Description:FIELD OF THE INVENTION
This invention relates to Successive Interference Cancellation detection for Non-Orthogonal Multiple Access using Deep Neural Networks - Long Short-Term Memory. The present invention relates to the field of wireless communication systems, specifically to the detection and cancellation of interference in Non-Orthogonal Multiple Access (NOMA) systems. More particularly, the invention leverages Deep Neural Networks (DNN) and Long Short-Term Memory (LSTM) networks for Successive Interference Cancellation (SIC) in Multi-Input Multi-Output (MIMO) NOMA systems. The invention addresses challenges associated with interference in high-density, high-speed communication environments, such as 5G/6G networks, by providing an efficient, real-time solution for detecting and separating overlapping signals transmitted from multiple users.
BACKGROUND OF THE INVENTION
The proposed invention addresses the problem of efficiently detecting and separating overlapping signals transmitted from multiple users in modern communication systems. In traditional methods, the process is slow, prone to errors, and struggles to keep up with rapidly changing conditions, especially in real-time environments like 5G/6G networks. This invention addresses these problems by leveraging Deep Neural Networks (DNN) and Long Short-Term Memory (LSTM) networks for signal detection in multi input multi output –non-orthogonal multiple access (MIMO-NOMA) systems. The DNN is adept at handling complex, nonlinear representations of signals, while the LSTM excels in processing time-sequential data, making it highly effective in dynamic environments.
This invention aims to improve the speed, accuracy, and reliability of signal detection, overcoming the challenges of high computational demands, delays, and performance issues in dynamic environments. By providing a more efficient approach, the invention ensures better performance in modern wireless communication systems.
Several commercially available products use Successive Interference Cancellation (SIC) and other traditional methods to handle signal detection and separation in overlapping user signals. Some notable products include:
Huawei 5G C-Band Massive MIMO AAU, Ericsson AIR 6488, Nokia AirScale Base Station, Qualcomm Snapdragon X60 5G Modem-RF System, MediaTek Dimensity 1000 Series 5G SoCs
The existing CNN-LSTM networks for downlink signal detection systems can only handle structured spatial input. They may struggle with long-term temporal patterns, higher computational overhead due to convolutional layers.
Convolutional Neural Networks (CNNs) are good at capturing spatial patterns but struggle with capturing long-range temporal dependencies. When paired with LSTM, CNNs only focus on short-term relationships, which might not fully capture the complexities of time-varying signals in NOMA. The DNN-LSTM is best for time-series data and temporal dependencies, can handle unstructured or lower-dimensional data but CNN-LSTM can handle only structured spatial inputs (2D data).
Convolutional Neural Networks (CNNs) are good at capturing spatial patterns but struggle with capturing long-range temporal dependencies. When paired with LSTM, CNNs only focus on short-term relationships, which might not fully capture the complexities of time-varying signals in NOMA. The DNN-LSTM is best for time-series data and temporal dependencies, can handle unstructured or lower-dimensional data but CNN-LSTM can handle only structured spatial inputs (2D data).
SUMMARY OF THE INVENTION
This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention.
This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.
Traditional SIC involves multiple iterations, sequentially processing each user in the network, which increases the complexity. Our solution circumvents this by using DNN-LSTM, which learns to identify interference patterns in a single pass. The DNN extracts high-level features from the received signal, while the LSTM layers capture the temporal dependencies, enabling real-time signal detection without the need for multiple iterations. This results in significantly lower computational overhead compared to traditional SIC. Our proposed solution introduces a Deep Learning-based SIC framework using Deep Neural Networks (DNN) and Long Short-Term Memory (LSTM) networks to mitigate these issues. A DNN-LSTM model is developed to process the received signal data. The DNN layers are responsible for extracting key features from the signal, while the LSTM layers model the temporal dependencies in the signal data. The model is trained in a supervised manner, so it learns to predict interference patterns and accurately detect the intended signal for each user. During training, the model optimizes its weights to minimize the signal detection error, allowing it to generalize well to the real-world data. The DNN-LSTM network helps in reducing computational complexity, predicts and cancels interference for all users simultaneously, leading to immediate detection of the intended signal. The sequential processing step is eliminated, which leads to a faster signal detection. This deep learning algorithmic approach can replace the existing networks for better signal detection.
To further clarify 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 drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.
BRIEF DESCRIPTION OF THE DRAWINGS
The illustrated embodiments of the subject matter will be understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and methods that are consistent with the subject matter as claimed herein, wherein:
Figure 1: Scheme diagram for DNN-LSTM approach
The figures depict embodiments of the present subject matter for the purposes of illustration only. A person skilled in the art will easily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.
DETAILED DESCRIPTION OF THE INVENTION
The detailed description of various exemplary embodiments of the disclosure is described herein with reference to the accompanying drawings. It should be noted that the embodiments are described herein in such details as to clearly communicate the disclosure. However, the amount of details provided herein is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure as defined by the appended claims.
It is also to be understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present disclosure. Moreover, all statements herein reciting principles, aspects, and embodiments of the present disclosure, as well as specific examples, are intended to encompass equivalents thereof.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a",” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and/or “including,” when used herein, specify the presence of stated features, integers, steps, operations, elements and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or groups thereof.
It should also be noted that in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed concurrently or may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
In addition, the descriptions of "first", "second", “third”, and the like in the present invention are used for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" and "second" may include at least one of the features, either explicitly or implicitly.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which example embodiments belong. It will be further understood that terms, e.g., those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Traditional SIC involves multiple iterations, sequentially processing each user in the network, which increases the complexity. Our solution circumvents this by using DNN-LSTM, which learns to identify interference patterns in a single pass. The DNN extracts high-level features from the received signal, while the LSTM layers capture the temporal dependencies, enabling real-time signal detection without the need for multiple iterations. This results in significantly lower computational overhead compared to traditional SIC. Our proposed solution introduces a Deep Learning-based SIC framework using Deep Neural Networks (DNN) and Long Short-Term Memory (LSTM) networks to mitigate these issues. A DNN-LSTM model is developed to process the received signal data. The DNN layers are responsible for extracting key features from the signal, while the LSTM layers model the temporal dependencies in the signal data. The model is trained in a supervised manner, so it learns to predict interference patterns and accurately detect the intended signal for each user. During training, the model optimizes its weights to minimize the signal detection error, allowing it to generalize well to the real world data. The DNN-LSTM network helps in reducing computational complexity, predicts and cancels interference for all users simultaneously, leading to immediate detection of the intended signal. The sequential processing step is eliminated, which leads to a faster signal detection. This deep learning algorithmic approach can replace the existing networks for better signal detection.
DNN-LSTM models are better at identifying complex, non-linear relationships in the signal, resulting in more accurate interference cancellation and can handle an increasing number of users without significant increases in computational complexity.
The present invention relates to a system for detecting and separating overlapping signals in a Non-Orthogonal Multiple Access (NOMA) communication system using a Deep Neural Network (DNN) and Long Short-Term Memory (LSTM) model. The system addresses the challenges faced by traditional Successive Interference Cancellation (SIC) methods in efficiently processing multi-user signals, especially in dynamic environments such as modern 5G and 6G networks. By leveraging the strengths of DNN and LSTM, the invention significantly improves the accuracy, speed, and computational efficiency of signal detection in NOMA systems.
At the core of the system is the DNN, which is responsible for extracting high-level features from the received signal data. These features help in identifying and isolating the intended signal amidst overlapping signals from multiple users. Complementing the DNN, the LSTM network is used to capture the temporal dependencies within the signal data, allowing the system to process time-series data effectively. This combination of DNN and LSTM enables the system to identify interference patterns and separate user signals with high precision, making it well-suited for real-time communication scenarios.
One of the key advantages of the present system is its ability to process the received signal data in a single pass, unlike traditional SIC methods, which rely on multiple iterations to process and separate each user's signal sequentially. This reduces the computational overhead, making the system faster and more efficient. The DNN-LSTM model is trained in a supervised manner, optimizing its weights to minimize signal detection errors. This training process ensures that the model can generalize well to real-world signal data, thereby improving its robustness and reliability in real-world applications.
