optimized for different noise profiles and interference levels, further enhancing its ability to recover signals from noisy environments.
The channel estimation module 114 is configured to estimate the channel conditions , of each user equipment, characterized by the real-time analysis of channel gains to provide input to the power allocation module 104, ensuring optimal resource distribution among user equipment.
In an embodiment, the channel estimation module 114 is further designed to utilize machine learning algorithms for predictive modelling of future channel conditions, allowing the power allocation module 104 to preemptively adjust power levels to maintain optimal communication efficiency.
The superimposed signal management module 116 is configured to combine and transmit the signals of multiple user equipment using different power levels based on their channel conditions, characterized by its ability to handle multiple user equipment transmissions efficiently in a shared spectrum while ensuring the signal separation at the receiver is maintained.
In an embodiment, the superimposed signal management module 116 is configured to apply error correction coding to the superimposed signals before transmission, further reducing the potential for data loss and improving overall communication reliability.
The error minimization feedback loop module 118 is configured to continuously monitor the system's Bit Error Rate (BER) and adjust the power allocation and the deep learning-based decoder parameters in real-time, and further configured to adapt to changing channel conditions and user requirements to achieve minimal error rates across multiple user equipment.
In an embodiment, the error minimization feedback loop module 118 is further configured to continuously update both the power allocation module 104 and the deep learning-based signal decoding module 106 based on changing channel conditions, thereby providing a real-time adaptive solution for minimizing the system's BER.
Figure 2A-2B illustrates a flow chart depicting the steps involved in a method for a Non-Orthogonal Multiple Access (NOMA) in accordance with an embodiment of the present disclosure. The order in which method 200 is described is not intended to be construed as a limitation, and any number of the described method steps may be combined in any order to implement method 200, or an alternative method. Furthermore, method 200 may be implemented by processing resource or computing device(s) through any suitable hardware, non-transitory machine-readable medium/instructions, or a combination thereof. The method 200 comprises the following steps:
At step 202, the method 200 includes facilitating, by a network communication module 102, wireless communication between multiple user equipment \ and a base station, wherein the network communication module 102 enables simultaneous transmission and reception of superimposed signals from multiple user equipment using shared frequency and time resources, with signal separation achieved through the assignment of differentiated power levels assigned to each user equipment.
At step 204, the method 200 includes dynamically allocating, by a power allocation module 104, power to user's equipment based on their respective channel conditions , characterized by ensuring the user's equipment with weaker channel gains are assigned higher power levels, optimizing signal integrity and system efficiency while minimizing inter-user interference.
At step 206, the method 200 includes employing, by a deep learning-based signal decoding module 106, neural networks, particularly denoising autoencoders (AE), for each user equipment to recover their respective signals from a superimposed transmission, and mitigating channel noise and interference, thereby enhancing signal separation accuracy and minimizing Bit Error Rate (BER).
At step 208, the method 200 includes demodulating, by a demodulator module 108, the received signals after decoding, characterized by compatibility with multiple modulation schemes (BPSK, QPSK) and reducing any residual errors in the recovered signals by means of error correction techniques, thereby improving data accuracy for each user equipment.
At step 210, the method 200 includes monitoring and calculating, by a Bit Error Rate (BER) calculation module 110, the Bit Error Rate (BER) for each user equipment in real-time, characterized by interaction with the deep learning decoder and power allocation modules, providing feedback for adaptive system optimization to ensure minimized error rates.
At step 212, the method 200 includes decoding and denoising, by a denoising AutoEncoder (AE) detector module 112, each user equipment signal using a specific AE designed to separate the user equipment signal from the superimposed NOMA transmission, and reducing channel noise, mitigate interference, and enabling accurate signal recovery for each user equipment in a scalable and computationally efficient manner.
At step 214, the method 200 includes estimating, by a channel estimation module 114, the channel conditions of each user equipment, characterized by the real-time analysis of channel gains to provide input to the power allocation module, ensuring optimal resource distribution among user equipment.
At step 216, the method 200 includes combining and transmitting, by a superimposed signal management module 116, signals of multiple user's equipment using different power levels based on their channel conditions, characterized by its ability to handle multiple user equipment transmissions efficiently in a shared spectrum while ensuring the signal separation at the receiver is maintained.
