LoRaWAN 환경에서 딥러닝을 이용한 TDoA 측위 개선 방안
Improving TDoA Based Positioning Accuracy Using Deep Learning in a LoRaWAN
- 주제(키워드) Deep learning , TDoA , Location positioning , LoRaWAN , LoRa
- 발행기관 아주대학교
- 지도교수 Ki-Hyung Kim
- 발행년도 2019
- 학위수여년월 2019. 2
- 학위명 석사
- 학과 및 전공 일반대학원 지식정보공학과
- 실제URI http://www.dcollection.net/handler/ajou/000000028622
- 본문언어 영어
- 저작권 아주대학교 논문은 저작권에 의해 보호받습니다.
초록/요약
LoRa is one of the low power wide area communication technologies (LPWA) that enables low cost chip module design due to low power, high receiver sensitivity and license-exempt bandwidth. Because of this, it is a technology suitable for IoT services with low data throughput and variability. For low-power-based positioning in LoRa environments while various techniques have been tried, The error is over a hundred meters. Because of this it is difficult to commercialize practical location based services. In this paper, to reduce the TDoA positioning error, a train was made to correct the time error that occurs when transmitting. We propose a method of learning the time error in the Deep Neural Networks model and correcting it using the learned model in actual positioning. The experimental environment was constructed using python and keras. Experiment result is we confirmed that the error range decreases when the number of reference nodes and collected data are large and the mobile node is close to the reference node.
more목차
Chapter 1 Introduction 1
Chapter 2 Background 3
2.1. LoRa network architecture 3
2.1.1. LoRa gateway 4
2.1.2. LoRa network server 5
2.2. Time difference of arrival 6
2.3. Deep neural networks 7
Chapter 3 Related Work 9
3.1. RSSI proximity and path-loss model 10
3.2. Fingerprint in LoRaWAN 11
3.3. TDoA based positioning in a LoRaWAN 12
Chapter 4 Proposed Method 14
4.1. Reference node based DNN correction architecture 15
Chapter 5 Experiment 19
5.1. Method 19
5.2. Error measurement with DNN compensation model 21
5.3. Correlation with distance between mobile node to reference node 24
5.4. Correlation according to the number of reference node 25
Chapter 6 Conclusion 28
References 29