Energy Efficiency and Future Network Infrastructure
Department of Naval,
Electrical, Electronics and
Telecommunication
Engineering (DITEN)
Telecommunication
Networks and
Telematics Lab
University of Genoa
Green
networking:
lessons learned
and challenges
Prof. Raffaele Bolla
raffaele.bolla@unige.it
CNIT/University of Genoa
Amsterdam, 22 October 2014
•  Previous
results: the FP7 experience
•  Lessons
learned
•  Current
challenges
•  Conclusions
Energy Efficiency and Future Network Infrastructure
Summary
Near to zero
Standby
Idle
(for long
periods)
Idle
(for short
periods)
Smart
Standby
Low
Load
…..
Active state 1
Low
Power
Idle
Active state n-1
Low
Dynamic Adaptation
Active state n
Max
Idle
state
Power
Management
Energy Consumption
Energy profile
…..
Fully
Loaded
Energy Efficiency and Future Network Infrastructure
Recent (EU-FP7 projects) approaches in
network energy-efficiency
Demonstration Activities
See the online demo portal at https://www.econet-project.eu/demo
IXIA
Home Network Cloud
inject
ion
2
LQDE1-­‐5 Metro
Network
Cloud TEIA 5 x VDSL + 43 x VDSL loopbacks
L19
ETY1 INFO 1 x 10 GbE L21a 1 x 10 GbE L21b 1 x 10GbE
CNIT1
L-10
1 x 10 GbE 1 x 1GbE L-­‐18 1 x 10 GbE L-­‐7 1 x 10 GbE Access
Network
Cloud
L-­‐20 4 x 1 GbE L-­‐13 L-­‐5 8 x 1 GbE L-­‐12 Network
Emulation 2
Network
emulation 1
ETY2 1 x 1GbE 1 x 10 GbE L-­‐2 3 x 1GbE L3 L-­‐1 TEIB 1 x 10 GbE L-­‐16 Monitoring and OAM Cloud Spire
nt
inject
ion
4
1 x 10 GbE L-­‐24 1 x 10 GbE L-­‐17 MLX MLX Server 1 x 10 GbE L-­‐23 Datacenter Network Cloud
Network
emulation 3
1 x 10 GbE IXIA
inject
ion
1
Transport
Network
Cloud
L-­‐6 TEIC 5 x 1GbE ALU1 L-­‐11 1x
CNIT2 10GbE
L-4
Core
Network
Cloud
9 x 1GbE IXIA L22 inject
ion
3
ALU2 Energy Efficiency and Future Network Infrastructure
ECONET experience and results
Demonstration Activities
IXIA
Home Network Cloud
injectio
n
2
LQDE1-­‐5 Metro
Network
Cloud TEIA 5 x VDSL + 43 x VDSL loopbacks
L19
ETY1 INFO 1 x 10 GbE 1 x 10 GbE L21b L21a L-10
1 x 10 GbE 1 x 1GbE L-­‐7 L-­‐18 L-­‐6 4 x 1 GbE L-­‐13 L-­‐5 8 x 1 GbE L-­‐12 Network
NetworkEmulation 2
emulation 1
ETY2 Network
emulation 3
1 x 10 GbE IXIA
injectio
n
1
1 x 10 GbE Access
Network
Cloud
L-­‐20 1 x 1GbE L3 L-­‐1 1x
10GbE
CNIT2 L-4
Core
Network Cloud
TEIB 1 x 10 GbE L-­‐16 Monitoring and OAM Cloud L-­‐11 1 x 10 GbE L-­‐2 3 x 1GbE 1 x 10 GbE L-­‐17 9 x 1GbE Spirent
injectio
n
4
1 x 10 GbE L-­‐24 Transport
Network Cloud
1 x 10 GbE TEIC 5 x 1GbE ALU1 CNIT11 x 10GbE
MLX MLX Server 1 x 10 GbE L-­‐23 Datacenter Network Cloud
L22 IXIA
injectio
n
3
ALU2 Energy Efficiency and Future Network Infrastructure
ECONET experience and results
Impact results
90%
79.2%
80%
Energy Saving (%)
Short term Short-Term Impact
70%
60%
50%
55.0%
49.1%
53.6%
46.3%
51.5%
38.9%
40%
30%
20%
10%
0%
Transport
90%
Core
Metro
Datacenter
Access
Home
Total
Long-Term Impact
83.0%
73.4%
80%
Energy Saving (%)
Average energy reducOon of 51.6%. 70% 65.1%
60%
79.7%
77.6%
Home
Total
69.3%
53.7%
50%
40%
30%
20%
10%
0%
Transport
Core
Metro
Datacenter
Access
Saving of more than 190 Million € per year eonergy f OPEX. Average reducOon of 77.6%. Carbon footprint emissions Saving of more reducOon than 290 Million € equivalent per year of o
Of PEX. removing 50,000 Carbon cars per footprint year. emissions reducOon equivalent of removing 75,000 cars per year. Long term Energy Efficiency and Future Network Infrastructure
ECONET final results
•
Energy-aware hardware and autonomic low level power
management mechanisms are mandatory, but definitely not
sufficient.
•
Heterogeneous power-saving mechanisms often interfere among
each other, and cause heavy drawbacks:
–  Energy savings are not additive by default
–  Trade-off between energy consumption and network performance
•
Power management needs to be driven by upper levels:
–  to map their functional/logical resources and configurations with the underlying
hardware
–  to find the best energy-aware hardware configuration that optimizes the trade-off
between network performance and device/network energy consumption
•
Power management needs to be suitably orchestrated at
different levels:
–  Inside single devices
–  At the device level (logical/physical planes)
–  At the network level
•
Moreover, a relevant push toward standards and regulatory
actions is also essential (e.g., KPIs (Key Performance Indicators)).
Energy Efficiency and Future Network Infrastructure
Lessons Learned (1/3)
The Green Abstraction Layer
•
One of the main achievements of the ECONET project.
•
The GAL is a hierarchical
interface to control and to
orchestrate power
management primitives in
a network device in a
scalable and flexible way.
•
The GAL layers allows to
divide and conquer the
complex process of optimizing
the mapping between power
management primitives
(acting at the HW level) and
the network logical/virtual/
functional configuration.
•
The GAL has been approved in March 2014 as ETSI Standard
203 237.
Working Item: Reference operational model and interface for
improving energy efficiency of ICT network devices
Energy Efficiency and Future Network Infrastructure
Lessons Learned (2/3)
Performance
- Zero loss and very low latency services
- Very broadband wireless/fixed accesses
- Terabit transport networks
Tomorrow
Convergence
SDN
M2M
Today
Network
OS
NFV
Clouds
Programmability/Virtualization
Networks as multi-purpose service-aware infrastructures:
Energy Efficiency and Future Network Infrastructure
Future Internet/5G Challenges
•
In order to support all these objectives, we need to
deeply re-think and re-design network
architectures, devices, and base technologies:
In the small
–  HW programmability inside
networks and devices
–  HW offloading for high performance
–  Extreme virtualization paradigms to make
different services sharing network resources
–  Consolidation of services
System level
Network level
Tomorrow, classical network protocols like IP will be considered simply as pla7orm-­‐independent virtualized network services Energy Efficiency and Future Network Infrastructure
Future Internet/5G Challenges
The Future Internet basics
Technology Evolution
•
Strong presence of
programmable/general
purpose HW inside
networks and devices:
it is the main element for
introducing the flexibility
necessary for Future
Internet architectures
development.
Technological Impact
•
Costs & greenhouse gas
emissions:
sustainability is a must for
the Future Internet
deployment.
To introduce effective but sustainable technologies
enabling “network programmability” and realizing the
complete integration with information technologies
is a cornerstone of the Future Internet architecture
Energy Efficiency and Future Network Infrastructure
The Future Internet/5G Challenges
Programmability vs Energy
Efficiency
•
Fixed the silicon technology, energy consumption largely
depends on the number of gates in the network device/
chip hardware.
•
The number of gates is generally directly proportional to
the flexibility and programmability levels of HW
engines.
•
If we fix a target number of gates by using
–  General Purpose CPUs, we obtain:
•  Maximum flexibility,
•  Reduced performance (in the order of 100 Mbps/W)
–  Very specialized ASICs, we obtain:
•  Minimum flexibility
•  Greatly enhanced performance (in the order of 1 Gbps/W)
–  Other technologies (e.g., network/packet processors) provide
performance between these boundaries
Programmability currently is energy consuming! Energy Efficiency and Future Network Infrastructure
The Future Internet/5G Challenges
Programmability for Energy
Efficiency
Costs & greenhouse gas emissions
OPEX & CAPEX
E-sustainability
Scalability
Energy
Efficiency
-  Terabit transport networks
- Very broadband
wireless/fixed accesses
Performance
- Zero loss and very
low latency services
Programmability
/Virtualization
Networks as multi-purpose service-aware infrastructures:
-  Internet of Services
-  Internet of Things
-  Network integrated Cloud Services (SDN)
-  Network-as-a-Service (NFV)
Energy Efficiency and Future Network Infrastructure
The Future Internet/5G Challenges
In-Network Programmability for nextgeneration personal cloUd service supporT
INPUT will enable cloud applications
•  to go beyond classical service models (i.e., IaaS, PaaS, and SaaS)
•  and to replace physical Smart Devices (SD) with their “virtual
images,”
providing them to users “as a Service” (SD as a Service – SDaaS)
The virtual image will allow to reduce the carbon footprint of appliances of
50% - 75%.
Energy Efficiency and Future Network Infrastructure
An example: a new project in H2020
Dis
trib
Openflow redirection,
loadbalancing & network
offload
SW-based & General Purpose HW for
value-added and heterogeneus network
processing
(Software Routers)
Network
Services (e.g.,
IP)
Our vision
Ope
«energy-efficient»
uted
S
network
Pro W RO
ject
uter prototype/
architecture
nf lo
w/F
•  To extend network devices and architectures to Services
directly integrate multiple and heterogeneous
applications, functions and services.
•  Classical or innovative network services/
functions are just software objects dynamically
allocated (e.g., by OpenFlow) to general purpose
or specialized hardware resources.
Acceleration
•  The modularity and flexibility of this approach,
Engines
among others, open the possibility of driving
software object allocation by means of very
effective energy efficient polices.
orC
ES
sign
alin
g
Energy Efficiency and Future Network Infrastructure
An example: SDN, NFV and distributed/
This is a «cloud»
multi-­‐‑core router architectures
«multi-purpose»
Control
Elements
- Allocation on general purpose elements
- Dynamic offloading by means of
accelerators
- Dynamic redirections from accelerators
Given trade-off
between energyconsumption and
QoS per service
Traffic
General
purpose Cores
We control the
interactions with
“OpenFlow in the
Small”
•
The energy consumption in Networks (and more in general in ICT)
is currently still a very relevant issue
•
Trend based on both recent technologies and especially new
innovation challenges (virtualization and performance) are moving
the motivations from environmental impact and cost reduction to
sustainability/scalability
•
Smart power management should be able to give affordable
solutions, but
–  Energy efficiency should be a main target of the new technologies,
not a “simple” constraint.
–  The energy consumption management has to be natively
integrated in network control and management systems like, e.g.,
performance and fault recovery.
–  The integration process acting in Network and IT strongly suggests to
manage this issue (or may be everything) with integrated approaches
(within same unified “tools”)
–  Standard and regulatory actions are essential (including KPI)
Energy Efficiency and Future Network Infrastructure
Conclusions
Any Questions?
Energy Efficiency and Future Network Infrastructure
Thanks for Your Kind Attention