Route Optimization for Urban Waste Collection via LoRa Communication and Deep Q-Network in a Controlled Simulation
DOI:
https://doi.org/10.56294/dm2025829Keywords:
Routing Algorithms, Deep Reinforcement Learning (DQN), LoRa Technology, Smart Cities, Internet of Things (IoT)Abstract
Traditional urban solid waste management in Latin American cities operates using fixed routes, without considering the dynamic state of waste containers. This rigid approach leads to operational inefficiencies, excessive fuel consumption, and a significant environmental impact. A distributed architecture was designed that integrates HC-SR04 sensors (fill level) and MQ-135 sensors (air quality), connected to Heltec WiFi LoRa 32 V3 nodes. The captured data is transmitted via LoRa technology to a central gateway and stored in real-time on Firebase. These data were used to train a Deep Q-Network (DQN) model, developed in PyTorch using OpenAI Gym, with an input of 30 parameters (15 containers × 2 variables) and 15 possible actions. Training was performed over 1000 epochs with a learning rate of 0.0005 and a discount factor γ = 0.99. The model achieved a stable decision policy to dynamically prioritize critical collection points. Compared to static routes, there was a 16.4% reduction in distance traveled, 16.3% in operational time, and 16.4% in fuel consumption. Route planning was complemented by the Dijkstra algorithm and visualized in a geospatial interface using the Google Maps API. The system was implemented as a Flask API integrated with a hybrid mobile application, allowing real-time visualization of optimized routes and container status. This intelligent and scalable solution reduces resource usage, improves urban sustainability, and is well-suited for deployment in smart cities.
References
1. Mr. Shreyas Bharadhwaj SP, Mr. Adithya S, Mr. Vishwas AM, Ms. Sharanya R C. Dynamic Route Optimization for Urban Waste Collection. Int J Res Appl Sci Eng Technol. 2025 Sep;13(4):1608–13. doi: 10.22214/ijraset.2025.68614 DOI: https://doi.org/10.22214/ijraset.2025.68614
2. Jerbi H, Gnana Vincy VGA, Ben Aoun S, Abbassi R, Kchaou M. Optimizing waste management in smart Cities: An IoT-Based approach using dynamic bald eagle search optimization algorithm (DBESO) and machine learning. Journal of Urban Management. 2025 Jun 13;(13). doi: 10.1016/j.jum.2025.05.015 DOI: https://doi.org/10.1016/j.jum.2025.05.015
3. UNEP. Global Waste Management Outlook 2024 | UNEP - UN Environment Programme [Internet]. 2024 [cited 2025 Sep 14]. Available from: https://www.unep.org/resources/global-waste-management-outlook-2024
4. Olawade DB, Fapohunda O, Wada OZ, Usman SO, Ige AO, Ajisafe O, et al. Smart waste management: A paradigm shift enabled by artificial intelligence. Waste Management Bulletin. 2024 Jun 1;2(2):244–63. doi: 10.1016/j.wmb.2024.05.001 DOI: https://doi.org/10.1016/j.wmb.2024.05.001
5. Baldo D, Mecocci A, Parrino S, Peruzzi G, Pozzebon A. A Multi-Layer LoRaWAN Infrastructure for Smart Waste Management. Sensors 2021, Vol 21, Page 2600. 2021 Apr 7;21(8):2600. doi: 10.3390/S21082600 DOI: https://doi.org/10.3390/s21082600
6. Stephan T, Hari Krishna SM, Lin CC, Sumesh U, Agarwal S, Kim H. ProWaste for proactive urban waste management using IoT and machine learning. Sci Rep. 2025 Jul 30;15(1):27790. doi: 10.1038/S41598-025-08452-X DOI: https://doi.org/10.1038/s41598-025-08452-x
7. Khallaf N, Abd-El Rouf O, Algarni AD, Hadhoud M, Kafafy A. Enhanced vehicle routing for medical waste management via hybrid deep reinforcement learning and optimization algorithms. Front Artif Intell. 2025 Feb 12;8:1496653. doi: 10.3389/FRAI.2025.1496653 DOI: https://doi.org/10.3389/frai.2025.1496653
8. Nguyen DVA, Gunawan A, Misir M, Hui LK, Vansteenwegen P. Deep reinforcement learning for solving the stochastic e-waste collection problem. Eur J Oper Res. 2025 Nov 16;327:309–25. doi: 10.1016/j.ejor.2025.04.033 DOI: https://doi.org/10.1016/j.ejor.2025.04.033
9. Rabelo L, Rincón-Guio C, Laynes V, Gutierrez-Franco E, Bhat V, Zamora-Aguas J, et al. Effective last-mile delivery using reinforcement learning and social media-based traffic prediction in underdeveloped megacities. Discover Cities 2025 2:1. 2025 Aug 17;2(1):1–26. doi: 10.1007/S44327-025-00112-Z DOI: https://doi.org/10.1007/s44327-025-00112-z
