Multi-criteria Scheduling on Clouds Yacine KESSACI
|
|
- Roy Gallagher
- 6 years ago
- Views:
Transcription
1 Multi-criteria Scheduling on Clouds Yacine KESSACI Dolphin Project Team, Université Lille 1, LIFL-CNRS, Inria Lille-Nord Europe 1
2 About me Sessional lecturer and junior researcher at CNRS/LIFL/Inria Lille Nord Europe and Polytech lille (Université Lille1) - Attaché temporaire d enseignement et de recherche (ATER) Ph.D. student at Dolphin (LIFL/CNRS/Inria Lille Nord Europe) (Supervisors Nouredine Melab and El-Ghazali Talbi), defended on November 28 th 2013 (Highest Honors). Topic: Multi-criteria Scheduling on Clouds Master s degree in computer science at Université Lille 1 (France) Specialty : complex system and algorithmic - (Rank 2 nd ) Internship with Dolphin (LIFL/CNRS/INRIA Lille-Nord Europe) Topic : Multi-criteria Energy-aware Scheduling of Parallel Tasks with Precedence Constraints Yacine KESSACI Multi-criteria Scheduling on Clouds 2
3 I. Scientific context Outline II. III. Contributions 1. Service-level scheduling 2. Task-level scheduling 3. VM-level scheduling Conclusion and Future Works Yacine KESSACI Multi-criteria Scheduling on Clouds 3
4 What is a Cloud? Cloud computing is A type of parallel and distributed system consisting of a collection of interconnected and virtualized computers that are dynamically provisioned and presented as one or more unified computing resources based on service-level agreements. [Buyya et al, 2008] offering services services = infrastructures (IAAS) Cloud Source: Google Yacine KESSACI Multi-criteria Scheduling on Clouds 4
5 Cloud context: IAAS in (Multi-) Cloud Multi-cloud Meta-view Cloud Broker Cloud Broker Cloud Broker Broker-view Cloud 1 Cloud 2 Cloud n Cloud Manager-view Yacine KESSACI Multi-criteria Scheduling on Clouds 5
6 Scheduling Scheduling in IAAS (Multi-) Cloud Multi-cloud Meta-view Cloud Broker Cloud Broker Cloud Broker Broker-view Cloud 1 Cloud 2 Cloud n Cloud Manager-view Yacine KESSACI Multi-criteria Scheduling on Clouds 6
7 Scheduling vs Cloud Type (Cont. ) Service requests VM templates Applications (Tasks) Scheduling according to cloud type Public cloud (VM instances) Multi-cloud (data centers) Private cloud (hosts) Set of requests Bijective Set of IAAS clouds Yacine KESSACI Multi-criteria Scheduling on Clouds 7
8 Scheduling Problem Formulation Objective1 ( Objective2... Constraint2... ( Constraint1 (( N J i j N J i j (( N J i j N J i j Metric1 ij Metric 2 ij Metric 3 Metric 4 x x ij ij ij ij x x ) Time ) Time ij ) Time) Constraint ij ) Time) Constraint Cloud Conflicting Objectives value1 value2 J j x ij 1 for each i,1 i N Yacine KESSACI Multi-criteria Scheduling on Clouds 8
9 Optimization Problem Formulation Multi-Objective Energy CO 2 Profit Quality of Service Performance Resolution approaches Lexicographic Aggregation Pareto Min f( x) Const. ( f ( x), f ( x),..., f ( x)) Real time scheduling may be time intensive (NP-hard) 1 x S f 2 2 n Dominated solution Pareto solution f 1 n 2 Yacine KESSACI Multi-criteria Scheduling on Clouds 9
10 Metaheuristics Exact methods Optimal solutions Exponential complexity Heuristic methods High quality solutions Reasonable time Metaheuristics = Generic heuristics Yacine KESSACI Multi-criteria Scheduling on Clouds 10
11 Challenging Issues and Objectives State of the art: Critical analysis Basic schedulers based on simple heuristics Almost no Pareto-based multi-objective solving algorithms Very few realistic experiments (Simulation-oriented experiments) Rarely considering all the cloud stack levels Contributions Revisiting scheduling for clouds from different points of view: Modeling: multi-objective modeling, improvement of some metrics Design: Pareto-based multi-objective metaheuristics Implementation: Cloud manager embedded implementation and validation through realistic experiments Considering different levels of the cloud stack Yacine KESSACI Multi-criteria Scheduling on Clouds 11
12 I. Scientific context Outline II. Contributions 1. Service-level scheduling Energy-aware 2. Task-level scheduling III. 3. VM-level scheduling Conclusion and Future Works Yacine KESSACI Multi-criteria Scheduling on Clouds 12
13 Motivations Electricity doubled over the period 2005 to 2010 in worldwide. 2% of CO2 emissions. Source: Koomey 2007 Energy: 42% of the total data center budget. A multi-objective modeling is required! Source: Hamilton 2009 Yacine KESSACI Multi-criteria Scheduling on Clouds 13
14 Cloud Model: Cloud Federation / Multi-Cloud Cloud 2 Geographically distributed IAAS Cloud Cloud n Cloud 3 Cloud 1 Yacine KESSACI Multi-criteria Scheduling on Clouds 14
15 Multi-Cloud Characteristics Geographically distributed cloud, single provider 3 continents (America, Europe et Oceania) CO2 rate Department Of Energy (DOE) Electricity price Energy Information Administration (EIA) Other parameters Statistics on other works [Wang et al, 2008] or synthetic data generation Co2 Rate Electricity price Max Frequency Location COP Rate Nb processor ( kg/kw h) ($/kw h) (Ghz) New York, USA Pennsylvania, USA California, USA Ohio, USA North Carolina, USA Texas, USA France Australia Yacine KESSACI Multi-criteria Scheduling on Clouds 15
16 Service Model Flow of services (HPC) over meta-scheduler. Service j as a triplet: HPC Services (e j, n j, d j ) Cloud (IAAS) Service requests e j execution time of the service (booking) n j number of reserved processors d j deadline of the service Multi-cloud (data centers) Yacine KESSACI Multi-criteria Scheduling on Clouds 16
17 Service-level Scheduling (Meta scheduler) Solution Optimal service assignment based on metrics and with constraints satisfaction Scheduling approach Multi-objective genetic algorithm meta-scheduler (MSCF) Cloud 2 Geographically distributed IAAS Cloud Cloud n Clients Cloud 1 Service (e.g. HPC) assignment Service (e.g. HPC) application Meta-scheduler (MSCF) Yacine KESSACI Multi-criteria Scheduling on Clouds 17
18 Problem Modeling Solution encoding Scheduling J services on N clouds (NP hard) considering the constraints Deadline (strong constraint): no delays Atomic services Objectives Service (HPC application) Satisfying maximum client s requests Cloud to which the service (HPC application) is assigned by optimizing simultaneously (energy consumption, CO 2 footprint, profit) Yacine KESSACI Multi-criteria Scheduling on Clouds 18
19 Model: Metrics for Objectives Energy Minimizing the energy consumption Computation energy (E c ) Cloud cooling energy (E h ) E c ij ( f ) n i i 3 ij j e ji (CMOS architecture) Source: Google E h c E COP E total E c E h CO2 Minimizing the amount of CO 2 emission CO2 Etotal CO2Rate Source: Google Yacine KESSACI Multi-criteria Scheduling on Clouds 19
20 Model: Metrics for Objectives (Cont. ) Profit Optimizing the profit = maximizing the provider s earnings at each meta-scheduling phase Price charged to the client Electrical energy price Profit ij n j e ij p c ( p e i E ij ) n j number of processors e ij execution time of the service p c client s price per hour p ie electricity price E ij consumed energy Source: Google Yacine KESSACI Multi-criteria Scheduling on Clouds 20
21 Algorithm: MSCF Meta-Scheduler Flow of HPC services Init population MO-GA Each scheduling cycle External Pareto archive Selection of a solution according to user s parameters (Meta-selection) Vector Clouds state saving Y. Kessaci, N. Melab, E-G. Talbi. A Pareto-based GA for Scheduling HPC Applications on Distributed Cloud Infrastructures. International Conference on High Performance Computing and Simulation (HPCS), Istanbul, Turkey, Yacine KESSACI Multi-criteria Scheduling on Clouds 21
22 Pareto set f 1 f f f v f f v f f v Vector v 3 favors objective f 2 Vector v 1 favors objective f 1 v 2 v 3 v 1 Algorithm: Meta-Selection Mechanism Yacine KESSACI Multi-criteria Scheduling on Clouds 22 Y. Kessaci, N. Melab and E-G. Talbi, A Pareto-based Metaheuristic for Scheduling HPC Applications on a Geographically Distributed cloud Federation, Cluster Computing Journal 16(3): , 2012.
23 Experimentation MSCF parameters MO-GA parameters Comparison to other approaches Problem not treated in the literature with a multi-objective Pareto approach Compared with heuristic that maximizes the number of scheduled services (consolidation) Yacine KESSACI Multi-criteria Scheduling on Clouds 23
24 Results Instance LLNL Instance RICC Specific selection (vector orientation) Increase in the efficiency (normal arrival rates) Decrease in the efficiency (high arrival rates) Using neutral selection (Average) delays the problem Solution: Adapt the selection policies to improve solutions Yacine KESSACI Multi-criteria Scheduling on Clouds 24
25 Results (Cont. ) Criteria Energy consumption Green house gas emissions Provider s profit Number of scheduled services LLNL instance 26% 25.9% 1.8% 2.2% RICC instance 29.4% 26.3% 3.6% 3% Yacine KESSACI Multi-criteria Scheduling on Clouds 25
26 I. Scientific context Outline II. Contributions 1. Service-level scheduling 2. Task-level scheduling Satisfaction-aware III. 3. VM-level scheduling Conclusion and Future Works Yacine KESSACI Multi-criteria Scheduling on Clouds 26
27 Motivations Providers have a full control over performances and prices of their services Source: AWS Mandatory choice between price and performance VM spots and high price fluctuation Source: AWS for Asia (Singapore) for a representative week Yacine KESSACI Multi-criteria Scheduling on Clouds 27
28 Cloud Brokering Characteristics Instance A Instance B Instance C Source: Yacine KESSACI Multi-criteria Scheduling on Clouds 28
29 Task model Broker receives flows of tasks Each task is a quadruplet ( size,,, ) S rate size execution time of the task Applications (Tasks) S rate minimum satisfaction rate needed by the client α advantage to the costs β advantage to performances (response time) Public cloud (VM instances) Yacine KESSACI Multi-criteria Scheduling on Clouds 29
30 Task-level Scheduling Solution Optimal assignment of the tasks over VMs instances using metrics Scheduling approach Multi-objective Genetic Algorithm for Cloud Brokering (MOGA-CB) Reserving the most interesting spots Proposal of spots (VM instances with different specifications) Clients Scheduler (MOGA-CB) IAAS Cloud Cloud broker VM n VM 2 VM 1 Tasks Task assignment First tier Second tier Third tier Yacine KESSACI Multi-criteria Scheduling on Clouds 30
31 Problem Modeling Solution encoding Assigning dynamically J tasks on N VM instances (NP hard) Task Objectives Maximizing client s satisfaction minimizing primary objectives response time of the tasks and their costs Maximizing broker s profit VM instance to which the task (index) is assigned Yacine KESSACI Multi-criteria Scheduling on Clouds 31
32 Model: Metrics for Objectives Satisfaction of the client Primary objectives: response time and costs of the tasks Minimization Total Task Cost (p) N J cost i j j rpt ij price i Minimization Total Response Time (t) N i J j currenttim e arrivaltime j rpt ij Satisfaction (p,t)= S max α x p β x t Profit of the broker ( S max Satisfacti on Srate t) profit Yacine KESSACI Multi-criteria Scheduling on Clouds 32
33 Algorithm: MOGA-CB Scheduler Flow of tasks A scheduling round Instances prices recovering Init population MOGA-CB Algorithm External Pareto archive Selection of a solution according to the client s parameters Reinjection of the unfinished tasks Tasks updating Y. Kessaci, N. Melab and E-G. Talbi, A Pareto-based Genetic Algorithm for Optimized assignment of VM Requests on a Cloud Brokering Environment, Internationnal IEEE Congress on Evolutionary Computation (CEC), June Cancun, Mexico, Yacine KESSACI Multi-criteria Scheduling on Clouds 33
34 Service price Service price Algorithm: Pareto Selection Process Satisfaction according to Same satisfaction value & 1 8 Selected solution Satisfaction for one instance 1 1 Satisfaction for another instance Classical solving 9 1 Selected solution (0,0) Response time Pareto satisfaction values 1 8 Selected solution Pareto front for one instance Pareto solving 1 Selected solution Selected solution (0,0) Response time Yacine KESSACI Multi-criteria Scheduling on Clouds 34
35 Experimentation Experiment Parameters Tasks requirements VM instances Comparison Problem not addressed in the literature with a multi-objective Pareto approach Experimental study has been conducted to analyze the behavior of our approach according to different parameters. Yacine KESSACI Multi-criteria Scheduling on Clouds 35
36 Results (Pareto analysis) Uselessness of alpha and beta parameters simplification of the model Tradeoff between cost and response time objectives according to (α/β) parameters Yacine KESSACI Multi-criteria Scheduling on Clouds 36
37 Disappointment value Results (Behavior analysis) 45 Broker s profit inversely proportional to the instance price Preserve the client s satisfaction Average Spot Cost Average Response Time Broker Profit Scheduling rounds Satisfaction Disappointment Average spot cost Average response time Scheduling rounds Satisfaction more impacted by response time than by cost More significant variation of the tasks response time: Depending on both type of instance and tasks load Yacine KESSACI Multi-criteria Scheduling on Clouds 37
38 Results (Time analysis) Time (sec) Computation Time timeper per Iteration time interval Time intervals Scheduler s time processing Time interval 30 seconds in average MOGA-CB scheduler < 30 seconds Yacine KESSACI Multi-criteria Scheduling on Clouds 38
39 I. Scientific context Outline II. Contributions 1. Service-level scheduling 2. Task-level scheduling 3. VM-level scheduling III. Performance-aware Conclusion and Future Works Yacine KESSACI Multi-criteria Scheduling on Clouds 39
40 Motivations Colossal energy consumption of physical machines Using consolidation for energy reduction purposes Increase in VM response time according to the background utilization Decrease in VM performance Due to high memory needs, high rate of CPU cache misses Source: Verma 2008 Yacine KESSACI Multi-criteria Scheduling on Clouds 40
41 VM-level Scheduling (Global view) Users OpenNebula Cloud Manager Schedulers (EMLS-ONC /EMLS-ONC-MO) IAAS Cloud Host n Host 2 Host 1 VM requests (templates) VM assignement Yacine KESSACI Multi-criteria Scheduling on Clouds 41
42 Virtual Machine Model Template files with VM information Number of CPU Memory need Disk capacity Time reservation VMs are triplets VM templates ( e j, n j, m j ) e j execution time of the VM (booking) n j number of reserved processors m j required memory Private cloud (hosts) Yacine KESSACI Multi-criteria Scheduling on Clouds 42
43 VM-level Scheduling in a Cloud Manager Scheduling approach Energy aware single-objective Multi-start Local Search for OpenNebula Cloud manager (EMLS-ONC) Multi-Objective energy and performance aware Multi-start Local Search for OpenNebula Cloud manager (EMLS-ONC-MO) Users IaaS Cloud OpenNebula Interface Cloud Manager (OpenNebula Core) KVM Xen VMware Physical Computing Resources Default Scheduler Embedding EMLS-ONC/ EMLS-ONC-MO Schedulers Yacine KESSACI Multi-criteria Scheduling on Clouds 43
44 Problem Modeling Solution encoding Assigning VM instances to physical machines VM id Host on which the VM will be assigned OpenNebula pretreatment constraints Vector of potential hosts for each VM VM s IDs not in a sequential order Y. Kessaci, N. Melab, E-G. Talbi. An Energy-aware Multi-start Local Search Heuristic for Scheduling VMs on the OpenNebula Cloud Distribution. International Conference on High Performance Computing and Simulation (HPCS), Spain, Madrid, Yacine KESSACI Multi-criteria Scheduling on Clouds 44
45 Model: Metrics for Objectives Energy Minimizing energy consumption Energy needed for the computation (E c ) Dynamical evolution based on the CPU usage parameter N J c 3 CPU _ usagei Eij ( i i fij ) n j e ji 1 n j const _ value Note : The larger the CPU usage, the more cooling energy required Performance Minimizing the response time of the VMs to maximize their performance Memory related to VM performance [Verma et al, 2008]. N i J j Response_t ime ij Memory j Memory j Mem _ usage i Source: Yacine KESSACI Multi-criteria Scheduling on Clouds 45
46 Algorithm: EMLS-ONC/EMLS-ONC-MO Each scheduling cycle Updated list of VMs Filtering out incompatible hosts Affecting compatible hosts to each VM Updated list of hosts Launching the Multi-start Launching LS 1 Launching LS 2 Launching LS n Solution of LS 1 Solution of LS 2 Solution of LS n Best scheduling or Pareto scheduling Dispatching the VMs and updating hosts states according to the selected solution n: Min number of hosts and 20 Y. Kessaci, N. Melab, E-G Talbi, A Multi-start Local Search Heuristic for an Energy Efficient VMs Assignment on top of the OpenNebula Cloud Manager, Future Generation Computer Systems Journal, Available online 6 August 2013, ISSN X, Yacine KESSACI Multi-criteria Scheduling on Clouds 46
47 Neighborhood size Algorithm: Local Search Launching the LS 1 local search Local search LS 1 iterations VM s host list The neighborhood operator is a switch between the hosts of each VM Value of the VM id Value of the cell: representing the host on which the VM will be assigned Multi-start example with 4 LS LS1 LS3 LS4 LS2 Yacine KESSACI Multi-criteria Scheduling on Clouds 47
48 Experimentation Comparison scenarios Single objective EMLS-ONC, energy-aware FFD (specific greedy heuristic) and OpenNebula scheduler Pareto EMLS-ONC-MO, energy-aware FFD, memory-aware FFD approach and OpenNebula scheduler EMLS-ONC and OpenNebula scheduler (real deployment - GRID5000 infrastructure) Compared criteria Energy consumption of the infrastructure Performance of the hosted VMs Number of hosted VMs Computation time of schedulers Yacine KESSACI Multi-criteria Scheduling on Clouds 48
49 Parameter Settings VM parameters VM templates deduced from the type of VMs proposed by Amazon EC2 Small instances (1 CPU, 1.7 GBs memory) to extra large ones (8 CPUs, 15 GBs memory) Execution time: 1 to 10 hour(s) Synthetic cloud configuration Nancy Grid5000 site configuration Synthetic experiments Real experiments Yacine KESSACI Multi-criteria Scheduling on Clouds 49
50 Results (Synthetic) Experiments over a configuration of 100VMs/ scheduling cycle and 80 hosts during 20 cycles Energy EMLS-ONC vs Energy-FFD vs OpenNebula (Single-objective) VM Response time EMLS-ONC-MO vs Memory-FFD vs OpenNebula (Multi-objective) Energy EMLS-ONC-MO vs Energy-FFD vs OpenNebula (Multi-objective) Yacine KESSACI Multi-criteria Scheduling on Clouds 50
51 Results (Realistic) Cumulative results (EMLS-ONC vs OpenNebula scheduler) for 5 VMs/cycle on 50 GRID5000 machines Cumulative results (EMLS-ONC vs OpenNebula scheduler) for 100VMs/cycle on 200 GRID5000 machines Scheduling policy (Consolidation vs EMLS-ONC) Updating frequency of the hosts parameters (>> each scheduling cycle) Yacine KESSACI Multi-criteria Scheduling on Clouds 51
52 Results (Summary) Energy Reduction on average: 26% vs OpenNebula and 25% vs FFD approaches VM Performance Increase on average: 9% vs OpenNebula and equivalent to FFD approaches Number of hosted VMs Equivalent to OpenNebula s scheduler and FFD approaches Scheduler s time processing Scheduling cycle 30 seconds EMLS-ONC/ EMLS-ONC-MO maximum scheduling time 24.3 seconds Yacine KESSACI Multi-criteria Scheduling on Clouds 52
53 I. Scientific context Outline II. Contributions 1. Service-level scheduling 2. Task-level scheduling III. 3. VM-level scheduling Conclusion and Future Works Yacine KESSACI Multi-criteria Scheduling on Clouds 53
54 Conclusion Revisited metaheuristic schedulers for each level of the cloud Service-level scheduling Exploiting the geographical dispersion Task-level scheduling Managing the price fluctuations of the VM instances VM-level scheduling Using the disparity and the differences in the features of a cloud s hosts Metaheuristic-based schedulers fitting cloud constraints Embedded in a Cloud manager Efficient results within the scheduling time slot Pareto-based multi-objective approaches Simplifying the model Pareto selection mechanism for each scheduling level Yacine KESSACI Multi-criteria Scheduling on Clouds 54
55 Perspectives Relationship between the scheduling levels Several conflicting objectives for the whole problem at the different levels More than 3 objectives give bad results Combining all the different levels of scheduling as parts of the same scheduling workflow Yacine KESSACI Multi-criteria Scheduling on Clouds 55
56 Cross Perspectives OSMOSE (Optimisation Simulation MOdeliSation Evolutionnaire) Simulation, modelisation Optimisation and evolutionnary Ex: Combinatorial for weak Schur problem (Monte-Carlo TS, tabu search) Ex: Genetic programming Revisiting Metaheuristics (Single and population based) Already to problem constraint Computation time (Delta evaluation, number of generation ) Hardware and software constraints (Solution encoding, ) Next to the problem specification Landscape Parameters Other specifications Problem similarities with scheduling Harbor area (Logistic problems) Stevedoring (Scheduling) Loading of containers (Bin packing) Interested also by: Simulation, MOdeliSation Yacine KESSACI Multi-criteria Scheduling on Clouds 56
57 Thank you for your attention Yacine KESSACI Multi-criteria Scheduling on Clouds 57
58 Publications International Journals Y. Kessaci, N. Melab & E-G. Talbi, A Multi-start Local Search Heuristic for an Energy Efficient VMs Assignment on top of the OpenNebula Cloud Manager, Future Generation Computer Systems Journal, Y. Kessaci, N. Melab & E-G. Talbi, A Pareto-based metaheuristic for scheduling HPC applications on a geographically distributed cloud federation Cluster Computing Journal, M. Mezmaz, N. Melab, Y. Kessaci, Y. Lee, E-G. Talbi, A. Zomaya & D. Tuyttens, A parallel bi-objective hybrid metaheuristic for energyaware scheduling for cloud computing systems Journal of Parallel and Distributed Computing, International Conferences with selection process and proceedings Y. Kessaci, N. Melab, E-G. Talbi. A Pareto-based Genetic Algorithm for Optimized Assignment of VM Requests on a Cloud Brokering Environment. Internationnal IEEE Congress on Evolutionary Computation (CEC), June Cancun, Mexico Y. Kessaci, N. Melab, E-G. Talbi. An Energy-aware Multi-start Local Search Heuristic for Scheduling VMs on the OpenNebula Cloud Distribution. International Conference on High Performance Computing & Simulation (HPCS), Spain, Madrid, Y. Kessaci, N. Melab, E-G. Talbi. A Pareto-based GA for Scheduling HPC Applications on Distributed Cloud Infrastructures. International Conference on High Performance Computing & Simulation (HPCS), Istanbul, Turkey, M. Mezmaz, Y. Kessaci, Y.C. Lee, N. Melab, E-G. Talbi, A. Zomaya and D. Tuyttens. A Parallel Island-based Hybrid Genetic Algorithm for Precedence-constrained Applications to Minimize Energy Consumption and Makespan. Efficient Grids, Clouds and Clusters Workshop (E2GC2), in conj. with IEEE Grid 2010 conf.,brussels, Oct Book Chapters Y. Kessaci, M. Mezmaz, N. Melab, E-G. Talbi, D. Tuyttens. "Parallel Evolutionary Algorithms for Energy Aware Scheduling". Intelligent Decision Systems in Large-Scale Distributed Environments Series: Studies in Computational Intelligence, Vol. 362 Bouvry et al. (Eds.). (Chapter4), pp Yacine KESSACI Multi-criteria Scheduling on Clouds 58
IBM ICE (Innovation Centre for Education) Welcome to: Unit 1 Overview of delivery models in Cloud Computing. Copyright IBM Corporation
Welcome to: Unit 1 Overview of delivery models in Cloud Computing 9.1 Unit Objectives After completing this unit, you should be able to: Understand cloud history and cloud computing Describe the anatomy
More informationEnterprise APM version 4.2 FAQ
Meridium Enterprise Asset Performance Management (APM) version 4.2 is the next generation APM solution that helps your company simply and easily connect disparate systems and use that data to create and
More informationDYNAMIC RESOURCE PRICING ON FEDERATED CLOUDS
DYNAMIC RESOURCE PRICING ON FEDERATED CLOUDS CCGRID 2010 The 10th IEEE/ACM Intl. Symp. on Cluster, Cloud and Grid Computing Marian Mihailescu Yong Meng Teo Department of Computer Science National University
More informationOptimization in Supply Chain Planning
Optimization in Supply Chain Planning Dr. Christopher Sürie Expert Consultant SCM Optimization Agenda Introduction Hierarchical Planning Approach and Modeling Capability Optimizer Architecture and Optimization
More informationTowards Modelling-Based Self-adaptive Resource Allocation in Multi-tiers Cloud Systems
Towards Modelling-Based Self-adaptive Resource Allocation in Multi-tiers Cloud Systems Mehdi Sliem 1(B), Nabila Salmi 1,2, and Malika Ioualalen 1 1 MOVEP Laboratory, USTHB, Algiers, Algeria {msliem,nsalmi,mioualalen}@usthb.dz
More informationIBM Tivoli Monitoring
Monitor and manage critical resources and metrics across disparate platforms from a single console IBM Tivoli Monitoring Highlights Proactively monitor critical components Help reduce total IT operational
More informationISE480 Sequencing and Scheduling
ISE480 Sequencing and Scheduling INTRODUCTION ISE480 Sequencing and Scheduling 2012 2013 Spring term What is Scheduling About? Planning (deciding what to do) and scheduling (setting an order and time for
More informationInternational Journal of Computer Trends and Technology (IJCTT) volume 10number5 Apr 2014
Survey Paper for Maximization of Profit in Cloud Computing Ms. Honeymol.O Department of Computer Science and Engineering Nehru College of Engineering and Research Centre, Pampady, Thrissur, University
More informationINTEGRATING VEHICLE ROUTING WITH CROSS DOCK IN SUPPLY CHAIN
INTEGRATING VEHICLE ROUTING WITH CROSS DOCK IN SUPPLY CHAIN Farshad Farshchi Department of Industrial Engineering, Parand Branch, Islamic Azad University, Parand, Iran Davood Jafari Department of Industrial
More informationA Dynamic Optimization Algorithm for Task Scheduling in Cloud Computing With Resource Utilization
A Dynamic Optimization Algorithm for Task Scheduling in Cloud Computing With Resource Utilization Ram Kumar Sharma,Nagesh Sharma Deptt. of CSE, NIET, Greater Noida, Gautambuddh Nagar, U.P. India Abstract
More informationEl-Ghazali Talbi (Ed.) Metaheuristics for Bi-level Optimization. ^ Springer
El-Ghazali Talbi (Ed.) Metaheuristics for Bi-level Optimization ^ Springer Contents 1 A Taxonomy of Metaheuristics for Bi-level Optimization 1 El-Ghazali Talbi 1.1 Introduction 1 1.2 Bi-level Optimization
More informationMultiobjective Optimization. Carlos A. Santos Silva
Multiobjective Optimization Carlos A. Santos Silva Motivation Usually, in optimization problems, there is more than one objective: Minimize Cost Maximize Performance The objectives are often conflicting:
More informationA TUNABLE WORKFLOW SCHEDULING ALGORITHM BASED ON PARTICLE SWARM OPTIMIZATION FOR CLOUD COMPUTING
San Jose State University SJSU ScholarWorks Master's Projects Master's Theses and Graduate Research Spring 2014 A TUNABLE WORKFLOW SCHEDULING ALGORITHM BASED ON PARTICLE SWARM OPTIMIZATION FOR CLOUD COMPUTING
More informationPricing Models and Pricing Schemes of IaaS Providers: A Comparison Study
Pricing Models and Pricing Schemes of IaaS Providers: A Comparison Study Mohan Murthy M K Sanjay H A Ashwini J P Global Services Department of. Department of Curam Software International, Information Science
More informationBUILDING A PRIVATE CLOUD
INNOVATION CORNER BUILDING A PRIVATE CLOUD How Platform Computing s Platform ISF* Can Help MARK BLACK, CLOUD ARCHITECT, PLATFORM COMPUTING JAY MUELHOEFER, VP OF CLOUD MARKETING, PLATFORM COMPUTING PARVIZ
More informationDynamic Cloud Resource Reservation via Cloud Brokerage
Dynamic Cloud Resource Reservation via Cloud Brokerage Wei Wang*, Di Niu +, Baochun Li*, Ben Liang* * Department of Electrical and Computer Engineering, University of Toronto + Department of Electrical
More informationPh.D. Defense: Resource Allocation Optimization in the Smart Grid and High-performance Computing Tim Hansen
Ph.D. Defense: Resource Allocation Optimization in the Smart Grid and High-performance Computing Tim Hansen Department of Electrical and Computer Engineering Colorado State University Fort Collins, Colorado,
More informationMEANS HAPPIER CUSTOMERS
CLOUD COMPUTING MEANS HAPPIER CUSTOMERS TABLE OF CONTENTS 1 About the cloud 3 Cloud-based applications increase customer satisfaction 6 The human touch: Technology alone is not enough 7 Summary About the
More informationCLOUD COMPUTING- A NEW EDGE TO TECHNOLOGY
CLOUD COMPUTING- A NEW EDGE TO TECHNOLOGY Prof. Pragati Goel Asso. Prof. MCA Dept., Sterling Institute of Management Studies, Nerul, Navi Mumbai. Navi Mumbai, India Email: goelpragati78@gmail.com The Cloud
More informationCMS readiness for multi-core workload scheduling
CMS readiness for multi-core workload scheduling Antonio Pérez-Calero Yzquierdo, on behalf of the CMS Collaboration, Computing and Offline, Submission Infrastructure Group CHEP 2016 San Francisco, USA
More informationOptimized Virtual Resource Deployment using CloudSim
Optimized Virtual Resource Deployment using CloudSim Anesul Mandal Software Professional, Aptsource Software Pvt. Ltd., A-5 Rishi Tech Park, New Town, Rajarhat, Kolkata, India. Kamalesh Karmakar Assistant
More information1 Copyright 2011, Oracle and/or its affiliates. All rights reserved.
1 Copyright 2011, Oracle and/or its affiliates. All rights ORACLE PRODUCT LOGO Virtualization and Cloud Deployments of Oracle E-Business Suite Ivo Dujmović, Director, Applications Development 2 Copyright
More informationD-Storm: Dynamic Resource-Efficient Scheduling of Stream Processing Applications
D-Storm: Dynamic Resource-Efficient Scheduling of Stream Processing Applications Xunyun Liu and Rajkumar Buyya Cloud Computing and Distributed Systems (CLOUDS) Laboratory School of Computing and Information
More informationThe Green Index: A Metric for Evaluating System-Wide Energy Efficiency in HPC Systems
The Green Index: A Metric for Evaluating System-Wide Energy Efficiency in HPC Systems Balaji Subramaniam and Wu-chun Feng Department of Computer Science Virginia Tech {balaji, feng}@cs.vt.edu Abstract
More informationNaviCloud Sphere. NaviCloud Pricing and Billing: By Resource Utilization, at the 95th Percentile. A Time Warner Cable Company.
NaviCloud Sphere NaviCloud Pricing and Billing: By Resource Utilization, at the 95th Percentile June 29, 2011 A Time Warner Cable Company NaviCloud Sphere Pricing, Billing: By Resource Utilization, at
More informationWorkload Engineering: Optimising WAN and DC Resources Through RL-based Workload Placement
Workload Engineering: Optimising WAN and Resources Through RL-based Workload Placement Ruoyang Xiu Google rxiu@google.com John Evans Cisco john.evans@cisco.com ABSTRACT With the rise in data centre virtualization,
More informationWorkload balancing in identical parallel machine scheduling using a mathematical programming method
International Journal of Computational Intelligence Systems, Vol. 7, Supplement 1 (2014), 58-67 Workload balancing in identical parallel machine scheduling using a mathematical programming method Yassine
More informationHP Cloud Maps for rapid provisioning of infrastructure and applications
Technical white paper HP Cloud Maps for rapid provisioning of infrastructure and applications Table of contents Executive summary 2 Introduction 2 What is an HP Cloud Map? 3 HP Cloud Map components 3 Enabling
More informationCLOUD computing and its pay-as-you-go cost structure
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, VOL. 26, NO. 5, MAY 2015 1265 Cost-Effective Resource Provisioning for MapReduce in a Cloud Balaji Palanisamy, Member, IEEE, Aameek Singh, Member,
More informationReal time disruption recovery for integrated berth allocation and crane assignment in container terminals
Real time disruption recovery for integrated berth allocation and crane assignment in container terminals Mengze Li School of Naval Architecture, Ocean & Civil Engineering Shanghai Jiao Tong University
More informationDynamic Fractional Resource Scheduling for HPC Workloads
Dynamic Fractional Resource Scheduling for HPC Workloads Mark Stillwell 1 Frédéric Vivien 2 Henri Casanova 1 1 Department of Information and Computer Sciences University of Hawai i at Mānoa 2 INRIA, France
More informationCOMBINED-OBJECTIVE OPTIMIZATION IN IDENTICAL PARALLEL MACHINE SCHEDULING PROBLEM USING PSO
COMBINED-OBJECTIVE OPTIMIZATION IN IDENTICAL PARALLEL MACHINE SCHEDULING PROBLEM USING PSO Bathrinath S. 1, Saravanasankar S. 1 and Ponnambalam SG. 2 1 Department of Mechanical Engineering, Kalasalingam
More informationModeling a Four-Layer Location-Routing Problem
Modeling a Four-Layer Location-Routing Problem Paper 018, ENG 105 Mohsen Hamidi, Kambiz Farahmand, S. Reza Sajjadi Department of Industrial and Manufacturing Engineering North Dakota State University Mohsen.Hamidi@my.ndsu.edu,
More informationMicrosoft FastTrack For Azure Service Level Description
ef Microsoft FastTrack For Azure Service Level Description 2017 Microsoft. All rights reserved. 1 Contents Microsoft FastTrack for Azure... 3 Eligible Solutions... 3 FastTrack for Azure Process Overview...
More informationConnected Geophysical Solutions Real-Time Interactive Seismic Modeling & Imaging
Connected Geophysical Solutions Real-Time Interactive Seismic Modeling & Imaging September 2011 Seismic Imaging For ninety years, any given oil company s profitability has relied largely on the low risk
More informationComparative Analysis of Scheduling Algorithms of Cloudsim in Cloud Computing
International Journal of Computer Applications (975 8887) Comparative Analysis of Scheduling Algorithms of Cloudsim in Cloud Computing Himani Department of CSE Guru Nanak Dev University, India Harmanbir
More informationD5.1 Inter-Layer Cloud Stack Adaptation Summary
D5.1 Inter-Layer Cloud Stack Adaptation Summary The ASCETiC architecture focuses on providing novel methods and tools to support software developers aiming at optimising energy efficiency resulting from
More informationSunGard: Cloud Provider Capabilities
SunGard: Cloud Provider Capabilities Production and Recovery Solutions for Mid-Sized Enterprises www.sungardas.com Agenda Our Mission Use Cases Cloud Strategy Why SunGard 2 Our Mission Enable mid-sized
More informationCS 5220: VMs, containers, and clouds. David Bindel
CS 5220: VMs, containers, and clouds David Bindel 2017-10-12 1 Cloud vs HPC Is the cloud becoming a supercomputer? What does this even mean? Cloud resources for rent Compute cycles and raw bits, or something
More informationEnergy-Efficient Scheduling of Interactive Services on Heterogeneous Multicore Processors
Energy-Efficient Scheduling of Interactive Services on Heterogeneous Multicore Processors Shaolei Ren, Yuxiong He, Sameh Elnikety University of California, Los Angeles, CA Microsoft Research, Redmond,
More informationDistributed Algorithms for Resource Allocation Problems. Mr. Samuel W. Brett Dr. Jeffrey P. Ridder Dr. David T. Signori Jr 20 June 2012
Distributed Algorithms for Resource Allocation Problems Mr. Samuel W. Brett Dr. Jeffrey P. Ridder Dr. David T. Signori Jr 20 June 2012 Outline Survey of Literature Nature of resource allocation problem
More informationIBM Cognos Business Intelligence Extreme Performance with IBM Cognos Dynamic Query
IBM Cognos Business Intelligence Extreme Performance with IBM Cognos Dynamic Query Overview With the release of IBM Cognos Business Intelligence V10.1, the IBM Cognos Platform delivered a new 64-bit, in-memory
More informationECLIPSE 2012 Performance Benchmark and Profiling. August 2012
ECLIPSE 2012 Performance Benchmark and Profiling August 2012 Note The following research was performed under the HPC Advisory Council activities Participating vendors: Intel, Dell, Mellanox Compute resource
More informationCloud Cruiser for Cisco Intelligent Automation for Cloud
Cloud Cruiser for Cisco Intelligent Automation for Cloud Cloud Financial Management 1 How Do Cloud Cruiser and Cisco Intelligent Automation Work Together? Cisco IAC provisions the service A tenant user
More informationWorld Leading Storage Cloud at ETH Zürich
Felix Sutter Dr. Tilo Steiger IT Architect, IBM Switzerland Ltd Head of Storage Services, ETH Zürich Informatikdienste World Leading Storage Cloud at ETH Zürich Agenda The challenges From IT Silos to Cloud
More informationINTERNATIONAL JOURNAL OF APPLIED ENGINEERING RESEARCH, DINDIGUL Volume 2, No 3, 2011
Minimization of Total Weighted Tardiness and Makespan for SDST Flow Shop Scheduling using Genetic Algorithm Kumar A. 1 *, Dhingra A. K. 1 1Department of Mechanical Engineering, University Institute of
More informationCisco Unified Workforce Optimization for Cisco Unified Contact Center Express 9.0
Data Sheet Cisco Unified Workforce Optimization for Cisco Unified Contact Center Express 9.0 Cisco Unified Communications Solutions unify voice, video, data, and mobile applications on fixed and mobile
More informationAutonomic Metered Pricing for a Utility Computing Service
Autonomic Metered Pricing for a Utility Computing Service Chee Shin Yeo, Srikumar Venugopal, Xingchen Chu, Rajkumar Buyya Grid Computing and Distributed Systems Laboratory, Department of Computer Science
More informationRODOD Performance Test on Exalogic and Exadata Engineered Systems
An Oracle White Paper March 2014 RODOD Performance Test on Exalogic and Exadata Engineered Systems Introduction Oracle Communications Rapid Offer Design and Order Delivery (RODOD) is an innovative, fully
More informationOptimization of the NAS Battery Control System
Optimization of the NAS Battery Control System Background PG&E has purchased a 4MW, 28MWh sodium-sulfur (NAS) battery to be installed October, 2010 in San Jose at Hitachi headquarters. The site was chosen
More informationOn the Comparison of CPLEX-Computed Job Schedules with the Self-Tuning dynp Job Scheduler
On the Comparison of CPLEX-Computed Job Schedules with the Self-Tuning dynp Job Scheduler Sven Grothklags 1 and Achim Streit 2 1 Faculty of Computer Science, Electrical Engineering and Mathematics, Institute
More informationProduct presentation. Fujitsu HPC Gateway SC 16. November Copyright 2016 FUJITSU
Product presentation Fujitsu HPC Gateway SC 16 November 2016 0 Copyright 2016 FUJITSU In Brief: HPC Gateway Highlights 1 Copyright 2016 FUJITSU Convergent Stakeholder Needs HPC GATEWAY Intelligent Application
More informationApplying Simulation Optimization to Improve the Efficiency of Organ Allocation
Applying Simulation Optimization to Improve the Efficiency of Organ Allocation Nan Kong, Patricio Rocha Department of Industrial and Management Systems Engineering University of South Florida Outline Motivation
More informationApplication Performance Management for Cloud
Application Performance Management for Cloud CMG By Priyanka Arora prarora803@gmail.com Cloud Adoption Trends 2 Spending on public cloud Infrastructure as a Service hardware and software is forecast to
More informationOracle on Google Cloud Platform: Pitfalls, Real Options & Best Practices
Oracle on Google Cloud Platform: Pitfalls, Real Options & Best Practices February 22, 2018 Copyright House of Brick Technologies, LLC This work is the intellectual property of House of Brick Technologies,
More informationSizing SAP Central Process Scheduling 8.0 by Redwood
Sizing SAP Central Process Scheduling 8.0 by Redwood Released for SAP Customers and Partners January 2012 Copyright 2012 SAP AG. All rights reserved. No part of this publication may be reproduced or transmitted
More informationBig Data in Cloud. 堵俊平 Apache Hadoop Committer Staff Engineer, VMware
Big Data in Cloud 堵俊平 Apache Hadoop Committer Staff Engineer, VMware Bio 堵俊平 (Junping Du) - Join VMware in 2008 for cloud product first - Initiate earliest effort on big data within VMware since 2010 -
More informationTowers Watson Dr Andy Lingard
Towers Watson Dr Andy Lingard Delivering high performance analytics from workstations, datacenters and clouds www.licensinglive.com #twittertag Agenda About Towers Watson Software products Industry trends
More informationBed Management Solution (BMS)
Bed Management Solution (BMS) System Performance Report October 2013 Prepared by Harris Corporation CLIN 0003AD System Performance Report Version 1.0 Creation Date Version No. Revision History Description/Comments
More informationSt Louis CMG Boris Zibitsker, PhD
ENTERPRISE PERFORMANCE ASSURANCE BASED ON BIG DATA ANALYTICS St Louis CMG Boris Zibitsker, PhD www.beznext.com bzibitsker@beznext.com Abstract Today s fast-paced businesses have to make business decisions
More informationATAM. Architecture Trade-off Analysis Method with case study. Bart Venckeleer, inno.com
ATAM Architecture Trade-off Analysis Method with case study Bart Venckeleer, inno.com SEI Software Architecture Tools and Methods Active Reviews for Intermediate Designs (ARID) Architecture-Based System
More informationScheduling and Coordination of Distributed Design Projects
Scheduling and Coordination of Distributed Design Projects F. Liu, P.B. Luh University of Connecticut, Storrs, CT 06269-2157, USA B. Moser United Technologies Research Center, E. Hartford, CT 06108, USA
More informationResearch Statement. Nilabja Roy. August 18, 2010
Research Statement Nilabja Roy August 18, 2010 1 Doctoral Dissertation Large-scale, component-based distributed systems form the backbone of many service-oriented applications, ranging from Internet portals
More informationUsine Logicielle. Position paper
Philippe Mils: Contact : Thales Resear & Technology Usine Logicielle Project Coordinator philippe.mils@thalesgroup.com Abstract Usine Logicielle Position paper Usine Logicielle is a project operated in
More informationCOMPANY PROFILE.
COMPANY PROFILE www.itgility.co.za Contact anyone of our consultants: Vision Minesh +27 (0) 83 441 0745 Andre +27 (0) 83 357 5729 Francois +27 (0) 82 579 1705 Jacques +27 (0) 83 357 5659 ITgility is an
More informationHeuristic Techniques for Solving the Vehicle Routing Problem with Time Windows Manar Hosny
Heuristic Techniques for Solving the Vehicle Routing Problem with Time Windows Manar Hosny College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia mifawzi@ksu.edu.sa Keywords:
More informationA HYBRID MODERN AND CLASSICAL ALGORITHM FOR INDONESIAN ELECTRICITY DEMAND FORECASTING
A HYBRID MODERN AND CLASSICAL ALGORITHM FOR INDONESIAN ELECTRICITY DEMAND FORECASTING Wahab Musa Department of Electrical Engineering, Universitas Negeri Gorontalo, Kota Gorontalo, Indonesia E-Mail: wmusa@ung.ac.id
More informationGenetic Based Task Scheduling Algorithms in Distributed Environments- Its Strengths, Weaknesses, Opportunity and Threats
Genetic Based Task Scheduling Algorithms in Distributed Environments- Its Strengths, Weaknesses, Opportunity and Threats Sunil Kumar Assistant Professor, Guru Nanak College for Girls, Sri Muktsar Sahib
More informationCost-based Job Grouping and Scheduling Algorithm for Grid Computing Environments
Cost-based Job Grouping and Scheduling Algorithm for Grid Computing Environments Sonal Yadav M.Tech (CSE) Sharda University Greater Noida, India Amit Agarwal, Ph.D Associate Professor University of Petroleum
More informationA Viral Systems Algorithm for the Traveling Salesman Problem
Proceedings of the 2012 International Conference on Industrial Engineering and Operations Management Istanbul, Turkey, July 3 6, 2012 A Viral Systems Algorithm for the Traveling Salesman Problem Dedy Suryadi,
More informationStorage Allocation and Yard Trucks Scheduling in Container Terminals Using a Genetic Algorithm Approach
Storage Allocation and Yard Trucks Scheduling in Container Terminals Using a Genetic Algorithm Approach Z.X. Wang, Felix T.S. Chan, and S.H. Chung Abstract Storage allocation and yard trucks scheduling
More informationOn-demand provisioning of HEP compute resources on cloud sites and shared HPC centers
On-demand provisioning of HEP compute resources on cloud sites and shared HPC centers Gu nther Erli, Frank Fischer, Georg Fleig, Manuel Giffels, Thomas Hauth, Gu nter Quast, Matthias Schnepf (IEKP), Andreas
More informationIn Cloud, Can Scien/fic Communi/es Benefit from the Economies of Scale?
In Cloud, Can Scien/fic Communi/es Benefit from the Economies of Scale? By: Lei Wang, Jianfeng Zhan, Weisong Shi, Senior Member, IEEE, and Yi Liang Presented By: Ramneek (MT2011118) Introduc/on The power
More informationPlatform Solutions for CAD/CAE 11/6/2008 1
Platform Solutions for CAD/CAE 11/6/2008 1 Who We Are - Platform Computing The world s largest, most established provider of grid computing solutions Over 2000 customers in many vertical markets Electronics,
More informationKoen van den Biggelaar Senior Manager, Solutions Architecture Amazon Web Services
Koen van den Biggelaar Senior Manager, Solutions Architecture Amazon Web Services koen@amazon.com Amazon Cloud? Leadership Principles Innovation Approach Intro Amazon AWS Innovation Innovation Applied
More informationBudget Constrained Execution of Multiple Bag-of-Tasks Applications on the Cloud
Budget Constrained Execution of Multiple Bag-of-Tasks Applications on the Cloud Long Thai, Blesson Varghese and Adam Barker School of Computer Science, University of St Andrews, Fife, UK Email: {ltt2,
More informationTESTING AS A SERVICE (TAAS) AN ENHANCED SECURITY FRAMEWORK FOR TAAS IN CLOUD ENVIRONMENT K.V.ARUNKUMAR & E. SAMLINSON
TESTING AS A SERVICE (TAAS) AN ENHANCED SECURITY FRAMEWORK FOR TAAS IN CLOUD ENVIRONMENT K.V.ARUNKUMAR & E. SAMLINSON Sona College of Technology, Salem, India Email: kvarunkumarme@gmail.com, samlinson@gmail.com
More informationGROUPING BASED USER DEMAND AWARE JOB SCHEDULING APPROACH FOR COMPUTATIONAL GRID
GROUPING BASED USER DEMAND AWARE JOB SCHEDULING APPROACH FOR COMPUTATIONAL GRID P.SURESH Assistant Professor (Senior Grade), Department of IT, Kongu Engineering College, Perundurai, Erode Tamilnadu, India
More informationNetScaler Management and Analytics System (MAS)
Data Sheet NetScaler Management and Analytics System (MAS) NetScaler MAS provides centralized network management, analytics, automation, and orchestration to support applications deployed across hybrid
More informationTAAG: An Efficient Task Allocation Algorithm for Grid Environment
TAAG: An Efficient Task Allocation Algorithm for Grid Environment S. Vaaheedha Kfatheen #1, Dr. M. Nazreen Banu *2 # Research Scholar, Bharathiar University, Coimbatore, Tamil Nadu, India. E-Mail: abuthaheer67@gmail.com
More informationPredict the financial future with data and analytics
Aon Benfield Analytics Predict the financial future with data and analytics Predict the financial future with data and analytics In a world of ever-evolving regulation and accounting standards, coupled
More informationModeling and optimization of ATM cash replenishment
Modeling and optimization of ATM cash replenishment PETER KURDEL, JOLANA SEBESTYÉNOVÁ Institute of Informatics Slovak Academy of Sciences Bratislava SLOVAKIA peter.kurdel@savba.sk, sebestyenova@savba.sk
More informationCloud Capacity Management
Cloud Capacity Management Defining Cloud Computing Cloud computing is a type of Internet based computing that provides shared computer processing resources and data to computers and other devices on demand.
More informationHTCaaS: Leveraging Distributed Supercomputing Infrastructures for Large- Scale Scientific Computing
HTCaaS: Leveraging Distributed Supercomputing Infrastructures for Large- Scale Scientific Computing Jik-Soo Kim, Ph.D National Institute of Supercomputing and Networking(NISN) at KISTI Table of Contents
More informationToward Effective Multi-capacity Resource Allocation in Distributed Real-time and Embedded Systems
Toward Effective Multi-capacity Resource Allocation in Distributed Real-time and Embedded Systems Nilabja Roy, John S. Kinnebrew, Nishanth Shankaran, Gautam Biswas, and Douglas C. Schmidt Department of
More informationTiefere Einblicke in virtuelle Umgebungen
Tiefere Einblicke in virtuelle Umgebungen VMware vsphere with Operations Management (vsom) Tobias Mauer ARROW ECS Deutschland 2015 VMware Inc. All rights reserved. Agenda Today s Reality Goals & Evolution
More informationCOMPARING VARIOUS WORKFLOW ALGORITHMS WITH SIMULATED ANNEALING TECHNIQUE
COMPARING VARIOUS WORKFLOW ALGORITHMS WITH SIMULATED ANNEALING TECHNIQUE Dr.V.Venkatesakumar #1, R.Yasotha #2 # Department of Computer Science and Engineering, Anna University Regional Centre, Coimbatore,
More informationThe definitive end-to-end platform for automotive finance.
The definitive end-to-end platform for automotive finance. alfasystems.com Alfa Systems is the number one software choice for automotive finance companies worldwide. Live across four continents, our class-leading
More informationEnergy-Efficient Scheduling of Urgent Bag-of-Tasks Applications in Clouds through DVFS
2014 IEEE 6th International Conference on Cloud Computing Technology and Science Energy-Efficient Scheduling of Urgent Bag-of-Tasks Applications in Clouds through DVFS Rodrigo N. Calheiros and Rajkumar
More informationStrengths & Drawbacks of MILP, CP and Discrete-Event Simulation based Approaches for Large-Scale Scheduling
Strengths & Drawbacks of MILP, CP and Discrete-Event Simulation based Approaches for Large-Scale Scheduling Pedro M. Castro Assistant Researcher Laboratório Nacional de Energia e Geologia Lisboa, Portugal
More informationAdobe Deploys Hadoop as a Service on VMware vsphere
Adobe Deploys Hadoop as a Service A TECHNICAL CASE STUDY APRIL 2015 Table of Contents A Technical Case Study.... 3 Background... 3 Why Virtualize Hadoop on vsphere?.... 3 The Adobe Marketing Cloud and
More informationTask Scheduling in Cloud Computing using Lion Optimization Algorithm
Task Scheduling in Cloud Computing using Lion Optimization Algorithm Nora Almezeini and Prof. Alaaeldin Hafez College of Computer and Information Sciences King Saud University Riyadh, Saudi Arabia Abstract
More informationSAP Cloud Platform Pricing and Packages
Platform Pricing and Packages Get Started Packages Fast. Easy. Cost-effective. Get familiar and up-and-running with Platform in no time flat. Intended for non-production use. Designed to help users become
More informationPerformance of Multi-agent Coordination of Distributed Energy Resources
Proceedings of the 27 WSEAS International Conference on Computer Engineering and Applications, Gold Coast, Australia, January 17-19, 27 68 Performance of Multi-agent Coordination of Distributed Energy
More informationA NOVEL MULTIOBJECTIVE OPTIMIZATION ALGORITHM, MO HSA. APPLICATION ON A WATER RESOURCES MANAGEMENT PROBLEM
A NOVEL MULTIOBJECTIVE OPTIMIZATION ALGORITHM, MO HSA. APPLICATION ON A WATER RESOURCES MANAGEMENT PROBLEM I. Kougias 1, L. Katsifarakis 2 and N. Theodossiou 3 Division of Hydraulics and Environmental
More informationBOC Group Customer Success Story
BOC Group Customer Success Story customer profile BOC Group is an international leader in software and consultancy providing products and services for Business Process Management (BPM), Enterprise Architecture
More informationAddressing the I/O bottleneck of HPC workloads. Professor Mark Parsons NEXTGenIO Project Chairman Director, EPCC
Addressing the I/O bottleneck of HPC workloads Professor Mark Parsons NEXTGenIO Project Chairman Director, EPCC I/O is key Exascale challenge Parallelism beyond 100 million threads demands a new approach
More informationAdvanced Enterprise Work and Asset Management for Performance-Driven Utilities
Advanced Enterprise Work and Asset Management for Performance-Driven Utilities Asset & Resource Management (ARM) 2 CGI s Asset & Resource Management (ARM) 2 suite is a solution designed to streamline the
More informationFORECASTING & REPLENISHMENT
MANHATTAN ACTIVE INVENTORY FORECASTING & REPLENISHMENT MAXIMIZE YOUR RETURN ON INVENTORY ASSETS Manhattan Active Inventory allows you to finally achieve a single, holistic view of all aspects of your inventory
More informationTrasformare il Business con Soluzioni Cloud
Trasformare il Business con Soluzioni Cloud Marco Sebastiani Product Manager, IBM Tivoli Cloud Solutions 1 What is different about cloud computing? Without cloud computing With cloud computing Virtualized
More information