Gijun Park | Searcharxiv

arXiv2026

Quantifying Autoscaler Vulnerabilities: An Empirical Study of Resource Misallocation Induced by Cloud Infrastructure Faults

Resource autoscaling mechanisms in cloud environments depend on accurate performance metrics to make optimal provisioning decisions. When infrastructure faults including hardware malfunctions, network disruptions, and software anomalies corrupt these metrics, autoscalers may systematically over- or under-provision resources, resulting in elevated operational expenses or degraded service reliability. This paper conducts controlled simulation experiments to measure how four prevalent fault categories affect both vertical and horizontal autoscaling behaviors across multiple instance configurations and service level objective (SLO) thresholds. Experimental findings demonstrate that storage-related faults generate the largest cost overhead, adding up to $258 monthly under horizontal scaling policies, whereas routing anomalies consistently bias autoscalers toward insufficient resource allocation. The sensitivity to fault-induced metric distortions differs markedly between scaling strategies: horizontal autoscaling exhibits greater susceptibility to transient anomalies, particularly near threshold boundaries. These empirically-grounded insights offer actionable recommendations for designing fault-tolerant autoscaling policies that distinguish genuine workload fluctuations from failure artifacts.

cs.DC↗

arXiv2026

Bridging Temporal and Textual Modalities: A Multimodal Framework for Automated Cloud Failure Root Cause Analysis

Root cause analysis in modern cloud infrastructure demands sophisticated understanding of heterogeneous data sources, particularly time-series performance metrics that involve core failure signatures. While large language models demonstrate remarkable capabilities in textual reasoning, their discrete token-based architecture creates fundamental incompatibilities with continuous numerical sequences exhibiting temporal dependencies. Current methodologies inadequately address this modality mismatch, constraining the potential of language model-driven automation in incident management workflows. This paper presents a multimodal diagnostic framework that harmonizes time-series representations with pretrained language model embedding spaces. Our approach contributes three technical advances: (1) a semantic compression technique that distills temporal segments into single-token abstractions while preserving pattern semantics, (2) an alignment encoder utilizing gated cross-attention to project time-series features into language model latent space, and (3) a retrieval-augmented diagnostic pipeline that synthesizes aligned embeddings with historical incident knowledge for expert-level failure attribution. Comprehensive evaluation across six cloud system benchmarks demonstrates that our framework achieves leading performance, reaching 48.75% diagnostic accuracy with notable improvements on scenarios involving compound failure modes. The results validate embedding-space alignment as an effective strategy for enabling language models to reason over multimodal telemetry data in production incident response contexts.

cs.AI↗