Investigating the Influence of Temperature on UAV Signal Quality

Abstract

Advancements in drone technology make them important in many areas. military, industry, and disaster The efficacy of a drone's communication systems can be greatly impacted by temperature fluctuations, either from environmental conditions or mechanical problems in the drone's construction. This study gives an analysis and computational model of the impact of temperature on the performance of drone communication. Utilizing a one-dimensional convolutional neural network, we aim to forecast the signal-to-noise ratio (SNR) and received signal strength indicator (RSSI). Following the initial stage of dataset creation in the drone laboratory, proceed to reprocess the dataset and divide it into a 70% training set and a 30% testing set. Subsequently, a graphical user interface (GUI) was developed using MATLAB App Designer to enhance user friendliness. The outcome suggests that the efficiency of the drone communication system declines with rising temperatures. Using 1DCNN is our contribution to this work; other studies depend only on simulation to assess performance. One benefit of 1DCNN is that the impact may be evaluated by automatically extracting important features from the input dataset. Using 1DCNN is our special addition to this project; other research evaluate the UAV communication system's effectiveness only through simulation. We propose in this work to optimize system characteristics for improved performance, including power transfer, by adding a feedback loop between the CNN result and the communication system. Furthermore, we investigate how different weather conditions, such wind and rain, affect UAV communication systems.