The system is designed to simultaneously detect and cancel interference for all users in a NOMA network. By processing all user signals in a single pass, the DNN-LSTM model can detect the intended signal immediately, eliminating the delays associated with sequential processing. This leads to faster signal detection, which is critical for applications in dynamic and high-speed wireless communication systems like 5G and 6G networks.
Another significant benefit of the invention is its scalability. As the number of users in a NOMA system increases, the DNN-LSTM model can handle the additional complexity without a substantial increase in computational load. This scalability makes the system ideal for large-scale networks where a high volume of users must be supported efficiently, such as in urban environments or dense network settings.
In addition to its speed and accuracy, the DNN-LSTM model excels in capturing long-range temporal dependencies, making it particularly effective in dynamic communication environments where signal conditions can change rapidly. Traditional convolutional neural network (CNN)-LSTM models, while effective at capturing spatial patterns, struggle with long-term temporal dependencies. The DNN-LSTM, on the other hand, is optimized for time-series data, enabling it to detect and separate overlapping signals more accurately, even in complex, time-varying conditions.
This system also offers significant improvements over existing CNN-LSTM-based solutions. While CNN-LSTM models are typically limited to handling structured spatial inputs, the DNN-LSTM model is capable of processing unstructured or lower-dimensional data, making it more versatile and efficient for a variety of real-world communication scenarios. The ability to handle both spatial and temporal aspects of the signal data ensures that the system can deliver superior performance in a wide range of NOMA applications, from cellular networks to advanced wireless communication systems.
In conclusion, the DNN-LSTM-based interference cancellation system offers a more efficient and scalable solution for signal detection in NOMA systems. By reducing computational complexity, enabling real-time signal detection, and improving accuracy in dynamic environments, this invention represents a significant advancement in the field of wireless communication. It provides a robust alternative to traditional SIC methods, offering superior performance for modern 5G and 6G networks while also ensuring the ability to handle increasing user numbers without compromising performance.
, Claims:1. A system for detecting and separating overlapping signals in a Non-Orthogonal Multiple Access (NOMA) communication system, comprising a Deep Neural Network (DNN) and Long Short-Term Memory (LSTM) model configured to process the received signal data and perform interference cancellation in real-time; wherein the DNN extracts high-level features from the received signal to aid in signal detection and separation, and the LSTM captures temporal dependencies within the signal data, enabling improved performance in dynamic environments.
2. The system as claimed in claim 1, wherein the DNN-LSTM model processes multi-user signals in a single pass, eliminating the need for multiple iterations as seen in traditional Successive Interference Cancellation (SIC) systems, thereby reducing computational overhead and improving signal detection speed.
3. The system as claimed in claim 1, wherein the DNN-LSTM model is trained in a supervised manner to optimize its weights and minimize signal detection errors, thereby enabling the model to generalize effectively to real-world signal data.
4. The system as claimed in claim 1, wherein the DNN-LSTM model is specifically configured to handle time-series data and capture long-range temporal dependencies, thereby enhancing the accuracy and reliability of signal detection in time-varying NOMA systems.
5. The system as claimed in claim 1, wherein the DNN layers are responsible for extracting key features from the signal, and the LSTM layers model the temporal dependencies to predict interference patterns and accurately detect the intended signal for each user.
6. The system as claimed in claim 1, wherein the system is configured to simultaneously predict and cancel interference for all users in a NOMA network, leading to the immediate detection of the intended signal and significantly reducing signal processing time compared to traditional methods.
7. The system as claimed in claim 1, wherein the DNN-LSTM model is capable of handling an increasing number of users in a NOMA system without a significant increase in computational complexity, making it scalable for large-scale networks.
8. The system as claimed in claim 1, wherein the DNN-LSTM model is optimized for real-time signal detection and interference cancellation in modern wireless communication systems, including 5G and 6G networks, providing faster and more reliable performance than traditional SIC methods.
9. The system as claimed in claim 1, wherein the DNN-LSTM-based interference cancellation framework replaces existing convolutional neural network (CNN)-LSTM-based systems, providing enhanced detection capabilities by better handling non-linear relationships in multi-user signals.