Description:Technical field of the invention
[0002] The present invention relates to the field of 6th Generation Vehicle-to-Everything (6G-V2X) communication systems. Specifically, the invention pertains to adaptive beamforming methods aimed at enhancing the efficiency and reliability of communication between vehicles and their surrounding environment in dynamic urban settings.
Background of the invention
[0003] The advancement of the automotive industry towards greater connectivity and automation underscores the critical importance of reliable communication systems in facilitating real-time exchange of information among vehicles, infrastructure, pedestrians, and other elements within the transportation ecosystem. However, deploying effective communication in dense urban environments poses significant challenges due to increased interference from neighboring vehicles, infrastructure, and other wireless devices. Conventional communication methods often struggle to maintain reliable connectivity and signal quality in such complex and dynamic scenarios.
[0004] Further, many current solutions rely on static beamforming techniques, which lack the adaptability necessary to contend with the dynamic nature of vehicular environments. As vehicles traverse urban landscapes, their positions, velocities, and communication requirements constantly fluctuate. Consequently, static beamforming approaches often fall short in optimizing communication performance, leading to inefficiencies and suboptimal outcomes. Moreover, the dynamic scenarios inherent to vehicular environments pose further challenges to existing methodologies. Traditional techniques may struggle to adapt to rapidly changing conditions, such as sudden shifts in traffic patterns or unexpected obstacles, resulting in communication disruptions and potential safety hazards. Furthermore, noisy environments present another hurdle for current communication systems. Incomplete or corrupted data, coupled with the inherent variability of wireless communication channels, can undermine the robustness of existing solutions, impairing their ability to maintain reliable communication links.
[0005] The limited adaptability of current technologies exacerbates these challenges. With communication requirements evolving rapidly in response to changing environmental conditions, existing methodologies may prove insufficient in meeting the demands of dynamic urban landscapes, potentially compromising the safety and efficiency of connected and automated vehicles.
[0006] The shortcomings of current 6G-V2X communication systems underscore the critical need for innovative approaches that can address the complexities of urban environments and aims to enhance the efficiency, reliability, and adaptability of communication systems in urban settings, thereby facilitating safer and more efficient transportation networks.
[0007] For instance, the Patent Application No. IN202341073625A titled “An adaptive beamforming framework for 5G mm wave massive 3D-MIMO uplink Systems” discloses a a Deep Adaptive Learning-Based Beam Combining framework for 5G millimeter-wave massive 3D-MIMO uplink systems to address the challenges faced in such complex communication environments. By leveraging the power of deep learning and adaptive algorithms, this framework offers several advantages such as improved beamforming performance, adaptability to dynamic environments and enhanced user experience. The improved beamforming performance translates to a better user experience with higher data rates, lower latency, and reliable connectivity. This is essential for the success of 5G and future communication systems, which aim to support demanding applications like virtual reality, augmented reality, and ultra-high definition multimedia.
[0008] The Patent Application No. WO2023191674A1 titled “Method and wireless device for beamforming using Doppler shift to estimate angles of departure or arrival of signals.” discloses a method performed by a wireless device connected to a network node of a wireless communication network. The wireless device has a plurality of antennas for forming beams for directed wireless communication with the network node. The method comprising obtaining estimated angles of departure of signals communicated between the wireless device and the network node determined from estimated Doppler shifts of the wireless signals. Such estimated angles are converted to wireless device orientation-aligned directions based on information on orientation of the wireless device. Directions of possible beams of the wireless device are then compared to the wireless device orientation-aligned directions to select a much smaller amount of candidate beams out of the possible beams. The beam(s) used by the wireless device for communication is/are then selected only from those candidate beams, based on e.g. known scanning techniques.
[0032] As a result, to address the drawbacks, there is a necessity for an adaptive beamforming method with real-time adjustment based on vehicle dynamics, incorporation of machine learning for noise management, and deployment of comprehensive signal processing methods for interference mitigation.
Summary of the invention
[0037] The present invention addresses the limitations of the prior art by introducing a method for adaptive beamforming within a 6G-V2X communication system, aimed at enhancing communication performance in dynamic vehicular environments. The method comprises a series of innovative steps to optimize beamforming parameters and ensure reliable data transmission. The method dynamically adjusts the direction and strength of multiple communication beams to determine optimal beamforming parameters, leveraging real-time vehicle dynamics. Moreover, the integration of one or more auto encoders into the system architecture facilitates the optimization and learning of beamforming weights in real-time, based on historical communication data. This adaptive learning process effectively handles noisy and incomplete data, enhancing the robustness of communication links. Additionally, the method optimizes the utilization of multiple antennas in the system array by combining their weighting using either linear or nonlinear methods, ensuring efficient signal transmission and reception. Furthermore, a normalization step is incorporated to ensure unit power of beamforming weights, with adjustments based on signal-to-noise ratio measurements, further enhancing communication reliability. Moreover, the invention enables real-time adaptation by continuously updating beamforming parameters in response to changing communication conditions, thereby ensuring efficient and reliable communication performance in dynamic vehicular environments.
Brief Description of drawings
[0038] Figure 1 illustrates a flowchart of a method for adaptive beamforming within a 6G-V2X communication system, in accordance with an embodiment of the present invention.
[0039] Figure 2 illustrates the vehicle-mounted transmitter engaging in communication activities while concurrently gathering vehicle data for the Area of Interest (AoI) of beamforming, in accordance with an embodiment of the present invention.
[0040] Figure 3 illustrates the process of forecasting the Area of Interest (AoI) for beamforming operations, in accordance with an embodiment of the present invention.
Detailed description of the invention
[0041] In order to more clearly and concisely describe and point out the subject matter of the claimed invention, the following definitions are provided for specific terms, which are used in the following written description.
[0042] The term ‘Adaptive Beamforming’ defines a technique utilized in wireless communication systems to dynamically adjust the direction and strength of transmission beams based on environmental factors such as signal quality, interference, and user location.
[0043] The term ‘Auto encoder’ is a type of artificial neural network used for unsupervised learning that learns efficient data representations by training the network to reproduce its input at its output layer. In the context of the invention, auto encoders are employed to optimize and learn beamforming weights in real-time, enhancing communication performance.
[0044] The term ‘Normalization’ process of adjusting values to ensure uniformity or consistency within a given range or scale. In the context of the invention, normalization of beamforming weights is performed to ensure unit power, thereby optimizing the efficiency of the communication system.
[0045] The term ‘Signal-to-Noise Ratio (SNR)’ is defined as a measure used in communication systems to quantify the ratio of signal power to noise power. It indicates the quality of a communication signal relative to the level of background noise present. In the context of the invention, SNR measurements are utilized to adjust beamforming weights, ensuring optimal signal quality and reliability.
[0046] The term ‘Linear and Nonlinear Combining Methods’ are Techniques used to combine signals or weights in wireless communication systems. Linear combining methods involve simple arithmetic operations such as addition or multiplication, while nonlinear combining methods may involve more complex operations such as nonlinear mapping functions. In the context of the invention, these methods are employed to optimize the utilization of multiple antennas in the array, enhancing communication efficiency.
[0047] The present invention discloses a method for adaptive beamforming within 6G-V2X communication systems. The method entails dynamically adjusting beam direction and strength, integrating auto encoders for real-time optimization, optimizing antenna utilization, normalizing beamforming weights, and ensuring real-time adaptation based on changing communication conditions. The method enhances communication reliability and efficiency in dynamic vehicular environments, contributing to safer and more efficient transportation networks.
