Umeå University's logo

Cloud computing has transformed the IT landscape by offering users and orga-nizations on-demand access to computing power, storage, data processing, andmachine learning resources. Despite the benefits, cloud resource managementfaces challenges due to the heterogeneous and dynamic nature of workloads.Inefficient provisioning manifests in two critical forms: underprovisioning leadsto degraded Quality of Service (QoS) and unmet Service-Level Agreements(SLAs), while overprovisioning results in unnecessary energy consumption andhigh operational costs. With the current rise of AI and machine learning in-novations, machine learning-based workload prediction for resource provisionplays a vital role in predicting future scenarios and identifying new occurrences,enabling service providers to prepare ahead of time. However, various challengesare associated with machine learning-based workload prediction.This thesis addresses the challenges of machine learning-based workloadprediction in cloud environments, including data drift due to dynamic workloads,high computational overhead, and storage overhead. Firstly, cloud workloads aredynamic, and models trained with old historical data can become obsolete overtime. We addressed the challenge of accurate prediction and data drift by incor-porating machine learning and streaming data processing algorithms to assistadaptive prediction. Secondly, constantly training and updating deep learningmodels adds significant computational overhead to the cloud infrastructure. Weaddressed this problem by proposing a solution that incorporates a knowledgebase repository with transfer learning-based adaptation. Moreover, we exploredthe tradeoff between model accuracy and computational overhead. Finally, wepropose a data compression mechanism that leverages an autoencoder to reducestorage overhead resulting from the continuous generation of monitoring datain cloud management systems.Our findings reveal that the proposed methods have significantly improvedthe machine learning-based cloud management system. Extensive evaluationusing real-world datasets reveals that the proposed methods facilitate thecreation of accurate predictions, even in the face of ever-changing patterns incloud workloads. Moreover, the methods reduced computation overhead byleveraging existing knowledge and highlighting the tradeoff required to achievea balance between prediction accuracy and computation overhead.

Accurate future workload prediction is an essential step for proactive resource allocation and efficient provisioning in cloud computing environments. Deep learning strategies have proven successful for this task, but they face challenges due to the high dimensionality of monitoring data, extensive preprocessing requirements, and computational overhead. In this paper, we propose a hybrid framework that integrates autoencoders for workload compression with Long Short-Term Memory (LSTM) networks for time-series forecasting. Unlike prior studies, our approach systematically analyzes the trade-off between compression ratio and predictive accuracy, demonstrating how dimensionality reduction can improve both scalability and robustness. Thereby reducing the computational burden associated with processing massive-scale monitoring data. Experiments conducted on both synthetic and real-world datasets demonstrate that the proposed method achieves up to 60% data compression with minimal reconstruction loss, while also improving prediction accuracy compared to baseline LSTM models. We evaluate the overall performance of the framework using various metrics, including data reduction ratio, prediction accuracy, and the effects of different compression stages on predictive performance. Additionally, we quantify the computational savings in terms of CPU usage, memory footprint, and training/inference times, confirming the framework's feasibility for real-world deployment. These results underscore the potential of integrating compression and prediction to achieve scalable, accurate, and resource-efficient management of cloud workloads.

Machine Learning (ML) models play a crucial role in enabling intelligent decision-making across diverse cloud system management tasks. However, as cloud operational data evolves, shifts in data distributions can occur, leading to a gradual degradation of deployed ML models and, consequently, a reduction in the overall efficiency of cloud systems.

We introduce CloudResilienceML, a framework designed to maintain the resilience of ML models in dynamic cloud environments. CloudResilienceML includes: (1) a performance degradation detection mechanism, using dynamic programming change point detection to identify when a model needs retraining, and (2) a data valuation method to select a minimal, effective training set for retraining, reducing unnecessary overhead.

Evaluated with two ML models on real cloud operational data, CloudResilienceML significantly boosts model resilience and reduces retraining costs compared to incremental learning and data drift-based retraining. In high-drift scenarios (e.g., Wikipedia trace), it reduces overhead by 50% compared to concept drift retraining and by 91% compared to incremental retraining. In stable environments (e.g., Microsoft Azure trace), CloudResilienceML maintains high accuracy with retraining costs 96% lower than concept drift methods and 86% lower than incremental retraining.

Efficient workload prediction is essential for enabling timely resource provisioning in cloud computing environments. However, achieving accurate predictions, ensuring adaptability to changing conditions, and minimizing computation overhead pose significant challenges for workload prediction models. Furthermore, the continuous streaming nature of workload metrics requires careful consideration when applying machine learning and data mining algorithms, as manual hyperparameter optimization can be time-consuming and suboptimal. We propose an automated parameter tuning and adaptation approach for workload prediction models and concept drift detection algorithms utilized in predicting future workload. Our method leverages a pre-built knowledge-base based on historical data statistical features, enabling automatic adjustment of model weights and concept drift detection parameters. Additionally, model adaptation is facilitated through a transfer learning approach. We evaluate the effectiveness of our automated approach by comparing it with static approaches using synthetic and real-world datasets. By automating the parameter tuning process and integrating concept drift detection, in our experiments the proposed method enhances the accuracy and efficiency of workload prediction models by 50%.

Cloud management systems increasingly rely on machine learning (ML) models to predict incoming workload rates, load, and other system behaviors for efficient dynamic resource management. Current state-of-the-art prediction models demonstrate high accuracy, but assume that data patterns remain stable. However, in production use, systems may face hardware upgrades, changes in user behavior etc. that lead to concept drifts - significant changes in characteristics of data streams over time. To mitigate prediction deterioration, ML models need to be updated - but questions of when and how to best retrain these models are unsolved in the context of cloud management. We present a pilot study that address these questions for one of the most common models for adaptive prediction - Long Short Term Memory (LSTM) - using synthetic and real-world workload data. Our analysis of when to retrain explores approaches for detecting when retraining is required using both concept drift detection and prediction error thresholds, and at what point of retraining should actually take place. Our analysis of how to retrain focuses on the data required for retraining, and what proportion should be taken from before and after the need for retraining is detected. We present initial results that indicate that retraining of existing models can achieve prediction accuracy close to that of newly trained models but for much less cost, and present initial advice for how to provide cloud management systems with support for automatic retraining of ML-based methods.