scholarly journals FEATURE SELECTION FOR PREDICTING LIVE MIGRATION CHARACTERISTICS OF VIRTUAL MACHINES

T-Comm ◽  
2021 ◽  
Vol 15 (7) ◽  
pp. 62-70
Author(s):  
Denis E. Kirov ◽  
◽  
Natalia V. Toutova ◽  
Anatoly S. Vorozhtsov ◽  
Iliya A. Andreev ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Linear Regression ◽  
Virtual Machine ◽  
Performance Metrics ◽  
Virtual Machines ◽  
Cloud Services ◽  
Migration Time ◽  
Support Vector ◽  
Total Migration

Virtual machine migration is widely used in cloud data centers to scale and maintain the stability of cloud services. However, the performance metrics of virtual machine (VM) applications during migration that are set in the Service Level Agreements may deteriorate. Before starting a migration, it is necessary to evaluate the migration characteristics that affect the quality of service. These characteristics are the total migration time and virtual machine downtime, which are random variables that depend on a variety of factors. The prediction is based on the VM monitoring data. In this paper, we select the most suitable factors for forecasting five types of migrations: precopy migration, postcopy migration, and modification of precopy migration such as CPU throttling, data compression, and delta compression of modified memory pages. To do this, we analyzed a dataset that includes data on five types of migrations, approximately 8000 records of each type. Using correlation analysis, the factors that mostly affect the total migration time and the VM downtime are chosen. These characteristics are predicted using machine learning methods such as linear regression and the support vector machine. It is shown that the number of factors can be reduced almost twice with the same quality of the forecast. In general, linear regression provides relatively high accuracy in predicting the total migration time and the duration of virtual machine downtime. At the same time, the observed nonlinearity in the correlations shows that it is advisable to use the support vector machine to improve the quality of the forecast.

Analytical Approach to Estimating Total Migration Time of Virtual Machines With Various Applications

2020 ◽  
Vol 11 (2) ◽  
pp. 58-75
Author(s):  
Andrew Toutov ◽  
Anatoly Vorozhtsov ◽  
Natalia Toutova
Keyword(s):  
Analytical Approach ◽  
Virtual Machines ◽  
Migration Time ◽  
Characteristic Functions ◽  
Live Migration ◽  
File Storage ◽  
Laguerre Series ◽  
Cloud Applications ◽  
Total Migration

Cloud applications and services such as social networks, file sharing services, and file storage have become increasingly popular among users in recent years. This leads to the enlargement of data centers, and an increase in the number of servers and virtual machines. In such systems, live migration is used to move virtual machines from one server to another, which affects the quality of service. Therefore, the problem of finding the total migration time is relevant. This article proposes analytical approach to obtaining analytical expression of the probability density of the total migration time based on the use of the apparatus of characteristic functions. The obtained expression is used to calculate characteristics of migration, taking into account the applications contributing the most randomness to the total migration time. To simplify the calculation of migration characteristics, the use of the Laguerre series can be recommended as giving more reliable results compared to Gram-Charlier series.

scholarly journals Priority-Based Virtual Machine Selection Algorithm in Cloud Computing

2019 ◽  
Vol 8 (3) ◽  
pp. 1457-1462
Keyword(s):  
Cloud Computing ◽  
Quality Of Service ◽  
Virtual Machine ◽  
Virtual Machines ◽  
Service Level Agreement ◽  
Cloud Service ◽  
Service Level ◽  
Cloud Services ◽  
Cloud Service Provider

Cloud computing technology has gained the attention of researchers in recent years. Almost every application is using cloud computing in one way or another. Virtualization allows running many virtual machines on a single physical computer by sharing its resources. Users can store their data on datacenter and run their applications from anywhere using the internet and pay as per service level agreement documents accordingly. It leads to an increase in demand for cloud services and may decrease the quality of service. This paper presents a priority-based selection of virtual machines by cloud service provider. The virtual machines in the cloud datacenter are configured as Amazon EC2 and algorithm is simulated in cloud-sim simulator. The results justify that proposed priority-based virtual machine algorithm shortens the makespan, by 11.43 % and 5.81 %, average waiting time by 28.80 % and 24.50%, and cost of using the virtual machine by 21.24% and 11.54% as compared to FCFS and ACO respectively, hence improving quality of service.

scholarly journals An overview of virtual machine live migration techniques

2019 ◽  
Vol 9 (5) ◽  
pp. 4433
Author(s):  
Artan Mazrekaj ◽  
Shkelzen Nuza ◽  
Mimoza Zatriqi ◽  
Vlera Alimehaj
Keyword(s):  
Virtual Machine ◽  
Performance Metrics ◽  
Virtual Machines ◽  
Optimal Solutions ◽  
Live Migration ◽  
Time Performance ◽  
Virtual Machine Live Migration ◽  
Memory Network ◽  
And Storage ◽  
Total Migration

In a cloud computing the live migration of virtual machines shows a process of moving a running virtual machine from source physical machine to the destination, considering the CPU, memory, network, and storage states. Various performance metrics are tackled such as, downtime, total migration time, performance degradation, and amount of migrated data, which are affected when a virtual machine is migrated. This paper presents an overview and understanding of virtual machine live migration techniques, of the different works in literature that consider this issue, which might impact the work of professionals and researchers to further explore the challenges and provide optimal solutions.

Agile Support Vector Machine for Energy-efficient Resource Allocation in IoT-oriented Cloud using PSO

2022 ◽  
Vol 22 (1) ◽  
pp. 1-35
Author(s):  
Muhammad Junaid ◽  
Adnan Sohail ◽  
Fadi Al Turjman ◽  
Rashid Ali
Keyword(s):  
Resource Allocation ◽  
Support Vector Machine ◽  
Load Balancing ◽  
Virtual Machines ◽  
Critical Factor ◽  
Resource Provisioning ◽  
Cloud Services ◽  
Support Vector ◽  
Cloud Infrastructure ◽  
Data Formats

Over the years cloud computing has seen significant evolution in terms of improvement in infrastructure and resource provisioning. However the continuous emergence of new applications such as the Internet of Things (IoTs) with thousands of users put a significant load on cloud infrastructure. Load balancing of resource allocation in cloud-oriented IoT is a critical factor that has a significant impact on the smooth operation of cloud services and customer satisfaction. Several load balancing strategies for cloud environment have been proposed in the past. However the existing approaches mostly consider only a few parameters and ignore many critical factors having a pivotal role in load balancing leading to less optimized resource allocation. Load balancing is a challenging problem and therefore the research community has recently focused towards employing machine learning-based metaheuristic approaches for load balancing in the cloud. In this paper we propose a metaheuristics-based scheme Data Format Classification using Support Vector Machine (DFC-SVM), to deal with the load balancing problem. The proposed scheme aims to reduce the online load balancing complexity by offline-based pre-classification of raw-data from diverse sources (such as IoT) into different formats e.g. text images media etc. SVM is utilized to classify “n” types of data formats featuring audio video text digital images and maps etc. A one-to-many classification approach has been developed so that data formats from the cloud are initially classified into their respective classes and assigned to virtual machines through the proposed modified version of Particle Swarm Optimization (PSO) which schedules the data of a particular class efficiently. The experimental results compared with the baselines have shown a significant improvement in the performance of the proposed approach. Overall an average of 94% classification accuracy is achieved along with 11.82% less energy 16% less response time and 16.08% fewer SLA violations are observed.

scholarly journals Ambient Air Quality Classification by Grey Wolf Optimizer Based Support Vector Machine

2017 ◽  
Vol 2017 ◽  
pp. 1-12 ◽  
Author(s):  
Akash Saxena ◽  
Shalini Shekhawat
Keyword(s):  
Support Vector Machine ◽  
Air Quality ◽  
Industrial Development ◽  
Learning Algorithm ◽  
Ambient Air ◽  
Support Vector ◽  
Grey Wolf Optimizer ◽  
Mathematical Framework ◽  
Primary Concern