[0048] The present invention offers a multifaceted approach to address the challenges encountered in 6G-V2X communication systems, presenting several significant advantages over existing technologies. By employing adaptive beamforming, real-time learning with auto encoders, and robust handling of noisy data, the invention ensures optimal communication performance in dynamic vehicular environments. Furthermore, the methodology's efficient antenna utilization, power optimization through normalization, and consideration of Doppler shift contribute to improved signal quality and interference mitigation, crucial for reliable communication in dense urban settings. Moreover, the method aims at improving signal quality and mitigate interference, thereby contributing to the safety and efficiency of connected and automated vehicles, enhancing the overall transportation ecosystem.
[0049] Figure 1 illustrates a flowchart of a method for adaptive beamforming within a 6G-V2X communication system, in accordance with an embodiment of the present invention. The method (100) for adaptive beamforming within a 6G-V2X communication system, offers a systematic approach to enhance communication performance. The method (100) dynamically adjusts the direction and strength of multiple communication beams, facilitating the determination of optimal beamforming parameters in real-time in step 101. Further, by integrating one or more auto encoders in real time into the communication system architecture, the method (100) optimizes and learns beamforming weights continuously, ensuring adaptability and responsiveness to changing communication conditions in step 102. Additionally, the method (100) optimizes the utilization of multiple antennas in the array by combining the weighting of each antenna using either linear or nonlinear combining methods, enabling the formation of focused beams by transmitting signals with carefully controlled timing and amplitude directed towards desired locations, thereby enhancing overall communication system performance in step 103. Furthermore, a normalization step is incorporated in step 104 to ensure that beamforming weights maintain unit power, thereby ensuring the overall power utilized for communication is evenly distributed among the antennas and optimizing the efficiency of the communication system. More particularly, normalizing the beamforming weights involves adjusting the weights assigned to different antennas to ensure that the overall power used for communication is balanced and efficient. This process ensures that the sum of the squared weights equals one, effectively distributing the transmit power across all antennas. By achieving unit power, no single antenna dominates the transmission, optimizing the efficiency of the communication system. The method (100) adaptively optimize communication beams, improving signal quality, reliability, and efficiency in dynamic vehicular environments.
[0050] In an embodiment of the present invention, the method (100) begins with the input of various data parameters, including signals from the antenna array, vehicle velocities, positions, and maximum transmit power. These inputs serve as the foundation for subsequent calculations and adjustments. Based on the received vehicle data, the method (100) computes the time delay and steering angle for each antenna in the array. This calculation accounts for the relative positions of vehicles and the array, ensuring precise beamforming adjustments. Further, the Doppler shift for each antenna, taking into account the relative velocities of vehicles is calculated. This adjustment is crucial for accurately determining the frequency adjustments needed to maintain optimal communication. Using the computed time delays, steering angles, and Doppler shifts, the complex weights for each antenna is calculated. These weights determine the strength and direction of the communication beams emitted by the antennas. Once the weights are calculated for each antenna, they are combined using either linear or nonlinear combining methods, thereby ensuring that the contributions of each antenna are optimized for effective signal transmission. The combined weights undergo a normalization step to ensure unit power. This adjustment balances the power distribution among antennas, maximizing overall efficiency and signal quality. The integrated auto encoder is trained using historical input signals and optimal beamforming weights to optimize future signal transmission. Once trained, the auto encoder predicts optimal beamforming weights for new input signals in real-time. This predictive capability ensures continuous adaptation and optimization of communication performance. The entire method is executed and implemented within the communication system, which may run on dedicated hardware or software platforms. The arrangement of antennas, integration of auto encoders, and execution of calculations occur seamlessly to ensure efficient and reliable communication. This adaptive learning method ensures that the communication system remains optimized and responsive to changing environmental conditions.
