Auto-tuning Distributed Stream Processing Systems using Reinforcement Learning
This addresses the challenge of maintaining service quality in near real-time streaming systems, which is incremental as it automates an existing manual process.
The paper tackles the problem of manually tuning distributed stream processing systems by introducing an automated approach using supervised and reinforcement learning to recommend configurations based on load, resulting in substantially better configurations found in less time than human experts.
Fine tuning distributed systems is considered to be a craftsmanship, relying on intuition and experience. This becomes even more challenging when the systems need to react in near real time, as streaming engines have to do to maintain pre-agreed service quality metrics. In this article, we present an automated approach that builds on a combination of supervised and reinforcement learning methods to recommend the most appropriate lever configurations based on previous load. With this, streaming engines can be automatically tuned without requiring a human to determine the right way and proper time to deploy them. This opens the door to new configurations that are not being applied today since the complexity of managing these systems has surpassed the abilities of human experts. We show how reinforcement learning systems can find substantially better configurations in less time than their human counterparts and adapt to changing workloads.