Umeå universitets logga

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.