CPU-based Prediction with Self Organizing Map in Dynamic Cloud Data Centers

Author(s):Nabila Djennane*Meziane YacoubRachida Aoudjit and Samia Bouzefrane

Volume 11, Issue 7, 2021

Published on: 16 December, 2020

Page: [733 – 747]

Pages: 15

DOI: 10.2174/2210327910666201216123246


Backgroud: The major objective of resource management systems in the cloud environments is to assist providers in making consistent and cost-effective decisions related to dynamic resource allocation. However, because of the demand changes of the applications and the exponential evolution of the cloud, the resource management systems are constantly called into question with regard to their ability to guarantee effective resource provisioning.

Objective: To tackle these challenges, future demand prediction is a practical solution that has been adopted in the literature. The prediction has widely relied on CPU utilization since it is considered a leading cause of the Quality of Service dropping.

Methods: The successful application of artificial intelligence techniques in forecasting problems motivated us to use the Kohonen Self Organizing Maps that try to capture the gathered empirical CPU load time series in regular behaviors to perform an accurate forecast. The proposed solution is a two-step approach that first classifies the collected data and then predicts the future CPU load.

Results and Conclusion: The experimental results show that our proposed system outperforms other models reported in the literature. In addition, we proved that Self Organizing Maps known for their strength in classification are also effective for prediction. Read now: https://bit.ly/3Tz9GSe

Most Cited Article – Task Scheduling Algorithm Based on Reliability Perception in Cloud Computing

Author(s):Kuang YuejuanLuo Zhuojun* and Ouyang Weihao

Volume 14, Issue 1, 2021

Published on: 10 July, 2020

Page: [52 – 58]

Pages: 7

DOI: 10.2174/2352096513999200710140836


Background: In order to obtain reliable cloud resources, reduce the impact of resource node faults in cloud computing environment and reduce the fault time perceived by the application layer, a task scheduling model based on reliability perception is proposed.

Methods: The model combines the two-parameter weibull distribution and analyzes various interaction relations between parallel tasks to describe the local characteristics of the failure rules of resource nodes and communication links in different periods. The model is added into the particle swarm optimization (PSO) algorithm, and an adaptive inertial weighted PSO resource scheduling algorithm based on reliability perception is obtained.

Results: Simulation results show that when A increases to 0.3, the average scheduling length of the task increases rapidly. When it is 0.4-0.6, the growth rate is relatively slow. When greater than 0.8, the average scheduling length increases sharply, it can be seen that the r-PSO algorithm proposed in this paper can accurately estimate the relevant parameters of cloud resource failure rule, and the generated resource scheduling scheme has better fitness, and the optimization effect is more significant with the increase in the number of tasks.

Conclusion: With only a small amount of time added, the reliability of cloud services is greatly improved. Read more: https://bit.ly/3zaHYlc

Most Cited Article – Task-scheduling Algorithm based on Improved Genetic Algorithm in Cloud Computing Environment

Author(s):G.E. Weiqing* and Cui Yanru

Volume 14, Issue 1, 2021

Published on: 23 April, 2020

Page: [13 – 19]

Pages: 7

DOI: 10.2174/2352096513999200424075719


Background: Min-min and max-min algorithms were combined on the basis of the traditional genetic algorithm to make up for its shortcomings.

Methods: In this paper, a new cloud computing task-scheduling algorithm that introduces min-min and max-min algorithms to generate initialization population, selects task completion time and load balancing as double fitness functions, and improves the quality of initialization population, algorithm searchability and convergence speed, was proposed.

Results: The simulation results proved that the cloud computing task-scheduling algorithm was superior to and more effective than the traditional genetic algorithm.

Conclusion: The paper proposes the possibility of the fusion of the two quadratively improved algorithms and completes the preliminary fusion of the algorithm, but the simulation results of the new algorithm are not ideal and need to be further studied. Read more: https://bit.ly/3IRuuiR

Press Release | Cloud computing load balancing based on ant colony algorithms improves performance

The article by Dr. Awatif Ragmani et al. is published in Recent Patents on Computer Science, 2018


Cloud computing has strongly contributed to the revolution of the traditional IT model. This paradigm has also contributed to the rise of applications using large amounts of data. Particularly, the quality of service and cost are two major points in the Cloud environment. This new concept which proposes to offer applications and IT infrastructures in the form of service available on demand and payable according to the duration of use must optimize both the performance of its resources and the respect of attractive pricing policies.

The Cloud computing model relies on the exploitation of several datacenters installed on different geographical locations. Each datacenter hosts servers which include the virtual machines in charge of processing users’ requests. The geographic extent of the cloud architecture, as well as the number of interactions that exist between the physical components, make the mission of analysis and optimization of the performance highly complex. Our study proposes to study the performance by considering the Cloud model as a black box with a list of inputs gathering the factors that can influence the performance of the system and the outputs that translate the Key Performance Indicators (KPIs). Each KPI makes it possible to measure the evolution of an aspect of the system performance such as the response time or the cost of service. The process of identifying and evaluating the influencing factors was carried out on the basis of Taguchi experience plans. This study includes two steps that aim to improve the performance of Cloud services while ensuring a lower price level. The first step is the evaluation of the Cloud model via a performance analysis methodology inspired by Taguchi concept and the second step details the implementation of a three-tier architecture.

The modeling of the system, as well as all the simulation scenarios, were carried out via the CloudAnalyst simulator. This simulator dedicated to Cloud architecture allows the implementation of various inputs configurations defined on the basis of Taguchi tables in order to find out the function f that links each output to the system’s inputs. The conclusions of this study revealed the impact of the load balancing policy as well as the size of the queries and the location of the datacenters with respect to the user on the response time, the processing time and the total cost. Particularly, the load balancing demonstrated a substantial impact on the performance of the Cloud system.

Following a comparative study of several load balancing algorithms, it was possible to define a three-tier solution based on an ant colony algorithm. The choice of the ant colony algorithm was justified by its ability to identify an optimal solution within a reasonable time and to be able to manage a wide area network encompassing thousands of nodes. These characteristics have made it possible to have a solution that satisfies both the response time and cost criteria. The architecture has also two controllers in order to decrease the load of the main controller and contribute to improving the processing time of the system.

Browse the article details atA Performed Load Balancing Algorithm for Public Cloud Computing Using Ant Colony Optimization

Upcoming Thematic Issue – Smart Transportation Based on Multimedia Data Mining



%d bloggers like this: