CoScal: Multifaceted Scaling of Microservices With Reinforcement Learning

Abstract

The emerging trend towards moving from monolithic applications to microservices has raised new performance challenges in cloud computing environments. Compared with traditional monolithic applications, the microservices are lightweight, fine-grained, and must be executed in a shorter time. Efficient scaling approaches are required to ensure microservices' system performance under diverse workloads with strict Quality of Service (QoS) requirements and optimize resource provisioning. To solve this problem, we investigate the trade-offs between the dominant scaling techniques, including horizontal scaling, vertical scaling, and brownout in terms of execution cost and response time. We first present a prediction algorithm based on gradient recurrent units to accurately predict workloads assisting in scaling to achieve efficient scaling. Further, we propose a multi-faceted scaling approach using reinforcement learning called CoScal to learn the scaling techniques efficiently. The proposed CoScal approach takes full advantage of datadriven decisions and improves the system performance in terms of high communication cost and delay. We validate our proposed solution by implementing a containerized microservice prototype system and evaluated with two microservice applications. The extensive experiments demonstrate that CoScal reduces response time by 19% to 29% and decreases the connection time of services by 16% when compared with the state-of-the-art scaling techniques.

Edge AI: A survey

“…Sectors: Moving resources closer to the "fixed edge" represented by surveillance cameras, traffic flow enhancement systems, smart meters, etc., is a feature of FC [13]. Associated long-term data storage can therefore be allocated to cloud computing resources [30]. Mobile MEC users form a transient population with varying requirements [96].…”

“…Recent developments in key dimensions have made it possible to successfully deploy AI models at the edge [30]. Ultimately, the foundations for generalised machine learning have been laid by advances in neural networks and other areas of AI [31].…”

“…Standardization for micro-data centres is important to ensure consistency, reliability, and interoperability between different components and systems. It can also help reduce costs, simplify deployment, and improve overall efficiency [30]. Some of the key areas that should be standardized for micro-data centres.…”

Proactive Auto-Scaling Approach of Production Applications Using an Ensemble Model

“…Minxian Xu et al introduced a multi-faceted scaling approach using reinforcement learning called CoScal to learn the scaling techniques efficiently [16]. This approach applies a hybrid scaling technique that combines vertical, horizontal, and brownout, making adaptive decisions via reinforcement Learning (RL).…”

Microservice‐driven privacy‐aware cross‐platform social relationship prediction based on sequential information

“…In fact, accurate prediction of social relationships can not only effectively reduce users' selection burden regarding decision-making in social networks, but also help users quickly expand their communication space. What's more, for these different service platforms, accurate prediction of social relationships can subsequently improve service management [2][3][4] (e.g., product management and product recommendations) as well as bring economic benefits. Typically, users express their feelings and attitudes by reviewing/rating music, movies, and shopping on different platforms.…”