Rama Sundari MV - Academia.edu (original) (raw)

Papers by Rama Sundari MV

International journal of computer applications, Jul 18, 2014

Queuing models play a dominant role in many communication systems for optimum utilization of the ... more Queuing models play a dominant role in many communication systems for optimum utilization of the resources. In this paper, we develop and analyze a two node tandem communication network model with feedback for the first node, with an assumption that the arrivals follow homogeneous Poisson process. In this model, the service rates of each transmitter depends on the number of services in the buffer connected it. The model is analyzed using the difference-differential equations and a probability generating function of the number of packets in the buffer. Expressions are derived for performance measures including average number of packets in each buffer, the probability of emptiness of the network, the mean delay in the buffer and in the network, the throughput of the transmitters, and the variance of the number of packets in the buffer.

Page 1. International Journal of Computer Applications (0975 8887) Volume 31 No.1, October 201... more Page 1. International Journal of Computer Applications (0975 8887) Volume 31 No.1, October 2011 19 Three Node Tandem Communication Network Model with Dynamic Bandwidth Allocation and Non Homogeneous Poisson Arrivals ...

Indian journal of science and technology, Jan 8, 2016

Background/Objectives: Cloud computing is a large-scale distributed computing paradigm in which a... more Background/Objectives: Cloud computing is a large-scale distributed computing paradigm in which a pool of abstracted, virtualized, dynamically-scalable resources such as computing power, storage, platforms and services are delivered on demand to external customers over the Internet. In cloud computing scheduling is the process of deciding how to allocate resources in the form of virtual machines for the requested jobs. Methods: The proposed Deadline Aware Two Stage Scheduling in cloud computing is to schedule Virtual Machines (VM) for the requested jobs received from customers. In this model each job requires two types of VM's in a sequence to complete its task. This model allocates VM's as resource to the requested jobs based on processing time and scheduling the jobs by considering deadlines with respect to response time and waiting time. Findings and Improvements: A simulation environment was developed and analyzed to evaluate this model by considering the evaluation metrics of average turnaround time, average waiting time and violation in deadlines when compared with First Come First Serve (FCFS) and Shortest Job First (SJF) scheduling strategies. This model reduces the evaluation metrics by constant factor when compared with other scheduling approaches.

Journal of emerging technologies and innovative research, 2018

In order to eliminate redundancy of massive datasets, we developed parallel large-scale technique... more In order to eliminate redundancy of massive datasets, we developed parallel large-scale technique for knowledge reduction using rough set and MapReduce methods on patient massive datasets. Our technique will reduce the utilization of memory and processing time. The superfluous data is removed without significant accuracy loss using type of disease. In this paper we presented theoretical and experimental approach for knowledge reduction from large patient datasets using significance of attributes by organizing the data in discernibility and indiscernibility matrices. The experimental results demonstrate that the proposed parallel knowledge reduction method can efficiently process massive datasets on Hadoop platform, with highly speed up the grouping process and largely reduce the storage requirements. In all the experiments the introduced method based on significance of attributes is compared with the method based on positive region or information entropy. The comparison clearly show...

International Journal of Recent Technology and Engineering (IJRTE), 2021

The objective of comparing various dimensionality techniques is to reduce feature sets in order t... more The objective of comparing various dimensionality techniques is to reduce feature sets in order to group attributes effectively with less computational processing time and utilization of memory. The various reduction algorithms can decrease the dimensionality of dataset consisting of a huge number of interrelated variables, while retaining the dissimilarity present in the dataset as much as possible. In this paper we use, Standard Deviation, Variance, Principal Component Analysis, Linear Discriminant Analysis, Factor Analysis, Positive Region, Information Entropy and Independent Component Analysis reduction algorithms using Hadoop Distributed File System for massive patient datasets to achieve lossless data reduction and to acquire required knowledge. The experimental results demonstrate that the ICA technique can efficiently operate on massive datasets eliminates irrelevant data without loss of accuracy, reduces storage space for the data and also the computation time compared to o...

International Journal of Computer Applications, 2014

Tandem Queues are widely used in mathematical modeling of random processes describing the operati... more Tandem Queues are widely used in mathematical modeling of random processes describing the operation of Manufacturing systems , supply chains, Computer and telecommunication networks. In many of the communication systems the arrivals are time dependent and can be characterized by a non homogeneous Poisson process. In this paper we developed and analyzed three nodes connected in tandem Queue with feedback for the first and second nodes assuming that arrivals follow non homogeneous Poisson process. Using the difference-differential equations and a probability generating function of the number of packets in the buffer connected to the transmitter the System is analyzed. The System performance is analysed by deriving expressions for the performance measures of the network like mean content of the buffers, mean delays through put, transmitter utilization with mathematical illustrations. The sensitivity analysis of the model reveals that the non homogeneous Poisson arrivals and dynamic bandwidth allocation strategy can reduce burstness in buffer and improve quality of service.

International Journal of Computer and Electrical Engineering, 2014

The Communication Network model studied in this paper consists of two nodes connected in tandem w... more The Communication Network model studied in this paper consists of two nodes connected in tandem with feedback for both the nodes. Each node has buffer and a transmitter for holding packets and for transmitting packets respectively. The packets after transmitted by the nodes may move to the next node or returned back to the same node for retransmission in feedback. It is considered that the arrival of packets at the nodes follows Non Homogeneous Poisson (NHP) process and transmission is characterized by Poisson process. Transmission rate of both nodes are adjusted before transmission by using Dynamic Bandwidth Allocation (DBA) policy. The model is evaluated using the difference-differential equations and a probability generating function of the number of packets in the buffer connected to the transmitter. Through mathematical modeling, performance measures including average number of packets in each buffer, the probability of emptiness of the network, the average waiting time in the buffer and in the network, throughput of the transmitters, utilization and the variance of the number of packets in the buffer are derived under transient conditions.

Communication network models are important for design, development and monitoring the communicati... more Communication network models are important for design, development and monitoring the communication systems. Recently much emphasis is given for communication network with time dependent arrivals. In many practical situations the output of one transmitter is an input to other. In this transmission, in some system the packet after getting transmission first node may or may not get into second buffer. This type of transmission is called phase type transmission. In this paper, we develop and analyse a three node communication network model with assumption that the arrivals to each buffer are time dependent and follows a non homogeneous poisson process. The transmission at every node is dependent on content of buffer and its rate changes dynamically using difference differential equation. The joint probability generating function is derived. The system performance measures are enhanced. The sensitivity analysis of model reveals that the time dependent and DBA has significant influence o...

Normalization is a process of organizing relations (tables) and attributes (columns) of a relatio... more Normalization is a process of organizing relations (tables) and attributes (columns) of a relational database to reduce data redundancy and improves the data integrity. This is also known as Database Normalization. Normalization is a systematic approach to eliminate data redundancy by decomposing tables and also undesirable anomalies like insertion, deletion and update. Normalization can also remove data dependency i.e. data will be stored logically. In this paper reviews (a) theoretical and experimental approach for retrieving the required data from large patient datasets in computational complexity with respect to Comparison of CPU time taken for data retrieving from the dataset before and after using normal forms (b) Eliminating the redundant data while less amount of data is stored in Main Memory and (c) computation for generating the required dataset by joining normalized datasets.

INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY, 2014

In this paper, we develop a two node tandem communication network model with dynamic bandwidth al... more In this paper, we develop a two node tandem communication network model with dynamic bandwidth allocation and feedback for the first node. In most of the communication systems, the arrivals of packets follow Non-Homogeneous and arrival rate is time dependent. In this model, the transmission rate of each transmitter depends on the number of packets in the buffer connected it. The transmission rates at each transmitter are adjusted depending upon the content of the buffer connected to it. The packets transmitted through the first transmitter may be forwarded to the buffer connected to the second transmitter or returned back to the first buffer with certain probabilities. Using the difference-differential equations the performance measures including average number of packets in each buffer, the probability of emptiness of the network, the average waiting time in the buffer and in the network, the throughput of the transmitters, and the variance of the number of packets in the buffer ar...

