Kamal Mian Muhammad, Khan Ijaz, Al-Khasawneh M A, Saudagar Abdul Khader Jilani
School of Electronics and Communication Engineering, Quanzhou University of Information Engineering, Quanzhou, 362000, China.
Institute of Ultrasonic Technology, Shenzhen Polytechnic University, Shenzhen, 518055, China.
Sci Rep. 2025 Aug 27;15(1):31642. doi: 10.1038/s41598-025-16571-8.
Resource allocation in multiple-input multiple-output (MIMO)-enabled wireless networks is designated for multiple users, which aims to optimize the distribution of network resources. This network's main intent is to maximize system performance by improving energy efficiency. However, the users of MIMO need many resources for effective operation. Hence, deep learning (DL) techniques are developed in this 5G network field to attain better reliability and accuracy during resource allocation. Therefore, this paper introduces a hippo graylag goose optimization with XCovNet (HGGO_XCovNet) for resource allocation. Firstly, a base station (BS) with multiple users is considered and the resource allocation is carried out by considering various objective functions, namely signal-interference noise ratio (SINR), data rate, and power consumption. Moreover, the resource allocation is performed by employing a DL model called XCovNet, where Xception convolutional neural network (XCovNet) is trained using the proposed hippo graylag goose optimization (HGGO). Further, the HGGO is formulated by the combination of greylag goose optimization (GGO) and hippopotamus optimization algorithm (HO). Furthermore, the HGGO_XCovNet technique measured a maximum energy efficiency of 74.943 kbits/joule, a sum rate of 269.93 Mbps, and throughput of 551.262 Mbps.
在支持多输入多输出（MIMO）的无线网络中，资源分配是为多个用户指定的，旨在优化网络资源的分配。该网络的主要目的是通过提高能源效率来最大化系统性能。然而，MIMO的用户需要许多资源才能有效运行。因此，在这个5G网络领域中开发了深度学习（DL）技术，以便在资源分配期间获得更好的可靠性和准确性。因此，本文介绍了一种用于资源分配的带有XCovNet的河马灰雁优化算法（HGGO_XCovNet）。首先，考虑一个具有多个用户的基站（BS），并通过考虑各种目标函数来进行资源分配，即信号干扰噪声比（SINR）、数据速率和功耗。此外，资源分配是通过使用一种名为XCovNet的深度学习模型来执行的，其中Xception卷积神经网络（XCovNet）使用所提出的河马灰雁优化算法（HGGO）进行训练。此外，HGGO是由灰雁优化算法（GGO）和河马优化算法（HO）组合而成的。此外，HGGO_XCovNet技术测得的最大能源效率为74.943千比特/焦耳，总速率为269.93Mbps，吞吐量为551.262Mbps。
