Genetic Programming for Self-Adaptive Auto-Scaling of Microservices

2026-05-02

AI Summary

This work addresses the challenge of ensuring service-level objectives (SLOs) in microservice architectures, where conventional reactive autoscaling strategies often lead to over- or under-provisioning of resources. To overcome this limitation, the paper introduces AutoSLO, a novel framework that pioneers the integration of genetic programming into autoscaling mechanisms. AutoSLO continuously monitors system behavior and employs an adaptive feedback loop to evolve optimal scaling policies online, thereby shifting from reactive responses to proactive prevention of SLO violations. Experimental evaluations on both e-commerce and large language model–based chatbot systems demonstrate that AutoSLO significantly reduces resource consumption while maintaining an extremely low SLO violation rate, with any violations rapidly mitigated through its self-adaptive control.

Abstract

Microservice architecture is widely adopted in modern systems, where auto-scaling is critical for satisfying service-level objectives (SLOs). However, determining optimal scaling for microservices is difficult, and reactive resource allocation often leads to costly over- or under-provisioning. We propose AutoSLO, a learning-based, self-adaptive scaling framework that dynamically adjusts microservice replicas to meet SLOs while minimizing resource usage. AutoSLO uses a continuous monitoring-adaptation feedback loop and leverages genetic programming to learn and evolve scaling logic, enabling the deployed microservice system to proactively prevent SLO violations rather than repeatedly searching for one-off scaling actions. We evaluate AutoSLO on two case-study systems -- an online shopping platform and a chatbot based on large language models -- and show that this framework substantially reduces resource usage while maintaining a low frequency of SLO violations, all of which are resolved within a short time window.

Problem

• auto-scaling
• microservices
• service-level objectives
• resource provisioning
• SLO violations

Innovation

• Genetic Programming
• Self-Adaptive Auto-Scaling
• Microservices
• Service-Level Objectives (SLOs)
• Feedback Loop