An auto-scaling approach for microservices in cloud computing environments

Abstract

Abstract Today, web applications are one of the most common applications providing service to users. Web application providers have moved their applications to cloud data centers. In this regard, microservices have become a famous architecture for building cloud-native applications. Cloud computing provides flexibility for service providers, allowing them to remove or add resources depending on the workload of their web applications. If the resources allocated to the service are not aligned with its requirements, failure or delayed response will increase, resulting in customer dissatisfaction. This problem has become a significant challenge in microservices-based applications because thousands of microservices in the system may have complex interactions. Auto-scaling is a feature of cloud computing that enables resource scalability on demand. This allows service providers to deliver resources to their applications without human intervention under a dynamic workload to minimize resource cost and latency while maintaining the Quality of Service (QoS) requirements. In this research, we aimed to establish a computational model for analyzing the workload of all microservices. This is performed by considering the overall workload entered into the system and taking into account the relationships and call functions between microservices. This is because, in a large-scale application with thousands of microservices, it is usually difficult to accurately monitor all the microservices and gather precise performance metrics. Then, we introduce a multi-criteria decision-making method to select candidate microservices for scaling. The results of the conducted experiments show that the detection of input load toward microservices is performed with an average accuracy of 99% which is a significant value. Also, the proposed approach improves the maximum use of resources by an average of 22.73%, reducing the number of scaling times by 69.82%, and finally reducing the number of required resources which also affects the cost by 1.67% compared to existing approaches.