Transforming Mexico’s Electric Load Infrastructure: A Quantile Transformer Network Deep Learning Approach, 2019-2020

Abstract

To transform Mexico's electric load infrastructure, accurate electric load forecasts are required that are crucial to efficiently allocate resources, maintain system stability, and manage energy. The purpose of this study is to use the Quantile Transformer Network (QTN) as a novel approach for a deep learning framework for load forecasting, emphasizing its potential and practical consequences in enhancing the accuracy of load forecasting in real-world energy systems. Moreover, it is shown that QTN efficiently captures complex patterns, temporal relationships and interconnections among factors that influence electric load. The dataset utilized consists of past records of energy consumption in the Baja California System in Mexico. It includes several factors such as electricity demand, marginal prices, temporal characteristics, temperature-related variables, seasonal patterns, and holidays. Additionally, QTN is combined with the Rainbow Technique (RT) to manage categorical variables, resulting in the creation of a unified feature called category. In this case, RT examines the connections between descriptive phrases that reflect distinct combinations of categorical factors depending on the load values. Moreover, this research shows that the common Quantile Regression (QR) outperforms QTN in capturing dependencies in sequential data. Finally, several recommendations for promoting Mexico's Electric Load Infrastructure are provided.

Keywords

• Electric Load Forecasting, Quantile Transformer Network, Temporal Dependencies, Non-Linear Patterns, Rainbow Technique, Quantile Regression