10. Ramson SRJ, Vishnu S, Kirubaraj AA, Anagnostopoulos T, Abu-Mahfouz AM. A LoRaWAN IoT-Enabled Trash Bin Level Monitoring System. IEEE Trans Industr Inform. 2022 Feb 1;18(2):786–95. doi: 10.1109/TII.2021.3078556 DOI: https://doi.org/10.1109/TII.2021.3078556
11. Ayala A. NUEVOS RECOLECTORES DE RESIDUOS SÓLIDOS PARA LA CIUDAD [Internet]. 2022 [cited 2025 Sep 14]. Available from: https://www.ibarra.gob.ec/site/2022/07/nuevos-recolectores-de-residuos-solidos-para-la-ciudad/
12. Cruz N, Cota N, Tremoceiro J, Davoli L, Martalò M, Ferrari G. LoRaWAN and Urban Waste Management—A Trial. Sensors. 2021 Mar 18;21(6):2142. doi: 10.3390/s21062142 DOI: https://doi.org/10.3390/s21062142
13. Kavitha T, Chaganti KR, Elicherla SLR, Kumar MR, Chaithanya D, Manikanta K. Deep Reinforcement Learning for Energy Efficiency Optimization using Autonomous Waste Management in Smart Cities. In: 2025 5th International Conference on Trends in Material Science and Inventive Materials (ICTMIM). Kanyakumari, India: IEEE; 2025. p. 272–8. DOI: https://doi.org/10.1109/ICTMIM65579.2025.10988394
14. Yadav DK, M TAV, Aadil M. Open Lora Design and Implementation For IoT. In: 2023 International Conference on Power Energy, Environment & Intelligent Control (PEEIC). Greater Noida, India: IEEE; 2023. p. 822–6. DOI: https://doi.org/10.1109/PEEIC59336.2023.10451093
15. Croce D, Garlisi D, Giuliano F, Valvo A Lo, Mangione S, Tinnirello I. Performance of LoRa for Bike-Sharing Systems. In: 2019 AEIT International Conference of Electrical and Electronic Technologies for Automotive (AEIT AUTOMOTIVE). Turin, Italy: IEEE; 2019. p. 1–6. DOI: https://doi.org/10.23919/EETA.2019.8804519
16. Bhavanam BPR, Ragam P. Exploring LoRa Signal Propagation in Indoor and Outdoor Environments: A Comparative Study. In: 2024 IEEE International Conference on Smart Power Control and Renewable Energy (ICSPCRE). Rourkela, India: IEEE; 2024. p. 1–6. DOI: https://doi.org/10.1109/ICSPCRE62303.2024.10675046
17. Soto-Ortiz SI, Tolentino-Cruz MG, Porras-Rosas U. IoT monitoring and control prototype with Zabbix and LoRa communication, for Tilapia Biofloc systems. In: 2024 IEEE International Conference on Engineering Veracruz (ICEV). Boca del Rio, Veracruz, México: IEEE; 2024. DOI: https://doi.org/10.1109/ICEV63254.2024.10766033
18. Wulandari A, Ramadhani EH, Fathurahman M, Hikmaturokhman A. Implementation Analysis of the PRESENT Algorithm on ATmega328P for Securing RFM95W LoRa Communications. In: 2024 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT). Mataram, Indonesia: IEEE; 2024. p. 615–21. DOI: https://doi.org/10.1109/COMNETSAT63286.2024.10862268
19. Liu Y, Cai J, Qiu M. Research on low-power and low-cost smart animal husbandry positioning system based on LoRa transmission. In: 2025 5th International Symposium on Computer Technology and Information Science (ISCTIS). Xi’an, China: IEEE; 2025. p. 571–5. DOI: https://doi.org/10.1109/ISCTIS65944.2025.11065437
20. Sujatha V, Prasanna KL, Niharika K, Charishma V, Sai KB. Network Intrusion Detection using Deep Reinforcement Learning. In: 2023 7th International Conference on Computing Methodologies and Communication (ICCMC). Erode, India: IEEE; 2023. p. 1146–50. DOI: https://doi.org/10.1109/ICCMC56507.2023.10083673
21. Jayakody D. Deep Q-Networks (DQN) - A Quick Introduction (with Code) [Internet]. 2022 [cited 2025 Apr 19]. Available from: https://dilithjay.com/blog/dqn
22. Caiza G, Soto-Rodríguez A, Ayala P, Garcia CA, García M V. Applying Deep Q-Networks to Local Route Optimization. In: 2024 IEEE 22nd International Conference on Industrial Informatics (INDIN). Beijing, China: IEEE; 2024. p. 1–8. DOI: https://doi.org/10.1109/INDIN58382.2024.10774080
23. Heltec Automation. WiFi LoRa 32(V3) [Internet]. 2024 [cited 2025 May 20]. Available from: https://heltec.org/project/wifi-lora-32-v3/.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Gabriela Caragulla-Briceño, Francisco Ger-Ortega, Fabián Cuzme-Rodríguez, Luis Suárez-Zambrano, Alejandra Pinto-Erazo, Henry Farinango-Endara (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
The article is distributed under the Creative Commons Attribution 4.0 License. Unless otherwise stated, associated published material is distributed under the same licence.
