An Energy Harvesting Algorithm for UAV-Assisted TinyML Consumer Electronic in Low-Power IoT Networks

Unmanned aerial vehicles (UAVs) play a crucial role in remote environmental applications of the Low-Power Internet of Things (IoT) network. However, the interaction between a large number of consumer electronics products integrated with TinyML (CEP-TML) may lead to serious interference and overlap issues in Low-Power IoT networks, which still pose challenges to the lifespan of UAVs. To address this issue, this paper proposes an interference hypergraph-based energy harvesting resource allocation (IH-EHRA) algorithm in UAV-assisted CEP-TML communication (UAV-CEPC-TML) networks, aimed at ensuring effective resource management in overlapping interference scenarios. Firstly, we established an interference hypergraph model to analyze the types and relationships of interference in a Low-Power IoT network, to reduce interference and optimize spectrum resource utilization. Then, in the overlapping interference scenario, we propose an EH optimization model with imperfect channel state information (CSI), aiming to maximize network throughput while improving the service life of UAVs. Finally, we optimize the model into two subproblems and apply learning theory to reduce the impact of imperfect CSI to obtain the optimal solution to the problem. The simulation results show that the algorithm can effectively ensure the EH requirements of UAVs, and improve the interference efficiency and throughput of the network.