Air-ground collaborative network coverage enhancement algorithm based on power grid and deep learning

Mainstream power communication methods can no longer meet the growing communication needs of the power industry. Airborne networks can significantly improve wireless coverage and network capacity, and it can meet the communication needs of the power industry in cities with different population densities. However, the coverage capacity is severely affected by the limited energy of the over-the-air network. Therefore, how to significantly enhance the coverage performance of airborne base stations with limited range time is a key issue. Based on this, we deeply analyze the characteristics of the power grid scenario and establish an air-ground collaborative network architecture to meet the application of the power grid scenario. And then, we analyze the air-ground collaborative network coverage performance optimization problem, and we first transform the coverage enhancement problem into a highly dynamic deployment problem of air-ground network base stations. We propose a deep learning-based coverage enhancement algorithm for air-ground collaborative networks, and we fully consider coverage energy efficiency and time efficiency in the design of the reward function. Furthermore, we utilize a collaborative approach between ground and air networks to continuously optimize and adjust the highly dynamic deployment strategy of air network base stations, thus enhancing the air collaborative network coverage performance. Simulation experimental results show that the algorithm we proposed consistently achieves higher coverage efficiency compared to the sequential service algorithm, and it significantly improves coverage efficiency compared to other mainstream algorithms.