کنفرانس مهندسی برق ایران

صفحه اصلی / سی و دومین کنفرانس بین المللی مهندسی برق

Using GA and ML to Improve LoRa Network Performance

نویسندگان :

Yas Hosseini Tehrani¹ Seyed mojtaba Atarodi²

1- دانشگاه صنعتی شریف 2- دانشگاه صنعتی شریف

کلمات کلیدی :

LoRawan scalability،Power consumption،Genetic algorithm،Machine learning،Adaptive data rate

چکیده :

Nowadays, the Internet of Things has become one of the leading fields in the industry, and among various technologies, LoRa has been able to gain a good position due to its low power consumption and high operating range. Due to the importance of power consumption reduction in LoRa networks, many ideas have been proposed and one of the most important of them is network parameters optimization. The main purpose of this paper is to obtain the most optimal possible state for network power consumption and scalability with the help of optimization algorithms such as genetic algorithms along with network performance prediction methods such as machine learning. We will also prove the superiority of the obtained method by comparing the results obtained with the ADR method, which is known as a traditional method to set network parameters. Finally, we will test the parameters obtained from this method on a real network. The obtained results verify the performance and efficiency of the proposed method.