International Journal of Computer Applications, 2011

Communication networks create lot of interest due to their ready applicability in performance eva... more Communication networks create lot of interest due to their ready applicability in performance evaluation of several communication systems. In communication systems it is customary to consider that the arrivals are characterized by Poisson process. This assumption holds good if the arrivals are homogeneous and independent of time. But in many tele and satellite communication systems the arrivals are non homogeneous and the arrival rate is time dependent. Hence, in this paper we develop and analyze a three node communication network model with the assumption that the arrivals are characterized by non homogeneous Poisson process. It is further assumed that transmission time required by each packet at each node is dependent on the content of the buffer connected to it. The transient behavior of the network model is analyzed by deriving the system performance measures like mean number of packets in each buffer, mean delay in transmission, the throughput of the nodes, utilization of transmitters, etc,. The sensitivity analysis of the model reveals that the non homogeneous Poisson arrivals and dynamic bandwidth allocation strategy can reduce burstness in buffer and improve quality of service. A comparative study of communication network with non homogeneous Poisson arrivals and Poisson arrivals is also given.

2016 IEEE 6th International Conference on Advanced Computing (IACC), 2016

Cloud Computing provides the computing environment where different resources, infrastructures, de... more Cloud Computing provides the computing environment where different resources, infrastructures, development platforms and software are delivered as a service to customers virtually on pay-as-use basis. In cloud computing a job request may requires m number of resources types to complete its tasks. Scheduling of cloud resources for end users is an important task in cloud computing. In this paper we have proposed Multi Stage scheduling in cloud computing to schedule Virtual Machines (VM) for the requested jobs received from customers. We considered the model that a job requires 'm' different types of VM's in a sequence to complete its task. This model also extended for deadline aware Multi Stage scheduling with respect to response time and waiting time. We developed and analyzed a model for evaluation of average turnaround time, average waiting time and violation in deadlines when compared with First Come First Serve (FCFS), Shortest Job First (SJF) and Multi Stage Scheduling strategies.

International Journal of Applied Mathematics and Computer Science

Modeling and performance prediction are becoming increasingly important issues in the design and ... more Modeling and performance prediction are becoming increasingly important issues in the design and operation of computer communications systems. In this paper a review is carried out on how Tandem queuing models with Dynamic Bandwidth Allocation have been applied so far into the performance evaluation of Communication Networks. Queuing network models with finite/infinite capacity buffers and blocking have been applied as more realistic models of systems with finite capacity resources. First we review basic properties of exponential queuing systems, and then give an overview of recent progress made in the areas of dynamic bandwidth allocation for tandem queuing network models and performance measures.

2012 International Conference on Cloud Computing Technologies, Applications and Management (ICCCTAM), 2012

In this paper we have proposed a priority based Erlang service distribution with k-phases for clo... more In this paper we have proposed a priority based Erlang service distribution with k-phases for cloud computing architecture. The multiple users from the public cloud entering into two serially connected M/M/s and M/E k /1 (Erlang service queue) queues are served based on the non-pre-emptive priority discipline. We have assumed each user of different priority class i, (i ≥ 2) desired to wait until the current user is being served if priority of the service is similar, as per FCFS policy. If the servers are free, users can enter into the M/M/s queue, then enter into the M/E k /1 queue with probability φ and leave the system after service completion or leave the system with probability (1φ) without entering into the ESQ. We have obtained waiting time for both the queues in the cloud system and shown numerically the total waiting time is lower than the existing system.

British Journal of Mathematics & Computer Science, 2015

Cloud computing is an evolutionary approach that completely changes how computing services are pr... more Cloud computing is an evolutionary approach that completely changes how computing services are produced, priced and delivered. Cloud computing allows to access services that reside in a distant datacenter, other than local computers. Resource provisioning is the key process in cloud computing. The Virtual Machine (VM) is a software implementation of a machine that executes programs like a physical machine. Two stage scheduling is a novel approach in cloud computing. In this case a job may request two virtual machines in sequence to complete their needs. This paper presents a novel two stage scheduling algorithm to schedule the given job requests in cloud environment by extending Johnson’s Scheduling algorithm. Simulation results show that this algorithm reduces average waiting time and total elapsed time when compared to other scheduling algorithms.