Dataset Information

Data on performance prediction for cloud service selection.

ABSTRACT: This paper contains data on Performance Prediction for Cloud Service Selection. To measure the performance metrics of any system you need to analyze the features that affect these performance, these features are called " workload parameters". The data described here is collected from the KSA Ministry of Finance that contains 28,147 instances from 13 cloud nodes. It was recorded during the period from March 1, 2016, to February 20, 2017, in continuous time slots. In this article we selected 9 workload parameters: Number of Jobs in a Minute, Number of Jobs in 5?min, Number of Jobs in 15?min, Memory Capacity, Disk Capacity,: Number of CPU Cores, CPU Speed per Core, Average Receive for Network Bandwidth in Kbps and Average Transmit for Network Bandwidth in Kbps. Moreover, we selected 3 performance metrics: Memory utilization, CPU utilization and response time in milliseconds. This data article is related to the research article titled "An Automated Performance Prediction Model for Cloud Service Selection from Smart Data" (Al-Faifi et al., 2018) [1].

SUBMITTER: Al-Faifi AM

PROVIDER: S-EPMC6138836 | biostudies-other | 2018 Oct

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Data on performance prediction for cloud service selection.

Al-Faifi Abdullah Mohammed AM Song Biao B Hassan Mohammad Mehedi MM Alamri Atif A Gumaei Abdu A

Data in brief 20180831

This paper contains data on Performance Prediction for Cloud Service Selection. To measure the performance metrics of any system you need to analyze the features that affect these performance, these features are called " workload parameters". The data described here is collected from the KSA Ministry of Finance that contains 28,147 instances from 13 cloud nodes. It was recorded during the period from March 1, 2016, to February 20, 2017, in continuous time slots. In this article we selected 9 wor ...[more]

PMID: 30225319

Similar Datasets

Project description:Recently, manufacturing firms and logistics service providers have been encouraged to deploy the most recent features of Information Technology (IT) to prevail in the competitive circumstances of manufacturing industries. Industry 4.0 and Cloud manufacturing (CMfg), accompanied by a service-oriented architecture model, have been regarded as renowned approaches to enable and facilitate the transition of conventional manufacturing business models into more efficient and productive ones. Furthermore, there is an aptness among the manufacturing and logistics businesses as service providers to synergize and cut down the investment and operational costs via sharing logistics fleet and production facilities in the form of outsourcing and consequently increase their profitability. Therefore, due to the Everything as a Service (XaaS) paradigm, efficient service composition is known to be a remarkable issue in the cloud manufacturing paradigm. This issue is challenging due to the service composition problem's large size and complicated computational characteristics. This paper has focused on the considerable number of continually received service requests, which must be prioritized and handled in the minimum possible time while fulfilling the Quality of Service (QoS) parameters. Considering the NP-hard nature and dynamicity of the allocation problem in the Cloud composition problem, heuristic and metaheuristic solving approaches are strongly preferred to obtain optimal or nearly optimal solutions. This study has presented an innovative, time-efficient approach for mutual manufacturing and logistical service composition with the QoS considerations. The method presented in this paper is highly competent in solving large-scale service composition problems time-efficiently while satisfying the optimality gap. A sample dataset has been synthesized to evaluate the outcomes of the developed model compared to earlier research studies. The results show the proposed algorithm can be applied to fulfill the dynamic behavior of manufacturing and logistics service composition due to its efficiency in solving time. The paper has embedded the relation of task and logistic services for cloud service composition in solving algorithm and enhanced the efficiency of resulted matched services. Moreover, considering the possibility of arrival of new services and demands into cloud, the proposed algorithm adapts the service composition algorithm.

Project description:BACKGROUND:The advent of next-generation sequencing (NGS) has made whole-genome sequencing of cohorts of individuals a reality. Primary datasets of raw or aligned reads of this sort can get very large. For scientific questions where curated called variants are not sufficient, the sheer size of the datasets makes analysis prohibitively expensive. In order to make re-analysis of such data feasible without the need to have access to a large-scale computing facility, we have developed a highly scalable, storage-agnostic framework, an associated API and an easy-to-use web user interface to execute custom filters on large genomic datasets. RESULTS:We present BAMSI, a Software as-a Service (SaaS) solution for filtering of the 1000 Genomes phase 3 set of aligned reads, with the possibility of extension and customization to other sets of files. Unique to our solution is the capability of simultaneously utilizing many different mirrors of the data to increase the speed of the analysis. In particular, if the data is available in private or public clouds - an increasingly common scenario for both academic and commercial cloud providers - our framework allows for seamless deployment of filtering workers close to data. We show results indicating that such a setup improves the horizontal scalability of the system, and present a possible use case of the framework by performing an analysis of structural variation in the 1000 Genomes data set. CONCLUSIONS:BAMSI constitutes a framework for efficient filtering of large genomic data sets that is flexible in the use of compute as well as storage resources. The data resulting from the filter is assumed to be greatly reduced in size, and can easily be downloaded or routed into e.g. a Hadoop cluster for subsequent interactive analysis using Hive, Spark or similar tools. In this respect, our framework also suggests a general model for making very large datasets of high scientific value more accessible by offering the possibility for organizations to share the cost of hosting data on hot storage, without compromising the scalability of downstream analysis.

Dataset Information

Data on performance prediction for cloud service selection.

Publications

Data on performance prediction for cloud service selection.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure