Simulation and Performance Analysis of Data Intensive and Workload Intensive Cloud Computing Data Centers

Abstract

Data centers are becoming increasingly popular for the provisioning of computing resources. The cost and operational expenses of data centers have skyrocketed with the increase in computing capacity [1]. Energy consumption is a growing concern for data center operators. It is becoming one of the main entries on a data center operational expenses (OPEX) bill [2,3]. The Gartner Group estimates energy consumptions to account for up to 10% of the current OPEX, and this estimate is projected to rise to 50% in the next few years [4]. However, computing-based energy consumption is not the only power-related portion of the OPEX bill. High power consumption generates heat and requires an accompanying cooling system that costs in a range of $2-$5 million per year for classical data centers [5]. Failure to keep data center temperatures within operational ranges drastically decreases hardware reliability and may potentially violate the service level agreement (SLA) with the customers.From the perspective of energy efficiency, a cloud computing data center can be defined as a pool of computing and communication resources organized in the way to transform the received power into computing or data transfer work to satisfy user demands. The first power saving solutions focused on making the data center hardware components power efficient. Technologies, such as dynamic voltage and frequency scaling (DVFS), and dynamic power management (DPM) [6], were

A Comprehensive Evaluation of Scheduling Methods of Virtual Machine Migration for Energy Conservation

“…Since a workload type has a significant influence on the energy consumption and the performance of data centers, workload types have to be fully considered in the evaluation of scheduling methods [4]. The workload types requiring to be taken into consideration include CPU-intensive, memoryintensive, bandwidth-intensive, disk-intensive workload, and their combined workload, which are discussed here based on relevant researches and conclusions [13].…”

“…Nowadays, with the development of the cloud computing [2] and the utilization of the virtualization technology [3], the scale of data centers is increasing. Meanwhile, the resource utilization of the servers in a data center is generally relatively low [4], which make the energy consumption of data centers constantly increase. How to improve the resource efficiency of data centers by adopting energysaving scheduling methods becomes an important problem.…”

Performance analysis of data intensive cloud systems based on data management and replication: a survey

“…The list of metrics used for the comparison and analysis of existing literature in this survey are: (a) Availability (the probability that a system is alive and functioning well in a stated environment, or the degree of liveliness of the system), (b) Reliability (the probability that a system will operate predictably under the stated environmental conditions over a specific period of time), (c) Scalability (the property of the system to grow, usually achieved by adding or upgrading hardware), (d) Fault-Tolerance (the ability of the system to respond gracefully to any unexpected failure of software or hardware), (e) Load balancing (the property of or methodology used by the system to divide the workload across servers, network links, CPUs, disks or other resources to achieve optimal utilization, throughput maximization, reduced response time and avoid overloading), (f) Throughput (amount of data or size of the message a system can process or transact per unit of time), and (g) Consistency (the probability that a system will not derive contradictory statements). Data management and data replication are the key elements instrumental for the success of the data-intensive applications in cloud computing environments [6,38]. Data management strategies provide scalability, adoptability, load and user balancing, multi-tenancy, and flexibility to the cloud services.…”

On energy consumption of switch-centric data center networks

“…On the other hand, P chasis and P linecard depend solely on the power status of the device and affected only when device is powered down for lack of network traffic [14]. The server energy consumption model is derived by [14,25]:…”