AN INTELLIGENT LEARNING-DRIVEN FOR DYNAMIC WASTE COLLECTION ROUTING USING LSTM AND EVOLUTIONARY CVRP OPTIMIZATION
DOI:
https://doi.org/10.33480/jitk.v12i1.8357Keywords:
CVRP, Evolutionary Algorithms, LSTM, Smart City, Waste Collection RoutingAbstract
Inefficient waste collection routes result in significant operational costs and environmental impacts. Traditional static routes based on historical averages often deviate substantially from actual requirements. This study proposes an intelligent framework integrating Long Short-Term Memory (LSTM) networks for dynamic time-series forecasting with an Evolutionary Capacitated Vehicle Routing Problem (CVRP) optimizer. The LSTM model captures temporal waste generation patterns using a 7-day sliding window; these patterns are fed into a metaheuristic optimizer that minimizes travel distance to disposal sites while eliminating redundant trips. Experimental results demonstrate high prediction accuracy, with the Mean Squared Error (MSE) converging at 0.0001 during the validation phase. Furthermore, the optimization process achieved a 10.95% reduction (22.5 km/day) in average travel distance compared to the baseline model. In high-density scenarios, the framework improved route efficiency by up to 15.99%. The study concludes that combining deep learning memory capabilities with evolutionary optimization provides a reliable decision-support system for smart city waste management..
Downloads
References
[1] W. Li, H. Ibrahim, T. F. Ng, and S. L. Wang, “A literature review of the state of the art of sustainable waste collection and vehicle routing problem,” J. Air & Waste Manag. Assoc., vol. 74, no. 11, pp. 851–876, 2024, doi: 10.1080/10962247.2024.2415298.
[2] C. Hess, A. G. Dragomir, K. F. Doerner, and D. Vigo, “Waste Collection Routing: a Survey on Problems and Methods,” Comput. & Oper. Res., vol. 150, p. 106090, 2023, doi: 10.1016/j.cor.2023.106090.
[3] Y. Niu, C. Xu, S. Liao, S. Zhang, and J. Xiao, “Multi-objective location-routing optimization based on machine learning for green municipal waste management,” Waste Manag., vol. 181, pp. 157–167, 2024, doi: 10.1016/j.wasman.2024.04.001.
[4] C. Fernandez and others, “Decision Support Systems for Smart City Waste Management: A survey,” IEEE Access, vol. 10, pp. 45012–45028, 2022, doi: 10.1109/ACCESS.2022.3168234.
[5] T. Nguyen and others, “Deep Learning in Solid Waste Management: A state-of-the-art review,” Waste Manag., vol. 144, pp. 205–220, 2022.
[6] S. Kumari and S. Kumar, “The vehicle routing problem as applied to residential solid waste collection operations: A systematic review,” Grow. Sci., vol. 14, no. 1, pp. 1–18, 2024.
[7] J. Kim, A. Manna, A. Roy, and I. Moon, “Clustered Vehicle Routing Problem For Waste Collection With Smart Operational Management Approaches,” Int. Trans. Oper. Res., vol. 32, no. 2, pp. 1025–1048, 2025, doi: 10.1111/itor.13364.
[8] L. Xu, Q. Wang, and Z. Li, “Long short-term memory neural network and improved particle swarm optimization–based modeling and scenario analysis for municipal solid waste generation in Shanghai, China,” Waste Manag., vol. 139, pp. 101–112, 2022, doi: 10.1016/j.wasman.2021.11.036.
[9] T. Desalegn and others, “Predicting Municipal Solid Waste Generation using LSTM, ARIMA and Random Forest models,” Environ. Model. & Assess., vol. 29, no. 4, pp. 501–515, 2024.
[10] A. Sobhanan, J. Park, J. Park, and C. Kwon, “Genetic Algorithms with Neural Cost Predictor for Solving Hierarchical Vehicle Routing Problems,” Transp. Sci., vol. 57, no. 1, pp. 1–20, 2023, doi: 10.1287/trsc.2023.0163.
[11] A. Hentout, A. Maoudj, A. Kouider, and A. Mustapha, “Effective GA approach for municipal solid waste collection: dynamic capacitated vehicle routing in smart cities,” Int. J. Artif. Intell. Soft Comput., vol. 7, pp. 329–352, 2022, [Online]. Available: https://api.semanticscholar.org/CorpusID:258321907
[12] Q. S. Khalid, S. Maqsood, J. Mumtaz, and S. M. Qureshi, “An emission-capacitated vehicle routing model for sustainable urban waste collection using hybrid guided local search,” Sci. Rep., vol. 16, p. 1234, 2026, doi: 10.1038/s41598-026-38829-5.
[13] Y. Bouleft and A. E. Alaoui, “Dynamic Multi-Compartment Vehicle Routing Problem for Smart Waste Collection,” Appl. Syst. Innov., vol. 6, no. 1, p. 18, 2023, doi: 10.3390/asi6010018.
