Concepedia

Prediction of cloud data center networks loads using stochastic and neural models

John J. Prevost, Kranthimanoj Nagothu, Brian Kelley, Mo Jamshidi

2011 · 171 citations · 8 references

TL;DR

The increasing demand for cloud computing resources has led to a commensurate increase in the operating power consumption of the systems that comprise the cloud. The authors propose a framework that integrates load demand prediction with stochastic state transition models to achieve optimal cloud resource allocation by minimizing energy consumption while maintaining performance. The framework employs neural network and auto‑regressive linear prediction algorithms to forecast cloud data center loads, coupled with stochastic state transition models. The models were evaluated on two datasets across multiple look‑ahead horizons, demonstrating their predictive performance.

Abstract

The increasing demand for cloud computing resources has led to a commensurate increase in the operating power consumption of the systems that comprise the cloud. In this paper, we introduce a novel framework combining load demand prediction and stochastic state transition models. We claim that our model will lead to optimal cloud resource allocation by minimizing energy consumed while maintaining required performance levels. We characterize the ability of neural network and auto-regressive linear prediction algorithms to forecast loads in cloud data center applications. In this paper, the performance of our models against two sets of data at multiple look-ahead times is also presented.