کنفرانس مهندسی برق ایران

صفحه اصلی / سی و چهارمین کنفرانس بین المللی مهندسی برق

A Model-Driven Deep Learning Approach to Signal Detection in Large-Scale MIMO Systems

نویسندگان :

Nima Kiaheyrati¹ Mojtaba Amiri² Ali Olfat³

1- School of Electrical and Computer Engineering, University of Tehran 2- School of Electrical and Computer Engineering, University of Tehran 3- School of Electrical and Computer Engineering, University of Tehran

کلمات کلیدی :

Massive MIMO،Detection،Deep learning،Iterative algorithm

چکیده :

Massive multiple-input multiple-output (MIMO) has become a technology for next-generation wireless communication systems due to its potential to significantly increase capacity and spectral efficiency. However, efficient signal detection in massive MIMO systems remains a major challenge, particularly when aiming to balance accuracy and computational complexity. In this paper, we propose a new model-driven deep learning architecture for massive MIMO detection, inspired by an iterative framework. For the first time, we define a novel loss function that not only accelerates convergence during training but also improves the overall detection quality. Furthermore, simulation results demonstrate that our detector achieves up to $25\%$ performance improvement compared to state-of-the-art methods.