Evaluación de producción de energía renovable utilizando tres modelos autorregresivos

Abstract

The prediction and analysis of weather phenomena is of vital importance in meteorology to understand and anticipate climatic changes over time. In this context, autoregressive AR, moving average MA, autoregressive moving average ARMA, autoregressive integrated moving average ARIMA, and seasonal autoregressive integrated moving average SARIMA models have proven to be effective and versatile tools for studying climatic time series. These models are based on the relationship between current observations and their past observations, allowing them to capture temporal patterns and make accurate forecasts regarding climatic variables such as temperature, precipitation, and wind speed, among others. In this article, we investigate the applicability and efficiency of AR, MA, ARMA, ARIMA, and SARIMA autoregressive models in the field of meteorology. By analyzing these datasets, we aim to evaluate how each model fits and accurately predicts climatic changes, with a particular focus on the impact of temperature, radiation, and wind speed on weather patterns.