Genetic Algorithm-Based Calibration of PV System Parameters Utilizing Deep Learning Architectures

Abstract

This study introduces a new method for optimizing evolutionary algorithms to learn characteristics of unknown solar energy systems or subsystems. When used together, Genetic Algorithm (GA) and Deep Learning methods allow for precise PV system calibration. By combining GA's optimization powers with deep learning models' pattern recognition abilities, this technique achieves precise system calibration by fine-tuning model parameters. One way to create a connection between variables like irradiance, temperature, and voltage, which are input parameters, and variables like power production or defect detection, is to employ a model that uses deep learning, and brain networks in particular. Feature extraction is a strong suit of CNNs, making them a promising tool for image analysis in the context of spatial pattern defect detection. Using GA, one may optimize the settings of either the PV system or the deep learning model. To do this, one must define a fitness function that represents the target performance metric. This metric might be anything from maximizing power production to reducing prediction error. In order to decrease the discrepancy between the expected and actual electrical output, GA may optimize the biases and weights of a neural network. To sum up, optimizing and calibrating PV systems has never been easier than with the help of a genetic algorithm and deep learning. Together, these things have the potential to make solar energy systems more efficient, provide better results, and enhance model accuracy. This method optimizes seven parameters of a PV system based on observed PV power: nominal power, tilt, azimuth, albedo, irradiance, temperature dependence, and the DC/AC ratio, which is the proportion of nominal module power to nominal inverter power. Through the optimization of these parameters, a digital twin is generated that faithfully mimics the real characteristics and actions of the unidentified solar power plants or subsystems. In order to create this method, we used data on the PV system's on-site power output, surrounding temperature, and irradiance as collected by satellite in southwest Germany. Here, we provide a method that, when applied to nominal power, produces a mean bias error of around 10%, 3° for azimuth with tilt angles, a temperature coefficient ranging from 0.01% to 0.09%, and now-casts having an accuracy of about 6%. As a conclusion, we provide a novel approach to properly parametrize and model PV systems with little to no prior information about their characteristics and elements.