AI-based workload prediction for cloud resource optimization: A comprehensive framework

Abstract

Cloud computing has revolutionized modern IT infrastructure by offering scalable and on-demand resources. However, unpredictable workload variations often lead to inefficient resource allocation, increasing operational costs or causing performance degradation. AI-based workload prediction techniques leverage machine learning (ML) and deep learning (DL) models to optimize cloud resource allocation efficiently. This paper proposes an advanced AI-driven workload prediction framework using Long Short-Term Memory (LSTM) and Transformer models to predict workload fluctuations. The framework is designed to improve resource utilization efficiency, minimize costs, and enhance service reliability in cloud environments. Experimental results demonstrate the superiority of AI-based models over traditional approaches, with significant improvements in prediction accuracy and resource optimization. Future research directions include integrating reinforcement learning and federated learning for adaptive and privacy-preserving workload prediction.