At step 218, the method 200 includes continuous monitoring, by an error minimization feedback loop module 118, the system's Bit Error Rate (BER) and adjusting the power allocation and the deep learning-based decoder parameters in real-time and adapting to changing channel conditions and user requirements to achieve minimal error rates across multiple users equipment.
Figure 3 illustrates a prototype of a system for Non-Orthogonal Multiple Access (NOMA) in accordance with an embodiment of the present disclosure.
The system 100 includes the network communication module 102 configured to facilitate as a wireless transceiver of superimposed signals from various user equipment to enable wireless communication between multiple user equipment and a base station and with shared frequency and time resources. Signal separation is achieved by assigning different power levels to each user's equipment. The network communication module 102 provides users with better channel quality, allowing for higher data rates, while ensuring reliable communication for users with weaker channel conditions through increased power levels managed by the power allocation module 104.
The power allocation module 104 comprises the user equipment to dynamically assign power to user equipment based on their channel conditions, with a focus on allocating higher power levels to user equipment with weaker channel gains and optimization aims to enhance signal integrity, system efficiency, and minimize interference among users. The power allocation module 104 adjusts power levels in real-time based on feedback from the Bit Error Rate (BER) Calculation Module 110 to optimize power distribution and minimize BER for all user equipment.
The deep learning-based signal decoding module 106 is configured to utilize neural networks, particularly denoising autoencoders, for each user equipment to recover signals from superimposed transmissions, effectively mitigating channel noise and interference. The deep learning-based signal decoding module 106 is trained using supervised learning methods to adapt to specific channel conditions, thereby enhancing signal recovery accuracy and improving decoding efficiency. Additionally, the deep learning-based signal decoding module 106 can operate in real-time using unsupervised learning techniques to continuously enhance signal separation accuracy and reduce BER without prior training data.
The demodulator module 108 comprises the processes that receive signals after decoding, supporting multiple modulation schemes like BPSK and QPSK to reduce errors and enhance data accuracy for each user. The demodulator module 108 employs adaptive modulation schemes based on recovered signal quality to optimize data throughput and maintain accuracy.
The Bit Error Rate (BER) calculation module 110 is configured to monitor and compute the BER for each user equipment in real-time, interacting with the deep learning decoder and power allocation module 104 to provide feedback for system optimization and error rate minimization. The Bit Error Rate (BER) calculation module 110 is designed to make real-time adjustments to the deep learning-based signal decoding module 106 to enhance system performance by updating the decoding process according to current BER values.
Figure 4 illustrates an architectural diagram of a system for Non-Orthogonal Multiple Access (NOMA) in accordance with an embodiment of the present disclosure. Figure 4 illustrates the end to end signal transmission and reception of the NOMA system which has deep learning based receiver for signal decoding.
In the proposed system, NOMA allows simultaneous transmission of signal from N-users and combined as the superimposed signal in the power domain. The superimposed signal (x) is represented as

Where P is the transmit power, are the power allocation factors of users and is assumed that user 1 has better channel conditions than other users, whereas user N has poor channel conditions , are the Rayleigh channel fading coefficients of user 1, user 2, and user N respectively. Therefore, the maximum power is allocated to user N and the least power to user 1, that is .
At the receiver end, users are receiving the superimposed signal and expressed for ith user as
, where i=1, 2, ..., N
In the receiver, a trained denoising autoencoder-based detector is proposed to decode respective the user information from the superimposed signal instead of using a conventional successive interference cancellation mechanism.
The system includes a network communication module 102 that enables simultaneous transmission of superimposed signals from multiple user equipment using shared frequency and time resources, with signal separation achieved through the assignment of differentiated power levels assigned to each user equipment.
The power allocation module 104 dynamically assigns power levels to each user's equipment based on their individual channel conditions and quality of service requirements. This is achieved through a power allocation algorithm represented by the block labelled "Power allocation (α)." The power allocation module 104 ensures user equipment with weaker channel gains receives higher power levels, optimizing signal integrity and minimizing inter-user interference. The allocated power levels including denoted as α₁, α₂, ..., αN, where N represents the number of users.
