Scholarlink

<p>A technology used in wireless communications that engages numerous antennas on both the transmitter and receiver ends is called Multiple-Input Multiple Output (MIMO). MIMO is vital in enhancing the communication process by enhancing link reliability and data throughput in 5G networks. However, the key issues of MIMO in 5G&#xa0;are higher power consumption, high hardware complexity, high cost, and proportional to traffic load. Thus, an efficient African Vulture Shepherd Optimization Algorithm (AVSOA) is applied for traffic offloading in a massive MIMO system. This work offers a holistic review of the AVSOA Deep QNN devised for traffic offloading in comparison with Wireless edge-computing systems and the prevailing methods. The steps followed by the hybrid optimization approach are as follows. Initially, the service request arrives at macro-cells, and the offloading process is prompted by considering the system load of the cell. Next, the system load prediction is done by a Deep Quantum Neural Network (Deep QNN), based on which conditional offloading is performed by AVSOA. Moreover, the proposed AVSOA attained higher throughput, spectral efficiency, energy efficiency, and empirical Cumulative Distribution Function (CDF) of 17.926 Mbps, 2.589 Mbits/Joule, 57.68 bits/s/Hz, and 0.98, and a low system load of 245.878.</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

Hybrid optimization techniques for traffic offloading in 5G: insights from AVSOA performance analysis

  • 期刊论文

  • 发表日期：

    2026年5月13日

查看全文
  • A. B. Farakte,
  • K. P. Sridhar,
  • M. B. Rasale

摘要

A technology used in wireless communications that engages numerous antennas on both the transmitter and receiver ends is called Multiple-Input Multiple Output (MIMO). MIMO is vital in enhancing the communication process by enhancing link reliability and data throughput in 5G networks. However, the key issues of MIMO in 5G are higher power consumption, high hardware complexity, high cost, and proportional to traffic load. Thus, an efficient African Vulture Shepherd Optimization Algorithm (AVSOA) is applied for traffic offloading in a massive MIMO system. This work offers a holistic review of the AVSOA Deep QNN devised for traffic offloading in comparison with Wireless edge-computing systems and the prevailing methods. The steps followed by the hybrid optimization approach are as follows. Initially, the service request arrives at macro-cells, and the offloading process is prompted by considering the system load of the cell. Next, the system load prediction is done by a Deep Quantum Neural Network (Deep QNN), based on which conditional offloading is performed by AVSOA. Moreover, the proposed AVSOA attained higher throughput, spectral efficiency, energy efficiency, and empirical Cumulative Distribution Function (CDF) of 17.926 Mbps, 2.589 Mbits/Joule, 57.68 bits/s/Hz, and 0.98, and a low system load of 245.878.