Top Banner
Artificial Intelligence & Energy Bertrand Cornélusse, Raphaël Fonteneau 1
38

Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Sep 20, 2019

Download

Documents

dariahiddleston
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Artificial Intelligence & Energy

Bertrand Cornélusse, Raphaël Fonteneau

1

Page 2: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

TheSmartgridsteamispartoftheMontefioreResearchUnitoftheULg,containsaround15researchersandisheadedbyPr.DamienErnst

http://blogs.ulg.ac.be/damien-ernst2

Page 3: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

OurvisionofArtificialIntelligence

3

Page 4: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Roadmap

Artificial intelligence

OptimizationMachine learning

Reinforcement learning

4

Page 5: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Roadmap

Machine learning

5

Page 6: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Machinelearningisaboutextracting{patterns,knowledge,information}fromdata

Clusterimages

SIRICortona OK Google

Convertvoicesignalintosentences

Makeon-linerecommandations

Recognizepatternsinimages

Interpretsentences

Google photos

6

Page 7: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Machinelearningstudiesandbuildsalgorithmsthatlearnfromandmakepredictionsondata

SupervisedLearninginanutshell:

Imagineyouhaveasetofdata {(x1, y1), (x2, y2), …, (xn, yn)}

represented by black points on thefigure.

To be able to estimate the value of anoutputy for any inputx, You “train” aMachineLearningalgorithmusingthesedata.Youobtaintheblueline.

Thequalityoftheestimatedependsondataquality/quantity:withmorepoints,e.g. the black circles, you would forinstancegettheredcurve.

7

x

y

Page 8: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Recentadvancesinmachinelearning

Machinelearningalgorithmshaverecentlyshownimpressiveresults,inparticularwhen input data are images: this has led to the identification of a subfield ofMachineLearningcalledDeepLearning.

The term “deep” refers to the fact that those learning architectures, mainlyArtificialNeuralNetworks,aremadeofseverallayers.

Zoom on a neuron

8

Page 9: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Deepneuralnetworkarchitectures

Source: http://www.ais.uni-bonn.de/deep_learning/images/Convolutional_NN.jpg

9

Page 10: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Wait…ANNarenotnew,right?

ANNdatebacktothesixties.TrainingANNwasnotaneasytaskuntilrecently.Recentprogressistwofold:

• Smart(er)trainingapproaches• GPUcalculus

10

Page 11: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Optimization

Artificial intelligence

Roadmap

Machine learning

Reinforcement learning

11

Page 12: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Fromsupervisedlearningtoreinforcementlearning

Supervisedlearningtechniques(inparticular(deep)convolutionalnetworks)maybeusedas a block in a more complex structure, inparticular in Dynamic Programming (DP) orModelPredictiveControl(MPC)schemes.

This connects to reinforcement learning, anarea of machine learning originally inspiredby behaviorist psychology, concerned withhowsoftwareagentsoughttotakeactionsinan environment so as to maximize somenotionofcumulativereward.

Deepreinforcementlearningcombinesdeeplearning with reinforcement learning (and,consequently,inDP/MPCschemes).

12

Agent

Environment

ActionReward

Page 13: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

PlayingAtariwithdeepreinforcementlearning

13

At Google Deepmind At ULg

Human-levelcontrolthroughdeepreinforcementlearning.Nature,2015.VolodymyrMnih,KorayKavukcuoglu,DavidSilver,AndreiA.Rusu,JoelVeness,MarcG.Bellemare,AlexGraves,MartinRiedmiller,AndreasK.Fidjeland,GeorgOstrovski,StigPetersenCharlesBeattie,AmirSadik,IoannisAntonoglou,HelenKing,DharshanKumaran,DaanWierstra,ShaneLegg&DemisHassabis

Page 14: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Breakingnews

Recentbreakthroughs in the fieldofAI for thegameofGOhavebeendonebyGoogleDeepmind.

These results have been obtained by combining Deep Convolutional NetworkswithMonteCarloTreeSearchtechniques.

Theresultingagent,AlphaGo,achieved99.8%winningrateagainstotherGOAI,anddefeatedtheEuropeanGochampionby5gamesto0.

14

MasteringthegameofGowithdeepneuralnetworksandtreesearch.Nature,2016.DavidSilver,AjaHuang,ChrisJ.Maddison,ArthurGuez,LaurentSifre,GeorgevandenDriessche,JulianSchrittwieser,IoannisAntonoglou,VedaPanneershelvam,MarcLanctot,SanderDieleman,DominikGrewe,JohnNham,NalKalchbrenner,IlyaSutskever,TimothyLillicrap,MadeleineLeach,KorayKavukcuoglu,ThoreGraepel&DemisHassabis

Page 15: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Wanttoknowmore?

Googleislaunchinganewdeeplearningcourse(incollaborationwithUdacity):https://www.udacity.com/course/deep-learning--ud730

YoumayalsobeinterestedinNVidiaDeepLearningcourse:https://developer.nvidia.com/deep-learning-courses

OrevenStanfordMoocaboutMachineLearning:https://www.coursera.org/learn/machine-learning

15

Page 16: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Optimization

Artificial intelligence

Roadmap

Machine learning

Reinforcement learning

16

Page 17: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Optimization: decide the values that some variables can take,underasetofcontraints,soastomaximizeanobjective.

A long tradition of numerical solutions and theoretical analysis.Givenassumptionsonmodels,onecaneventuallygetguaranteesaboutsolutions.

Howisoptimizationconnectedtomachinelearning?Learningproblemscanbecastedasoptimizationproblems

Howismachinelearningconnectedtooptimization?Machine learning actually solves some (or part of) optimizationproblems(e.g:RL,ortuningofanalgo,orproxytoanalgo)

Machinelearningistightlycoupledtooptimization

17

Page 18: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Machinelearningistightlycoupledtooptimization

Anillustrationofthesimplexalgorithm. The simplexalgorithmwasinventedbyG.Dantzig. Itdatesback to thesecondworldwar.

This can be used to solvemany practical optimizationproblems.

18

Page 19: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

set NUTRIENT ordered; set FOOD ordered;

param cost {FOOD} >= 0; param minNutrient {NUTRIENT} >= 0; param maxNutrient {i in NUTRIENT} >= minNutrient[i]; param amount {NUTRIENT,FOOD} >= 0;

# Variables var Buy {j in FOOD} integer;

# Objective minimize Total_Cost: sum {j in FOOD} cost[j] * Buy[j];

(or minimize nutrient_amount {i in NUTRIENT}: sum {j in FOOD} amount[i,j] * Buy[j];)

# Constraints subject to Diet {i in NUTRIENT}: minNutrient[i] <= sum {j in FOOD} amount[i,j] * Buy[j] <= maxNutrient[i];

Optimizationreliesonananalyticalmodel...

Example: Building the lunch menu, a first application of AI for energy ;)

19

Page 20: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

set NUTRIENT ordered; set FOOD ordered;

param cost {FOOD} >= 0; param minNutrient {NUTRIENT} >= 0; param maxNutrient {i in NUTRIENT} >= minNutrient[i]; param amount {NUTRIENT,FOOD} >= 0;

# Variables var Buy {j in FOOD} integer;

# Objective minimize Total_Cost: sum {j in FOOD} cost[j] * Buy[j];

(or minimize nutrient_amount {i in NUTRIENT}: sum {j in FOOD} amount[i,j] * Buy[j];)

# Constraints subject to Diet {i in NUTRIENT}: minNutrient[i] <= sum {j in FOOD} amount[i,j] * Buy[j] <= maxNutrient[i];

Optimizationreliesonananalyticalmodel...

Example: Building the lunch menu, a first application of AI for energy ;)

+ Data

Your lunch menu

20

Page 21: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Optimizationreliesonananalyticalmodel,machinelearningmaynot

+

+

+

21

Page 22: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

OptimizationandMachinelearninghavedifferentaims

Intheoptimizationworld,amethodtargetsoneproblemclass,orevenaninstanceofaproblem,andatheoryisobsessedbyoptimality(canIproveitmathematically?)andefficiency(canIcomputeitefficiently?)

Machinelearningisfocusedonstatisticalsignificance(reachinga trade off between overfitting and “misrepresentation”),replicability to other problems with few adaptation, andinterpretabilityofresults

22

Page 23: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Roadmap

Artificial intelligence

OptimizationMachine learning

Reinforcement learning

23

Page 24: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Energeticapplications

24

Page 25: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Worldenergyconsumptionoutlookaround2010

Fossil fuels Nuclear Renewables

Biomass heatSolar hotwaterGeothermal heatHydropowerEthanolBiodieselBiomass electricityWind powerGeothermal electricitySolar PV powerSolar CSPOcean powerSources: IEA

25

Page 26: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

OptimizationhasplentyofapplicationsintheEnergyindustry

Electricalpowersystems:• Productionplanning:unitcommitment• Managinggridconstraints:optimalpowerflow

Oilandgasindustry:• Wheretodig?Inwhichsequence?

Logisticsandtransportation:• VehicleRoutingProblems

Industrialprocesses:• Reductionordisplacementofenergyconsumption

26

Page 27: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Example:Day-aheadelectricitypricesinEuropearedeterminedbyEuphemia

EUPHEMIA is the market coupling algorithm for European Power exchanges, implemented and developed in-house by N-SIDE, a spin-off of UCL and ULg

Used daily by Power Exchanges to fix pan-EU day-ahead electricity prices in 19 EU countries.

