An efficient heuristic-aided adaptive autoencoder-based dilated DNN with attention mechanism for enhancing the performance of the MIMO system in 5G communication

On considering modern society, the wireless communication system plays a most significant role. This system has kept evolving and deployed into a wireless system of Fifth Generation (5G). One of the significant factors of the 5G system has utilized Machine Learning (ML) as well as Artificial Intelligence (AI) for the wireless network. Each of the building block and components of the wireless system, which is familiar and involves one or other ML/AI techniques are required. Here, the 5G generation has been used as the digital technology as well as run over higher radio frequencies. Further, the development of new techniques as well as the advanced features over the 5G network has raised some issues for the networking operators. ML is regarded as the AI that is accepted to unlock the capability of difficult large-scale issues over traditional Multiple-Input Multiple-Output (MIMO) systems. Today's wireless system has incomplete the MIMO system that has become common in recent years due to the increased potential in both energy efficiency and spectrum efficiency at a significant rate. AI-dependent ML has resolved the issues and then offers more energy efficiency and throughput in the 5G system. Hence, an effective artificial intelligence-based solution is introduced for resolving the aforementioned challenges to execute an efficient MIMO system in this proposal. In this work, the operations that are carried out for developing an efficient MIMO communication system are channel estimation, spectrum sensing of channels, fault/anomaly detection, resource allocation, and edge computation offloading. For performing all these functions, a deep learning method called Adaptive Autoencoder-Based Dilated DNN with Attention Mechanism (AADD-AM) is implemented. The parameters of the designed model are optimized with the help of Modified Update of Ant Lion and Horse herd Optimization (MU-ALHO) to achieve an accurate and effective outcome. The performance of the suggested efficient MIMO model is validated by comparing it with various performance metrics. Throughout the result analysis, the accuracy and sensitivity rate of the designed model is 94.86% and 95.18%. Therefore, it is revealed that the recommended model achieves high-speed wireless communication in a wide range of applications.