LoRa Tabanlı Bir Orman Yangını Yönetim Sistemi Dijital İkizinin Ayrıntıları

Öz

Orman yangınlarının erken tespiti, ekosistemler için hayati önem taşır. Bu amaçla sensör ağları, sıcaklık ve nem gibi verileri toplayarak ormanlardaki değişiklikleri izler. Özellikle LoRa gibi uzun menzilli ve düşük enerjili iletişim teknolojileri, bu ağlarda yaygın olarak kullanılır. Ancak bu ağların yönetimi, her bir ormanın farklı gereksinimleri olduğundan karmaşık olabilir. Dijital ikiz teknolojisi, bu sorunu çözmek için fiziksel sistemlerin sanal kopyalarını oluşturarak, farklı senaryoları simüle etmeye ve sistemleri optimize etmeye olanak tanır. Lakin bilgisayar ağlarının ilişkisel yapısı dijital ikizde kullanılan bazı yapay zeka modelleri için zorlayıcı olabilir. Grafik sinir ağları ise dijital ikizlerin, ağların karmaşık yapısını anlamasına ve optimize etmesine yardımcı olur. Ayrıca, nesnelerin interneti ağlarının, dijital ikizlerin iki yönlü ve sürekli iletişim talebini karşılaması uygulanabilir değildir. Bu nedenle, bu çalışmada dijital ikizlerin bu ağlara entegrasyonunu kolaylaştıracak bir tahminci modeli tasarlanmıştır. Tahminci ağın geçmiş durumlarından gelecek durumlarını tahmin ederek dijital ikizin ihtiyacı olan veriyi sağlar. Çalışmanın ilk sonuçları özellikle küçük ölçekli ağlar için umut vericidir. Ancak ağın ölçeği büyüdükçe sistemin yaptığı hatalar da artmaktadır.

Anahtar Kelimeler

• Dijital İkiz
• Nesnelerin İnterneti
• Grafik Sinir Ağları
• Orman Yangını Tespiti

Details of a Digital Twin for a LoRa Based Forest Fire Management System

Öz

Early detection of forest fires is vital for ecosystems. For this purpose, sensor networks collect data such as temperature and humidity and monitor changes in forests. Long-range and low-energy communication technologies such as LoRa are especially widely used in these networks. However, the management of these networks can be complicated since each forest has different requirements. Digital twin technology allows the simulation of different scenarios and optimization systems by creating virtual copies of physical systems to solve this problem. However, the relational structure of computer networks can be challenging for some artificial intelligence models used in digital twins. Graph neural networks help digital twins to understand and optimize the complicated structure of networks. In addition, it is not feasible for Internet of Things networks to meet digital twins’ two-way and continuous communication demand. Therefore, in this study, a forecaster model is designed to facilitate the integration of digital twins into these networks. The forecaster provides the data the digital twin needs by predicting the network’s future states from its past states. The first results of the study are promising, especially for small-scale networks. However, as the scale of the network grows, the errors made by the system also increase.

Anahtar Kelimeler

• Digital Twin
• IoT
• Graph Neural Networks
• Forest Fire Detection

Kaynakça

1. OGM. “Official statistics.” (accessed: 19/01/2025). (2024), [Online]. Available: https://www.ogm.gov.tr/tr/e-kutuphane/resmi-istatistikler.
2. V. Chowdary, M. Gupta, and R. Singh, “A review on forest fire detection techniques: A decadal perspective,” International Journal of Engineering & Technology, vol. 7, p. 1312, Jul. 2018. DOI: 10.14419/ijet.v7i3.12.17876.
3. K. Grover, D. Kahali, S. Verma, and B. Subramanian, “Wsn-based system for forest fire detection and mitigation,” in Emerging Technologies for Agriculture and Environment, B. Subramanian, S.-S. Chen, and K. R. Reddy, Eds., Singapore: Springer Singapore, 2020, pp. 249–260, ISBN: 978-981-13-7968-0.
4. A. Molina-Pico, D. Cuesta-Frau, A. Araujo, J. Alejandre, and A. Rozas, “Forest monitoring and wildland early fire detection by a hierarchical wireless sensor network,” Journal of Sensors, vol. 2016, no. 1, p. 8 325 845, 2016. DOI: https://doi.org/10.1155/2016/8325845. eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1155/2016/8325845. [Online]. Available: https://onlinelibrary.wiley.com/doi/abs/10.1155/2016/8325845.
5. G. Saldamli, S. Deshpande, K. Jawalekar, P. Gholap, L. Tawalbeh, and L. Ertaul, “Wildfire detection using wireless mesh network,” in 2019 Fourth International Conference on Fog and Mobile Edge Computing (FMEC), 2019, pp. 229–234. DOI: 10.1109/FMEC.2019.8795316.
6. J. Granda Cantuña, D. Bastidas, S. Solórzano, and J.-M. Clairand, “Design and implementation of a wireless sensor network to detect forest fires,” in 2017 Fourth International Conference on eDemocracy & eGovernment (ICEDEG), 2017, pp. 15–21. DOI: 10.1109/ICEDEG.2017.7962508.
7. U. Dampage, L. Bandaranayake, R. Wanasinghe, K. Kottahachchi, and B. Jayasanka, “Forest fire detection system using wireless sensor networks and machine learning,” Scientific Reports, vol. 12, no. 1, p. 46, Jan. 2022, ISSN: 2045-2322. DOI: 10.1038/s41598-021-03882-9. [Online]. Available: https://doi.org/10.1038/s41598-021-03882-9.
8. W. Benzekri, A. E. Moussati, O. Moussaoui, and M. Berrajaa, “Early forest fire detection system using wireless sensor network and deep learning,” International Journal of Advanced Computer Science and Applications, vol. 11, no. 5, 2020. DOI: 10.14569/IJACSA.2020.0110564. [Online]. Available: http://dx.doi.org/10.14569/IJACSA.2020.0110564.