Computing market prices & volumes by: • coupling national markets • maximizing total economical welfare • optimizing network capacity utilization • modeling complex economical constraints

Extension to whole Europe in progress

http://energy.n-side.com/day-ahead/

27

Page 28: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

EvolutionoftheenergysystemGlobal Grid(s) versus Microgrids

Prof. Damien Ernst - University of LiègeELIA Stakeholders͛ days

28

Page 29: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Fromdecentralization…

29

Page 30: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Fromdecentralizationtocentralization

30

Page 31: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Fromdecentralizationtocentralization,andback

31

Page 32: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

WhyarewenowtalkingaboutAI,andnotjustaboutoptimization?

Wearenowtryingtooptimizemoreandmorelocally,becauserenewable energy sources are distributed, data is ubiquitousandcomputationpoweraswell.

However,theratio“gain/(timetospendforgatheringthedataand solving the problem)” is way smaller than for largecentralizedprojects.

AI offers the possibility to automate the data gathering,modelingandoptimizationstages.Forinstance,learnfromthehabitsofusersofahouse,proposesomecarpoolingoptions,correlateallthiswithcalendarevents.

32

Page 33: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Rethinkingtheoperationofdistributionsystems

Activenetworkmanagement.Smart modulation of generation sources, loads and storages so as to operatesafelytheelectricalnetworkwithouthavingtorelyonsignificant investments ininfrastructure.

GREDORproject.Redesigning in an integrated way the whole decision chain used for managingdistributionnetworksinordertoperformactivenetworkmanagementoptimally(i.e.,maximisationofsocialwelfare).

www.gredor.be

33

Page 34: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

Empoweringconsumersanddistributedgeneration

Microgrids aremodern, localized, small-scalegrids, contrary to the traditional, centralizedelectricitygrid(macrogrid).

Some microgrids can operate disconnectedfrom the centralized grid and operateautonomously, strengthen grid resilience andhelpmitigategriddisturbances.

Optimizing the sizing and the operation of amicrogrid requires both optimization and AItechniques.

34

Page 35: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

35Smart lighting

Smart homes

Smart mobility

SmartCities

Smart sensors

Wireless communication

Page 36: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

UrbanAgriculture

36

Page 37: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

So,whyusingaPVpanelasagoban?

37

Page 38: Artificial Intelligence & Energy · Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran,

ReferencesHowtodiscountdeepreinforcementlearning:towardsnewdynamicstrategies.V.François-Lavet,R.Fonteneau,D.Ernst.DeepReinforcementLearningWorkshop,NIPS2015.http://arxiv.org/abs/1512.02011

Benchmarkingforbayesianreinforcementlearning.M.Castronovo,D.Ernst,A.Couëtoux,R.Fonteneau,http://arxiv.org/pdf/1509.04064.pdf

ImitativeLearningforOnlinePlanninginMicrogrids.S.Aittahar,V.François-Lavet,S.Lodeweyckx,D.Ernst,R.Fonteneau.DataAnalyticsforRenewableEnergyIntegration,Volume9518oftheseriesLectureNotesinComputerSciencepp1-15,2015.

Theglobalgrid.S.Chatzivasileiadis,D.Ernst,G.Andersson.RenewableEnergy,Volume57,September2013,Pages372–383.

GlobalGrid(s)versusMicrogrids.Ernst,D.http://hdl.handle.net/2268/188217

TheGREDORproject.Redesigningthedecisionchainformanagingdistributionnetworks.Ernst,D.http://hdl.handle.net/2268/188487

Activenetworkmanagementforelectricaldistributionsystems:problemformulationandbenchmark.Gemine,Q.,Ernst,D.,&Cornélusse,B.(2014).arXivpreprintarXiv:1405.2806.

DSIMA:Atestbedforthequantitativeanalysisofinteractionmodelswithindistributionnetworks.Mathieu,S.,Louveaux,Q.,Ernst,D.,&Cornélusse,B.(2016).SustainableEnergy,GridsandNetworks,5,78-93.

ActiveManagementofLow-VoltageNetworksforMitigatingOvervoltagesDuetoPhotovoltaicUnits.Olivier,F.,Aristidou,P.,Ernst,D.,VanCutsem,T.IEEETransactionsonSmartGrid,2016.

Supervisedlearningofintra-dailyrecoursestrategiesforgenerationmanagementunderuncertainties.Cornélusse,B.,Vignal,G.,Defourny,B.,&Wehenkel,L.(2009,June).InPowerTech,2009IEEEBucharest(pp.1-8).IEEE.

38