一种BP神经网络和遗传算法混合的云平台负载 预测方法

A Load Forecasting Method of Cloud Platform Based on BP Neural Network And Genetic Algorithm

在云计算提供高效,便捷等强大服务的背后,是日益攀升的能耗问题。准确的预测云平台的负载(如CPU,内存的使用)在任务调度,云能效方面具有重要意义。在以往研究中,线性自回归算法在预测请求资源的粒度上存在不足,本文提出一种基于BP神经网络与遗传算法混合的负载预测方法,结合遗传算法良好的全局搜索能力与神经网络强大的非线性拟合能力,建立CPU资源的请求预测模型。实验通过Google的云平台数据作为训练,测试集。实验结果表明该方法有效的预测了CPU资源请求量,进而可以在此基础上调整服务资源,实现绿色调度。

The problem with the efficient,convenient and powerful service provided by cloud compute,is the serious energy consumption.the load prediction on the cloud platform(such as CPU and memory usage)is of great significance in task scheduling and energy efficiency.There exists some shorts on the granularity in research of linear regression algorithm,this paper puts forward a kind of load forecasting method based on BP neural network and genetic algorithm,with Google data as the training and test set.The result shows that the method effectively predict the amount of CPU request,which can be the reference in the assignment for service resources.