Computation-Accuracy Trade-Off in Service-Oriented Model-Based Control
Hazem Ibrahim, Julius Beerwerth, Lorenz Dörschel, Bassam Alrifaee
TL;DR
This work tackles the challenge of static, fixed-control architectures by introducing Service-Oriented Model-Based Control (SOMC), which treats each control-loop element as a service and uses a central orchestrator to assemble executable control paths. A graph-based framework defines a layered service graph and employs A$^\star$ path planning to find the optimal service composition under a multi-objective cost that combines computation time and control accuracy, with Contextual Bayesian Optimization learning the trade-off weight $\alpha$ from context. The approach enables online, performance-driven reconfiguration of the control architecture as operating conditions evolve, demonstrated on a vehicle longitudinal-velocity control case study. The results show the framework can selectively prioritize accuracy or speed, achieving substantial runtime adaptability while respecting real-time requirements, thereby integrating control and software structure in a unified SOMC framework.
Abstract
Representing a control system as a Service-Oriented Architecture (SOA)-referred to as Service-Oriented Model-Based Control (SOMC)-enables runtime-flexible composition of control loop elements. This paper presents a framework that optimizes the computation-accuracy trade-off by formulating service orchestration as an A$^\star$search problem, complemented by Contextual Bayesian Optimization (BO) to tune the multi-objective cost weights. A vehicle longitudinal-velocity control case study demonstrates online, performancedriven reconfiguration of the control architecture. We show that our framework not only combines control and software structure but also considers the real-time requirements of the control system during performance optimization.