Eco-friendly Reduction of Travel Times in European Smart Cities (GECCO'14)

Daniel H. Stolfi
Daniel H. StolfiResearch Associate
ECO-FRIENDLY REDUCTION OF TRAVEL TIMES 
IN EUROPEAN SMART CITIES 
Daniel H. Stolfi 
dhstolfi@lcc.uma.es 
Enrique Alba 
eat@lcc.uma.es 
Departamento de Lenguajes y Ciencias de la Computación 
University of Malaga 
Genetic and Evolutionary Computation Conference 
July 2014 
Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 1 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
CONTENTS 
1 INTRODUCTION 
2 PROPOSAL 
3 EXPERIMENTS 
4 CONCLUSIONS 
Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 2 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
INTRODUCTION 
Nowadays there is a higher amount of vehicles in streets 
The number of traffic jams is increasing 
Tons of air pollutants are emitted to the atmosphere 
The inhabitants’ health and quality of life is decreasing 
Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 3 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
Red Swarm 
Architecture 
Case Studies 
Evolutionary Algorithm 
RED SWARM 
Our proposal, Red Swarm, consists of: 
A few spots distributed throughout the city 
I Installed at traffic lights 
I Linked to vehicles by using Wi-Fi 
Our Evolutionary Algorithm 
Our Rerouting Algorithm 
Several User Terminal Units 
I They visualize the alternatives routes 
suggested 
I They could be smartphones, tablets, or 
On Board Units 
Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 4 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
Red Swarm 
Architecture 
Case Studies 
Evolutionary Algorithm 
RED SWARM 
Red Swarm offers: 
Personalized information for each vehicle (online, distributed) 
Prevention of traffic jams 
Reduction of greenhouse gas emissions 
Sensing of the city’s state 
Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 5 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
Red Swarm 
Architecture 
Case Studies 
Evolutionary Algorithm 
RED SWARM ARCHITECTURE 
Configuration: 
Spot’s configuration is calculated by the Evolutionary Algorithm (offline) 
Deployment and Use: 
Spots suggest new alternative routes to vehicles (online) 
Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 6 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
Red Swarm 
Architecture 
Case Studies 
Evolutionary Algorithm 
RED SWARM SPOT 
Connects with vehicles and suggests alternative routes 
Runs an instance of the Rerouting Algorithm 
S1 and S2 are the Input Streets where vehicles arrive the junction 
An output street is selected according to the probability value calculated 
by our EA. 
Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 7 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
Red Swarm 
Architecture 
Case Studies 
Evolutionary Algorithm 
REROUTING EXAMPLE 
Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 8 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
Red Swarm 
Architecture 
Case Studies 
Evolutionary Algorithm 
SCENARIO BUILDING 
We work with real maps imported from OpenStreetMap 
We clean the irrelevant elements by using JOSM 
We define the vehicle flows (experts’ solution) by using DUAROUTER 
We import the city model into SUMO by using NETCONVERT 
Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 9 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
Red Swarm 
Architecture 
Case Studies 
Evolutionary Algorithm 
CASE STUDIES (I) 
Malaga 
I 2.5 Km2 
I 262 traffic lights 
I 10 Red Swarm spots 
I 1200 vehicles 
I 169 routes 
Stockholm 
I 2.9 Km2 
I 498 traffic lights 
I 12 Red Swarm spots 
I 1400 vehicles 
I 131 routes 
Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 10 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
Red Swarm 
Architecture 
Case Studies 
Evolutionary Algorithm 
CASE STUDIES (II) 
Berlin 
I 7 Km2 
I 770 traffic lights 
I 10 Red Swarm spots 
I 1300 vehicles 
I 122 routes 
Paris 
I 5.6 Km2 
I 575 traffic lights 
I 10 Red Swarm spots 
I 1200 vehicles 
I 125 routes 
Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 11 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
Red Swarm 
Architecture 
Case Studies 
Evolutionary Algorithm 
SYSTEM CONFIGURATION 
If a vehicle which is driving to Destination 2 enters by Street 1 
in the coverage area of a red swarm spot, a new route will be 
suggested by the Rerouting Algorithm according to the 
probability values stored in the system configuration. 
Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 12 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
Red Swarm 
Architecture 
Case Studies 
Evolutionary Algorithm 
STATUS VECTOR 
It represents the configuration of the N streets which are input 
to a junction controlled by a red swarm spot. There are M 
chunks of probabilities values in each street block in order to 
hold different configurations depending on the vehicles’ final 
destination. 
Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 13 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
Red Swarm 
Architecture 
Case Studies 
Evolutionary Algorithm 
EVOLUTIONARY ALGORITHM 
The result of the algorithm is the configuration for all 
the spots 
The configuration is calculated in the offline stage. 
(10+2)-EA 
Evaluates individuals by using the SUMO traffic 
simulator 
The rerouting made by the Rerouting Algorithm is 
implemented in SUMO by TraCI. 
Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 14 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
Red Swarm 
Architecture 
Case Studies 
Evolutionary Algorithm 
FITNESS FUNCTION 
F = 1(  n) + 
+ 2 
1 
n 
Xn 
i=1 
COi + 3 
1 
n 
Xn 
i=1 
CO2i + 4 
1 
n 
Xn 
i=1 
HCi + 
+ 5 
1 
n 
Xn 
i=1 
PMi + 6 
1 
n 
Xn 
i=1 
NOi + 7 
1 
n 
Xn 
i=1 
Fueli (1) 
: Total amount of vehicles 
n: Vehicles that end their itinerary during the period analyzed 
1 to 7: Normalize each variable 
The lower, the better 
Daniel H. Stolfi  Enrique Alba Eco-friendly Reduction of Travel Times. . . 15 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
Results 
50 Scenarios 
Graphs 
AVERAGE AND BEST IMPROVEMENTS 
We have reduced the CO, CO2, HC, PM, and NO emissions 
We have also reduced travel times and fuel consumption 
Case Study T:Time CO CO2 HC PM NO Fuel 
Malaga 5.5% 4.1% -1.5% 3.0% 0.9% -1.8% -1.6% 
Average Stockholm 14.2% 12.6% 3.2% 11.0% 8.5% 3.0% 3.0% 
50 Berlin 11.7% 10.6% 1.7% 8.7% 6.0% 1.5% 1.6% 
scenarios Paris 4.1% 2.2% 0.2% 1.8% 1.1% -0.1% 0.2% 
Average 8.9% 7.4% 0.9% 6.1% 4.1% 0.7% 0.8% 
Malaga 12.2% 11.3% 4.1% 10.2% 9.9% 5.7% 4.0% 
Best Stockholm 17.5% 16.1% 7.1% 16.1% 16.7% 10.2% 6.8% 
improvement Berlin 13.9% 13.2% 4.8% 13.3% 14.5% 7.9% 4.6% 
achieved Paris 8.9% 11.6% 3.8% 10.4% 5.1% 3.9% 3.8% 
Average 13.1% 13.0% 5.0% 12.5% 11.5% 6.9% 4.8% 
Daniel H. Stolfi  Enrique Alba Eco-friendly Reduction of Travel Times. . . 16 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
Results 
50 Scenarios 
Graphs 
PERCENTAGE OF SCENARIOS IMPROVED 
We have improved more than 58% of 200 scenarios on average 
Case Study T:Time CO CO2 HC PM NO Fuel 
Malaga 90.0% 88.0% 24.0% 82.0% 58.0% 36.0% 22.0% 
% Stockholm 100.0% 100.0% 92.0% 100.0% 98.0% 78.0% 92.0% 
scenarios Berlin 100.0% 100.0% 90.0% 100.0% 98.0% 74.0% 84.0% 
improved Paris 94.0% 74.0% 52.0% 74.0% 66.0% 46.0% 50.0% 
Average 96.0% 90.5% 64.5% 89.0% 80.0% 58.5% 62.0% 
Each scenario consists of different traffic distributions 
We have worked with 50 different scenarios of each case study (200) 
Daniel H. Stolfi  Enrique Alba Eco-friendly Reduction of Travel Times. . . 17 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
Results 
50 Scenarios 
Graphs 
ACCUMULATED VALUES OF THE VEHICLES’ EMISSIONS 
CO [g] 
PM [g] 
CO2 [Kg] 
NO [g] 
HC [g] 
Fuel [l] 
Daniel H. Stolfi  Enrique Alba Eco-friendly Reduction of Travel Times. . . 18 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
CONCLUSIONS AND FUTURE WORK 
We have addressed the reduction of greenhouse gas emissions, travel 
times and fuel consumption in Malaga, Stockholm, Berlin, and Paris 
We have designed an effective evolutionary algorithm to optimize the 
scenarios 
Our proposal has achieved average reductions up to 13.0% in CO, 
12.5% in HC, 11.5% in PM, and above 5% in the rest of emissions and 
fuel consumption 
Additionally, we have shortened travel times up to 13.1% on average 
Results were influenced by the different characteristics of vehicles as 
well as the distribution of the cities’ streets 
As a matter for future work, we are testing different strategies to further 
improve upon our results 
We are also implementing the rerouting by city districts to be able to 
install Red Swarm throughout the entire city 
Daniel H. Stolfi  Enrique Alba Eco-friendly Reduction of Travel Times. . . 19 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
http://neo.lcc.uma.es 
http://danielstolfi.com/redswarm/ 
Daniel H. Stolfi  Enrique Alba Eco-friendly Reduction of Travel Times. . . 20 / 20
Introduction 
Proposal 
Experiments 
Conclusions 
http://neo.lcc.uma.es 
http://danielstolfi.com/redswarm/ 
Questions? 
Daniel H. Stolfi  Enrique Alba Eco-friendly Reduction of Travel Times. . . 20 / 20
1 of 21

