An QPSL Queuing Model for Load Balancing in Cloud Computing

2020 ◽  
Vol 16 (3) ◽  
pp. 33-48
Author(s):  
Shadab Siddiqui ◽  
Manuj Darbari ◽  
Diwakar Yagyasen
Keyword(s):  
Cloud Computing ◽  
Load Balancing ◽  
Queuing Theory ◽  
Service Rate ◽  
Queuing Model ◽  
Queuing Models ◽  
Fifo Queue ◽  
Queue Discipline ◽  
Service Rates ◽  
Waiting Lines

Load balancing is the process of distributing a workload among various servers. Queuing is the most common scenario for day-to-day applications. Queuing theory is used to study the problem of waiting lines. Queuing theory bridges the gap between service demands and the delay in replies given to users. The proposed QPSL Queuing Model makes use of M/M/k queue with FIFO queue discipline for load balancing in cloud computing. The model makes use of exponential distribution for calculating service rates and Poisson distribution for calculating waiting lines. The proposed QPSL queuing model is also compared with other existing queuing models for load balancing on various parameters. The experimental analysis depicts that QPSL model performed better in terms of service rate and response time.

Optimization of Queuing Theory Based on Vague Environment

2016 ◽  
Vol 5 (1) ◽  
pp. 1-26 ◽  
Author(s):  
Verónica Andrea González-López ◽  
Ramin Gholizadeh ◽  
Aliakbar M. Shirazi
Keyword(s):  
Everyday Life ◽  
Real World ◽  
Queuing Theory ◽  
Arrival Rate ◽  
Service Rate ◽  
New Approach ◽  
The Real ◽  
Processing Times ◽  
Queuing Models ◽  
Service Rates

Waiting lines or queues are commonly occurred both in everyday life and in a variety of business and industrial situations. The various arrival rates, service rates and processing times of jobs/tasks usually assumed are exact. However, the real world is complex and the complexity is due to the uncertainty. The queuing theory by using vague environment is described in this paper. To illustrate, the approach analytical results for M/M/1/8 and M/M/s/8 systems are presented. It optimizes queuing models such that the arrival rate and service rate are vague numbers. This paper results a new approach for queuing models in the vague environment that it can be more effective than deterministic queuing models. A numerical example is illustrated to check the validity of the proposed method.

scholarly journals Stability Analysis and Optimization of Airport Security System

2017 ◽  
Vol 6 (1) ◽  
pp. 56
Author(s):  
Yang Li ◽  
Lanya Ma ◽  
Yuanbiao Zhang ◽  
Weijie Yang
Keyword(s):  
Computer Simulation ◽  
Queuing Theory ◽  
Security System ◽  
Airport Security ◽  
Service Rate ◽  
Queuing Network ◽  
Queuing Model ◽  
Scanning Process ◽  
Development Direction ◽  
Check System

In this paper, we have established a composite queuing network model on the basis of the queuing theory and combining with the current security system of the airport. We have made division of the whole security system into different processes which include ID check process, x-ray scanning process, and millimeter scanning process, and find out the unit of security system according to the proportion of different security lanes, what’s more, these processes were distinguished into different kinds of queuing system, and then, we established the queuing network using these different queuing model into the unit. We applied the method of computer simulation to analyze the bottleneck, and we find that ID check process in pre-check system is unstable based on the current proportion of pre-check lane. Meanwhile, we optimized the number of each unit using the system design model and prove the effectiveness by computer simulation, then, we optimized the service rate of the baggage and body screening in pre-check lane follow the above process. Finally, we further discussed development direction of this model.

scholarly journals Dynamic Security Exchange Scheduling Model for Business Workflow Based on Queuing Theory in Cloud Computing

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Rongbin Xu ◽  
Jianguo Wu ◽  
Yongliang Cheng ◽  
Zhiqiang Liu ◽  
Yuanmo Lin ◽  
...  
Keyword(s):  
Cloud Computing ◽  
Dynamic Process ◽  
Queuing Theory ◽  
Business Processes ◽  
Virtual Machines ◽  
Service Discipline ◽  
Security Issue ◽  
Queuing Model ◽  
Scheduling Model ◽  
Cloud Resources

With the rapid development of e-business, large volume of business processes need to be handled in a constrained time. There is always a security issue related to on-time completion in many applications in the economic fields. So, how to effectively manage and organize business processes became very important. By using cloud computing, instance-intensive processes can be handled more effectively by applying just-right virtual machines. Hence, the management of cloud resources became an important issue that many researchers focus on to fully utilize the advantage of cloud. In this paper, we mainly discuss the queuing theory and put forward our novel dynamic process scheduling model based on queuing theory, which is named M/G/k/l-P for business processes. This model can solve the issue of allocating appropriate number of cloud resources based on the number of tasks and execution stages to ensure whether the numbers of cloud resources are sufficient and adequate or not, which can improve the security issue for business process. The service discipline in our model can provide a dynamic process by setting different priorities to improve the experience of users. Evaluations prove that the queuing model of M/G/k/l-P can work very well for business workflow scheduling.

scholarly journals Minimal cost service rate in priority queuing models for emergency cases in hospitals

2018 ◽  
Vol 6 (2) ◽  
pp. 50
Author(s):  
Nse S. Udoh ◽  
Idorenyin A. Etukudo
Keyword(s):  
Waiting Time ◽  
Service Rate ◽  
Time Cost ◽  
Service Cost ◽  
Queuing Model ◽  
Total Cost ◽  
Lower Priority ◽  
Queuing Models ◽  
Optimum Cost ◽  
Expected Waiting Time

Performance measures and waiting time cost for higher priority patients with severe cases over lower priority patients with stable cases using preemptive priority queuing model were obtained. Also, a total expected waiting time cost per unit time for service and the expected service cost per unit time for priority queuing models: M/M/2: ∞/NPP and M/M/2: ∞/PP were respectively formulated and optimized to obtain optimum cost service rate that minimizes the total cost. The results were applied to obtain optimum service rate that minimizes the total cost of providing and waiting for service at the emergency consulting unit of hospital.    

scholarly journals PENERAPAN METODE ANTRIAN DALAM MENENTUKAN FASILITAS YANG OPTIMAL PADA SPBU MAWADDAH

2018 ◽  
Vol 3 (5) ◽  
Author(s):  
Diana Khairani Sofyan ◽  
Sri Meutia
Keyword(s):  
Diesel Fuel ◽  
Arrival Rate ◽  
Service Level ◽  
Service Rate ◽  
Queuing Model ◽  
Fuel Pump ◽  
Gas Stations ◽  
Scenario Design ◽  
Service Rates ◽  
Number Of Customers

Gas stations Mawaddah Is one of the gas stations located in the Village Batuphat East Lhokseumawe. The gas station has 5 oil pumps consisting of premium with two pumps, diesel consists of two pumps, and pertamax consists of one pump. Preliminary data have been made regarding the arrival rate of vehicles in each pump, which is a two-wheeled premium filling pump of 195 vehicles, four or more 166 wheels or four wheels filling pumps, four or more diesel fuel pumps of 156 and a feeding pump of 138 vehicles. High vehicle arrival rate resulted in queue. To calculate the level of service has never been done so it is not known the maximum time for service on each pump. The research method used is queuing model related to arrival rate and service level, with result of research which obtained is vehicle arrival rate at each pump that is 2 wheel of premium gasoline pump is 2.59 minutes. The premium 4 wheels charging pump is 6.98. The 4 wheelers diesel fuel pump is 5.97 minutes and the first charging pump is 6.65 minutes with the facility number 1. Vehicle service rates of premium 2 and 4 wheelers are 15.52 minutes and 14.11 minutes, 4 wheel diesel fuel pump is 14.21 minutes and the first feed pump is 13.55 minutes with scenario design on each pump is Scenario 1 with 2 pumps, Probability of medium system empty 0.87500, Number of subscribers in the system and number of customers waiting in the queue of each 1 customer, the average customer time in the system 0.06696 minutes and waiting time as long as the customer in the queue 0.00030 minutes.Keywords: Queue, facility, arrival rate, service rate.

scholarly journals A Study of Service in Restaurant by Using Queuing Model

2013 ◽  
Vol 5 ◽  
pp. 14-18
Author(s):  
G.D. Mishra ◽  
Vijiya Singh Chauhan ◽  
Nikita Chandra
Keyword(s):  
Numerical Model ◽  
Waiting Time ◽  
Queuing Theory ◽  
Arrival Rate ◽  
Utilization Rate ◽  
Service Rate ◽  
Case Scenario ◽  
Queuing Model ◽  
Restaurant Management ◽  
Potential Customers

The restaurants want to avoid losing their customers due to a long wait on the line. This shows a need of a numerical model for the restaurant management to understand the situation better. This paper aims to show that queuing theory satisfies the model when tested with a real-case scenario. We obtained the data from a restaurant. We then derive the arrival rate, service rate, utilization rate, waiting time in queue and the probability of potential customers to balk based on the data using Little’s Theorem and M/M/1 queuing model. We conclude the paper by discussing the benefits of performing queuing analysis to a busy restaurant.

