| Summary: | Our research focuses on developing an advanced data fusion methodology tailored for 6G wireless sensor networks (WSNs) to optimize data transmission efficiency and network performance. We introduce a multi-faceted approach for cluster head (CH) selection and relay node optimization, leveraging group intelligence optimisation techniques. The CH selection process comprehensively evaluates multiple parameters, including residual energy, node degree, connectivity, link stability, and node centrality. Edge-assisted unmanned aerial vehicles (UAVs) are strategically employed as relay nodes, considering factors such as link stability, channel state information, signal-to-noise ratio, and channel gain to minimize data ambiguity and enhance delivery rates. Our methodology employs quad tree-based clustering to partition the network into quadrants based on node density, facilitating efficient data aggregation and transmission. Soft actor-critic algorithms are utilised for coverage hole detection and recovery, optimising node selection and minimising data loss with minimal energy consumption. Dynamic sleep scheduling is integrated using hidden Markov model algorithms, considering buffer capacity, historical data, expected coverage rates, and residual energy to prolong network lifetime while reducing energy consumption. Furthermore, group intelligence optimization using krill herd optimization is applied for optimal UAV-relay selection, effectively minimising transmission delays and energy consumption. This holistic approach significantly enhances network reliability, stability, and performance, paving the way for efficient 6G WSNs. The performance outcomes demonstrate the proposed work achieves better performance compared to other state-of-the-art works. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.
|
|---|