Loading...

LoRa Network Optimization with Emphasis on Power Consumption and Scalability

Haghighipour, Saeed | 2023

37 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 56528 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Atarodi, Mojtaba
  7. Abstract:
  8. The Internet of Things is one of those concepts that, while it has gained significant importance in recent years in scientific and industrial communities, still faces various challenges, such as power consumption and scalability. In networks powered by batteries, it is necessary to optimize power consumption to extend the network's lifespan to the maximum possible extent. Additionally, considering the large number of connected devices in the Internet of Things network, it is essential to optimize the number of devices connected per gateway, ultimately reducing the need for fewer gateways in a network. In this research, we utilized simulation-based methods to extract output parameters of a network, such as power consumption and packet transmission rates, for a large number of networks. Using this data and machine learning techniques, we proposed a model for estimating the output parameters of an unknown network. Finally, with the help of a genetic algorithm, we identified the optimal parameters for the network in question. In this study, compared to the baseline article, power consumption improved by 52.26%, and scalability improved by 6.72%. In the next crucial step, the network was practically implemented with the help of a gateway and several end nodes, and the optimal settings presented in the previous step were applied. In this phase as well, power consumption improved by 32.24%, and scalability improved by 4.58%. Due to certain immeasurable parameters and uncertainties in the environment, the improvement percentage was slightly lower compared to the simulation stage. Considering these results, it can be claimed that the proposed method in this research has achieved a relative superiority over other presented methods
  9. Keywords:
  10. Internet of Things ; LoRa Technology ; Optimization ; Power Consumption ; Scalability ; Genetic Algorithm ; Machine Learning

 Digital Object List

 Bookmark

No TOC