Recommended

Red Swarm: Smart Mobility in Cities with EAs (GECCO'13) by
Red Swarm: Smart Mobility in Cities with EAs (GECCO'13)Red Swarm: Smart Mobility in Cities with EAs (GECCO'13)
Red Swarm: Smart Mobility in Cities with EAs (GECCO'13)Daniel H. Stolfi
2.1K views36 slides
Bio-inspired Computing and Smart Mobility by
Bio-inspired Computing and Smart MobilityBio-inspired Computing and Smart Mobility
Bio-inspired Computing and Smart MobilityDaniel H. Stolfi
741 views108 slides
Smart Mobility Policies with Evolutionary Algorithms: The Adapting Info Panel... by
Smart Mobility Policies with Evolutionary Algorithms: The Adapting Info Panel...Smart Mobility Policies with Evolutionary Algorithms: The Adapting Info Panel...
Smart Mobility Policies with Evolutionary Algorithms: The Adapting Info Panel...Daniel H. Stolfi
734 views67 slides
The Simulation of Reduced Scale Automotive Mock-up Applied to Drag Reduction ... by
The Simulation of Reduced Scale Automotive Mock-up Applied to Drag Reduction ...The Simulation of Reduced Scale Automotive Mock-up Applied to Drag Reduction ...
The Simulation of Reduced Scale Automotive Mock-up Applied to Drag Reduction ...Altair
734 views26 slides
Mixed Integer Linear Programming Formulation for the Taxi Sharing Problem by
Mixed Integer Linear Programming Formulation for the Taxi Sharing ProblemMixed Integer Linear Programming Formulation for the Taxi Sharing Problem
Mixed Integer Linear Programming Formulation for the Taxi Sharing Problemjfrchicanog
961 views14 slides
Predicting Car Park Occupancy Rates in Smart Cities by
Predicting Car Park Occupancy Rates in Smart CitiesPredicting Car Park Occupancy Rates in Smart Cities
Predicting Car Park Occupancy Rates in Smart CitiesDaniel H. Stolfi
780 views81 slides

More Related Content

Similar to Eco-friendly Reduction of Travel Times in European Smart Cities (GECCO'14)

Dr Glyn Rhys-Tyler - Road vehicle exhaust emissions; 'an age of uncertainty' ... by
Dr Glyn Rhys-Tyler - Road vehicle exhaust emissions; 'an age of uncertainty' ...Dr Glyn Rhys-Tyler - Road vehicle exhaust emissions; 'an age of uncertainty' ...
Dr Glyn Rhys-Tyler - Road vehicle exhaust emissions; 'an age of uncertainty' ...IES / IAQM
401 views30 slides
Eco dynamics green_city_logistics_strategies by
Eco dynamics green_city_logistics_strategiesEco dynamics green_city_logistics_strategies
Eco dynamics green_city_logistics_strategiesEcoDynamics Greece
262 views14 slides
The real fleet and real driving emissions by
The real fleet and real driving emissionsThe real fleet and real driving emissions
The real fleet and real driving emissionsInstitute for Transport Studies (ITS)
911 views19 slides
Computing New Optimized Routes for GPS Navigators Using Evolutionary Algorithms by
Computing New Optimized Routes for GPS Navigators Using Evolutionary AlgorithmsComputing New Optimized Routes for GPS Navigators Using Evolutionary Algorithms
Computing New Optimized Routes for GPS Navigators Using Evolutionary AlgorithmsDaniel H. Stolfi
340 views78 slides
STEP Conference 2016 - James Tate, ITS - The Real Fleet & Their Real Driving ... by
STEP Conference 2016 - James Tate, ITS - The Real Fleet & Their Real Driving ...STEP Conference 2016 - James Tate, ITS - The Real Fleet & Their Real Driving ...
STEP Conference 2016 - James Tate, ITS - The Real Fleet & Their Real Driving ...STEP_scotland
221 views19 slides
James Tate - DMUG 2014 by
James Tate -  DMUG 2014James Tate -  DMUG 2014
James Tate - DMUG 2014IES / IAQM
1.4K views25 slides

