Applications of machine learning approach on multi-queue message scheduling

Due to limited resource contentions and deadline constraints, messages on the controller area network (CAN) are competing for service from the common resources. This problem can be resolved by assigning priorities to different message classes to satisfy time-critical applications. Actually, because of the fluctuation of network traffic or an inefficient use of resources, these static or dynamic priority policies may not guarantee flexibility for different kinds of messages in real-time scheduling. Consequently, the message transmission which cannot comply with the timing requirements or deadlines may deteriorate system performance significantly. In this paper, we have proposed a controller-plant model, where the plant is analogous to a message queue pool (MQP) and the message scheduling controller (MSC) is responsible to dispatch resources for queued messages according to the feedback information from the MQP. The message scheduling controller, which is realized by the radial basis function (RBF) network, is designed with machine learning algorithm to compensate the variations in plant dynamics. The MSC with the novel hybrid learning schemes can ensure a low and stable message waiting time variance (or a uniform distribution of waiting time) and lower transmission failures. A significant emphasis of the MSC is the variable structure of the RBF model to accommodate to complex scheduling situations. Simulation experiments have shown that several variants of the MSC significantly improve overall system performance over the static scheduling strategies and the dynamic earliest-deadline first (EDF) algorithms under a wide range of workload characteristics and execution environments.

Research highlights
► This study explores a machine learning approach on multi-queue message scheduling. The novelty of this investigation is the introduction of type I and type II learning for message scheduling.
► Type I learning prevents possible causes of non-uniform bandwidth allocation among requesting messages, while type II learning is intended to reduce possibilities of transmission failures.
► The learning mechanism is implemented by the Radial Basis Function (RBF) network with variable RBF structure to accommodate to complex scheduling situations and system dynamics.
► Simulation results demonstrate that the proposed MSC outperforms the existing scheduling methods. It is also noteworthy that the cooperation of type I and II learning offers very good resistances to the workload variations.