AI-Driven and MEC-Empowered Confident Information Coverage Hole Recovery in 6G-Enabled IoT

With the development of 6G, a series of ultra-reliable intelligent IoT applications have been promoted, which puts forward higher requirements for the security and reliability of networks. Coverage Holes (CHs) pose great challenges to the network coverage reliability, and it is essential to repair CHs quickly and effectively. In this paper, we focus on the problem of CHs recovery of 6G IoT based on Mobile Edge Computing (MEC) and Artificial Intelligence (AI) to ensure reliable coverage. A Confident Information Coverage Hole Recovery Algorithm (CICHRA) is proposed based on the fusion model of the disc model and the confident information model, which takes advantage of the spatial correlation. The mobile edge node uses the utility to guide its movement, and the CHs are recovered by repeated games based on Q-learning. Furthermore, an Improved Confident Information Coverage Hole Recovery Algorithm (I-CICHRA) is proposed to enhance recovery performance and reduce time complexity. The I-CICHRA makes edge nodes' movement more directional and accurate, thus improving repair efficiency. A series of simulation comparisons with the Distributed Payoff-based Q-learning Algorithm (DPQA) indicate that the proposed algorithms have better performance in overall coverage, iteration times, energy consumption, and energy efficiency.