Service Rate Optimization of Manufacturing Cell Based on Cost Models

2011 ◽  
Vol 314-316 ◽  
pp. 2055-2059
Author(s):  
Yan Yan Zhang ◽  
Cheng Su ◽  
Yong Shang ◽  
Zhong Xue Li
Keyword(s):  
Queuing Theory ◽  
Design Method ◽  
Cost Model ◽  
Service Rate ◽  
Cost Models ◽  
Expected Cost ◽  
Manufacturing Cell ◽  
Service Rates ◽  
Traditional Manufacturing ◽  
Rate Optimization

Since most traditional manufacturing cell design methods and some involved algorithms developed in the past few years always investigate the selection and arrangement of equipment during the design process, this paper describes a new methodology focusing on optimizing the service rates of the manufacturing cell under developing. At first, the expected cost model based on queuing theory of each process in a manufacturing cell is developed and then the optimal service rates of the equipment that make the cost the least could be obtained. Next, the designer can choose the facilities according to these parameters to configure a new manufacturing cell whose total expected cost is optimal. Finally, a numerical example is used to illustrate the advantage and validity of the new design method.

Enhanced active VM load balancing algorithm using fuzzy logic and K-means clustering

2021 ◽  
Vol 17 (1) ◽  
pp. 59-82
Author(s):  
Mostefa Hamdani ◽  
Youcef Aklouf
Keyword(s):  
Cloud Computing ◽  
Fuzzy Logic ◽  
Load Balancing ◽  
Response Time ◽  
Data Center ◽  
Service Rate ◽  
Dynamic Allocation ◽  
Use Of Resources ◽  
Cloud Computing System ◽  
Load Balancing Algorithm

With the rapid development of data and IT technology, cloud computing is gaining more and more attention, and many users are attracted to this paradigm because of the reduction in cost and the dynamic allocation of resources. Load balancing is one of the main challenges in cloud computing system. It redistributes workloads across computing nodes within cloud to minimize computation time, and to improve the use of resources. This paper proposes an enhanced ‘Active VM load balancing algorithm’ based on fuzzy logic and k-means clustering to reduce the data center transfer cost, the total virtual machine cost, the data center processing time and the response time. The proposed method is realized using Java and CloudAnalyst Simulator. Besides, we have compared the proposed algorithm with other task scheduling approaches such as Round Robin algorithm, Throttled algorithm, Equally Spread Current Execution Load algorithm, Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO). As a result, the proposed algorithm performs better in terms of service rate and response time.

scholarly journals Analysis of Fuzzy Non-preemptive Priority Queuing Model with Unequal Service Rate

2021 ◽  
Vol 12 (5) ◽  
pp. 1457-1460
Author(s):  
K. Selvakumari, Et. al.
Keyword(s):  
Performance Measures ◽  
Fuzzy Number ◽  
Fuzzy Numbers ◽  
Arrival Rate ◽  
Triangular Fuzzy Number ◽  
Priority Queues ◽  
Service Rate ◽  
Preemptive Priority ◽  
Queuing Model ◽  
Service Rates

This article provides an effective method to analyze the performance measures of non-preemptive fuzzy priority queues with unequal service rates. Here the arrival rate and the service rate are in fuzzy numbers. Using a new ranking method, the fuzzy values are reduced to the crisp values. For that cause, both the Triangular Fuzzy Number (TFN) and Trapezoidal Fuzzy Number (TpFN) are chosen to establish the proposal's effectiveness. An illustration is given to find the efficiency of the performance measures of the fuzzy queuing model.

scholarly journals Effective Servicing of a Busy Base Station using Queuing Models in Cognitive Radio Networks

2019 ◽  
Vol 8 (4) ◽  
pp. 11351-11356
Keyword(s):  
Cognitive Radio ◽  
Queuing Theory ◽  
Service Providers ◽  
Radio Networks ◽  
Base Station ◽  
Service Rate ◽  
Effective Utilization ◽  
Queuing Models ◽  
Number Of Customers ◽  
System Average

This paper aims the effective utilization of spectrum using queuing models in cognitive radio. The data from various service providers are obtained and considered for our analysis. Analytical mathematical models based on queuing theory are developed for effectively servicing the arrival calls and improving the service rate. Based on the following parameters, we design a model to service the calls effectively: Average number of customers in the system, Average number of customers in the queue, Average wait in the system and Average wait in queue.

Sign in / Sign up

Export Citation Format

Share Document