服务网格中资源可用性评估方法研究*

资源可用性的预测与评估是动态网格环境下合理资源选择和保证服务质量的前提和基础。基于相关资源和任务的历史信息，利用概率论方法对资源可用性进行了预测与评估，提出了资源离线时间、本地任务执行时间、等待队列长度、等待时间等可用性尺度，证明并给出这些尺度的分布函数。实验表明，基于相关历史信息对资源可用性进行预测方法有效，并且根据资源可用性评估及提取的相关可用性尺度来确定任务调度的候选资源，可大大减少候选资源数目，从而降低调度的时间复杂度。

Research on methodology of resource availability evaluation in service grid environment

In dynamic grid environment,prediction and evaluation of resource availability are the prerequisite for reasonable resource selection and good QoS guarantee.Based on some related resource and task historical traces,applied probability theory to resource availability prediction and evaluation.Presented the availability metrics including resource off-line time,local task execution time,waiting queue length and waiting time and gave and proved the distribution functions of these metrics.The experiment results show that the prediction is effective,and the amount of candidate resources determined by resource availability evaluation is decreased significantly,therefore lowering time complexity of task scheduling.