Scaling Energy Adaptive Applications for Sustainable Profitability - - PowerPoint PPT Presentation
Scaling Energy Adaptive Applications for Sustainable Profitability Fabien Hermenier , Giovanni Giuliani, Andre Milani, Sophie Demassey Let existing and new data centres become energy adaptive Adapting the power consumption to the availability
Fabien Hermenier, Giovanni Giuliani, Andre Milani, Sophie Demassey
Let existing and new data centres become energy adaptive
Being adapted to the requests of a Smart City Energy Management Authority Adapting the power consumption to the availability of renewable energy
Client Energy authority
regulate energy usage
An economical approach to avoid
best performance
forecasts energy providers sustainable objective
Easc
application descriptor elected working modes smart city authority
Easc
...
web service video transcoder
energy adaptive applications
Orchestrates EASC for profitable sustainability Optimises over 24-hrs time window (96 time-slots of 15 minutes) Called every 15 minutes to accommodate uncertainty
[ucc 2015]
Per time-slot data or forecasts for the next 24 hours % issues from renewable sources price capacity
day-to-day periods Objective
Regulate energy usage through contracts
Incentive
At least X% renewable, Power budget, … Penalty function (flat, linear, composite)
Smart city energy authority
EASC characterisation
daily-based deferrable workloads
Service Level Objectives
flat or linear pricing policies slot-based non-deferrable workloads
performance level power consumption transition cost actuator
The working modes
discretise elastic applications states manual or automatic calibration
3 use cases inside DC4Cities
Webservice, video transcoding, e-health
For every time-slot find 1 working mode per EASC using available energy (viable dispatch)
+ transition costs + various Energy Authority policies + Instant and cumulative objectives + generic pricing policies
96 NP-hard bin-packing problems to solve
I dont want a heuristic full of corner cases
the right model for the right problem deterministic composition high-level constraints
An Open-Source java library for constraint programming
time 5 6 7 8 9 10 11 12
An automaton to model each EASC life-cycle Counters to accumulate daily incomes
Modelling - TLDR;
∞
Energy to use is dispatched among the sources Energy authority pricing policy
Working mode
Trading energy, performance and energy authority conformance to maximise the daily running costs
real deployments 3 testbeds running production softwares
CSUC @ Barcelona Video transcoding
Trento @ Italy e-health Openstack
Web service Mixed EASCs Bare metal HP Lab @ Milan
20 HP moonshot cartridges in 2 chassis no virtualisation layer 20 Watts peak 8m2 of solar panels 4 typical days from a 1 y. data collect
200 400 600 16/01 17/01 18/01 19/01 20/01
Date Power (W)
25 50 75 100 16/01 17/01 18/01 19/01 20/01
Date renewable power (%)
65% renewable target 100€ / pp. un-pure energy market price The grid The green Energy authority expectations
1000 1500 2000 2500 3000 23:00 05:00 11:00 17:00 23:00
Time Request/s
e-learning courses for Entrepreneurs instant SLO 6 working modes penalty from a step function Injectors mimic the production workload production software stack with 3 EASCs
Web service
cumulative SLOs 3 working modes penalty from a linear function
E-learning, G-learning
Production mode Cache built at midnight Lowest suitable working mode for the WebSite
Most efficient working mode when renewable energy is here Lowest otherwise
Sustainable profitability
100 200 300 400 500 16/01 17/01 18/01 19/01 20/01
Date Watts application
E−learning G−indexing Website
Perf Green Carver
B a t c h a c t i v i t i e s f
l
t h e s u n G r e e n i s b i n a r y
Ignores energy availability Workload affinity: human work during days
200 400 16/01 17/01 18/01 19/01 20/01
Date Watts application
E−learning G−indexing Website 200 400 16/01 17/01 18/01 19/01 20/01
Date Watts application
E−learning G−indexing Website
17/01/15 18/01/15 19/01/15 20/01/15
64.2 65.6 67.7 55.6 57.9 58.5 53.9 56.7 57.3 45.7 46.8 47.4
40 50 60 70
p e r f C a r v e r g r e e n p e r f C a r v e r g r e e n p e r f C a r v e r g r e e n p e r f C a r v e r g r e e n
renewable %
17/01/15 18/01/15 19/01/15 20/01/15
1999 1466 1999 1999 1352 1933 1999 1305 1936 1999 1072 1955
500 1000 1500 2000
perf green Carver perf green Carver perf green Carver perf green Carver
SLO penalty (euros)
Carver sticked to the green threshold Carver sticked to the SLO
Customer incomes
max achievement % renewable
Green neglects the clients Perf neglects the energy authority Carver trades
17/01/15 18/01/15 19/01/15 20/01/15
1000 2000
p e r f g r e e n C a r v e r p e r f g r e e n C a r v e r p e r f g r e e n C a r v e r p e r f g r e e n C a r v e r
Running cost (euros) expense
energy SLO SMA
17/01/15 18/01/15 19/01/15 20/01/15
1000 2000
p e r f g r e e n C a r v e r p e r f g r e e n C a r v e r p e r f g r e e n C a r v e r p e r f g r e e n C a r v e r
Running cost (euros) expense
energy SLO SMA
The balance is still slightly pure performance oriented
nothing to do to please the energy authority (natural workload affinity) @Day 1 @Day 4 Only minor trading possibilities
every price <<< pricing policies to avoid bankruptcy
Energy price does not play a role small data centres human resources / software support dominates
17/01/15 18/01/15 19/01/15 20/01/15
1000 2000
p e r f g r e e n C a r v e r p e r f g r e e n C a r v e r p e r f g r e e n C a r v e r p e r f g r e e n C a r v e r
Running cost (euros) expense
energy SLO SMA
being generic is costly
CP composability helps but data makes the problem static analysis for stronger models
require favorable hardware and software
variable working modes energy-efficient hardware
a multifacet tool
PV array sizer cost modelling prospective deployment
A flexible solving algorithm to cope with the problem variability A multi-faceted tool Conciliation possibilities validated
http:/ /www.dc4cities.eu
deliverables, scientific publications, trial results, software repositories