Results 1  10
of
10
Data Intensive Grid Scheduling: Multiple Sources with Capacity Constraints
 IN PROC. OF THE INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED COMPUTING SYSTEMS, (PDCS
, 2003
"... In this paper, we apply divisible load theory to model the Grid scheduling problem involving multiple sources to multiple sinks, and present an optimized scheduling technique for this scenario. This scheduling technique can be easily extended to schedule resources with buffer space constraints. We p ..."
Abstract

Cited by 22 (9 self)
 Add to MetaCart
In this paper, we apply divisible load theory to model the Grid scheduling problem involving multiple sources to multiple sinks, and present an optimized scheduling technique for this scenario. This scheduling technique can be easily extended to schedule resources with buffer space constraints. We provide a stepwise scheduling algorithm for these constraints. Two example calculations will show the practical utility and efficiency of DLT.
Wireless sensor networks: scheduling for measurement and data reporting
 IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS
, 2006
"... ..."
(Show Context)
Grid Scheduling Divisible Loads From Multiple Sources Via Linear Programming
 IASTED INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED COMPUTING AND SYSTEMS (PDCS 2004
, 2004
"... To date solutions for optimal finish time and job allocation in divisible load theory are largely obtained only for network topologies with a single load originating (root) processor. However in largescale data intensive problems with geographically distributed resources, load is generated from mul ..."
Abstract

Cited by 8 (3 self)
 Add to MetaCart
To date solutions for optimal finish time and job allocation in divisible load theory are largely obtained only for network topologies with a single load originating (root) processor. However in largescale data intensive problems with geographically distributed resources, load is generated from multiple sources. This paper introduces a new divisible load scheduling strategy for tree networks with two load originating processors. Solutions for an optimal allocation of fraction of loads to nodes in single level tree networks are obtained via linear programming. Performance evaluation of a two source homogeneous single level tree network with concurrent communication strategy is presented.
Divisible load scheduling with multiple sources: Closed form solutions
 Conference on Infomation Sciences and Systems
, 2005
"... Closed form solutions for optimal finish time and job allocation are largely obtained only for network topologies with a single load originating (root) processor. However, it often happens that load can be generated from multiple sources as in largescale data intensive problems with geographically ..."
Abstract

Cited by 6 (0 self)
 Add to MetaCart
(Show Context)
Closed form solutions for optimal finish time and job allocation are largely obtained only for network topologies with a single load originating (root) processor. However, it often happens that load can be generated from multiple sources as in largescale data intensive problems with geographically distributed resources. This paper introduces load scheduling strategy for tree networks with two load originating processors. A unique scheduling strategy that allows one to obtain closed form solutions for the optimal finish time and load allocation for each processor in the network is proposed.
Grid Scheduling Divisible Loads from Two Sources
"... To date closed form solutions for optimal finish time and job allocation are largely obtained only for network topologies with a single load originating (root) processor. However in largescale data intensive problems with geographically distributed resources, load is generated from multiple sources ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
(Show Context)
To date closed form solutions for optimal finish time and job allocation are largely obtained only for network topologies with a single load originating (root) processor. However in largescale data intensive problems with geographically distributed resources, load is generated from multiple sources. This paper introduces a new divisible load scheduling strategy for single level tree networks with two load originating processors. Solutions for an optimal allocation of fractions of load to nodes in single level tree networks are obtained via linear programming. A unique scheduling strategy that allows one to obtain closed form solutions for the optimal finish time and load allocation for each processor in the network is also presented. The Preprint submitted to Elsevier Science 30 June 2009tradeoff between linear programming and closed form solutions in terms of underlying assumptions is examined. Finally, a performance evaluation of a two source homogeneous single level tree network with concurrent communication strategy is presented.
A product form solution tree networks with divisible loads. Parallel Processing Letters, June 2011
 In Proceedings of the 2002 Conference on Information Sciences and Systems
, 2002
"... A product form solution for the optimal fractions of divisible load to distribute to processors in a multilevel tree network is described. Here optimality involves parallel processing the load in a minimal amount of time. This tractable solution is similar to the product form solution for equilibri ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
(Show Context)
A product form solution for the optimal fractions of divisible load to distribute to processors in a multilevel tree network is described. Here optimality involves parallel processing the load in a minimal amount of time. This tractable solution is similar to the product form solution for equilibrium state probabilities arising in Markovian queueing networks. The existence of this product form solution answers a long standing open question for divisible load scheduling.
Simple Performance Bounds for Multicore and Parallel Channel Systems
"... Abstract—A simple modification of existing divisible load scheduling algorithms, boosting link speed by M for M parallel channels per link, allows time optimal load scheduling and performance prediction for parallel channel systems. The situation for multicore models is more complex but can be handl ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract—A simple modification of existing divisible load scheduling algorithms, boosting link speed by M for M parallel channels per link, allows time optimal load scheduling and performance prediction for parallel channel systems. The situation for multicore models is more complex but can be handled by a substitution involving equivalent processor speed. These modifications yield upper bounds on such parallel systems’ performance. This concept is illustrated for ideal single level (star) tree networks under a variety of scheduling policies. Less than ideal parallelism can also be modeled though mechanisms of inefficiency require further research. I.
1Scheduling Divisible Workloads from Multiple Sources in Linear Daisy Chain Networks
"... Abstract—This paper considers scheduling divisible workloads from multiple sources in linear networks of processors. We propose a two phase scheduling strategy to minimize the overall processing time of these workloads by taking advantage of the processor equivalence technique. A case study with two ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract—This paper considers scheduling divisible workloads from multiple sources in linear networks of processors. We propose a two phase scheduling strategy to minimize the overall processing time of these workloads by taking advantage of the processor equivalence technique. A case study with two sources of workloads is presented to illustrate the general approach for multiple sources of workloads. At the first phase, following the equivalent processor model to represent the processors inbetween two load sources, we derive recursive equations to obtain nearoptimal workload distribution for all processors and the minimum processing time of the overall workloads. At the second phase, we propose an efficient algorithm to obtain nearoptimal load distribution for all processors represented by the equivalent processor. The simulation results and analysis for various scenarios are presented to show the behavior and efficiency of the proposed method.
Scheduling Divisible Workloads from Multiple Sources in Linear Daisy Chain Networks
"... Abstract — This paper considers scheduling divisible workloads from multiple sources in linear networks of processors. We propose a two phase scheduling strategy (TPSS) to minimize the overall processing time of these workloads by taking advantage of the processor equivalence technique. A case study ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract — This paper considers scheduling divisible workloads from multiple sources in linear networks of processors. We propose a two phase scheduling strategy (TPSS) to minimize the overall processing time of these workloads by taking advantage of the processor equivalence technique. A case study with two sources of workloads is presented to illustrate the general approach for multiple sources of workloads. In the first phase, using processor equivalence, we derive recursive equations to obtain nearoptimal workload distribution for all processors and the minimum processing time of the overall workloads. In the second phase, we propose an efficient algorithm to obtain nearoptimal load distribution among processors represented by the equivalent processor. Experimental evaluation through simulations demonstrate performance improvement using our schemes compared to the equal partition scheme.
Modeling for Integration of Divisible Load Theory and Markov Chains
"... In this paper the equivalence between various divisible loadscheduling policies and continuous time Markov chains is demonstrated. The problem is to show optimal divisible load schedules for various network topologies have Markov chain analogs. This paper is a continuation of our initial short pape ..."
Abstract
 Add to MetaCart
(Show Context)
In this paper the equivalence between various divisible loadscheduling policies and continuous time Markov chains is demonstrated. The problem is to show optimal divisible load schedules for various network topologies have Markov chain analogs. This paper is a continuation of our initial short paper [1] that introduced this unification between divisible load theory and Markov chain models for the first time. A detailed analytical analysis of linear daisy chains and single and two level tree networks is presented in this paper. While most of the Markov chains are one dimensional in topology, the labeling of transitions is di#erent from the usual practice in queueing theory.