Abdullahi Kutiriko Abubakar
Nishanth Sastry
ABSTRACT
Low Power Wide Area Networks (LPWANs) are a subset of IoT transmission technologies that have gained traction in recent years with the number of such devices exceeding 200 million. This paper considers the scalability of one such LPWAN, LoRaWAN, as the number of devices in a network increases. Various existing optimisation techniques target LoRa characteristics such as collision rate, fairness, and power consumption. This paper proposes a machine learning ensemble to reduce the total distance between devices and improve the average received signal strength, resulting in improved network throughput, the scalability of LoRaWAN, and the cost of networks. The ensemble consists of a constrained K-Means clustering algorithm, a regression model to validate new gateway locations and a Neural network to estimate signal strength based on the location of the devices. Results show a mean distance reduction of 51% with an RSSI improvement of 3% when maintaining the number of gateways, also achieving a distance reduction of 27% and predicting an RSSI increase of 1% after clustering with 50% of the number of gateways.
- Abdullahi Kutiriko Abubakar, Nishanth Sastry, and Mohamed Kassem. 2021. Internet islands: first class networked communities in isolated regions. In Proceedings of the 16th ACM Workshop on Mobility in the Evolving Internet Architecture (MobiArch ’21.Google Scholar
Digital Library
- F. Adelantado, X. Vilajosana, P. Tuset-Peiro, B. Martinez, J. Melia-Segui, and T. Watteyne. 2017. Understanding the limits of lorawan. (2017).Google Scholar
- M. Aernouts, R. Berkvens, K. V. Vlaenderen, and M. Weyn. 2019. Sigfox and lorawan datasets for fingerprint localization in large urban and rural areas. (2019). https://doi.org/10.5281/zenodo.3904158Google ScholarCross Ref
- Paul E. Black. 2005. greedy algorithm. (2005). https://xlinux.nist.gov/dads/HTML/greedyalgo.htmlGoogle Scholar
- M. Bor and U. Roedig. 2017. Lora transmission parameter selection. (2017).Google Scholar
- P. Bradley, K. Bennett, and A. Demiriz. 2000. Constrained k-means clustering. (2000). https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/Google Scholar
- A. Djoudi, R. Zitouni, N. Zangar, and L. George. 2020. Reconfiguration of lora networks parameters using fuzzy c-means clustering. In 2020 International Symposium on Networks. Computers and Communications (ISNCC, 1–6.Google Scholar
- Dahlqvist Fredrik, Patel Mark, Rajko Alexander, and Shulman Jonathan. 2022. Growing opportunities in the Internet of Things. (2022). https://www.mckinsey.com/industries/private-equity-and-principal-investors/our-insights/growing-opportunities-in-the-internet-of-thingsGoogle Scholar
- R. Gore, J. Li, M. Manry, L. Liu, and C. Yu. 2005. Iterative design of neural network classifiers through regression. International Journal of Artificial Intelligence Tools 14 (2005), 281–302.Google ScholarCross Ref
- K. Hornik, M. Stinchcombe, and H. White. 1989. Multilayer feedforward networks are universal approximators. (1989).Google Scholar
- G. Hufford, A. Longley, and W. Kissick. [n. d.]. A guide to the use of the its irregular terrain model in the area prediction mode. 16 ([n. d.]). https://www.ntia.doc.gov/files/ntia/publications/ntia_82-100_20121129145031_555510.pdfGoogle Scholar
- S. Lathuilière, P. Mesejo, X. Alameda-Pineda, and R. Horaud. 2020. A comprehensive analysis of deep regression. (2020).Google Scholar
- Josh Levy-Kramer. 2022. k-means-constrained. (2022). https://pypi.org/project/k-means-constrained/Google Scholar
- L. Liu, Y. Yao, Z. Cao, and M. Zhang. 2021. Deeplora: Learning accurate path loss model for long distance links in lpwan. In IEEE INFOCOM 2021 - IEEE Conference on Computer Communications. 1–10.Google Scholar
- R. Mina, H. Maryam, R. Zaidi, and S. Ali. 2019. Computational methods for network-aware and network-agnostic iot low power wide area networks (lpwans). IEEE Internet of Things Journal 6, 3 (2019), 5732–5744.Google ScholarCross Ref
- J. H. I. Moerman and J. Hoebeke. 2017. Lora scalability: A simulation model based on interference measurements. Sensors 17(2017), 6.Google Scholar
- N. C. M. Neto. 2020. Fuzzy c-means based GW placement algorithm for lorawan. Ph. D. Dissertation. Guam a University Campus.Google Scholar
- C. N. Nyirenda. 2021. On the efficacy of particle swarm optimization for GW placement in lorawan networks. in intechopen.Google Scholar
- A. Perkov, T. Zhangirov, A. Liss, and N. Grigoryeva. 2020. Peculiarities of regression model design based on neural networks. (2020).Google Scholar
- R. Sandoval, A.-J. Garcia-Sanchez, and J. Garcia-Haro. 2019. Performance optimization of lora nodes for the future smart city/industry. in EURASIP Journal on Wireless Communications and Networking.Google Scholar
- N. Sornin, M. Luis, T. Eirich, T. Kramp, and O. Hersent. 2016. Lorawan specification v1.0.1. Tech. Rep.Google Scholar
- Z. Tan, M. Rahman, A. Rahman, A. Hamid, N. Amin, H. Munir, and M. Zabidi. 2019. Analysis on LoRa RSSI in Urban, Suburban, and Rural Area for Handover Signal Strength-Based Algorithm. (2019).Google Scholar
- The Things Network Global Team. 2020. LoRa World Record Broken: 832km/517mi using 25mW. (2020). https://www.thethingsnetwork.org/article/lorawan-world-record-broken-twice-in-single-experiment-1Google Scholar
- H. Tian, M. Weitnauer, and G. Nyengele. 2018. Optimized GW placement for interference cancellation in transmit-only lpwa networks. in sensors 18(2018), 11.Google Scholar
- A. M. Yousuf, E. M. Rochester, B. Ousat, and M. Ghaderi. 2018. Throughput, Coverage and Scalability of LoRa LPWAN for Internet of Things. In 2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS. 1–10.Google Scholar
Index Terms
- Constrained Machine Learning for LoRa Gateway Location Optimisation
Recommendations
Analysis of time-weighted LoRa-based positioning using machine learning
AbstractLocalization systems have gained attention owing to the paradigm shift from human-centric communication systems (1G to 4G) to the machine-to-machine architectures (5G and beyond). The commercial localization applications standardized ...
Performance Evaluation of RSSI-based Positioning System with Low-cost LoRa Devices
PE-WASUN '19: Proceedings of the 16th ACM International Symposium on Performance Evaluation of Wireless Ad Hoc, Sensor, & Ubiquitous NetworksAlong the last years, we have witnessed the growing demand for services, applications, and systems that depend on the specific location of both people and a variety of things and gadgets. Currently, the Global Positioning System (GPS) offers good ...
An Adaptive and Autonomous LoRa Gateway for Throughput Optimisation
ACSW '19: Proceedings of the Australasian Computer Science Week MulticonferenceThe purpose of this study is twofold. First, this study proposes a cost-effective LoRa gateway to improve bandwidth utilisation to achieve optimal network throughput for LoRa networks from a hardware design perspective. Secondly, this study creates a ...
Comments