K8S Power Irrigation: Deep Reinforcement Learning for Performance-Aware Power Efficiency of Kubernetes Cloud-Native Microservices

Abstract

Modern cloud platforms are facing a sharp increase in power demand driven by the rapid adoption of AI-powered applications, making power optimization urgent under net-zero commitments and sustainability goals. Yet, reducing power in production remains challenging for latency-sensitive microservices, where performance violations directly affect user experience and operational risk. Such services exhibit heterogeneous workload characteristics and dynamic load patterns. In multi-tenant environments, contention on shared uncore resources, including last-level cache and memory bandwidth, can degrade performance, especially for memory-intensive workloads. As a safeguard, providers often run servers in performance mode, fixing core and uncore frequencies at high levels. Existing power governors largely ignore application-level performance requirements and uncore interference, leading to systematic power over-provisioning. To address this, we introduce K8SPI, a hierarchical reinforcement learning controller that jointly optimizes CPU core and uncore frequencies for cloud-native deployments. K8SPI uses a two-stage architecture: a coarse-grained agent rapidly mitigates performance violations, while a fine-grained agent minimizes power once requirements are satisfied. Using telemetry from hardware, Kubernetes, and application layers, K8SPI adapts to workload heterogeneity and cross-microservice interference. We evaluate K8SPI on a Kubernetes testbed across multiple scenarios. Results show that K8SPI reduces node-level power by 23--30\% compared with the Linux performance governor while keeping performance requirement violations below 2--3\%, even under severe uncore contention and dynamic load fluctuations.