Automated Enforcement of SLA for Cloud Services

摘要

Orchestration and management of cloud computing entities necessitate measuring and analysis of real-time monitored performance metrics. However, decision making in current management platforms are addressed separately in different cloud stack layers. These isolated active management decisions may degrade the total performance of the cloud system. Since, cloud computing platforms lack an integrated analytics and management capability, in this paper, we propose an integrated platform to detect and predict situations where corrective actions are required. First, a Dynamic Bayesian Network (DBN) is trained and updated by collected data to calculate the causal dependencies among various entities in different cloud service layers. The correlation values are then fed into a Long Short-Term Memory (LSTM) neural network to predict the future states. States that violate the Service Level Agreement(SLA) of cloud services are learned with training data, and if the forecasted states threaten the SLA of cloud services, associated events are generated to trigger management actions. Next, management actions are assigned a different set of events using a reinforcement learning approach. A set of experiments based on collected data from a real cloud service environment is conducted to validate the proposed approach. Experimental results indicate that the proposed method outperforms the current management solutions and improves web request response time by up to 7% and decreases SLA violation by 79% in the context of web application auto-scaling.