发表机构
The Quantum Cloud Computing and Distributed Systems (qCLOUDS) Laboratory, School of Computing and Information Systems, The University of Melbourne（墨尔本大学计算与信息系统学院量子云计算与分布式系统实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Darpan是面向计算连续体的数字孪生框架，通过物理与数字双执行实时验证决策，提升调度效率，预测误差0.485秒，并显著增强PPO调度器性能。
AI 中文摘要
计算连续体应用将工作分布在设备、边缘系统、雾资源和云上。当正在做出放置、调度或恢复决策时，资源可用性、网络条件和应用进度可能发生变化，因此该决策在执行时可能已失效。现有运行时执行预先确定的决策，而模拟工具在预配置环境中比较备选方案；两者都未直接从运行中应用的当前状态探索替代结果。我们提出一个名为Darpan的数字孪生框架，支持物理和数字执行：物理侧运行真实应用并持续观察其运行时状态，而数字侧基于这些物理观察维护一个持续更新、可执行的虚拟对应物。Darpan从相同起点独立评估候选决策，并将选定决策返回物理侧，在实际执行前根据最新物理状态验证其可行性。在真实有向无环图（DAG）工作负载中，Darpan预测物理响应时间的平均绝对误差为0.485秒，并在40个节点时保留93.1%的扩展效率。在状态变更试验中，Darpan从状态捕获到拒绝失效决策平均耗时约2毫秒，在数据传输前停止请求，避免不必要的物理执行开销。在相同物理DAG预算下，Darpan生成的体验使较弱的近端策略优化（PPO）调度器优于两个最先进的深度强化学习（DRL）调度器，分别高出29.1%和20.2%。
英文摘要
Computing-continuum applications distribute work across devices, edge systems, fog resources, and clouds. While a placement, scheduling, or recovery decision is being made, resource availability, network conditions, and application progress may change, so the decision can be invalid by the time it is executed. Existing runtimes enact predetermined decisions, whereas simulation tools compare alternatives in preconfigured environments; neither explores alternative outcomes directly from the current state of a running application. We propose a Digital Twin framework, called Darpan, that supports both physical and digital execution: the physical side runs real applications and continuously observes their runtime state, while the digital side maintains a continuously updated, executable virtual counterpart based on these physical observations. Darpan evaluates candidate decisions independently from the same starting point and returns the selected decision to the physical side, where its feasibility is validated against the latest physical state before actual execution. Across real Directed Acyclic Graph (DAG) workloads, Darpan predicts physical response time with a mean absolute error of 0.485 s and retains 93.1% scale-out efficiency at 40 nodes. In the state-change trials, Darpan takes about 2 ms on average from state capture to rejection of an invalidated decision, stopping the request before data transfer and avoiding unnecessary physical execution overhead. Under the same physical-DAG budget, Darpan-generated experience enables a weaker Proximal Policy Optimization (PPO) scheduler to outperform two state-of-the-art Deep Reinforcement Learning (DRL) schedulers by 29.1% and 20.2%.