[14] Y. Kumar, P. Gupta, K. Panwar, and K. Deep, “Efficient Waste Collection Routing Using F-CVRP and Dynamic Parameter Optimization via Q-Learning,” Expert Syst. Appl., vol. 270, p. 126584, 2025, doi: 10.1016/j.eswa.2025.126584.
[15] B. Jin and H. Ma, “Research on Dynamic Waste Collection Routing Optimization Based on Deep Learning and Incremental Reinforcement Learning,” in 6th International Conference on Computer Engineering and Intelligent Control (ICCEIC), 2025, pp. 145–149. doi: 10.1109/icceic67916.2025.11308838.
[16] S. Ahmed and T. F. Sanam, “Exploration of an E-waste Prediction Model for Collection System Optimization Using Deep Learning Models in E-waste Management Facilities,” in 2nd International Conference on Next-Generation Computing, IoT and Machine Learning (NCIM), 2025, pp. 1–6. doi: 10.1109/ncim65934.2025.11160027.
[17] M. Hasan, S. M. Rahman, and others, “Enhanced LSTM model (e-LSTM) with SigmoReLU and RAdam for domestic solid waste forecasting,” Sci. Rep., vol. 13, p. 12345, 2023, doi: 10.1038/s41598-023-39257-1.
[18] S. Liu and Y. Chen, “Comparative analysis of LSTM and traditional time series models for waste generation prediction,” J. Environ. Manage., vol. 345, p. 118543, 2023.
[19] S. Ali and others, “Time-series forecasting of municipal solid waste: A comparison between LSTM and GRU models integrated with Grey Relational Analysis,” J. Clean. Prod., vol. 390, p. 136112, 2023.
[20] K. Yilmaz, “Bidirectional LSTM networks for municipal solid waste quantity prediction and biogas potential analysis,” Energy Convers. Manag., vol. 291, p. 117289, 2023.
[21] S. S. Ghorbani, S. Ghorbany, and E. Noorzai, “Development of a Data-Driven Framework to Predict Waste Generation and Evaluate Influential Factors: Machine Learning Innovations in Construction Waste Management,” Clean. Waste Syst., 2025, [Online]. Available: https://api.semanticscholar.org/CorpusID:278264840
[22] C. C. Ferrão, J. A. R. Moraes, and others, “Optimizing routes of municipal waste collection: an application algorithm combining constructive genetic algorithms and tabu search,” Manag. Environ. Qual. An Int. J., vol. 35, no. 3, pp. 678–695, 2024, doi: 10.1108/MEQ-06-2023-0182.
[23] C. Hamontree, J. Koiwanit, and A. Sinchai, “Sustainable urban waste collection using a hybrid heuristic-genetic approach: a Bangkok case study,” Front. Sustain. Cities, vol. 5, p. 130456, 2026, doi: 10.3389/frsc.2026.130456.
[24] A. Pratama and others, “Solving The Waste Collection Routing Problem Using Geographic Information System-Genetic Algorithm,” in Journal of Physics: Conference Series, 2024, p. 12025.
[25] I. A. Hasugian, N. Lestari, D. M. Nasution, and F. R. A. Bukit, “Optimization of Medan city garbage transport routes using genetic algorithm,” AIP Conf. Proc., vol. 2741, no. 1, p. 60010, 2023, doi: 10.1063/5.0129214.
[26] M. Al-Jubori and others, “Optimization of Vehicles Routing Problem using GA For AL-Rasheed municipality, Baghdad, Iraq,” Wasit J. Eng. Sci., vol. 10, no. 1, pp. 45–56, 2022.
[27] H. Jiang, M. Lu, X. Zhang, and Y. Tian, “An evolutionary algorithm for solving Capacitated Vehicle Routing Problems by using local information,” Appl. Soft Comput., vol. 117, p. 108431, 2022, doi: 10.1016/j.asoc.2022.108431.
[28] X. Li and others, “Routing optimization method of waste transportation vehicle using biological evolutionary algorithm under the perspective of low carbon and environmental protection,” Environ. Eng. Res., vol. 27, no. 6, p. 210456, 2022.
[29] R. Rachmawati and S. Yosmar, “Using Ant Colony Optimization to Solve a Vehicle Routing Problem: Waste Transportation Routes in Bengkulu City Case Study,” J. Adv. Res. Appl. Sci. Eng. Technol., vol. 55, no. 1, pp. 1–12, 2025, doi: 10.37934/araset.55.1.1.
[30] A. Tamilmani, D. Thayalnayaki, J. Santhosh, S. J. P. Rosaline, P. Latha, and V. A. Shanmugavelu, “Forecasting urban construction and demolition waste generation with LSTM neural networks,” in AIP Conference Proceedings, 2024. doi: 10.1063/5.0236998.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Muhammad Amin, Muhammad Iqbal, Irvanizam Irvanizam
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
-a.jpg)
-b.jpg)
