具有成本高昂的响应准备的动态云服务容量部署
Dynamic Cloud Service-Capacity Deployment with Costly Response Readiness
浏览论文内容
中文总结 AI 辅助
研究人工智能产品发布时公司如何联合决定当前容量部署与未来响应准备，通过有限期动态规划及保留 - 部署分解，实施CBAP框架，实验表明其可降低生命周期成本，区分预测与操作，明确二者为不同决策边际。
中文摘要 AI 辅助
人工智能产品发布需要在有足够特定产品工作负载历史之前做出服务容量决策。早期服务观察更新了对剩余工作负载的信念，但工作负载不像库存需求那样实际消耗容量。保留快速响应能力可能还需要成本高昂的容量访问和运营安排。我们研究公司应如何联合决定当前容量部署和未来响应准备情况。我们制定了一个具有工作负载信念、可用容量和吸收性响应通道状态的有限期动态规划。一种保留 - 部署分解为每个延续选择解决一个部署问题，并比较由此产生的优化值。这种结构确定了何时应保留响应准备情况以及应部署多少容量。我们通过冷启动信念可操作性策略（CBAP）实施该框架，该策略使用从预测信念中得出的工作负载场景估计特定边的值。我们还确定了其决策和生命周期性能损失的界限。数值实验和基于BurstGPT的评估表明，CBAP通过避免过早部署和不必要的准备支出，相对于基准策略降低了生命周期成本。结果区分了预测信息性和操作可操作性，并表明当前部署和未来响应准备是分开的决策边际。零部署可能代表待机而非退出，而正部署不一定意味着保留响应通道。
英文摘要
AI product launches require service-capacity decisions before sufficient product-specific workload histories are available. Early service observations update beliefs about remaining workload, but workload does not physically deplete capacity as inventory demand does. Preserving rapid-response capability may also require costly capacity-access and operational arrangements. We study how a firm should jointly decide current capacity deployment and future response readiness. We formulate a finite-horizon dynamic program with workload beliefs, serviceable capacity, and an absorbing response-channel state. A preservation-deployment decomposition solves one deployment problem for each continuation choice and compares the resulting optimized values. This structure identifies when response readiness should be preserved and how much capacity should be deployed. We operationalize the framework through the Cold-Start Belief Actionability Policy (CBAP), which estimates side-specific values using workload scenarios drawn from predictive beliefs. We also establish bounds on its decision and lifecycle performance losses. Numerical experiments and a BurstGPT-based evaluation show that CBAP reduces lifecycle cost relative to benchmark policies by avoiding premature deployment and unnecessary readiness spending. The results distinguish forecast informativeness from operational actionability and show that current deployment and future response readiness are separate decision margins. Zero deployment may represent Standby rather than Exit, while positive deployment need not imply preserving the response channel.