9. P. Pokhrel and H. Soliman, “Advancing early forest fire detection utilizing smart wireless sensor networks,” in Ambient Intelligence, A. Kameas and K. Stathis, Eds., Cham: Springer International Publishing, 2018, pp. 63–73, ISBN: 978-3-030-03062-9.
10. Imran, N. Iqbal, S. Ahmad, and D. H. Kim, “Towards mountain fire safety using fire spread predictive analytics and mountain fire containment in iot environment,” Sustainability, vol. 13, no. 5, 2021, ISSN: 2071-1050. DOI: 10.3390/su13052461. [Online]. Available: https://www.mdpi.com/2071-1050/13/5/2461.
11. M. Ferriol-Galmés, K. Rusek, J. Suárez-Varela, et al., “Routenet-erlang: A graph neural network for network performance evaluation,” in IEEE INFOCOM 2022 - IEEE Conference on Computer Communications, 2022, pp. 2018–2027. DOI: 10.1109/INFOCOM48880.2022.9796944.
12. M. Ferriol-Galmés, J. Paillisse, J. Suárez-Varela, et al., “Routenet-fermi: Network modeling with graph neural networks,” IEEE/ACM Transactions on Networking, vol. 31, no. 6, pp. 3080–3095, 2023. DOI: 10.1109/TNET.2023.3269983.
13. P. Almasan, J. Suárez-Varela, K. Rusek, P. Barlet-Ros, and A. Cabellos-Aparicio, “Deep reinforcement learning meets graph neural networks: Exploring a routing optimization use case,” Computer Communications, vol. 196, pp. 184–194, Dec. 2022, ISSN: 0140-3664. DOI: 10.1016/j.comcom.2022.09.029. [Online]. Available: http://dx.doi.org/10.1016/j.comcom.2022.09.029.
14. M. Ferriol-Galmés, J. Suárez-Varela, J. Paillissé, et al., “Building a digital twin for network optimization using graph neural networks,” Computer Networks, vol. 217, p. 109 329, 2022, ISSN: 1389-1286. DOI: https://doi.org/10.1016/j.comnet.2022.109329. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1389128622003681.
15. M. Wang, L. Hui, Y. Cui, R. Liang, and Z. Liu, “Xnet: Improving expressiveness and granularity for network modeling with graph neural networks,” in IEEE INFOCOM 2022 - IEEE Conference on Computer Communications, 2022, pp. 2028–2037. DOI: 10.1109/INFOCOM48880.2022.9796726.
16. M. Abdel-Basset, H. Hawash, K. M. Sallam, I. Elgendi, and K. Munasinghe, “Digital twin for optimization of slicing-enabled communication networks: A federated graph learning approach,” IEEE Communications Magazine, vol. 61, no. 10, pp. 100–106, 2023. DOI: 10.1109/MCOM.003.2200609.
17. H.Wang, Y.Wu, G. Min, andW. Miao, “A graph neural network-based digital twin for network slicing management,” IEEE Transactions on Industrial Informatics, vol. 18, no. 2, pp. 1367–1376, 2022. DOI: 10.1109/TII.2020.3047843.
18. H. Shin, S. Oh, A. Isah, I. Aliyu, J. Park, and J. Kim, “Network traffic prediction model in a data-driven digital twin network architecture,” Electronics, vol. 12, no. 18, 2023, ISSN: 2079-9292. DOI: 10.3390/electronics12183957. [Online]. Available: https://www.mdpi.com/2079-9292/12/18/3957.
19. M. Hata, “Empirical formula for propagation loss in land mobile radio services,” IEEE Transactions on Vehicular Technology, vol. 29, no. 3, pp. 317–325, 1980. DOI: 10.1109/T-VT.1980.23859.