故障检测器是构建可靠的存储区域网所必需的部分。针对系统中节点状态变化快的特点,设计了一种基于神经网络的故障检测器。它结合心跳策略和神经网络模型,根据环境的变化预测出被检测节点的状态,在一定的检测时间内,提高了故障检测器的精度。实验表明,该故障检测器具有较好的性能,提高了存储区域网的可靠性。
Failure detectors have been an important abstraction to build dependable communication applications over storage area network subject to faults.To address the dynamic characteristics of node in system,a failure detector,which can combine heartbeat strategy with neural net,is designed to forecast the status of detected node according to network environment changes.The examination result shows that the fault detector has better performance.