Modeling UrbanWater Demand Using Agent-based Simulation: A Case Study in Salvador

  • Edmilson dos Santos de Jesus UFBA
  • Célia Ghedini Ralha UFBA
  • Gecynalda Soares da Silva Gomes UFBA
  • Karen Auzidéa dos Santos Pereira UFBA

Resumo


This paper uses a data-driven reasoning model and inference rules to propose a Multi-Agent System (MAS) for water demand forecasting in the Metropolitan Region of Salvador (MRS). For implementation, the GAMA platform (GIS Agent-Based Modeling Architecture), its language, GAML (GAMA Modeling Language), and Python were used for simulation, preprocessing, and normalizing input data. The model considers population growth, average consumption per household, and housing type, enabling more individualized mediumand long-term forecasting. The results demonstrate the feasibility of using Multi-Agent Systems to support agencies and entities responsible for water resource management, providing valuable contributions to water supply’s strategic and managerial planning.

Referências

Alves, J. E. D. (2019). Crescimento populacional e mudanças climáticas vão aumentar o estresse hídrico. Accessed: Feb. 2025.

Ehsanitabar, A., Hassanzadeh, Y., Aalami, M., and Sadeghfam, S. (2025). Agent-based modeling for demand management of reservoirs considering social and hydrological interactions under uncertainty. Journal of Environmental Management, 380:125089.

Galán, J. M., López-Paredes, A., and Del Olmo, R. (2009). An agent-based model for domestic water management in valladolid metropolitan area. Water Resources Research, 45(5).

IBGE - Instituto Brasileiro de Geografia e Estatística (2022). Projeções de população. Accessed: Feb. 2025.

Iwakin, O. and Moazeni, F. (2024). Improving urban water demand forecast using conformal prediction-based hybrid machine learning models. Journal of Water Process Engineering, 58:104721.

Kavya, M., Mathew, A., Shekar, P. R., and P, S. (2023). Short term water demand forecast modelling using artificial intelligence for smart water management. Sustainable Cities and Society, 95:104610.

Koutiva, I. and Makropoulos, C. (2016). Modelling domestic water demand: An agent based approach. Environmental Modelling & Software, 79:35–54.

Rees, P., Clark, S., and Nawaz, R. (2020). Household forecasts for the planning of long-term domestic water demand: Application to london and the thames valley. Population, Space and Place.

Rosa, A. M. F., Souza, G. B. G., and Cavalcante, M. M. (2022). A urbanização do bairro de itapuã, salvador (ba). Accessed: Feb. 2025.

VanBerlo, B., Ross, M. A. S., and Hsia, D. (2021). Univariate long-term municipal water demand forecasting. [link]. arXiv preprint arXiv:2105.08486.

Vidal-Lamolla, P., Molinos-Senante, M., Oliva-Felipe, L., Alvarez-Napagao, S., Cortés, U., Martínez-Gomariz, E., Noriega, P., Olsson, G., and Poch, M. (2024). Assessing urban water demand-side management policies before their implementation: An agent-based model approach. Sustainable Cities and Society, 107:105435.
Publicado
29/09/2025
JESUS, Edmilson dos Santos de; RALHA, Célia Ghedini; GOMES, Gecynalda Soares da Silva; PEREIRA, Karen Auzidéa dos Santos. Modeling UrbanWater Demand Using Agent-based Simulation: A Case Study in Salvador. In: WORKSHOP-ESCOLA DE SISTEMAS DE AGENTES, SEUS AMBIENTES E APLICAÇÕES (WESAAC), 19. , 2025, Fortaleza/CE. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2025 . p. 218-229. ISSN 2326-5434. DOI: https://doi.org/10.5753/wesaac.2025.37537.