Gemelo digital experimental con control MPPT y analítica energética en microrredes DC aisladas

The development of data-driven control and monitoring strategies is a key factor in optimizing the energy performance of photovoltaic direct-current (DC) microgrids. This paper presents the implementation of an experimental digital twin for load regulation using Maximum Power Point Tracking (MPPT) technology, complemented by an energy analytics module to evaluate system efficiency and stability. The proposed methodology integrates a Matlab-Simulink simulation with a physical implementation on an ESP32 microcontroller, executing a Perturb and Observe (P&O) algorithm coupled to a Boost DC/DC converter. Electrical and environmental data are processed using data science tools (Python, Pandas, NumPy, Seaborn) to determine correlations among irradiance, temperature, voltage, and power. Experimental results demonstrate an overall efficiency of 91.6 % under real irradiance conditions and a 99.7 % correlation between simulation and physical measurement, validating the reliability of the digital twin. The hybrid approach combines electronic control, digital modeling, and statistical analysis, establishing a low-cost intelligent energy monitoring platform suitable for rural microgrids and educational environments.