PRISM：面向边缘微服务的预测式运行时就地扩展与模型选择
PRISM: Predictive Runtime In-place Scaling and Model Selection for Edge Microservices
浏览论文内容
中文总结 AI 辅助
PRISM是一种预测引导的运行时框架，可针对容器化边缘微服务联合选择模型变体与CPU分配，经ALPR流水线评估，能降低能源消耗、减少CPU分配并保持良好性能，提升边缘AI微服务的能效。
中文摘要 AI 辅助
对延迟敏感的边缘AI服务必须平衡严格的截止期限、输出质量以及有限的计算与能源预算。然而，静态CPU配置会造成资源浪费，因为推理成本会因输入、模型变体和运行时条件的不同而大幅变化。我们提出PRISM，这是一种预测引导的运行时框架，可针对容器化边缘微服务联合选择模型变体与CPU分配。利用容器级能源监控和轻量级回归模型，PRISM在截止期限、资源以及离线模型级结果质量（QoR）约束下，就地调整每个流水线阶段，并最小化预测的CPU-封装能源。我们在包含检测和识别阶段的自动车牌识别（ALPR）流水线中，对超过52000个请求评估PRISM。对于检测阶段，与最强的静态配置相比，PRISM降低了36%的能源消耗，同时保持了相当的成功率，且平均CPU分配不到一半；对于识别阶段，它以更低的平均CPU分配达到了接近静态最优的性能。这些结果表明，预测式就地适配是一种实用机制，可让对时间敏感的AI微服务流水线在边缘更节能。
英文摘要
Latency-sensitive edge AI services must balance strict deadlines, output quality, and limited compute and energy budgets. However, static CPU provisioning wastes resources because inference cost varies substantially across inputs, model variants, and runtime conditions. We present PRISM, a prediction-guided runtime framework that jointly selects model variants and CPU allocations for containerized edge microservices. Using container-level energy monitoring and lightweight regression models, PRISM adapts each pipeline stage in place and minimizes predicted CPU-package energy under deadline, resource, and offline model-level Quality of Result (QoR) constraints. We evaluate PRISM on more than 52,000 requests in an Automatic License Plate Recognition (ALPR) pipeline with detection and recognition stages. For detection, PRISM reduces energy consumption by 36 % compared to the strongest static configuration while preserving a comparable success rate and using less than half of the average CPU allocation. For recognition, it reaches near-static-best performance with lower average CPU allocation. These results show that predictive in-place adaptation is a practical mechanism for making time-sensitive AI microservice pipelines more energy-efficient at the edge.
