Cloud Resource Prediction using Hybrid GRU-LSTM Deep Learning Model

Abstract

The efficient allocation and prediction of cloud resources are pivotal challenges in the cloud computing domain, necessitating advanced approaches to ensure cost-effectiveness and service quality. This paper introduces a novel hybrid deep learning model that integrates Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) layers, augmented with dropout layers for regularization and dense layers for feature extraction, to predict cloud resource usage accurately. the hybrid model leverages the complementary strengths of GRU and LSTM networks to effectively model sequential data and capture both short-term and long-term dependencies, addressing key issues such as the vanishing gradient problem and overfitting. experimental results demonstrate the model's superior performance in predicting resource usage, offering significant improvements over traditional methods. the proposed approach not only enhances prediction accuracy but also contributes to the optimization of resource allocation in cloud environments, thereby supporting sustainable and efficient cloud computing operations