Multiagent Architecture for Distributed Adaptive Scheduling of Reconfigurable Real-Time Tasks With Energy Harvesting Constraints

This paper presents new challenges for the real-time scheduling of distributed reconfigurable embedded systems powered by a renewable energy. Reconfigurable computing systems have to deal with unpredictable events from the environment, such as activation of new tasks and hardware or software failures, by adapting the task allocation and scheduling in order to maintain the system feasibility and performance. The proposed approach is based on an intelligent multiagent distributed architecture composed of: 1) a global agent “coordinator” associated with the whole distributed system and 2) four local agents, such as supervisor, scheduler, battery manager, and reconfiguration manager, belong to each subsystem. The efficiency and completeness of the reconfiguration adaptative strategy is proved as all possible reconfiguration forms are considered to guarantee a feasible system with a graceful quality of service. Two communication protocols, such as an intra-subsystem communication protocol and an inter-subsystem communication protocol, are proposed to ensure the effectiveness of the proposed reconfiguration strategy. Extensive simulations show the effectiveness of the proposed intelligent multiagent distributed architecture in terms of the number of exchanged messages, deadline success ratio, and the energy consumption.