The superposition and transmission following the power allocation, the deep learning signal decoding Module 116 comes into work role. The deep learning signal decoding Module 116 includes combining and transmitting the signals of multiple user equipment using different power levels based on their respective channel conditions. Allocated power levels coordinate with the superimposed signal to be transmitted over the wireless channel, and is represented by the equation: Where P₁ to Pn are the individual transmit powers of each user, and s₁ to sn are the corresponding user signals.
The reception upon transmission with the superimposed signal management module 116 each user equipment receives the superimposed signal, which contains their own signal as well as the signals from other users. The received signal at user k, denoted as yk, is influenced by the channel coefficient hk between the base station and user k, as well as the additive white Gaussian noise nk.
The denoising autoencoder (AE) detectors module 112 is configured to separate their intended signal from the received superimposed signal, each user equipment employs the Denoising AutoEncoder (AE) Detector Module 112. This module utilizes denoising autoencoders to remove interference and noise from the received signal, reconstructing the desired signal and providing the estimated signal represented as ŝk.
Figure 5 illustrates an experimental setup of a system for Non-Orthogonal Multiple Access (NOMA) in accordance with an embodiment of the present disclosure. The system 100 includes, power allocation module 104 For the near user and the far user, the power allocation algorithm within this module dynamically assigns power levels based on their respective channel conditions. The far user is assigned a higher power level compared to the near user to compensate for the weaker channel conditions due to the increased distance.
The deep learning signal module 116 combines the signals from both the near and far users using the allocated power levels and transmits the combined signal over the wireless channel. The different power levels assigned to the near and far users are reflected in the superimposed signal transmission, with appropriate power scaling for each user's signal.
Both the near user and the far user receive the superimposed signal by a superimposed signal management module 116, which contains their own signals as well as signals from other users. The far user's received signal is subject to more significant attenuation and potentially higher noise levels due to the increased distance from the base station compared to the near user.
Each user, including the near user and the far user, utilizes the Denoising AutoEncoder (AE) Detector Module 112 to separate their desired signals from the received superimposed signal. The AE detectors help mitigate interference and noise, aiding in the reconstruction of the individual user signals.
Figure 6 illustrates a Deep-Learning-based receiver system for Non-Orthogonal Multiple Access (NOMA) in accordance with an embodiment of the present disclosure. The system includes a denoising autoencoder model (AE) 112, which consists of an encoder and decoder part. The encoder compresses the input data, while the decoder reconstructs the clean input from the compressed representation.
The system comprises, a training dataset suitable for the denoising autoencoder model 112. The dataset includes input-output pairs where the input is a noisy or corrupted signal, and the output is the clean version of the input. The training dataset is for the autoencoder to learn to remove noise and reconstruct the original signal.
The system comprises an activation function Rectified Linear Unit (ReLU) is a set for the neural network layers. ReLU is a deep learning model. The input size is reshaped according to the 1D data at the encoding layer to suit the model architecture.
The system comprises a decoder part of the autoencoder, the output nodes are initialized with the linear activation function. Linear activation allows for scaling the output without introducing non-linearities, which is suitable for reconstructing the clean signal.
The denoising autoencoder 112 is compiled with the training data, denoted as y_train= [y_train1, y_train2, ..., y_trainN]. Each y_train sample represents a signal under Rayleigh fading channel with Additive White Gaussian Noise (AWGN). Compilation involves setting up the training process, loss functions, and optimization algorithms.
The superimposed signal management module 116 calculates the loss and accuracy of the trained model for varying numbers of epochs. Loss measures the difference between predicted and actual output, guiding the training process. Accuracy metrics evaluate the model's performance in terms of signal reconstruction and noise removal.
The trained denoising autoencoder model 112 is tested with noisy data with error minimization feedback loop module 118. A testing phase evaluates the model's ability to effectively remove noise and reconstruct the signal from noisy input, demonstrating the model's performance in real-world noisy conditions.
The following are the steps:
(i) Initialize the denoising autoencoder model;
(ii) Generate, and modify the training dataset, according to the autoencoder model and vice versa;
(iii) Set the activation function as ReLu and reshape the input size according to 1D data at the encoding layer;
(iv) Initialize the output nodes at the decoder part with the linear activation function;
(v) Compile the autoencoder with the training data , where each one represents the superimposed sample under the Rayleigh fading channel with AWGN noise;
(vi) Calculate the loss and accuracy of the trained model for the different numbers of epochs;
(vii) Test the model with the noisy data using the compiled model .

In an operative configuration, the system 100 provides for a Non-Orthogonal Multiple Access. The system comprises a network communication module 102 is responsible for facilitating wireless communication between multiple users and a base station, wherein the network communication module 102 enables simultaneous transmission and reception of superimposed signals from multiple users using shared frequency and time resources, with signal separation achieved through the assignment of differentiated power levels assigned to each user. The power allocation module 104 is responsible for dynamically allocating by power to users based on their respective channel conditions, characterized by ensuring that users with weaker channel gains are assigned higher power levels, optimizing signal integrity and system efficiency while minimizing inter-user interference.
The deep learning-based signal decoding module 106 is responsible for employing neural networks, particularly denoising autoencoders (AE), for each user to recover their respective signals from a superimposed transmission, and mitigating channel noise and interference, thereby enhancing signal separation accuracy and minimizing Bit Error Rate (BER). The demodulator module 108 is responsible for Demodulating the received signals after decoding, characterized by compatibility with multiple modulation schemes (BPSK, QPSK) and reducing any residual errors in the recovered signals by means of error correction techniques, thereby improving data accuracy for each user.
The Bit Error Rate (BER) calculation module 110 is responsible for Monitoring and calculating a Bit Error Rate (BER) for each user in real-time, characterized by interaction with the deep learning decoder and power allocation modules, providing feedback for adaptive system optimization to ensure minimized error rates. The denoising autoencoder (AE) detector module 112 is responsible for Decoding and denoising each user's signal using a specific AE designed to separate the user's signal from the superimposed NOMA transmission, and reduce channel noise, mitigate interference, and enable accurate signal recovery for each user equipment in a scalable and computationally efficient manner.
The channel estimation module 114 is responsible for estimating the channel conditions , by a channel estimation module 114 of each user's equipment, characterized by the real-time analysis of channel gains to provide input to power allocation module 104, ensuring optimal resource distribution among users' equipment.
The superimposed signal management module 116 is responsible for Combining and transmitting the signals of multiple users using different power levels based on their channel conditions, characterized by its ability to handle multiple user transmissions efficiently in a shared spectrum while ensuring that signal separation at the receiver is maintained. The error minimization feedback loop module 118 is responsible for continuously monitoring by an error minimization feedback loop module, the system's Bit Error Rate (BER) and adjusting the power allocation and the deep learning-based decoder parameters in real-time and adapting to changing channel conditions and user requirements to achieve minimal error rates across multiple users.
Advantageously, a system for Non-Orthogonal Multiple Access (NOMA) offers significant advantages in wireless communication to optimize communication efficiency and minimize errors. The power allocation module 104 dynamically adjusts power levels based on real-time Bit Error Rate (BER) feedback to ensure optimal power distribution, enhancing system efficiency.
Additionally, the demodulator module 108 utilizes adaptive modulation schemes based on signal quality, enhancing data transmission efficiency by switching between modulation schemes such as BPSK and QPSK. The deep learning-based signal decoding module 106 operates in real-time using unsupervised learning techniques to continuously improve signal recovery efficiency and reduce errors without prior training data. The channel estimation module 114 leverages machine learning algorithms to predict future channel conditions, enabling preemptive power adjustments for optimal resource distribution among user equipment, contributing to enhanced communication efficiency, and the error minimization feedback loop module 118 continuously monitors the system's BER and adjusts power allocation and decoder parameters in real-time, ensuring minimal error rates and high reliability across multiple user equipment.
The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Other examples and implementations are within the scope and spirit of the disclosure and appended claims. For example, due to the nature of software, functions described above can be implemented using software executed by a processor, hardware, firmware, hardwiring, or combinations of any of these. Features implementing functions may also be physically located at various positions, including being distributed such that portions of functions are implemented at different physical locations.
The foregoing description of the embodiments has been provided for purposes of illustration and is not intended to limit the scope of the present disclosure. Individual components of a particular embodiment are generally not limited to that particular embodiment, but are interchangeable. Such variations are not to be regarded as a departure from the present disclosure, and all such modifications are considered to be within the scope of the present disclosure.
