A Deep Learning Model for Accurate Prediction in Cloud Computing Workloads

Hybrid deep learning model for the task scheduling in cloud computing

A deep learning-based model for task scheduling in cloud computing that employs a convolutional neural network to predict the optimal machines for task allocation and consumes less energy than other models is proposed, demonstrating its effectiveness in cloud task scheduling.

A CNN and BiLSTM Network for Predicting Job Failures in Dynamic Cloud Workloads

Cloud service providers face significant challenges in preventing hardware and software failures due to the large-scale and heterogeneous nature of cloud computing. Although many studies have focused on characterising failed jobs, fewer have explored proactive failure prediction. This paper presents a deep learning-based failure prediction model that integrates Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) networks to identify job failures before they occur. The proposed model improves the performance of cloud computing applications by reducing job failures and optimising resource utilisation. Using the Google Cluster Traces dataset, we analyse failure patterns and evaluate the effectiveness of the model across multiple performance metrics. The results demonstrate the robustness of the proposed scheme, achieving an accuracy of 99.96%, along with a high F1-score of 99.92% when compared to existing models. These findings highlight the potential of deep learning in proactive failure mitigation, providing a foundation for future advances in cloud workload reliability.

A Hybrid Deep Reinforcement Learning Framework for Efficient Cloud Resource Scheduling

A hybrid Deep Reinforcement Learning (DRL) framework that combines Deep Q-Network, Proximal Policy Optimization and Advantage Actor-Critic to enable adaptive resource scheduling in cloud environments is proposed.

Predicting CNN training latency on cloud GPUs without disclosing model architecture

AI-Enabled Workload Prediction for Elastic Cloud Computing Systems

In conclusion, the proposed AI-based workload prediction framework significantly enhances cloud resource management by accurately forecasting future workload demands and enabling proactive resource allocation. By utilizing machine learning and deep learning techniques such as LSTM, Random Forest Regression, and Gradient Boosting, the system improves resource utilization, reduces response time, lowers operational costs, and minimizes SLA violations. The results demonstrate superior prediction accuracy compared to traditional methods, leading to better Quality of Service (QoS) and energy efficiency. This study highlights the potential of AI-driven predictive analytics to transform cloud computing from reactive resource management to intelligent, autonomous, and adaptive cloud ecosystems. Future research can further improve performance through the integration of federated learning, reinforcement learning, and edge-cloud computing technologies.

Two Stage Decomposition with Hybrid BiLSTM-BiGRU Networks for Accurate and Efficient Data Center Workload Prediction

Accurate workload prediction in cloud data centers is essential for efficient resource management, yet high-dimensional and noisy operational data often hinder forecasting performance. This work extends the original CVCBM model by integrating a lightweight Bidirectional GRU (BiGRU) with Bidirectional LSTM (BiLSTM) to enhance prediction efficiency while maintaining temporal feature extraction. Initially, workload signals are denoised and decomposed using a two-stage process—Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) followed by Variational Mode Decomposition (VMD). Sample Entropy (SE) selects meaningful components, and K-Means clustering prioritizes high workload data for training. The hybrid Conv1D-BiLSTM-BiGRU architecture captures multi-scale temporal patterns and both short-term and long-term dependencies. The trained model is deployed using the Flask framework for real-time workload prediction, allowing interactive input of datasets and immediate forecasting. Experimental evaluation demonstrates that the extended model reduces computational overhead while improving prediction accuracy, providing robust, scalable, and real-time forecasting for cloud data center resource management.