[0051] In the ant embodiment of the present invention, several key components and methodologies are employed to facilitate adaptive beamforming in a 6G-V2X communication system. The antenna array serves as a fundamental element, comprising a structured arrangement of antennas designed to both receive and transmit communication signals. These antennas are strategically positioned to optimize signal reception and transmission efficiency within the vehicular environment. Additionally, the auto encoders, neural network components specifically engineered for machine learning, play a pivotal role. The auto encoders are tasked with learning and optimizing signal transmission strategies based on historical data, continually improving their performance over time. Further, the Doppler shift calculation is utilized to accurately assess changes in signal frequency resulting from vehicle motion. The calculation involves mathematical computations based on the relative velocities of vehicles, ensuring precise adjustment of signal parameters. In the combining method, mathematical processes are employed to effectively aggregate signals from multiple antennas. The method maximizes communication strength by combining signals in the most efficient manner possible. Finally, the normalization step ensures balanced and efficient power usage for communication purposes. Through mathematical adjustments, this step guarantees that no antenna exerts excessive or insufficient power, optimizing overall communication performance.
[0052] In an embodiment of the present invention, the antenna array, arranged in a specific formation resembling spokes on a wheel, ensuring comprehensive coverage over a wide area. The strategic placement of antennas enables effective communication with surrounding vehicles by evenly spacing them and strategically positioning them to maximize coverage. Furthermore, the integration of auto encoders into the communication system architecture enhances its learning capabilities. The auto encoders, connected to the antennas, continuously learn from received signals, enabling them to optimize future transmissions. The integration ensures that the communication system evolves over time, improving its performance based on past experiences. The execution of the methodology takes place on dedicated computing hardware such as a desktop computer, notebook or laptop computer, a tablet computer or any suitable combination thereof, where it processes data from the auto encoders and adjusts antenna signals accordingly. This real-time processing allows for adaptive communication strategies that respond dynamically to changing environmental conditions, such as Doppler Shift and vehicle positions.
[0053] Figure 2 illustrates the vehicle-mounted transmitter engaging in communication activities while concurrently gathering vehicle data for the Area of Interest (AoI) of beamforming, in accordance with an embodiment of the present invention.. In an embodiment of the present invention, the transmitter, an integral component of the 6G-V2X communication infrastructure, initiates and maintains communication links with nearby vehicles. Concurrently, it collects essential data concerning the surrounding vehicles, including their positions, velocities, and potentially other pertinent parameters. The term "Area of Interest (AoI)" delineates the specific geographical region or scope within which the transmitter focuses its beamforming operations. By scrutinizing and interpreting vehicle data within this AoI, the transmitter dynamically adjusts its beamforming parameters to optimize communication with target vehicles. The adaptive approach augments communication efficiency and reliability in dynamic vehicular settings, ensuring that transmissions are precisely directed towards intended recipients while mitigating interference from extraneous sources. Further, empowering the communication system to fine-tune its beamforming strategy in response to real-time vehicle data, thereby enhancing connectivity and performance in 6G-V2X communication systems.
[0054] Figure 3 illustrates the process of forecasting the Area of Interest (AoI) for beamforming operations, in accordance with an embodiment of the present invention. The illustration involves analyzing real-time data regarding the behaviors and state of the vehicle. The real-time behaviors include dynamic factors such as changes in vehicle speed, direction, and maneuvers, while the state of the vehicle encompasses its current position, velocity, and possibly other relevant parameters. By monitoring these real-time behaviors and vehicle states, the communication system can predict the likely trajectory or path of the vehicle, thereby determining the AoI where communication signals need to be directed. The predictive analysis enables the communication system to anticipate the future position and movement of the vehicle, allowing it to proactively adjust its beamforming parameters to maintain optimal communication with the target vehicle. By leveraging real-time data and predictive modeling, the communication system optimizes the allocation of resources and enhances the efficiency of communication in dynamic vehicular environments. The approach contributes to improved reliability and performance of 6G-V2X communication systems by ensuring seamless connectivity and effective signal transmission between vehicles