TECHNICAL ADVANCEMENTS
The present disclosure described herein above has several technical advantages including, but not limited to, the realization of a system for a Non-Orthogonal Multiple Access (NOMA) that:
• provides power levels based on real-time BER feedback;
• optimizing power distribution for minimal errors and enhanced system performance;
• provide switch between according to signal quality, maximizing data throughput and accuracy for efficient communication;
• improve signal separation accuracy and reduce BER without prior training data, boosting signal recovery efficiency;
• allowing preemptive power adjustments for optimal resource distribution among user equipment, enhancing communication efficiency; and
• provide a real-time adaptation for BER Minimization for minimal error rates and high reliability across user equipment in changing conditions.
The embodiments herein and the various features and advantageous details thereof are explained with reference to the non-limiting embodiments in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
The foregoing description of the specific embodiments so fully reveals the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.
The use of the expression "at least" or "at least one" suggests the use of one or more elements or ingredients or quantities, as the use may be in the embodiment of the disclosure to achieve one or more of the desired objects or results.
While considerable emphasis has been placed herein on the components and component parts of the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiment as well as other embodiments of the disclosure will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be interpreted merely as illustrative of the disclosure and not as a limitation.
, C , Claims:WE CLAIM
1. A system (100) for a Non-Orthogonal Multiple Access (NOMA), said system (100) comprises:
• a network communication module (102) configured to facilitate wireless communication between multiple user equipment and a base station, wherein said network communication module (102) enables simultaneous transmission and reception of superimposed signals from multiple user equipment using shared frequency and time resources, with signal separation achieved through assignment of differentiated power levels assigned to each user equipment;
• a power allocation module (104) configured to dynamically allocate power to the user equipment based on their respective channel conditions , characterized by ensuring that user equipment with weaker channel gains being assigned higher power levels, optimizing signal integrity and system efficiency while minimizing inter-user interference;
• a deep learning-based signal decoding module (106) configured to employ neural networks, including denoising autoencoders (AE), for each user equipment to recover their respective signals from a superimposed transmission, and further configured to mitigate channel noise and interference, thereby enhancing signal separation accuracy and minimizing Bit Error Rate (BER);
• a demodulator module (108) configured to demodulate said received signals after decoding, characterized by compatibility with multiple modulation schemes (BPSK, QPSK) and further reduce any residual errors in the recovered signals by means of error correction techniques, thereby improving data accuracy for each user;
• a Bit Error Rate (BER) calculation module (110) configured to monitor and calculate the Bit Error Rate (BER) for each user equipment in real-time, characterized by interaction with the deep learning decoder and power allocation modules, providing feedback for adaptive system optimization to ensure minimized error rates;
• a denoising AutoEncoder (AE) detector module (112) configured to decode and denoise each user equipment's signal using a specific AE designed to separate the user equipment's signal from the superimposed NOMA transmission, and further configured to reduce channel noise, mitigate interference, and enable accurate signal recovery for each user equipment in a scalable and computationally efficient manner;
• a channel estimation module (114) configured to estimate the channel conditions of each user equipment, characterized by the real-time analysis of channel gains to provide input to said power allocation module, ensuring optimal resource distribution among user equipment;
• a superimposed signal management module (116) configured to combine and transmit the signals of multiple user equipment using different power levels based on their channel conditions, characterized by its ability to handle multiple user equipment transmissions efficiently in a shared spectrum while ensuring that signal separation at the receiver is maintained; and
• an error minimization feedback loop module (118) configured to continuously monitor said system's Bit Error Rate (BER) and adjust said power allocation and said deep learning-based decoder parameters in real-time, and further configured to adapt to changing channel conditions and user requirements to achieve minimal error rates across multiple user equipment's.
2. The system (100) as claimed in claim 1, wherein said network communication module (102) is configured to prioritize user equipment with higher channel quality by allowing for higher data rates while ensuring user equipment with weaker channel conditions maintains reliable communication with increased power levels, as managed by the power allocation module (104).
3. The system (100) as claimed in claim 1, wherein said power allocation module (104) is further configured to adjust the power levels of user equipment dynamically based on real-time feedback from the Bit Error Rate (BER) Calculation Module (110), ensuring optimal power distribution to minimize BER across all users equipment.
