动态调节函数实例保留时间，兼顾延迟与碳排放。
Green or Fast? Learning to Balance Cold Starts and Idle Carbon in Serverless Computing
- 用深度强化学习动态调整实例保留时长
- 冷启动减少51.69%，闲置碳排放降低77.08%
- 适合关注绿色计算与云性能优化的开发者
无服务器计算简化了云部署，但带来了服务延迟与碳排放管理的新挑战。降低冷启动延迟需保留活跃函数实例，而减少碳排放则倾向回收空闲资源。这一权衡因电网碳强度波动和工作负载变化而加剧，静态保活策略效率低下。我们提出LACE-RL框架，将函数实例保留建模为序列决策问题，利用深度强化学习动态调整保活时长，联合建模冷启动概率、函数特定延迟成本与实时碳强度。基于华为公有云日志数据，实验显示，相较于华为静态策略，LACE-RL使冷启动减少51.69%，闲置保活碳排放降低77.08%，且在延迟-碳排放权衡上优于现有启发式与单目标基线方法，接近理想最优（Oracle）性能。
原文摘要 · Abstract (English)
Serverless computing simplifies cloud deployment but introduces new challenges in managing service latency and carbon emissions. Reducing cold-start latency requires retaining warm function instances, while minimizing carbon emissions favors reclaiming idle resources. This balance is further complicated by time-varying grid carbon intensity and varying workload patterns, under which static keep-alive policies are inefficient. We present LACE-RL, a latency-aware and carbon-efficient management framework that formulates serverless pod retention as a sequential decision problem. LACE-RL uses deep reinforcement learning to dynamically tune keep-alive durations, jointly modeling cold-start probability, function-specific latency costs, and real-time carbon intensity. Using the Huawei Public Cloud Trace, we show that LACE-RL reduces cold starts by 51.69% and idle keep-alive carbon emissions by 77.08% compared to Huawei's static policy, while achieving better latency-carbon trade-offs than state-of-the-art heuristic and single-objective baselines, approaching Oracle performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。