Abstract
Urban waste collection is a time-consuming and inefficient procedure for city municipalities. The loads on disposal units might differ by area, day or season. However, garbage trucks empty bins according to predefined routes and days, visiting bins that are often still not filled and increasing unnecessary expenses. This work aims to develop an urban waste collection management solution based on providing intelligence to garbage bins, using an IoT prototype with sensors. The Municipality of Delft (South Holland, Netherlands) is used as a case study. A grid-based approach is designed in order to estimate the Waste Stress Index and to identify 15 out of 1323 bins to be equipped with ultrasonic sensors able to read bins filling levels. The collected sensors data are used to predict future bins filling rates through a Convolutional Neural Network (CNN). Bins are then ranked according to their need to be emptied, and bins to be reached in each shift are selected solving a knapsack problem. To further reduce operational costs, the optimal set of routes for the fleet of garbage trucks are determined solving a graph-based asymmetric Vehicle Routing Problem (VRP). The optimized routes are then displayed both on a web-based Smart Waste Management Dashboard and on a mobile web app provided to waste collectors. As future work, 50 new sensors will be installed to further refine the predictions and increase the ranking accuracy. The CNN will be improved to support changes in garbage behaviour caused by events that take place in the municipality area.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
The World Bank Group: Solid Waste Management (2019). https://www.worldbank.org/en/topic/urbandevelopment/brief/solid-waste-management. Accessed 8 Feb 2022
Vicentini, F., et al.: Sensorized waste collection container for content estimation and collection optimization. Waste Manag. (2009). https://doi.org/10.1016/j.wasman.2008.10.017
Aithal, P.S.: Smart city waste management through ICT and IoT driven solution. Int. J. Appl. Eng. Manag. Lett. (IJAEML) 5(1), 51–65 (2021). https://doi.org/10.5281/zenodo.4739109
BrighterBins Homepage. https://www.brighterbins.com/. Accessed 3 Feb 2022
FIWARE Homepage. https://www.fiware.org/. Accessed 31 Jan 2022
Borovykh, A., Bohte, S., Oosterlee, C.W.: Conditional Time Series Forecasting with Convolutional Neural Networks. arXiv:1703.04691v5 [stat.ML] (2018). https://doi.org/10.48550/arXiv.1703.04691
Seravalli, A.: Urban Data per monitorare l’obsolescenza urbana - turismo e commercio nei centri storici. [Urban data for the monitoring of urban obsolescence - tourism and trade in the historic centers], In: Rapporto sulle cittá il governo debole delle economie urbane. Working Papers. Urban@it Online Journal 2/2018 (2018)
Seravalli, A., De Palma, I.: Modello dinamico per lo smart waste urbano: l’esperienza di Delft. [Dynamic model for the urban smart waste: the Delft experience]. In: ASITA Conference 2019 (12–14 November, Trieste, Italy). Acts of the Conference, pp. 955–961. http://atti.asita.it/ASITA2019/. Accessed 9 Feb 2022
Chia-Shang, J.C.: Time series segmentation: a sliding window approach. Inf. Sci. 85(1–3), 147–173 (1995). https://doi.org/10.1016/0020-0255(95)00021-G
Lara-Benítez, P., Carranza-García, M., Riquelme, J.C.: An experimental review on deep learning architectures for time series forecasting. Int. J. Neural Syst. 31(03), 2130001 (2021). https://doi.org/10.1142/S0129065721300011
Hota, H.S., Handa, R., Shrivas, A.K.: Time series data prediction using sliding window based RBF neural network. Int. J. Comput. Intell. Res. 13(5), 1145–1156 (2017). ISSN 0973–1873
Kellerer, H., Pferschy, U., Pisinger, D.: Multiple knapsack problems. In: Kellerer, H., Pferschy, U., Pisinger, D. (eds.) Knapsack Problems, pp. 285–316. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-24777-7
Toth, P., Vigo, D.: The Vehicle Routing Problem. Monographs on Discrete Mathematics and Applications, vol. 9. Society for Industrial and Applied Mathematics, Philadelphia (2002)
Ahuja, R.K., Mehlhorn, K., Orlin, J., Tarjan, R.E.: Faster algorithms for the shortest path problem. J. ACM 37(2), 213–223 (1990). https://doi.org/10.1145/77600.77615
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
D’Agostini, M., Venturi, S., Vigo, E. (2022). Smart Urban Waste Management System: The Case Study of Delft, Netherlands. In: Borgogno-Mondino, E., Zamperlin, P. (eds) Geomatics for Green and Digital Transition. ASITA 2022. Communications in Computer and Information Science, vol 1651. Springer, Cham. https://doi.org/10.1007/978-3-031-17439-1_13
Download citation
DOI: https://doi.org/10.1007/978-3-031-17439-1_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-17438-4
Online ISBN: 978-3-031-17439-1
eBook Packages: Computer ScienceComputer Science (R0)