4. The system (100) as claimed in claim 1, wherein said deep learning-based signal decoding module (106) is trained using supervised learning methods to enhance the accuracy of signal recovery by adapting to the specific channel conditions of each user equipment, thereby improving decoding efficiency.
5. The system (100) as claimed in claim 1, wherein said deep learning-based signal decoding module (106) is further configured to operate using unsupervised learning techniques in real-time to continuously improve signal separation accuracy and reduce Bit Error Rate (BER) without prior training data.
6. The system (100) as claimed in claim 1, wherein said demodulator module (108) is further configured to utilize adaptive modulation schemes based on the quality of the recovered signal, switching between modulation schemes (BPSK, QPSK, etc.) to maximize data throughput and maintain accuracy.
7. The system (100) as claimed in claim 1, wherein said Bit Error Rate (BER) Calculation Module (110) is further configured to provide real-time adjustments to said deep learning-based signal decoding module (106), thereby improving system performance by dynamically updating the decoding process based on current BER values.
8. The system (100) as claimed in claim 1, wherein said denoising AutoEncoder (AE) detector module (112) is configured with a neural network model that is optimized for different noise profiles and interference levels, further enhancing its ability to recover signals from noisy environments.
9. The system (100) as claimed in claim 1, wherein said channel estimation module (114) is further configured to utilize machine learning algorithms for predictive modelling of future channel conditions, allowing said power allocation module (104) to pre-emptively adjust power levels to maintain optimal communication efficiency.
10. A method (200) for a Non-Orthogonal Multiple Access (NOMA), said method (200) comprises the following steps:
• facilitating, by a network communication module (102), wireless communication between multiple user equipment and a base station, wherein said network communication module (102) enables simultaneous transmission and reception of superimposed signals from multiple user equipment using shared frequency and time resources, with signal separation achieved through the assignment of differentiated power levels assigned to each user equipment;
• dynamically allocating, by a power allocation module (104), power to user equipment based on their respective channel conditions , characterized by ensuring that user equipment with weaker channel gains are assigned higher power levels, optimizing signal integrity and system efficiency while minimizing inter-user equipment interference;
• employing, by a deep learning-based signal decoding module (106), neural networks, particularly denoising autoencoders (AE), for each user equipment to recover their respective signals from a superimposed transmission, and mitigating channel noise and interference, thereby enhancing signal separation accuracy and minimizing Bit Error Rate (BER);
• demodulating, by a demodulator module (108), said received signals after decoding, characterized by compatibility with multiple modulation schemes (BPSK, QPSK) and reducing any residual errors in the recovered signals by means of error correction techniques, thereby improving data accuracy for each user equipment;
• monitoring and calculating, by a Bit Error Rate (BER) calculation module (110), the Bit Error Rate (BER) for each user equipment in real-time, characterized by interaction with the deep learning decoder and power allocation modules, providing feedback for adaptive system optimization to ensure minimized error rates;
• decoding and denoising, by a denoising Autoencoders (AE) detector module (112), each user equipment's signal using a specific AE designed to separate the user equipment's signal from the superimposed NOMA transmission, and reduce channel noise, mitigate interference, and enable accurate signal recovery for each user equipment's in a scalable and computationally efficient manner;
• estimating, by a channel estimation module (114), the channel conditions of each user equipment, characterized by the real-time analysis of channel gains to provide input to said power allocation module, ensuring optimal resource distribution among user equipment;
• combining and transmitting, by a superimposed signal management module (116), signals of multiple user equipment using different power levels based on their channel conditions, characterized by its ability to handle multiple user equipment's transmissions efficiently in a shared spectrum while ensuring that signal separation at the receiver is maintained; and
• continuously monitoring, by an error minimization feedback loop module (118), said system's Bit Error Rate (BER) and adjusting said power allocation and said deep learning-based decoder parameters in real-time, and adapting to changing channel conditions and user requirements to achieve minimal error rates across multiple user equipment's.
Dated this 13th Day of November, 2024

_______________________________
MOHAN RAJKUMAR DEWAN, IN/PA - 25
OF R. K. DEWAN & CO.
AUTHORIZED AGENT OF APPLICANT

TO,
THE CONTROLLER OF PATENTS
THE PATENT OFFICE, AT CHENNAI

Documents