实时系统可变工作量建模及计算方法

传统实时系统性能分析以最差情况下执行时间(worst-case execution time,WCET)作为主要输入,导致分析过于保守.针对实时系统设计时预留冗余过大的问题,建立了以到达事件类型、数量和分布为决策变量,包括工作量曲线(workload curves)、逆工作量曲线(inverse workload curves)、工作量比率曲线(workload ratio curves)在内的实时系统可变工作量模型,给出了相关计算方法.基于可变工作量模型分析了其在混合调度中的应用,结果表明:采用可变工作量模型和算法可显著减少任务所需的执行工作量,降低了实时系统的资源需求.

A Variable Workload Model and Algorithm for Real-Time Systems

The traditional performance analysis of real-time systems relied on the input variable of worst-case execution time， which turned to be too pessimistic.Aiming at the problem of remarkably redundant design in real-time， a new model to characterize variable workload was created including workload curves， inverse workload curves and workload ratio curves. In the proposed model， event type， number and distribution were used as decision-variable， and relevant algorithm was proposed to solve the above model. In addition， the realistic applications were analyzed in mix scheduling based on VWM (variable workload model). The result indicates that the VWM can remarkably reduce execution workload of tasks， thus reducing the resource requirement of real-time systems.