Abstract: The states of resources are dynamic in grid. Only when the states of resources are known can resources be better managed and scheduled. Since the change of resources has certain periodicity, a resource prediction model is proposed. The prediction mechanism can predict the periodicity and the abnormality of the resource. It modifies the model of the prediction and gives better predictions by distinguishing between the stability and instability of the states, periodical time and abnormal time.

Key words: prediction, neural network, grid computing

摘要： 网格环境下的资源具有动态性，只有了解资源状态，才能更好地进行资源管理和调度。资源状态的变化具有周期性，该文提出一种网格资源状态预测算法，能够预测资源状态变化的周期性和异常性，通过区分稳定状态与非稳定状态、周期性时刻与异常性时刻，对预测模型进行调整，从而较为准确地预测资源的状态。

关键词: 预测, 神经网络, 网格计算

CLC Number: 

• TP393