Scenario Generation by Physical Model-Free Approaches for Multiple Renewables

Abstract

The augmentation of renewable energy sources within the global energy portfolio is imperative for mitigating the impacts of climate change. Nonetheless, the inherent variability, intermittency, and unpredictability associated with certain forms of renewable energy present significant challenges. Effective integration of these energy sources into existing grids is contingent upon accurate predictions and robust scenario planning. To address this, we introduce a novel data-driven framework that facilitates the generation of energy scenarios without relying on intricate physical models or extensive assumptions. This framework is underpinned by an innovative combination of a grey neural network, which is fine-tuned using a genetic algorithm, and a Gaussian Copula to enhance the prediction accuracy. Extensive experimental analyses validate the effectiveness and advanced capabilities of our proposed model. Moreover, the adaptable nature of this data-driven approach allows for its potential application across various sectors within the sustainable industry, further underscoring its versatility and utility.