Scholarlink

<p>The rapid advancement of 5G and the emergence of 6G technologies have intensified the need for robust solutions to challenges in digital communication systems, such as channel estimation, interference management, network optimization, adaptive modulation, and spectrum sensing. Traditional methods like Least Squares (LS) estimation and fixed power allocation struggle with dynamic wireless environments, leading to suboptimal performance. This paper proposes a novel hybrid Machine Learning (ML) framework that integrates a Deep Neural Network (DNN) for channel estimation, a Deep Q-Network (DQN) for interference management, and a Support Vector Machine (SVM) for spectrum sensing, optimized through a unified loss function. The framework is implemented in MATLAB and evaluated on a 5G-like Orthogonal Frequency Division Multiplexing (OFDM) system under Rayleigh fading. Results show a reduction in Mean Squared Error (MSE) for channel estimation, improvement in Signal-to-Interference Ratio (SIR), and increase in spectrum sensing accuracy compared to baseline methods. This work highlights the transformative potential of ML in enhancing reliability and efficiency in modern communication systems.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Novel Hybrid Framework for Channel Estimation Interference Management and Spectrum Sensing in 5G OFDM Systems

  • 期刊论文

  • 发表日期：

    2026年3月9日

查看全文
  • Khawla A. Alnajjar,
  • Hassan Idries,
  • Mahmoud A. Albreem,
  • Saeed Abdallah

摘要

The rapid advancement of 5G and the emergence of 6G technologies have intensified the need for robust solutions to challenges in digital communication systems, such as channel estimation, interference management, network optimization, adaptive modulation, and spectrum sensing. Traditional methods like Least Squares (LS) estimation and fixed power allocation struggle with dynamic wireless environments, leading to suboptimal performance. This paper proposes a novel hybrid Machine Learning (ML) framework that integrates a Deep Neural Network (DNN) for channel estimation, a Deep Q-Network (DQN) for interference management, and a Support Vector Machine (SVM) for spectrum sensing, optimized through a unified loss function. The framework is implemented in MATLAB and evaluated on a 5G-like Orthogonal Frequency Division Multiplexing (OFDM) system under Rayleigh fading. Results show a reduction in Mean Squared Error (MSE) for channel estimation, improvement in Signal-to-Interference Ratio (SIR), and increase in spectrum sensing accuracy compared to baseline methods. This work highlights the transformative potential of ML in enhancing reliability and efficiency in modern communication systems.