Optimizing Energy Consumption and Coverage in Underwater Magnetic Induction-Assisted Acoustic WSNs Using Learning Automata-Based Cooperative MIMO Formation

Underwater Wireless Sensor Networks (UWSNs) offer promising exploration capabilities in challenging underwater environments, necessitating a focus on reducing energy consumption while guaranteeing monitoring coverage. Underwater magnetic induction (MI)-assisted acoustic cooperative multiple-input–multiple-output (MIMO) WSNs have shown advantages over traditional UWSNs in various aspects due to the seamless integration of sensor networks and communication technology. However, as an emerging topic, a critical gap exists, as they often overlook the vital considerations of monitoring coverage requirements and the dynamic nature of the unknown underwater environment. Moreover, these advantages can be further enhanced by harnessing the collaborative potential of multiple independent underwater nodes. This paper introduces a significant advancement to the field of MI-assisted Acoustic Cooperative MIMO WSNs leveraging the innovative Confident Information Coverage (CIC) and a reinforcement learning paradigm known as Learning Automata (LA). The paper presents the LA-based Cooperative MIMO Formation (LACMF) algorithm designed to minimize communication energy consumption in sensors while concurrently maximizing coverage performance. Experimental results demonstrate the LACMF considerably outperforms other schemes in terms of energy consumption, and network coverage to satisfy the imposed constraints, the CIC can be improved up to by an additional 52%, 11% reduction in energy consumption.