E-STAB: Energy-Efficient Scheduling for Cloud Computing Applications with Traffic Load Balancing Dzmitry KliazovichUniversity of Luxembourg, Luxembourg.

Slides:



Advertisements
Similar presentations
RED Enhancement Algorithms By Alina Naimark. Presented Approaches Flow Random Early Drop - FRED By Dong Lin and Robert Morris Sabilized Random Early Drop.
Advertisements

SDN + Storage.
Min Song 1, Yanxiao Zhao 1, Jun Wang 1, E. K. Park 2 1 Old Dominion University, USA 2 University of Missouri at Kansas City, USA IEEE ICC 2009 A High Throughput.
Walter Binder University of Lugano, Switzerland Niranjan Suri IHMC, Florida, USA Green Computing: Energy Consumption Optimized Service Hosting.
Stratos: A Network-Aware Orchestration Layer for Middleboxes in the Cloud Aditya Akella, Aaron Gember, Anand Krishnamurthy, Saul St. John University of.
1 Communication Networks Kolja Eger, Prof. Dr. U. Killat 1 From Packet-level to Flow-level Simulations of P2P Networks Kolja Eger, Ulrich Killat Hamburg.
APOHN: Subnetwork Layering to Improve TCP Performance over Heterogeneous Paths April 4, 2006 Dzmitry Kliazovich, Fabrizio Granelli, University of Trento,
Xavier León PhD defense
The major IT companies, such as Microsoft, Google, Amazon, and IBM, pioneered the field of cloud computing and keep increasing their offerings in data.
On Modeling Feedback Congestion Control Mechanism of TCP using Fluid Flow Approximation and Queuing Theory  Hisamatu Hiroyuki Department of Infomatics.
1 TCP-LP: A Distributed Algorithm for Low Priority Data Transfer Aleksandar Kuzmanovic, Edward W. Knightly Department of Electrical and Computer Engineering.
Rethinking Internet Traffic Management: From Multiple Decompositions to a Practical Protocol Jiayue He Princeton University Joint work with Martin Suchara,
Using Prices to Allocate Resources at Access Points Jimmy Shih, Randy Katz, Anthony Joseph One Administrative Domain Access Point A Access Point B Network.
Performance and Robustness Testing of Explicit-Rate ABR Flow Control Schemes Milan Zoranovic Carey Williamson October 26, 1999.
Color Aware Switch algorithm implementation The Computer Communication Lab (236340) Spring 2008.
Multipath Protocol for Delay-Sensitive Traffic Jennifer Rexford Princeton University Joint work with Umar Javed, Martin Suchara, and Jiayue He
Kick-off meeting 3 October 2012 Patras. Research Team B Communication Networks Laboratory (CNL), Computer Engineering & Informatics Department (CEID),
1 Algorithms for Bandwidth Efficient Multicast Routing in Multi-channel Multi-radio Wireless Mesh Networks Hoang Lan Nguyen and Uyen Trang Nguyen Presenter:
1 Scheduling calls with known holding times Reinette Grobler * Prof. M. Veeraraghavan University of Pretoria Polytechnic University
Advanced Energy Management in Cloud Computing multi data center environments Giuliana Carello, DEI, Politecnico di Milano Danilo.
Dynamic Resource Allocation Using Virtual Machines for Cloud Computing Environment.
1 Enabling Large Scale Network Simulation with 100 Million Nodes using Grid Infrastructure Hiroyuki Ohsaki Graduate School of Information Sci. & Tech.
OPTIMAL SERVER PROVISIONING AND FREQUENCY ADJUSTMENT IN SERVER CLUSTERS Presented by: Xinying Zheng 09/13/ XINYING ZHENG, YU CAI MICHIGAN TECHNOLOGICAL.
Network Aware Resource Allocation in Distributed Clouds.
Towards Sustainable Portable Computing through Cloud Computing and Cognitive Radios Vinod Namboodiri Wichita State University.
DENS: Data Center Energy-Efficient Network-Aware Scheduling
1 Distributed Process Scheduling: A System Performance Model Vijay Jain CSc 8320, Spring 2007.
A Dynamic Data Grid Replication Strategy to Minimize the Data Missed Ming Lei, Susan Vrbsky, Xiaoyan Hong University of Alabama.
Distance-Dependent RED Policy (DDRED)‏ Sébastien LINCK, Eugen Dedu and François Spies LIFC Montbéliard - France ICN07.
Data Placement and Task Scheduling in cloud, Online and Offline 赵青 天津科技大学
OPERETTA: An Optimal Energy Efficient Bandwidth Aggregation System Karim Habak†, Khaled A. Harras‡, and Moustafa Youssef† †Egypt-Japan University of Sc.
Data Replication and Power Consumption in Data Grids Susan V. Vrbsky, Ming Lei, Karl Smith and Jeff Byrd Department of Computer Science The University.
Vertical Optimization Of Data Transmission For Mobile Wireless Terminals MICHAEL METHFESSEL, KAI F. DOMBROWSKI, PETER LANGENDORFER, HORST FRANKENFELDT,
DaVinci: Dynamically Adaptive Virtual Networks for a Customized Internet Jiayue He, Rui Zhang-Shen, Ying Li, Cheng-Yen Lee, Jennifer Rexford, and Mung.
Intradomain Traffic Engineering By Behzad Akbari These slides are based in part upon slides of J. Rexford (Princeton university)
Bidirectional Light-Trails Dzmitry Kliazovich, Fabrizio Granelli, University of Trento, Italy GLOBECOM’05 November 29, 2005 Hagen Woesner, Imrich Chlamtac.
Dzmitry Kliazovich University of Luxembourg
CprE 458/558: Real-Time Systems (G. Manimaran)1 CprE 458/558: Real-Time Systems Real-Time Networks – WAN Packet Scheduling.
Dzmitry Kliazovich University of Luxembourg, Luxembourg
ARQ Proxy (for WiFi networks) Ischia island, Italy Sept. 11, 2007 Dzmitry Kliazovich Nadhir Ben Halima Fabrizio Granelli University of Trento, Italy.
Data Center Energy-Efficient Network-Aware Scheduling
CATNIP – Context Aware Transport/Network Internet Protocol Carey Williamson Qian Wu Department of Computer Science University of Calgary.
GreenCloud: A Packet-level Simulator of Energy-aware Cloud Computing Data Centers Dzmitry Kliazovich ERCIM Fellow University of Luxembourg Apr 16, 2010.
Accounting for Load Variation in Energy-Efficient Data Centers
Indian Institute of Technology Bombay 1 Abhay Karandikar Associate Professor Department of Electrical Engineering
Data Consolidation: A Task Scheduling and Data Migration Technique for Grid Networks Author: P. Kokkinos, K. Christodoulopoulos, A. Kretsis, and E. Varvarigos.
Ensieea Rizwani An energy-efficient management mechanism for large-scale server clusters By: Zhenghua Xue, Dong, Ma, Fan, Mei 1.
Internet Measurement and Analysis Vinay Ribeiro Shriram Sarvotham Rolf Riedi Richard Baraniuk Rice University.
1 Traffic Engineering By Kavitha Ganapa. 2 Introduction Traffic engineering is concerned with the issue of performance evaluation and optimization of.
Survey on Signaling Techniques for Cognitive Networks Dzmitry KliazovichUniversity of Luxembourg, Luxembourg Fabrizio GranelliUniversity of Trento, Italy.
Cognitive Information Service Basic Principles and Implementation of A Cognitive Inter-Node Protocol Optimization Scheme Dzmitry Kliazovich Fabrizio Granelli.
Analysis and Forming of Energy Efficiency and Green IT Metrics Framework for Sonera Helsinki Data Center HDC Matti Pärssinen Thesis supervisor: Prof. Jukka.
Review of Useful Definitions Statistical multiplexing is a method of sharing a link among transmissions. When computers use store-and-forward packet switching,
Software-Defined Architecture for Mobile Clouds in Device-to-Device Communication Muhammad Usman; Anteneh A. Gebremariam; Fabrizio Granelli; Dzmitry Kliazovich.
Scalable Congestion Control Protocol based on SDN in Data Center Networks Speaker : Bo-Han Hua Professor : Dr. Kai-Wei Ke Date : 2016/04/08 1.
-1/16- Maximum Battery Life Routing to Support Ubiquitous Mobile Computing in Wireless Ad Hoc Networks C.-K. Toh, Georgia Institute of Technology IEEE.
Delay-based Congestion Control for Multipath TCP Yu Cao, Mingwei Xu, Xiaoming Fu Tsinghua University University of Goettingen.
Web Servers load balancing with adjusted health-check time slot.
Dzmitry Kliazovich, Fabrizio Granelli, University of Trento, Italy
DENS: Data Center Energy-Efficient Network-Aware Scheduling
Performance and Energy Efficiency Metrics for Communication Systems of Cloud Computing Data Centers Hrushikesh Mahapatro IT
GreenCloud: A Packet-level Simulator of Energy-aware Cloud Computing Data Centers Dzmitry Kliazovich, Pascal Bouvry, Yury Audzevich, and Samee Ullah Khan.
Dzmitry Kliazovich, Fabrizio Granelli, University of Trento, Italy
Cognitive Link Layer for Wireless Local Area Networks
A Cognitive Approach for Cross-Layer Performance Management
Multi-hop Coflow Routing and Scheduling in Data Centers
   Storage Space Allocation at Marine Container Terminals Using Ant-based Control by Omor Sharif and Nathan Huynh Session 677: Innovations in intermodal.
In-network computation
Dzmitry Kliazovich University of Luxembourg, Luxembourg
Towards Predictable Datacenter Networks
Presentation transcript:

e-STAB: Energy-Efficient Scheduling for Cloud Computing Applications with Traffic Load Balancing Dzmitry KliazovichUniversity of Luxembourg, Luxembourg Pascal Bouvry Sisay T. ArzoUniversity of Trento Fabrizio Granelli Samee U. KhanNorth Dakota State University, U.S.A.

Cloud Computing Cloud computing market: $241 billion in 2020 Main focus is on Software-as-a-Service (SaaS) Aug 22, 2013Dzmitry Kliazovich Source: Larry Dignan, “Cloud computing market”, ZDNet, 2011.

Cloud Computing Applications Aug 22, 2013Dzmitry Kliazovich

Resource Requirements of Cloud Applications Aug 22, 2013Dzmitry Kliazovich Computing Network Bandwidth Communication delays (tolerance) Degree of interactivity Storage

Resource Requirements of Cloud Applications Aug 22, 2013Dzmitry Kliazovich Computing Network Bandwidth Communication delays (tolerance) Storage Degree of interactivity

Cloud Computing Applications Aug 22, 2013Dzmitry Kliazovich Communication resources

Cloud Computing Applications Traditional resource allocation and scheduling – Distribute incoming jobs to the pool of servers – Communication requirements and networking are not taken into account Aug 22, 2013Dzmitry Kliazovich

Scheduling in Data Centers Aug 22, 2013Dzmitry Kliazovich Network congestion!!!

Scheduling in Data Centers Aug 22, 2013Dzmitry Kliazovich Network is balanced !!!

eSTAB Scheduling

eSTAB Scheduling in Data Centers Aug 22, 2013Dzmitry Kliazovich e-STAB: Energy-Efficient Scheduling for Cloud Computing Applications with Traffic Load Balancing Treat communication and computing demands equally #1 Optimize energy efficiency and load balancing of network traffic #2 Formal model for selection of servers, racks, and network modules #3

eSTAB Scheduling in Data Centers Aug 22, 2013Dzmitry Kliazovich Step 1 – Select servers connected to the data center network with the highest available bandwidth (low network load) Step 2 – Within the selected group of servers, select a computing server with the smallest available computing capacity (high server load)

Step #1: Selecting a Rack

eSTAB Model Aug 22, 2013Dzmitry Kliazovich

eSTAB Model Aug 22, 2013Dzmitry Kliazovich

eSTAB Model Aug 22, 2013Dzmitry Kliazovich

eSTAB Model Aug 22, 2013Dzmitry Kliazovich Available bandwidth weighted with the size of the bottleneck queue Favor Empty Queues Penalize Highly-Loaded Queues

eSTAB Model Aug 22, 2013Dzmitry Kliazovich

eSTAB Model Aug 22, 2013Dzmitry Kliazovich eSTAB traffic related metric

Step #2: Selecting a Server

eSTAB Model Aug 22, 2013Dzmitry Kliazovich

eSTAB Model Aug 22, 2013Dzmitry Kliazovich

eSTAB Model Aug 22, 2013Dzmitry Kliazovich

eSTAB Model Aug 22, 2013Dzmitry Kliazovich eSTAB metric for server selection Penalize Selection of Idle Servers Select Servers According to their Energy Consumption

Performance Evaluation

Cloud Computing Simulator Aug 22, 2013Dzmitry Kliazovich – Measures cloud performance and energy efficiency – First to simulate cloud communications with packet-level precision – Implements network-aware scheduling – Implements complete TCP/IP protocol stack available at available at

Simulation Setup Setup Parameters Aug 22, 2013Dzmitry Kliazovich

e-STAB Results Aug 22, 2013Dzmitry Kliazovich Processing Load Distribution Among Servers Racks are overloaded Racks load is balanced

e-STAB Results Aug 22, 2013Dzmitry Kliazovich Traffic Distribution Among Racks Racks are overloaded Racks load is balanced

e-STAB Results Aug 22, 2013Dzmitry Kliazovich Task Completion Delay 80 ms (Green) 20 ms (e-STAB)

e-STAB Results Aug 22, 2013Dzmitry Kliazovich Energy Consumption Improved Performance Comes at a Price of Increased Energy Consumption of Network Switches

Conclusions Considering communication fabric is essential to allocate resource efficiently in cloud computing e-STAB is a new communication-aware scheduler for cloud application e-STAB minimizes communication-related delays and can avoid congestion-related packet losses at a price of minor increase in energy consumption of network switches Aug 22, 2013Dzmitry Kliazovich

Thank you! Contact information: Dzmitry Kliazovich University of Luxembourg