预测性滚动时域优化：面向时空边缘动态下承诺感知的模型并行推理

中文摘要 AI 辅助

动态边缘系统上的模型并行推理需要调度决策，这些决策不仅要考虑即时资源，还要考虑未来的资源争用和可靠的服务承诺。然而，现有的边缘推理设计主要基于当前或短期系统状态来优化性能指标，没有明确地将当前分配与未来的承诺履行耦合起来。为解决这一问题，我们提出了PROMISE，一个在时空边缘动态下用于承诺感知的模型并行推理的预测性滚动时域框架。PROMISE联合建模了随机任务生成、移动性引起的通信变化、隐私感知的模型分区以及负载相关的边缘计算能力。我们引入承诺完成时间（CCT）作为内生服务决策，并制定联合SD-ES映射和CCT确定，以平衡承诺履行和服务奖励。为解决跨时隙耦合问题，PROMISE在自适应时域上估计未来任务到达和计算工作负载，并将其嵌入到确定性等价ES状态展开中。随后，一个进度感知的替代函数评估可行的当前阶段映射，而相应的CCT从预测完成时间中解析恢复。仅第一阶段决策被承诺，优化以滚动时域方式根据新观察到的状态重复进行。数值实验展示了在不同系统规模和工作负载动态下的稳健调度性能，而基于树莓派的实验验证了模型并行边缘推理的实际可行性和关键系统特性。

英文摘要

Model-parallel inference over dynamic edge systems requires scheduling decisions that account for not only instantaneous resources but also future resource contention and reliable service commitments. Existing edge-inference designs, however, predominantly optimize performance metrics based on current or short-term system states, without explicitly coupling current assignments with future commitment fulfillment. To address this issue, we propose PROMISE, a predictive rolling-horizon framework for commitment-aware model-parallel inference under spatio-temporal edge dynamics. PROMISE jointly models stochastic task generation, mobility-induced communication variations, privacy-aware model partitioning, and load-dependent edge computing capability. We introduce committed completion time (CCT) as an endogenous service decision and formulate joint SD--ES mapping and CCT determination to balance commitment fulfillment and service reward. To address cross-timeslot coupling, PROMISE estimates future task arrivals and computational workloads over an adaptive horizon and embeds them into certainty-equivalent ES-state rollout. A progress-aware surrogate then evaluates feasible current-stage mappings, while the corresponding CCTs are analytically recovered from predicted completion times. Only the first-stage decisions are committed, and the optimization is repeated with newly observed states in a receding-horizon manner. Numerical experiments demonstrate robust scheduling performance under diverse system scales and workload dynamics, while Raspberry-Pi-based experiments validate the practical feasibility and key system characteristics of model-parallel edge inference.

发表机构

• Tongji University（同济大学）
• Xiamen University（厦门大学）
• Western University（韦仕敦大学）

机构由 AI 辅助整理，请以论文原文为准。