Modelado predictivo de la demanda ATS para la optimización sectorial en CENAMER basado en datos 2024-2025
Loading...
Date
2026-05-01
Journal Title
Journal ISSN
Volume Title
Publisher
Universidad Tecnológica Centroamericana UNITEC
Abstract
La investigación analizó la demanda de servicio de tráfico aéreo (ATS) respecto al uso de los sectores operacionales utilizados por el Centro de Control de Área de Centroamérica (CENAMER); integrando el análisis de datos y modelos predictivos, el estudio plantea optimizar el uso de recursos. Con una propuesta de mejora mediante la reducción del 10% del uso de la capacidad máxima de los sectores aéreos, se estipula la disminución de la carga laboral y la optimización del uso de recursos para prevenir la subutilización o sobrecarga de estos. Utilizando data correspondiente a los periodos 2024 y 2025, y basado en una metodología cuantitativa (no experimental y longitudinal), el estudio analizó los registros operacionales mediante técnicas estadísticas y descriptivas con el propósito de generar modelos predictivos. El uso de series temporales permite la identificación y consideración de los patrones de sectores de vuelo, por lo que presenta una perspectiva especial para la recolección de datos y demás consideraciones. Es necesario integrar el modelado para la comparación de resultados; mediante el uso del modelo SARIMA, el cual presenta el mejor rendimiento, se facilita la división de variables con alta correlación y diferencias estadísticamente significativas correspondientes a distribuciones no paramétricas de los datos. Esto permite generar un modelo aplicable para la predicción de operaciones con la finalidad de estructurar mejoras para la reducción de costos y la optimización de recursos.
The research analyzed the demand for Air Traffic Services (ATS) in relation to the use of operational sectors managed by the Central American Area Control Center (CENAMER). By integrating data analysis and predictive modeling, the research aims to optimize the use of resources. Through a proposed improvement plan consisting of a 10% reduction in the use of the maximum capacity of airspace sectors, the study seeks to decrease workload while optimizing resource utilization to prevent both the underutilization and exploitation of resources. Using data corresponding to 2024 and 2025 and based on a quantitative methodology (non-experimental and longitudinal), the study intends to use operational records for statistical and descriptive analysis to develop predictive models. The integration of time series models enables the identification of patterns related to flight sectors, offering a robust framework for data collection and analysis. It is essential for comparing results to integrate models, such as the SARIMA model, which demonstrated the best performance among the evaluated approaches. This model facilitates the differentiation of variables with high correlation and statistically significant differences, particularly in the context of non-parametric data distributions. Consequently, the study establishes a predictive framework applicable to forecasting operations, supporting decision-making processes and the optimization of resource usage.
The research analyzed the demand for Air Traffic Services (ATS) in relation to the use of operational sectors managed by the Central American Area Control Center (CENAMER). By integrating data analysis and predictive modeling, the research aims to optimize the use of resources. Through a proposed improvement plan consisting of a 10% reduction in the use of the maximum capacity of airspace sectors, the study seeks to decrease workload while optimizing resource utilization to prevent both the underutilization and exploitation of resources. Using data corresponding to 2024 and 2025 and based on a quantitative methodology (non-experimental and longitudinal), the study intends to use operational records for statistical and descriptive analysis to develop predictive models. The integration of time series models enables the identification of patterns related to flight sectors, offering a robust framework for data collection and analysis. It is essential for comparing results to integrate models, such as the SARIMA model, which demonstrated the best performance among the evaluated approaches. This model facilitates the differentiation of variables with high correlation and statistically significant differences, particularly in the context of non-parametric data distributions. Consequently, the study establishes a predictive framework applicable to forecasting operations, supporting decision-making processes and the optimization of resource usage.
Keywords
Aeronáutica, Analítica de Datos, CENAMER, Series de Tiempo, Tráfico Aéreo