Dynamic Low-Power Reconfiguration of Real-Time Systems With Periodic and Probabilistic Tasks

• Published in: IEEE transactions on automation science and engineering 2015-01, Vol.12 (1), p.258-271
• Main Authors: Wang, Xi, Khemaissia, Imen, Khalgui, Mohamed, Li, ZhiWu, Mosbahi, Olfa, Zhou, MengChu
• Format: Article
• Language: English
• Subjects: Agent-based architecture; Computer architecture; dynamic reconfiguration; Dynamical systems; Dynamics; EDF scheduling; Educational institutions; Energy consumption; low-power; Power consumption; Power demand; Probabilistic logic; Probabilistic methods; Probability theory; Program processors; Real time; real-time system; Real-time systems; Reconfiguration; Runtime; Simulation; Software; Tasks
• ISSN: 1545-5955; 1558-3783
• DOI: 10.1109/TASE.2014.2309479

This paper deals with the dynamic low-power reconfiguration of a real-time system. It processes periodic and probabilistic tasks that have hard/soft deadlines corresponding to internal/external events. A runtime event-based reconfiguration scenario is a dynamic operation allowing the addition/removal of the assumed periodic/probabilistic tasks. Thereafter, some tasks may miss their hard deadlines and the power consumption may increase. In order to reconfigure the system to be feasible, i.e., satisfying its real-time constraints with low-power consumption, this research presents a software-agent-based architecture. An intelligent agent is developed, which provides four solutions to reconfigure the system at runtime. For these solutions, in order to reconfigure the probabilistic tasks to be feasible, the agent modifies their temporal parameters dynamically; moreover, in order to feasibly serve the probabilistic tasks and reduce the system's power consumption, the agent provides three virtual processors by dynamically extending the periods of the periodic tasks. A simulation study verifies the effectiveness of the agent.