Energy-Efficient Resource Allocation and Provisioning Framework for Cloud Data Centers

Abstract

Energy efficiency has recently become a major issue in large data centers due to financial and environmental concerns. This paper proposes an integrated energy-aware resource provisioning framework for cloud data centers. The proposed framework: i) predicts the number of virtual machine (VM) requests, to be arriving at cloud data centers in the near future, along with the amount of CPU and memory resources associated with each of these requests, ii) provides accurate estimations of the number of physical machines (PMs) that cloud data centers need in order to serve their clients, and iii) reduces energy consumption of cloud data centers by putting to sleep unneeded PMs. Our framework is evaluated using real Google traces collected over a 29-day period from a Google cluster containing over 12,500 PMs. These evaluations show that our proposed energy-aware resource provisioning framework makes substantial energy savings.

Resource Scheduling in Cloud Environmet: A Survey

“…Proposed approach significantly reduces energy by 13-23% as compared to other heuristic approaches [50] In [52], a predictive design which aims to combine the machine learning clustering and stochastic theory to estimate both the number of VM requests and the amount of cloud resources associated with each request is formulated. An amalgamated resource conditioning framework depending upon this method has been used by the authors to make suitable energy-aware resource supervised decisions which is further evaluated using real Google traces collected over a 29-day period from a Google cluster containing over 12,500 PMs.…”

System-Level Analysis and Design under Uncertainty

“…The work in [25], which is more directly relevant to the topic of this chapter, is concerned with cloud data centers. The authors propose a framework for predicting the number of virtual-machine requests together with the required amounts of cpu and memory.…”

“…The framework makes use of k-means clustering [46] for identifying different types of requests, and then it utilizes Wiener filters in order to estimate the aggregate workload with respect to each identified type. Similarly to [25], the work in [53] is focused on forecasting virtualmachine requests in cloud data centers and relies on k-means clustering as the first step. Unlike [25], the main workhorse in the case of the technique in [53] is extreme learning machines, which are feedforward neural networks.…”

“…Similarly to [25], the work in [53] is focused on forecasting virtualmachine requests in cloud data centers and relies on k-means clustering as the first step. Unlike [25], the main workhorse in the case of the technique in [53] is extreme learning machines, which are feedforward neural networks. An ensemble model [46] is presented in [9] targeted at predicting cpu usage in cloud environments.…”

“…In addition, note that the predictions delivered by the techniques proposed in [9,25,53] are coarse. They treat virtual-machine requests or computational resources as a fluid and predict the level that this fluid will attain at the next moment in time.…”