基于灰色预测容错时钟同步算法

针对分布式实时系统中无主式时钟同步存在时钟拜占庭故障和节点通信链路丢失故障的问题，文中提出一种基于灰色预测容错时钟同步算法。该算法基于广播式通信网络LL模型，使用GM(1,1)的灰色预测方法对前轮次的校正偏差值进行分析，从而预测出该节点在故障伦次中的校正偏差值，再通过计算得到修正值。实验结果表明，文中提出的灰色预测算法能够容忍拜占庭故障，同时可克服节点通信链路丢失故障带来的问题，提升了FTA算法的普适性。通过数据对比分析结果表明，该算法的时钟同步精密度相比于原始算法提高了24.3%;相较于其他算法，文中算法在复杂度上也有一定的优势。

Fault-Tolerant Clock Synchronization Algorithm Based on Grey Prediction

In view of the problem of clock Byzantine failure and node communication link loss failure in the non-master clock synchronization in the distributed real-time system, a fault-tolerant clock synchronization algorithm based on gray prediction is proposed in this study. The proposed algorithm is based on the LL model of the broadcast communication network, and uses the gray prediction method of GM (1,1) to analyze the correction deviation value of the previous round, so as to predict the correction deviation value of the node in the failure order, and then obtain the correction value through calculation. The experimental results show that the gray prediction algorithm proposed in this study can tolerate Byzantine faults, and at the same time, it can overcome the problems caused by the failure of node communication link loss, and improve the universality of the FTA algorithm. The data comparison analysis results show that the clock synchronization precision of this algorithm is improved by 24.3% when compared with Original algorithm. At the same time, the algorithm complexity has certain advantages when compared with other algorithms.