Optimization of Energy Consumption Forecasting in Puno using Parallel Computing and ARIMA Models: An Innovative Approach to Big Data Processing

TL;DR

This paper introduces a parallel computing approach combined with ARIMA models to improve energy consumption forecasting in Puno, Peru, emphasizing speed, scalability, and accuracy for better energy management in developing regions.

Contribution

It presents an innovative integration of parallel computing with ARIMA for energy forecasting, enhancing efficiency and scalability over traditional methods.

Findings

Significant speed improvements in computation.

Maintained prediction accuracy with parallel implementation.

Enhanced data processing for large datasets.

Abstract

This research presents an innovative use of parallel computing with the ARIMA (AutoRegressive Integrated Moving Average) model to forecast energy consumption in Peru's Puno region. The study conducts a thorough and multifaceted analysis, focusing on the execution speed, prediction accuracy, and scalability of both sequential and parallel implementations. A significant emphasis is placed on efficiently managing large datasets. The findings demonstrate notable improvements in computational efficiency and data processing capabilities through the parallel approach, all while maintaining the accuracy and integrity of predictions. This new method provides a versatile and reliable solution for real-time predictive analysis and enhances energy resource management, which is particularly crucial for developing areas. In addition to highlighting the technical advantages of parallel computing in this field, the study explores its practical impacts on energy planning and sustainable development in regions like Puno.