Similar to Eco-friendly Reduction of Travel Times in European Smart Cities (GECCO'14)(20)

Dr Glyn Rhys-Tyler - Road vehicle exhaust emissions; 'an age of uncertainty' ... by IES / IAQM
Dr Glyn Rhys-Tyler - Road vehicle exhaust emissions; 'an age of uncertainty' ...Dr Glyn Rhys-Tyler - Road vehicle exhaust emissions; 'an age of uncertainty' ...
Dr Glyn Rhys-Tyler - Road vehicle exhaust emissions; 'an age of uncertainty' ...
IES / IAQM401 views
Eco dynamics green_city_logistics_strategies by EcoDynamics Greece
Eco dynamics green_city_logistics_strategiesEco dynamics green_city_logistics_strategies
Eco dynamics green_city_logistics_strategies
EcoDynamics Greece262 views
Computing New Optimized Routes for GPS Navigators Using Evolutionary Algorithms by Daniel H. Stolfi
Computing New Optimized Routes for GPS Navigators Using Evolutionary AlgorithmsComputing New Optimized Routes for GPS Navigators Using Evolutionary Algorithms
Computing New Optimized Routes for GPS Navigators Using Evolutionary Algorithms
Daniel H. Stolfi340 views
STEP Conference 2016 - James Tate, ITS - The Real Fleet & Their Real Driving ... by STEP_scotland
STEP Conference 2016 - James Tate, ITS - The Real Fleet & Their Real Driving ...STEP Conference 2016 - James Tate, ITS - The Real Fleet & Their Real Driving ...
STEP Conference 2016 - James Tate, ITS - The Real Fleet & Their Real Driving ...
STEP_scotland221 views
James Tate - DMUG 2014 by IES / IAQM
James Tate -  DMUG 2014James Tate -  DMUG 2014
James Tate - DMUG 2014
IES / IAQM1.4K views
Fine Tuning of Traffic in Our Cities with Smart Panels: The Quito City Case S... by Daniel H. Stolfi
Fine Tuning of Traffic in Our Cities with Smart Panels: The Quito City Case S...Fine Tuning of Traffic in Our Cities with Smart Panels: The Quito City Case S...
Fine Tuning of Traffic in Our Cities with Smart Panels: The Quito City Case S...
Daniel H. Stolfi341 views
RapidAIR- a new urban dispersion modelling platform for air quality analysis ... by Scott Hamilton
RapidAIR- a new urban dispersion modelling platform for air quality analysis ...RapidAIR- a new urban dispersion modelling platform for air quality analysis ...
RapidAIR- a new urban dispersion modelling platform for air quality analysis ...
Scott Hamilton751 views
European Green Cars Initiative Projects HELIOS Proposal Paper (July 2012) by Andrew Gelston
European Green Cars Initiative Projects HELIOS Proposal Paper (July 2012)European Green Cars Initiative Projects HELIOS Proposal Paper (July 2012)
European Green Cars Initiative Projects HELIOS Proposal Paper (July 2012)
Andrew Gelston381 views
High energy lithium ion storage solutions by Andrew Gelston
High energy lithium ion storage solutionsHigh energy lithium ion storage solutions
High energy lithium ion storage solutions
Andrew Gelston451 views
Dr James Tate - Better estimation of vehicle emissions for modelling - DMUG17 by IES / IAQM
Dr James Tate - Better estimation of vehicle emissions for modelling - DMUG17Dr James Tate - Better estimation of vehicle emissions for modelling - DMUG17
Dr James Tate - Better estimation of vehicle emissions for modelling - DMUG17
IES / IAQM366 views

More from Daniel H. Stolfi

Improving Pheromone Communication for UAV Swarm Mobility Management by
Improving Pheromone Communication for UAV Swarm Mobility ManagementImproving Pheromone Communication for UAV Swarm Mobility Management
Improving Pheromone Communication for UAV Swarm Mobility ManagementDaniel H. Stolfi
6 views26 slides
Competitive Evolution of a UAV Swarm for Improving Intruder Detection Rates by
Competitive Evolution of a UAV Swarm for Improving Intruder Detection RatesCompetitive Evolution of a UAV Swarm for Improving Intruder Detection Rates
Competitive Evolution of a UAV Swarm for Improving Intruder Detection RatesDaniel H. Stolfi
266 views8 slides
A Cooperative Coevolutionary Approach to Maximise Surveillance Coverage of UA... by
A Cooperative Coevolutionary Approach to Maximise Surveillance Coverage of UA...A Cooperative Coevolutionary Approach to Maximise Surveillance Coverage of UA...
A Cooperative Coevolutionary Approach to Maximise Surveillance Coverage of UA...Daniel H. Stolfi
251 views37 slides
Optimizing the Performance of an Unpredictable UAV Swarm for Intruder Detection by
Optimizing the Performance of an Unpredictable UAV Swarm for Intruder DetectionOptimizing the Performance of an Unpredictable UAV Swarm for Intruder Detection
Optimizing the Performance of an Unpredictable UAV Swarm for Intruder DetectionDaniel H. Stolfi
243 views38 slides
Ocupación de Aparcamientos y Predicción by
Ocupación de Aparcamientos y PredicciónOcupación de Aparcamientos y Predicción
Ocupación de Aparcamientos y PredicciónDaniel H. Stolfi
61 views20 slides
Un Algoritmo Evolutivo para la Reducción de Tiempos de Viaje y Emisiones Util... by
Un Algoritmo Evolutivo para la Reducción de Tiempos de Viaje y Emisiones Util...Un Algoritmo Evolutivo para la Reducción de Tiempos de Viaje y Emisiones Util...
Un Algoritmo Evolutivo para la Reducción de Tiempos de Viaje y Emisiones Util...Daniel H. Stolfi
952 views67 slides

More from Daniel H. Stolfi(6)

Improving Pheromone Communication for UAV Swarm Mobility Management by Daniel H. Stolfi
Improving Pheromone Communication for UAV Swarm Mobility ManagementImproving Pheromone Communication for UAV Swarm Mobility Management
Improving Pheromone Communication for UAV Swarm Mobility Management
Competitive Evolution of a UAV Swarm for Improving Intruder Detection Rates by Daniel H. Stolfi
Competitive Evolution of a UAV Swarm for Improving Intruder Detection RatesCompetitive Evolution of a UAV Swarm for Improving Intruder Detection Rates
Competitive Evolution of a UAV Swarm for Improving Intruder Detection Rates
Daniel H. Stolfi266 views
A Cooperative Coevolutionary Approach to Maximise Surveillance Coverage of UA... by Daniel H. Stolfi
A Cooperative Coevolutionary Approach to Maximise Surveillance Coverage of UA...A Cooperative Coevolutionary Approach to Maximise Surveillance Coverage of UA...
A Cooperative Coevolutionary Approach to Maximise Surveillance Coverage of UA...
Daniel H. Stolfi251 views
Optimizing the Performance of an Unpredictable UAV Swarm for Intruder Detection by Daniel H. Stolfi
Optimizing the Performance of an Unpredictable UAV Swarm for Intruder DetectionOptimizing the Performance of an Unpredictable UAV Swarm for Intruder Detection
Optimizing the Performance of an Unpredictable UAV Swarm for Intruder Detection
Daniel H. Stolfi243 views
Ocupación de Aparcamientos y Predicción by Daniel H. Stolfi
Ocupación de Aparcamientos y PredicciónOcupación de Aparcamientos y Predicción
Ocupación de Aparcamientos y Predicción
Daniel H. Stolfi61 views
Un Algoritmo Evolutivo para la Reducción de Tiempos de Viaje y Emisiones Util... by Daniel H. Stolfi
Un Algoritmo Evolutivo para la Reducción de Tiempos de Viaje y Emisiones Util...Un Algoritmo Evolutivo para la Reducción de Tiempos de Viaje y Emisiones Util...
Un Algoritmo Evolutivo para la Reducción de Tiempos de Viaje y Emisiones Util...
Daniel H. Stolfi952 views

