5G Performance and Enhancement with Dust Storm Conditions

The increasing demand for ultra-fast data, high capacity, and low latency in 5G and beyond networks is driving the adoption of millimeter-Wave (mm-Wave) frequencies (3–300 GHz), which utilize spatial multiplexing and beamforming for improved performance. However, environmental factors like humidity, temperature, dust, and sandstorms, particularly in the Middle East, pose significant challenges. The parameters of the channel model and how it behaves statistically when exposed to dust and sandstorms have been analyzed using NYUSIM simulator and MATLAB. Wireless communication channels face challenges like time variability, frequency-selective fading, and interference from adjacent subcarriers, making traditional estimation methods less effective. This paper introduces a DNN model based on Bidirectional Long Short-Term Memory (BI-LSTM) networks, which excel at processing time-series data with long-range dependencies, outperforming standard RNNs. An end-to-end channel estimation and signal detection process using the Bi-LSTM-based detector is simulated and compared with traditional techniques such as LS, ZF, and MMSE. Results show that DNN provides higher estimation accuracy, especially with fewer pilots, achieving SER 30 to 35 times lower than ZF and MMSE. Additionally, the DNN model offers an SNR gain of approximately 10–15 dB or more compared to conventional methods. The proposed approach shows cases promising advancements for not only 5G but also for the evolving requirements of beyond-5G networks, offering a reliable solution for maintaining efficient Multiple-Input Multiple-Output Orthogonal Frequency Division Multiplexing MIMO-OFDM communication under diverse weather conditions.