In order to meet the high transmission speed and flexible coverage demands of future generation networks, researchers are exploring the use of unmanned aerial vehicles (UAVs), also known as drones. However, there are challenges associated with using drones in network infrastructure, such as the need for numerous antennas and increased signal propagation losses, resulting in higher energy consumption. In light of these challenges, a team of mathematicians from RUDN University, in collaboration with researchers from Egypt, China, Saudi Arabia, and Uzbekistan, have developed an artificial neural network to optimize energy consumption in drone networks.
The researchers introduced an intelligent resource allocation system called IRA-AEODL (intelligent resource allocation using an artificial ecosystem optimizer with deep learning). This system utilizes a unique composite offloaded encoder architecture to distribute resources efficiently in wireless networks connected to drones. The key principle of its operation is to generate a response at the output layer that closely matches the desired output. Through the use of an artificial ecosystem optimizer, the system identifies the optimal parameters for the neural network.
Compared to existing systems, IRA-AEODL has demonstrated significant improvements in performance. In trials with 2-6 drones, the average network throughput increased by 3%-17%, and when the number of users increased, the improvements reached up to 30%. The system also incorporates mathematically stable approaches, enhancing its reliability and efficiency.
“A network built using drones expands network capacity and coverage. In addition, drones are used as mobile charging stations to supply power to low-power gadgets. Since batteries on drones are typically limited in capacity, it is important to make tradeoffs between coverage area and energy use, as well as maintenance time. To improve coverage and energy efficiency, it is important to allocate resources, namely subchannels, transmission power, and user services,” explained Ammar Muthanna, Ph.D., the Director of the Scientific Center for Modeling Wireless 5G Networks at RUDN University.
The research published in the journal Drones highlights the potential of this innovative system to optimize energy consumption and enhance the performance of drone networks. With further development and integration, it could pave the way for more efficient and reliable communication networks in the future.
The source of the article is from the blog publicsectortravel.org.uk