Hybrid ARMA-LSTM model for adaptive link prediction in dynamic underwater sensor networks

Abstract

Underwater wireless sensor network (UWSN) is highly vulnerable to packet loss due to varied features of underwater channels, including multipath fading, high latency, and environmental interference. Accurate prediction of packet loss is critical for improving data reliability and network performance. Our research presents a new approach to forecasting using a combination of autoregressive moving average (ARMA) and long short-term memory (LSTM) networks which are statistical models. A synthetic dataset was generated to facilitate model development and evaluation, simulating realistic UWSN conditions by varying key parameters such as signal-to-noise ratio (SNR), received signal strength indicator (RSSI), depth, distance, and temperature. The ARMA model captures linear temporal trends, while the LSTM network is trained on the ARMA residuals to learn nonlinear correction patterns. The findings indicate that the hybrid ARMA-LSTM model exhibits a marked superiority over the standalone ARMA model, achieving an approximate 87.5% reduction in mean absolute error (MAE), an 84% enhancement in root mean square error (RMSE),a significant boost in predictive accuracy as reflected by the R² score, which improved from -0.45 to nearly 0. The results highlight the hybrid method a strong and precise solution for predicting packet loss in UWSN, directly impacting the improvement of reliability in underwater communication.