SLIDE 1
Simulating Energy Aware Networks in Large Scale Distributed Systems - - PowerPoint PPT Presentation
Simulating Energy Aware Networks in Large Scale Distributed Systems - - PowerPoint PPT Presentation
Simulating Energy Aware Networks in Large Scale Distributed Systems Betsegaw Lemma Amersho Supervised by: Prof. Martin Quinson, Dr. Anne-C ecile Orgerie Master Thesis Defence, June 30, 2017 Outline Recent Trends in Large-Scale Networks 1
SLIDE 2
SLIDE 3
Recent Trends in Large-Scale Networks
Networked Devices are Increasing 17.1 billion in 2016 to 27.1 billion in 2021 IP Traffic is Growing Global IP traffic will increase threefold over the next 5 years Cloud Infrastructure Dependency is Increasing By 2020, 92% of workloads will be processed by cloud data centers Data Center are Expanding In response to the added components and the increased service demand This Expansion Led to Energy Consumption Concern
SLIDE 4
Recent Trends in Large-Scale Networks
Networked Devices are Increasing 17.1 billion in 2016 to 27.1 billion in 2021 IP Traffic is Growing Global IP traffic will increase threefold over the next 5 years Cloud Infrastructure Dependency is Increasing By 2020, 92% of workloads will be processed by cloud data centers Data Center are Expanding In response to the added components and the increased service demand This Expansion Led to Energy Consumption Concern
SLIDE 5
Recent Trends in Large-Scale Networks
Networked Devices are Increasing 17.1 billion in 2016 to 27.1 billion in 2021 IP Traffic is Growing Global IP traffic will increase threefold over the next 5 years Cloud Infrastructure Dependency is Increasing By 2020, 92% of workloads will be processed by cloud data centers Data Center are Expanding In response to the added components and the increased service demand This Expansion Led to Energy Consumption Concern
SLIDE 6
Recent Trends in Large-Scale Networks
Networked Devices are Increasing 17.1 billion in 2016 to 27.1 billion in 2021 IP Traffic is Growing Global IP traffic will increase threefold over the next 5 years Cloud Infrastructure Dependency is Increasing By 2020, 92% of workloads will be processed by cloud data centers Data Center are Expanding In response to the added components and the increased service demand This Expansion Led to Energy Consumption Concern
SLIDE 7
Energy Proportionality
Ideal Energy Proportional Network Equipment Consume no power when idle (Static Power) Consume power in proportion to their work load (Dynamic Power) Energy Inefficiency of Current Network Equipment Current Network Equipment have narrow dynamic power range
SLIDE 8
Energy Proportionality
Ideal Energy Proportional Network Equipment Consume no power when idle (Static Power) Consume power in proportion to their work load (Dynamic Power) Energy Inefficiency of Current Network Equipment Current Network Equipment have narrow dynamic power range
SLIDE 9
Common Research Methods
Experimenting on Real Production Environment (in vivo) Can give real picture of the problem being studied Difficult to repeat experiments Might not be available for experimentation Experimenting on Experimental Test-Bed (in vivo) Offers full control over the experiment Limited in scalablility and for testing different scenarios Experimenting using Simulation Software (in silico) Gives full control, more flexible, less expensive and less time consuming Might fail to correctly model the real situation
SLIDE 10
Common Research Methods
Experimenting on Real Production Environment (in vivo) Can give real picture of the problem being studied Difficult to repeat experiments Might not be available for experimentation Experimenting on Experimental Test-Bed (in vivo) Offers full control over the experiment Limited in scalablility and for testing different scenarios Experimenting using Simulation Software (in silico) Gives full control, more flexible, less expensive and less time consuming Might fail to correctly model the real situation
SLIDE 11
Common Research Methods
Experimenting on Real Production Environment (in vivo) Can give real picture of the problem being studied Difficult to repeat experiments Might not be available for experimentation Experimenting on Experimental Test-Bed (in vivo) Offers full control over the experiment Limited in scalablility and for testing different scenarios Experimenting using Simulation Software (in silico) Gives full control, more flexible, less expensive and less time consuming Might fail to correctly model the real situation
SLIDE 12
Network Simulation
Packet Level Simulators Modeling at a packet-level (capture low-level details) Are close to the real network phenomenon being modeld Fail to scale well when simulating large-scale networks Flow Level Simulators Abstract away low-level details and use analytical equations Suitable for simulating large-scale networks (Scalable) Loss of low-level details/accuracy The Goal of this Study To investigate the level of energy estimation accuracy that can be
- btained from flow-level energy consumption models.
SLIDE 13
Network Simulation
Packet Level Simulators Modeling at a packet-level (capture low-level details) Are close to the real network phenomenon being modeld Fail to scale well when simulating large-scale networks Flow Level Simulators Abstract away low-level details and use analytical equations Suitable for simulating large-scale networks (Scalable) Loss of low-level details/accuracy The Goal of this Study To investigate the level of energy estimation accuracy that can be
- btained from flow-level energy consumption models.
SLIDE 14
Network Simulation
Packet Level Simulators Modeling at a packet-level (capture low-level details) Are close to the real network phenomenon being modeld Fail to scale well when simulating large-scale networks Flow Level Simulators Abstract away low-level details and use analytical equations Suitable for simulating large-scale networks (Scalable) Loss of low-level details/accuracy The Goal of this Study To investigate the level of energy estimation accuracy that can be
- btained from flow-level energy consumption models.
SLIDE 15
Our Approach
Energy Consumption Model Literature Search Model Implementation Model Validation Simulating Energy Consumption Simulating Energy Consumption M
- d
e l V a l i d a t i
- n
Comparing Scalability
Ⓐ Ⓑ Ⓒ Ⓓ Ⓔ Ⓕ Ⓖ
SLIDE 16
Proposed Flow Level Model
Energy Consumption E(T) = T P(t)dt Power Consumption Ptotal = Pstatic + Pdynamic Flow-Level Model Implemented in SimGrid E(T) = T (Pstatic + Pdynamic)(t)dt where, Pdynamic = (Pbusy − Pidle) ∗ u
SLIDE 17
Proposed Flow Level Model
Energy Consumption E(T) = T P(t)dt Power Consumption Ptotal = Pstatic + Pdynamic Flow-Level Model Implemented in SimGrid E(T) = T (Pstatic + Pdynamic)(t)dt where, Pdynamic = (Pbusy − Pidle) ∗ u
SLIDE 18
Proposed Flow Level Model
Energy Consumption E(T) = T P(t)dt Power Consumption Ptotal = Pstatic + Pdynamic Flow-Level Model Implemented in SimGrid E(T) = T (Pstatic + Pdynamic)(t)dt where, Pdynamic = (Pbusy − Pidle) ∗ u
SLIDE 19
Validation Experiments
Accuracy Scenarios Data Size: [10,500] MB Traffic Flow: [1,4] Network Path Length: 1 and 3 Scalability Scenarios Simulation Time and Memory Usage Traffic Flow: 2 Data Size: [50,500] MB Network Path Length: 1, 2, 4, 6, 8, & 10
SLIDE 20
Validation Experiments
Accuracy Scenarios Data Size: [10,500] MB Traffic Flow: [1,4] Network Path Length: 1 and 3 Scalability Scenarios Simulation Time and Memory Usage Traffic Flow: 2 Data Size: [50,500] MB Network Path Length: 1, 2, 4, 6, 8, & 10
SLIDE 21
Accuracy Validation Result
ECOFEN vs SimGrid Comparison for all scenarios the accuracy estimation error is < 0.3% Flows 2, Path-Length 1 Flows 2, Path-Length 3
SLIDE 22
Scalability Validation Result
Simulation Time and Peak Memory Usage Comparison SimGrid is 243 to 2723 times faster than ECOFEN SimGrid is 2 to 15 times more memory efficent than ECOFEN Simulation Time Peak Memory Usage
SLIDE 23