Answers are grounded in this paper and cite their sources.
In the current era of technological advancement, the use of drones has expanded in various fields. These fields include aerial photography, medical supply delivery to accident scenes, forestry, and agricultural monitoring. However, the presence of a large number of drones operating simultaneously within a shared airspace and common spectrum bands creates a significant challenge. This challenge lies in managing communication interference between these aircrafts. This research aims to address this problem by developing a framework based on deep reinforcement learning techniques to adaptively manage interference and make decisions according to the current state of the network. The Policy Proximal Optimization (PPO) algorithm is employed to respond to network conditions in real-time and dynamically select the most appropriate action. These actions include adjusting transmission power, repositioning, maintaining the current state, or reducing transmission power as needed. The proposed model achieved an average performance of 85.7%, representing a 23.4% improvement compared to the pre-optimization value. It also demonstrated a 13.8% improvement in high-interference scenarios and a 14.9% enhancement in signal-to-noise ratio. These results highlight the potential of deep reinforcement learning as an adaptive and effective solution for mitigating interference in drone networks.
No takes yet. Share an insight, caveat, or question.
Fidel Ahmad Ibrahim (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: