Enhanced Autoregressive Integrated Moving Average (ARIMA) Model for Forecasting Network Traffic

Abstract

Precise forecasting of network traffic is crucial for maintaining the stability and effectiveness of contemporary computer networks. This research presents Enhanced Autoregressive Integrated Moving Average (ARIMA) models combined with sophisticated machine learning methods to enhance the precision of traffic forecasting. Utilizing historical data and external factors, the suggested model tackles essential issues like non-linear trends and time-dependent dynamics. The execution reaches a Mean Absolute Percentage Error (MAPE) of 1.23%, showcasing notable advancements compared to conventional techniques. These findings highlight the promise of hybrid forecasting models in enhancing resource distribution and reducing security threats in ever-changing network settings.