**Development of a Solar-Powered Edge Processing Perimeter Alert System with AI and LoRa/LoRaWAN Integration for Drone Detection and Enhanced Security**
------------------------------------------------------------------------
M. Mejia-Herrera, J.S Botero-Valencia, J. Ortega, and R. Hernández-García
![Exploded System Assembly][2]
**Abstract**: Edge processing is a trend for developing new technologies that can utilize Artificial Intelligence without transmitting large volumes of data to centralized artificial intelligence services. This can be particularly interesting for security matters, where it is necessary to reduce the possibility
of intrusion or data breaches and decentralize alert systems simultaneously. In this work, we present the development of a perimeter alert system that combines multiple sensors with AI algorithms processed at the edge and can be integrated into a LoRa or LoRaWAN network powered by solar energy. The system features a PDM microphone based on an Arduino Nano 33 BLE. As a proof of concept, it was trained to identify a drone or a UH-60 from an audio spectrogram. The system is complemented by two PIR motion sensors and a microwave sensor with a range of up to 11 meters. Additionally, the DC magnetic field is measured to identify possible sensor movements or changes caused by large bodies. A configurable RGB light signal is used to visually indicate motion or sound detection. The monitoring system communicates with a second MCU integrated with a LoRa or LoRaWAN communication module, allowing information to be sent over kilometers away. The system is powered by a LiPo battery, which is recharged using solar energy. The perimeter alert system offers numerous advantages, such as edge processing for enhanced data privacy and reduced latency, integrating multiple sensors for increased accuracy, and a decentralized approach to improve security. Its compatibility with LoRa or LoRaWAN networks enables long-range communication, while solar-powered operation reduces environmental impact. The visually intuitive RGB light signal provides immediate feedback, and the system’s scalability ensures adaptability to various security contexts. These features make it a versatile and powerful solution for applications such as border control, protection of private property, and monitoring of critical infrastructure.
**Keywords**: IoT; Drone Detection; Aircraft Detection; Perimeter Security
[1]: https://osf.io/5n7ey
[2]: https://mfr.osf.io/export?url=https://osf.io/download/5n7ey/?direct=&mode=render&format=2400x2400.jpeg