Recently uploaded

NguyenChristine_Portfolio (1).pdf by
NguyenChristine_Portfolio (1).pdfNguyenChristine_Portfolio (1).pdf
NguyenChristine_Portfolio (1).pdfchnguyentv9
31 views41 slides
corporate-presentation.pdf by
corporate-presentation.pdfcorporate-presentation.pdf
corporate-presentation.pdfShaun Heinrichs
142 views22 slides
Use of Economic Evidence in Cartel Cases – ROBERTS – December 2023 OECD discu... by
Use of Economic Evidence in Cartel Cases – ROBERTS – December 2023 OECD discu...Use of Economic Evidence in Cartel Cases – ROBERTS – December 2023 OECD discu...
Use of Economic Evidence in Cartel Cases – ROBERTS – December 2023 OECD discu...OECD Directorate for Financial and Enterprise Affairs
98 views14 slides
Out-of-Market Efficiencies in Competition Enforcement – ROSENBOOM – December ... by
Out-of-Market Efficiencies in Competition Enforcement – ROSENBOOM – December ...Out-of-Market Efficiencies in Competition Enforcement – ROSENBOOM – December ...
Out-of-Market Efficiencies in Competition Enforcement – ROSENBOOM – December ...OECD Directorate for Financial and Enterprise Affairs
74 views10 slides
PPS.pptx by
PPS.pptxPPS.pptx
PPS.pptxmdabzayub
7 views51 slides
PRESENTATION.pptx by
PRESENTATION.pptxPRESENTATION.pptx
PRESENTATION.pptxyunuskhan558800
8 views14 slides

Recently uploaded(20)

NguyenChristine_Portfolio (1).pdf by chnguyentv9
NguyenChristine_Portfolio (1).pdfNguyenChristine_Portfolio (1).pdf
NguyenChristine_Portfolio (1).pdf
chnguyentv931 views
a timeline of the history of linguistics- BAUTISTA- BELGERA.pdf by FordBryantSadio
a timeline of the history of linguistics- BAUTISTA- BELGERA.pdfa timeline of the history of linguistics- BAUTISTA- BELGERA.pdf
a timeline of the history of linguistics- BAUTISTA- BELGERA.pdf
FordBryantSadio8 views
unmasking toxicity in online gaming by aminabumelha
unmasking toxicity in online gamingunmasking toxicity in online gaming
unmasking toxicity in online gaming
aminabumelha5 views
RTC2023_Boost-App-Integration-with-AI_Kim.pdf by hossenkamal2
RTC2023_Boost-App-Integration-with-AI_Kim.pdfRTC2023_Boost-App-Integration-with-AI_Kim.pdf
RTC2023_Boost-App-Integration-with-AI_Kim.pdf
hossenkamal28 views
Industrial Level Sensor by ketanRaut17
Industrial Level SensorIndustrial Level Sensor
Industrial Level Sensor
ketanRaut176 views
What I learnt in Antarctica about leadership, well-being and climate change by kristinashields1
What I learnt in Antarctica about leadership, well-being and climate changeWhat I learnt in Antarctica about leadership, well-being and climate change
What I learnt in Antarctica about leadership, well-being and climate change
kristinashields138 views
تنزيل (1).pdf DVT by taalali1
تنزيل (1).pdf  DVT تنزيل (1).pdf  DVT
تنزيل (1).pdf DVT
taalali19 views

Eco-friendly Reduction of Travel Times in European Smart Cities (GECCO'14)

