smart cities + energy + ai : edf labs perspectivesmart cities + energy + ai : edf labs perspective...
TRANSCRIPT
IA Symposium 2018
Titre
Smart Cities + Energy + AI :
EDF Labs perspective
Stéphane Tanguy, EDF Labs CIO
1
IA Symposium 2018
Summary
1. EDF Labs introduction
2. EDF Smart City platform
3. Singapore HDB project results
4. Electric mobility
5. Smart charging and AI
2
IA Symposium 2018 3
ELECTRIC Transition
CLIMATE Change
DIGITAL & SOCIAL Transition
Major Forces disrupting the utility industry
IA Symposium 2018 4
ELECTRIC Transition
CLIMATE Change
DIGITAL & SOCIAL Transition
EDF Labs 4 strategic priorities
Source: Newman&Kenworthy
Urban planning as a foundation of Smart CitiesWhy energy providers should get involved from planning stage
Smart cities : energy & comfort
Noise
Results from CEREMA, Study for EIFER &EDF,
2015
Air pollution
Results from Centrale Lyon, Study for EIFER
&EDF, 2015
Urban heat Island
Image LANDSAT des températures à Strasbourg, le
14 juillet 2013. - Capture d’écran ADEUS
Smart cities : supporting urban project introducing energy planning
Prospective for urban
developement
Exogenousscenarios
User scenarios
Simulation+ + =
Initiatives: parameters,
time, location, describing
investments, incentives, or urban policies
Evolution of oil price,
population, interest rates, temperatures
Integratedmodel with
multiple interactions at
each time step
Resultscorresponding
to eachscnenario: Decisionsupport
Time T1
Building refurbishment applied on neighborhood A
Time T2
PV investments applied on buildings X1+X2+…+X22
Time T3
District heating applied on neighborhood B+C+D
Prospective
I EDF I 2013
© 2
012
TH
OM
AS
SINGAPOUR SINGAPORE HDB PROJECT
I EDF I 201310
› Singapour, Housing & Development Board› Refurbishment› New neighborhoods
Strategic recommendationsKPI definitionTechnology choicesScenariosLong term impacts
Decision support platform Initiative parameters Precise scenarios Impact simulation Results analysis 3D visualisation
Yuhua (refurbish.)– 38 buildings
……(new) – 800 buildings
SINGAPORE HDB PROJECT
Implement Greenery to reduce cooling needs
Green Home Package to improve energy efficiency of appliances
Improve technology of Light in common areas with LED
Install PV panels to produce local energy Energy
EfficiencyUp to -12% Energy
Cons.
Green Energy~ 2,700 MWh/yr
prod.
CO2 -30 %
Costs SGD xxxK investment
PROJECT RESULTS
Electric Mobility : opportunity and challenges for cities and
utilities and where IA can help
Why Electric Vehicle charging should better be smart !
France 2035 scenario : 9 Million Electric Vehicles
• 30% of national vehicles fleet• 5% of national electricity consumption
• Without charging optimization : 20% of peak consumption
• without charging optimization : 5% of peak consumption !!
Smart management of EV charging offers multiple services opportunity for the electric system :
• Supply and demand equilibrium• Frequency and voltage regulation
• Absorption of renewable production surplus
Plug & chargeBasic control
with price signals
Advanced control at the building
level
Advanced control at the electricsystem level
Advanced control with bidirectional
power flow
Different smart charging strategies to accompany each step of EV roll-out:
IA Symposium 2018 14
Problem statement : How to optimize district EV charging in order to take into
account electric network constraints ?
Proposal : leverage reinforcement learning to train an EV charging algorythm
(home controller) taking into account home electricity consumption, mobility
habits, home presence, price signal ..
Results after 300 iterations : vehicle always charged, cost optimized, 1 charge
period
Perspectives :
- Adapt algorythm to specific EV owner requirement (tipical schedule, charging
rish aversion, cost aversion ..)
- Fleet management with Pmax constraint (charging operator, 1 central
controller)
- Complete district optimization with PowerFlow constraint (DSO use case)
- Multi agent modelisation at district scale
Leveraging AI to turn charging smart !