Global sensitivity analysis for a real-time electricity market forecast by a machine learning approach: A case study of Mexico

Abstract

The study presents the hybridization of global sensitivity analysis with data-driven techniques to evaluate the Mexican electricity market interaction and assess the impact of individual parameters concerning locational marginal prices. The study case pertains to Yucatan, Mexico's electricity grid and market characteristics. A comparison of three artificial intelligence techniques in the electricity market is presented to forecast electricity prices in real-time market conditions. The study contemplates exogenous input parameters classified as regional, operational, meteorological, and economic indicators. A sensitivity analysis was carried out to the model with the best performance of the Artificial Intelligence techniques. The results showed that the impact of the variables fluctuates according to market and consumption conditions. In this study, the most relevant variables were electricity generation (17.06%), fossil fuel costs (natural gas 12.54% and diesel 8.63%), load zone (11.17%), and the day of the year (8.51%). From the qualitative point of view, the complex behavior of the parameters was analyzed; moreover, the quantitative results weighted the relevance of the variables in the Locational Marginal Prices. The meteorological and economic parameters allow assessing the environment where it interacts and serves as an instrument for decision-making in the planning of the energy sector. The presented methodology can be implemented as an alternative tool for market participants to analyze electricity prices.