With the development of society along with an escalating population, the concerns regarding public health have cropped up. The quality of air becomes primary concern regarding constant increase in the number of vehicles and industrial development. With this concern, several indices have been proposed to indicate the pollutant concentrations. In this paper, we present a mathematical framework to formulate a Cumulative Index (CI) on the basis of an individual concentration of four major pollutants (SO2, NO2, PM2.5, and PM10). Further, a supervised learning algorithm based classifier is proposed. This classifier employs support vector machine (SVM) to classify air quality into two types, that is, good or harmful. The potential inputs for this classifier are the calculated values of CIs. The efficacy of the classifier is tested on the real data of three locations: Kolkata, Delhi, and Bhopal. It is observed that the classifier performs well to classify the quality of air.

PERBANDINGAN METODE PREDIKSI SUPPORT VECTOR MACHINE DAN LINEAR REGRESSION MENGGUNAKAN BACKWARD ELIMINATION PADA PRODUKSI MINYAK KELAPA

2019 ◽  
Vol 4 (2) ◽  
pp. 104-107
Author(s):  
Andi Bode
Keyword(s):  
Time Series ◽  
Support Vector Machine ◽  
Linear Regression ◽  
Support Vector ◽  
Backward Elimination

Pohon kelapa banyak dimanfaatkan oleh manusia, sehingga tumbuhan ini dianggap tumbuhan serbaguna, salah satunya minyak kelapa yang dihasilkan oleh buah pohon kelapa. Produksi jumlah minyak kelapa menjadi bagian penting disetiap perusahaan yang bergerak di bidang produksi dengan tujuan mencapai target hasil produksi. Namaun Produksi minyak setiap hari mengalami perubahan fluktuatif. Perusahaan sangat memerlukan prediksi jumlah produksi. Penelitian ini bermaksud membandingakn metode support vector machine dan linear regression mengunakan fitur seleksi backward elimination berdasarkan data time series Sales Order. Hasil penelitian pada dataset sales order dengan menggunakan metode Support Vector Machine (SVM) didapatkan RMSE 0,127, dengan menggunakan metode SVM dan Backward Elimination (BE) didapatkan RMSE 0,115, dengan metode Linear Regression (LR) didapatkan RMSE 0,118 dan dengan menggunakan metode LR dan Backward Elimination didapatkan RMSE 0,118.  Dari hasil perbandingan tersebut dapat disimpulkan bahwa kinerja SVM menggunakan Backward Elimination lebih baik dibanding SVM, LR dan LR menggunakan Backward Elimination

A Novel Image Segmentation Method for Cardiac MRI Using Support Vector Machine Algorithm Based on Particle Swarm Optimization

2021 ◽  
Vol 11 (12) ◽  
pp. 3174-3180
Author(s):  
Guanghui Wang ◽  
Lihong Ma
Keyword(s):  
Support Vector Machine ◽  
Particle Swarm Optimization ◽  
Image Segmentation ◽  
Heart Disease ◽  
Cardiac Mri ◽  
Support Vector ◽  
Swarm Optimization ◽  
Running Time ◽  
Segmentation Accuracy

