4. What is Big Data ?
Big data” refers to datasets
whose size is beyond the ability
of typical database software
tools to capture, store, manage,
and analyze
7. Intelen
Emerging new company
Differentiation
Focus on next generation Smart Grid IT We optimize the value for
Utility customers over a
Top 100 start-up global (red herring) unified Engagement 2.0
Cloud Platform
Rapid and Adaptive development Services
Big Data Analytics over cloud
LEAN innovation procedures for Demand Response &
Energy efficiency
Many world recognitions Adaptable Environments
Cloud services over IPv6
Presence in Greece, Cyprus and US
User Engagement
Strong Management & Advisory Boards Social Nets, Game
mechanics & Mobile apps
Revenue model
License-based cloud model
over retailer networks
8. Intelen
Intelen’s 3-tier service layers
Advanced algorithmics for Data management
Data Analytics and metering
Ability to handle & visualize Pbytes in real-time
Big Data & Info-graphics
Engage customers using behavioral dynamics
Game mechanics and Social
9. Intelen’s cloud IPv6
Social extensions
Buildings dynamics
with human Game extensions
behaviors
Big Data Analytics
Cloud cross
PVs Analytics platform
EVs
Storage
Harvesting
Industry dynamics
with production
behaviors
Utility MDM
12. Big Data Energy cases - 1
We have variable dynamic data basis: energy
– Target: find correlated customers for pricing
– Question: Find X customers that in a specific
timeframe have the same energy/power peak
based on similar weather conditions…
– Really tough, we need stream analytics
– Result: offer variable energy pricing contracts
according to variable Time-Of-Use (ToU) Demand
– Metrics: pricing ($, euro), Pmax, Pmin,
Timestamps, customer metadata, utility production
costs, SMP, etc
13. Examples: Dynamic pricing
Pricing zones Load profiles
14
12
10
8
6
4
2
0 0
0
0
0
0
0
0
00
00
00
00
00
:0
:0
:0
:0
:0
:0
:0
Time
0:
2:
4:
6:
8:
10
12
14
16
18
20
22
Different ToU ζώνες for each profile / day / week
14. Big Data Energy cases - 2
We have variable dynamic data basis: building
– Target: find optimal energy efficiency strategy
– Question: Find X buildings that in a specific
timeframe have correlated energy efficiency
metrics, according to local climate conditions,
human behaviors and building metadata
– Really tough, we need stream analytics
– Result: offer variable predictive maintenance and
personalized energy efficiency services
– Metrics: KWh/m2, Pmax, Pav, Temp, degreedays,
weather, human behavior, demographics, building
metadata, customer financial data
16. Big Data Energy cases - 3
We have variable dynamic data basis: microgrid
– Target: find optimal RES balancing nodes
– Question: Find X correlated buildings that match
their consumption and peak metrics to Y
Solar/Wind/EVs RES sources in a isolated grid
– Really tough, we need stream analytics
– Result: offer variable nodal pricing, according to the
local RES injection to the grid
– Metrics: RES production, weather conditions,
consumption profiling, nodal pricing, EVs position
(GIS), load grid estimation, etc
19. Intelen Algos insights
, [
C iNj = xi , j yi, j ] gN
⎛1 ⎞
g N =1 = {m1 , m2 K mn }∈ g
→
eiNj = ⎜ ∑ Ed μ
, ⎜n N
⎟
⎟
⎝ i∈d ( n ) ⎠
20. Conclusions
Big data is the future
Data scientists is a future position
Smart grids will move towards IoT
IoT will create a world “data havoc”
Correlations & data fusion the future of Big Data
Soon data variations will project our lives
Trend analytics will predict things