Example 1: Demonstrative illustration of usage of proposed invention
[0055] The method (100) initiates by acquiring input data, including antenna array input signals [n, m], where n represents the time index and m represents the antenna index. Vehicle velocities (vi) and positions (Pi), where i denotes the vehicle index and maximum transmit power (Pmax). Subsequently, employing specific formulas, the method computes essential parameters for beamforming. Firstly, the method (100) calculates the time delay (Ti) and steering angle (Ti) for each antenna relative to the vehicles' positions using the formulas:
Ti = C(Pi-d)
Ti= arctan (Piy/ Pix)
Here, Pi represents the position vector of vehicle i, d is the vector from the array center to vehicle i, and C is the speed of light. These calculations ensure accurate alignment of the antennas with the vehicles' positions and movements, optimizing signal transmission. Additionally, the method (100) computes the Doppler shift (fi) for each antenna based on the relative velocities of the vehicles using the formula:
fi=(Vi/C)·fc
Here, Vi is the relative velocity of vehicle i, and fc is the carrier frequency. The calculation adjusts the carrier frequency to account for vehicular motion, mitigating potential signal distortion. Subsequently, employing complex weighting calculations, the method determines optimal beamforming weights (W1) for each antenna based on time delay, steering angle, and Doppler shift parameters using the formula:

W1= (vPmax/ N ) exp (-j2pfiTi) exp (j (2pd/ ? ) sin(Ti))
Here, N is the number of antennas, ? is the wavelength, and d is the distance from the array center to vehicle i. These weights shape and focus communication beams towards target vehicles, enhancing signal strength and reliability. Following weight calculation, the method combines the weights for all vehicles using a linear or nonlinear combining method, ensuring coherent transmission across the antenna array. Subsequently, normalization of the combined weights is performed to maintain unit power, optimizing overall communication efficiency. Finally, the method involves training an auto encoder using input signals and optimal beamforming weights to facilitate real-time adaptation and optimization of beamforming parameters. The trained auto encoder enables the prediction of optimal beamforming weights for new input signals, ensuring continuous improvement and adaptability of the communication system.
[0056] The present invention discloses a method for adaptive beamforming in a 6G-V2X communication system, effectively mitigating shortcomings observed in prior art. By dynamically adjusting communication beams based on real-time vehicle dynamics, integrating machine learning techniques for noise handling, and employing robust signal processing methods for interference mitigation, the invention significantly enhances communication performance. Notably, the method (100) optimizes antenna array utilization, normalizes beamforming weights to ensure efficient power usage, and considers Doppler shift for improved reliability in dynamic vehicular environments. The disclosed method (100) offers several notable advantages, including adaptability to changing conditions, real-time learning capabilities, robustness against noisy data, efficient antenna utilization, and enhanced signal quality and interference mitigation. These advantages collectively contribute to improved safety and efficiency in connected and automated vehicular communication system.
, Claims:We claim:
1. A method for adaptive beamforming in a sixth-generation vehicle-to-everything (6G-V2X) communication system, the method (100) comprising the steps of:
a. dynamically adjusting direction and strength of a plurality of communication beams to determine optimal beamforming parameters;
b. integrating one or more auto encoders in real-time to optimize and learn beamforming weights;
c. optimizing utilization of a plurality of antennas in the array by combining weighting of each antenna to form focused beams directed towards desired locations; and
d. normalizing beamforming weights to ensure unit power, ensuring the overall power utilized for communication is evenly distributed among the antennas.
2. The method (100) as claimed in claim 1, wherein the direction and strength of the communication beams are adjusted based on real-time vehicle positions and velocities to determine optimal beamforming parameters.
3. The method (100) as claimed in claim 1, wherein the weightage of each antenna using linear or nonlinear combining methods
4. The method (100) as claimed in claim 1, wherein integrating the auto encoders to optimize and learn beamforming weights comprises training the auto encoders on historical communication data and effectively handling noisy and incomplete data.
5. The method (100) as claimed in claim 1, wherein enabling real-time learning and adaptation by incorporating the auto encoders further comprises updating beamforming parameters based on incoming signals and modifying beamforming in response to changing communication conditions.
6. The method (100) as claimed in claim 1, wherein normalizing beamforming weights to ensure unit power further comprises adjusting beamforming weights based on signal-to-noise ratio measurements.