At present, heart disease not only has a significant impact on the quality of human life but also poses a greater impact on people’s health. Therefore, it is very important to be able to diagnose heart disease as early as possible and give corresponding treatment. Heart image segmentation is the primary operation of intelligent heart disease diagnosis. The quality of segmentation directly determines the effect of intelligent diagnosis. Because the running time of image segmentation is often longer, coupled with the characteristics of cardiac MR imaging technology and the structural characteristics of the cardiac target itself, the rapid segmentation of cardiac MRI images still has challenges. Aiming at the long running time of traditional methods and low segmentation accuracy, a medical image segmentation (MIS) method based on particle swarm optimization (PSO) optimized support vector machine (SVM) is proposed, referred to as PSO-SVM. First, the current iteration number and population number in PSO are added to the control strategy of inertial weight λ to improve the performance of PSO inertial weight λ. Find the optimal penalty coefficient C and γ in the gaussian kernel function by PSO. Then use the SVM method to establish the best classification model and test the data. Compared with traditional methods, this method not only shortens the running time, but also improves the segmentation accuracy. At the same time, comparing the influence of traditional inertial weights on segmentation results, the improved method reduces the average convergence algebra and shortens the optimization time.

Comprehensive Evaluation on Power Quality of Tidal Current Convertors

2019 ◽  
Vol 53 (3) ◽  
pp. 46-53
Author(s):  
Caixia Xue ◽  
Xiang-nan Wang ◽  
Ning Jia ◽  
Yuan-fei Zhang ◽  
Hai-nan Xia
Keyword(s):  
Power Generation ◽  
Support Vector Machine ◽  
Power Quality ◽  
Tidal Current ◽  
Evaluation Method ◽  
Comprehensive Evaluation ◽  
Support Vector ◽  
Operational Data ◽  
Testing And Evaluation

AbstractWith the continuous development of testing and evaluation of tidal current convertors, power quality assessment is becoming more and more critical. According to the characteristics of Chinese tidal current power generation and power quality standards, this paper proposes a comprehensive evaluation method of power quality based on K-means clustering and a support vector machine. The fundamental purpose of the method is to automatically select the weights of various indicators in the comprehensive assessment of power quality, by which the influence of subjective factors can be eliminated. In order to achieve the above purpose, K-means clustering is used for automatically classifying the operational data into five different categories. Then, a support vector machine is used to study and estimate the relationship of the operational data and categories. Using the method proposed in the paper, the analysis of operational data of a tidal current power generation shows that calculation results can objectively reflect the power quality of the device, and the influence of subjective factors is eliminated. The method can provide a reference for the testing and evaluation of a large amount of tidal current convertors in the future.

scholarly journals Linear Regression Supporting Vector Machine and Hybrid LOG Filter-Based Image Restoration

2019 ◽  
Vol 29 (1) ◽  
pp. 1480-1495
Author(s):  
D. Khalandar Basha ◽  
T. Venkateswarlu
Keyword(s):  
Linear Regression ◽  
Image Restoration ◽  
Color Image ◽  
Estimation Method ◽  
Similarity Index ◽  
Block Matching ◽  
Support Vector ◽  
Image Block ◽  
Testing Stage

Abstract The image restoration (IR) technique is a part of image processing to improve the quality of an image that is affected by noise and blur. Thus, IR is required to attain a better quality of image. In this paper, IR is performed using linear regression-based support vector machine (LR-SVM). This LR-SVM has two steps: training and testing. The training and testing stages have a distinct windowing process for extracting blocks from the images. The LR-SVM is trained through a block-by-block training sequence. The extracted block-by-block values of images are used to enhance the classification process of IR. In training, the imperfections on the image are easily identified by setting the target vectors as the original images. Then, the noisy image is given at LR-SVM testing, based on the original image restored from the dictionary. Finally, the image block from the testing stage is enhanced using the hybrid Laplacian of Gaussian (HLOG) filter. The denoising of the HLOG filter provides enhanced results by using block-by-block values. This proposed approach is named as LR-SVM-HLOG. A dataset used in this LR-SVM-HLOG method is the Berkeley Segmentation Database. The performance of LR-SVM-HLOG was analyzed as peak signal-to-noise ratio (PSNR) and structural similarity index. The PSNR values of the house and pepper image (color image) are 40.82 and 36.56 dB, respectively, which are higher compared to the inter- and intra-block sparse estimation method and block matching and three-dimensional filtering for color images at 20% noise.

Sign in / Sign up

Export Citation Format

Share Document