  • 1. ECO-FRIENDLY REDUCTION OF TRAVEL TIMES IN EUROPEAN SMART CITIES Daniel H. Stolfi dhstolfi@lcc.uma.es Enrique Alba eat@lcc.uma.es Departamento de Lenguajes y Ciencias de la Computación University of Malaga Genetic and Evolutionary Computation Conference July 2014 Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 1 / 20
  • 2. Introduction Proposal Experiments Conclusions CONTENTS 1 INTRODUCTION 2 PROPOSAL 3 EXPERIMENTS 4 CONCLUSIONS Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 2 / 20
  • 3. Introduction Proposal Experiments Conclusions INTRODUCTION Nowadays there is a higher amount of vehicles in streets The number of traffic jams is increasing Tons of air pollutants are emitted to the atmosphere The inhabitants’ health and quality of life is decreasing Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 3 / 20
  • 4. Introduction Proposal Experiments Conclusions Red Swarm Architecture Case Studies Evolutionary Algorithm RED SWARM Our proposal, Red Swarm, consists of: A few spots distributed throughout the city I Installed at traffic lights I Linked to vehicles by using Wi-Fi Our Evolutionary Algorithm Our Rerouting Algorithm Several User Terminal Units I They visualize the alternatives routes suggested I They could be smartphones, tablets, or On Board Units Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 4 / 20
  • 5. Introduction Proposal Experiments Conclusions Red Swarm Architecture Case Studies Evolutionary Algorithm RED SWARM Red Swarm offers: Personalized information for each vehicle (online, distributed) Prevention of traffic jams Reduction of greenhouse gas emissions Sensing of the city’s state Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 5 / 20
  • 6. Introduction Proposal Experiments Conclusions Red Swarm Architecture Case Studies Evolutionary Algorithm RED SWARM ARCHITECTURE Configuration: Spot’s configuration is calculated by the Evolutionary Algorithm (offline) Deployment and Use: Spots suggest new alternative routes to vehicles (online) Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 6 / 20
  • 7. Introduction Proposal Experiments Conclusions Red Swarm Architecture Case Studies Evolutionary Algorithm RED SWARM SPOT Connects with vehicles and suggests alternative routes Runs an instance of the Rerouting Algorithm S1 and S2 are the Input Streets where vehicles arrive the junction An output street is selected according to the probability value calculated by our EA. Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 7 / 20
  • 8. Introduction Proposal Experiments Conclusions Red Swarm Architecture Case Studies Evolutionary Algorithm REROUTING EXAMPLE Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 8 / 20
  • 9. Introduction Proposal Experiments Conclusions Red Swarm Architecture Case Studies Evolutionary Algorithm SCENARIO BUILDING We work with real maps imported from OpenStreetMap We clean the irrelevant elements by using JOSM We define the vehicle flows (experts’ solution) by using DUAROUTER We import the city model into SUMO by using NETCONVERT Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 9 / 20
  • 10. Introduction Proposal Experiments Conclusions Red Swarm Architecture Case Studies Evolutionary Algorithm CASE STUDIES (I) Malaga I 2.5 Km2 I 262 traffic lights I 10 Red Swarm spots I 1200 vehicles I 169 routes Stockholm I 2.9 Km2 I 498 traffic lights I 12 Red Swarm spots I 1400 vehicles I 131 routes Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 10 / 20
  • 11. Introduction Proposal Experiments Conclusions Red Swarm Architecture Case Studies Evolutionary Algorithm CASE STUDIES (II) Berlin I 7 Km2 I 770 traffic lights I 10 Red Swarm spots I 1300 vehicles I 122 routes Paris I 5.6 Km2 I 575 traffic lights I 10 Red Swarm spots I 1200 vehicles I 125 routes Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 11 / 20
  • 12. Introduction Proposal Experiments Conclusions Red Swarm Architecture Case Studies Evolutionary Algorithm SYSTEM CONFIGURATION If a vehicle which is driving to Destination 2 enters by Street 1 in the coverage area of a red swarm spot, a new route will be suggested by the Rerouting Algorithm according to the probability values stored in the system configuration. Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 12 / 20
  • 13. Introduction Proposal Experiments Conclusions Red Swarm Architecture Case Studies Evolutionary Algorithm STATUS VECTOR It represents the configuration of the N streets which are input to a junction controlled by a red swarm spot. There are M chunks of probabilities values in each street block in order to hold different configurations depending on the vehicles’ final destination. Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 13 / 20
  • 14. Introduction Proposal Experiments Conclusions Red Swarm Architecture Case Studies Evolutionary Algorithm EVOLUTIONARY ALGORITHM The result of the algorithm is the configuration for all the spots The configuration is calculated in the offline stage. (10+2)-EA Evaluates individuals by using the SUMO traffic simulator The rerouting made by the Rerouting Algorithm is implemented in SUMO by TraCI. Daniel H. Stolfi & Enrique Alba Eco-friendly Reduction of Travel Times. . . 14 / 20
  • 15. Introduction Proposal Experiments Conclusions Red Swarm Architecture Case Studies Evolutionary Algorithm FITNESS FUNCTION F = 1( n) + + 2 1 n Xn i=1 COi + 3 1 n Xn i=1 CO2i + 4 1 n Xn i=1 HCi + + 5 1 n Xn i=1 PMi + 6 1 n Xn i=1 NOi + 7 1 n Xn i=1 Fueli (1) : Total amount of vehicles n: Vehicles that end their itinerary during the period analyzed 1 to 7: Normalize each variable The lower, the better Daniel H. Stolfi Enrique Alba Eco-friendly Reduction of Travel Times. . . 15 / 20
  • 16. Introduction Proposal Experiments Conclusions Results 50 Scenarios Graphs AVERAGE AND BEST IMPROVEMENTS We have reduced the CO, CO2, HC, PM, and NO emissions We have also reduced travel times and fuel consumption Case Study T:Time CO CO2 HC PM NO Fuel Malaga 5.5% 4.1% -1.5% 3.0% 0.9% -1.8% -1.6% Average Stockholm 14.2% 12.6% 3.2% 11.0% 8.5% 3.0% 3.0% 50 Berlin 11.7% 10.6% 1.7% 8.7% 6.0% 1.5% 1.6% scenarios Paris 4.1% 2.2% 0.2% 1.8% 1.1% -0.1% 0.2% Average 8.9% 7.4% 0.9% 6.1% 4.1% 0.7% 0.8% Malaga 12.2% 11.3% 4.1% 10.2% 9.9% 5.7% 4.0% Best Stockholm 17.5% 16.1% 7.1% 16.1% 16.7% 10.2% 6.8% improvement Berlin 13.9% 13.2% 4.8% 13.3% 14.5% 7.9% 4.6% achieved Paris 8.9% 11.6% 3.8% 10.4% 5.1% 3.9% 3.8% Average 13.1% 13.0% 5.0% 12.5% 11.5% 6.9% 4.8% Daniel H. Stolfi Enrique Alba Eco-friendly Reduction of Travel Times. . . 16 / 20
  • 17. Introduction Proposal Experiments Conclusions Results 50 Scenarios Graphs PERCENTAGE OF SCENARIOS IMPROVED We have improved more than 58% of 200 scenarios on average Case Study T:Time CO CO2 HC PM NO Fuel Malaga 90.0% 88.0% 24.0% 82.0% 58.0% 36.0% 22.0% % Stockholm 100.0% 100.0% 92.0% 100.0% 98.0% 78.0% 92.0% scenarios Berlin 100.0% 100.0% 90.0% 100.0% 98.0% 74.0% 84.0% improved Paris 94.0% 74.0% 52.0% 74.0% 66.0% 46.0% 50.0% Average 96.0% 90.5% 64.5% 89.0% 80.0% 58.5% 62.0% Each scenario consists of different traffic distributions We have worked with 50 different scenarios of each case study (200) Daniel H. Stolfi Enrique Alba Eco-friendly Reduction of Travel Times. . . 17 / 20
  • 18. Introduction Proposal Experiments Conclusions Results 50 Scenarios Graphs ACCUMULATED VALUES OF THE VEHICLES’ EMISSIONS CO [g] PM [g] CO2 [Kg] NO [g] HC [g] Fuel [l] Daniel H. Stolfi Enrique Alba Eco-friendly Reduction of Travel Times. . . 18 / 20
  • 19. Introduction Proposal Experiments Conclusions CONCLUSIONS AND FUTURE WORK We have addressed the reduction of greenhouse gas emissions, travel times and fuel consumption in Malaga, Stockholm, Berlin, and Paris We have designed an effective evolutionary algorithm to optimize the scenarios Our proposal has achieved average reductions up to 13.0% in CO, 12.5% in HC, 11.5% in PM, and above 5% in the rest of emissions and fuel consumption Additionally, we have shortened travel times up to 13.1% on average Results were influenced by the different characteristics of vehicles as well as the distribution of the cities’ streets As a matter for future work, we are testing different strategies to further improve upon our results We are also implementing the rerouting by city districts to be able to install Red Swarm throughout the entire city Daniel H. Stolfi Enrique Alba Eco-friendly Reduction of Travel Times. . . 19 / 20
  • 20. Introduction Proposal Experiments Conclusions http://neo.lcc.uma.es http://danielstolfi.com/redswarm/ Daniel H. Stolfi Enrique Alba Eco-friendly Reduction of Travel Times. . . 20 / 20
  • 21. Introduction Proposal Experiments Conclusions http://neo.lcc.uma.es http://danielstolfi.com/redswarm/ Questions? Daniel H. Stolfi Enrique Alba Eco-friendly Reduction of Travel Times. . . 20 / 20