Optimization of the Electrical Infrastructure in Paracho de Verduzco using Graph Simulation Algorithms and Artificial Intelligence
Keywords:
Graph theory, graph mining, machine learning development code, software development and technology.Abstract
Given the scalability of graph AI, it's possible to establish algorithms that simulate and optimize the graph database to obtain the optimal solution to a given problem. In this sense, AI contains machine learning (ML) codes capable of learning under certain conditions and making predictions through simulations. The simulation of a "Stress Scenario" (failure at the North node) demonstrates that the use of AI allows for efficient load redistribution in less than a second, drastically reducing economic losses. Centrality analysis identifies the exact nodes requiring priority investment, optimizing the public infrastructure budget. The implementation of this analysis not only modernizes the lighting network of Paracho, but also positions the municipality as a benchmark for technological innovation in the P´urépecha Plateau, linking artisanal tradition with cutting-edge energy efficiency.References
Ashraf Iqbal, M. (2010). Graph Theory and Algorithms, India: Central University of Punjab
Bastian, M., Heymann, S., & Jacomy, M. (2009). Gephi: An open source software for exploring and manipulating networks. Proceedings of the International AAAI Conference on Web and Social Media, 3(1), 361–362. https://doi.org/10.1609/icwsm.v3i1.13937
Bratanič, T. (2024). Graph algorithms for data science: With examples in Neo4j. Manning Publications.
Comisión Federal de Electricidad. (2010). Generación distribuida: Mapa de capacidad de alojamiento. CFE Distribución. https://app.cfe.mx/Aplicaciones/GeneracionDistribuida/GeneracionDistribuida/MapaCapacidadAlojamiento
Even, S. (2012). Graph Algorithms, NY: Cambridge University Press.
Google. (2026). Gemini [Large language model]. https://gemini.google.com
Google. (2026). Google Colab [Entorno de notebook interactivo]. https://colab.research.google.com
Gerón, A. (2019). Hands-on Machine Learning with Scikit-Learn, Keras & TensorFlow Concepts, Tools, and Techeniques to Build Intelligent Systems, Canada: O’Reilly books.
Han, J., Kamber, M. (2012). Data mining, concepts and techniques, USA: Morgan Kaufmann Publishers.
Harrington, P. (2012). Machine Learning in Action, NY: MANNING Shelter Island.
Hernández Sampieri, R., Fernández Collado, C., & Baptista Lucio, P. (2014). Metodología de la investigación (6.ª ed.). McGraw-Hill Education.
Hilera, J., y Martínez, V. (1995). Redes neuronales artificiales, fundamentos modelos y aplicaciones, Madrid: Rama.
Instituto Nacional de Estadística y Geografía. (2010). Compendio de información geográfica municipal 2010. Paracho, Michoacán de Ocampo. https://www.inegi.org.mx/contenidos/app/mexicocifras/datos_geograficos/16/16065.pdf
Russel, S., Norvig, P. (2004). Inteligencia artificial, un enfoque moderno, Madrid: Pearson.
Voloshin, V. (2009). Introduction to graph theory, USA-New York: NovaScience Publishers, Inc.
Witten, I., Frank, E. (2011). Data miming, practical machine learning tools and techeniques, USA: Morgan Kaufmann Publishers.
