<p>The growing penetration of renewable energy into electricity markets has significantly increased the levels of uncertainty and variability in both generation and demand. This challenge is particularly acute in developing countries like Mexico, where traditional simulation methods remain dominant and intelligent modeling approaches are still underutilized. Recent studies have explored the use of machine learning for price forecasting in the Mexican electricity market, but most rely on complex black-box models with limited interpretability or adaptability. In response to these limitations, this study proposes an intelligent and interpretable simulation model of locational marginal prices (LMPs), based on fuzzy subtractive clustering and particle swarm optimization. The methodological contribution lies in the hybridization of fuzzy clustering with particle swarm optimization algorithm, which allows for effective handling of uncertainty, adaptation to nonlinear market behaviors, and low computational cost. Unlike conventional models, this approach is capable of capturing the spatio-temporal dynamics of LMPs while maintaining transparency in structure and reasoning. Experimental results show high simulation accuracy compared to real market data, with significant improvements over benchmark methods. The convergence of the proposed algorithm has been analyzed, and its structural organization is detailed to ensure replicability. This model represents one of the first fuzzy intelligent forecasting approaches specifically developed for the Mexican market, addressing both the need for advanced forecasting tools and the structural characteristics of the national electricity system. These findings position the proposed model as a relevant and practical decision support tool in emerging electricity markets.</p>