real time traffic management - challenges and solutions

29
Real-Time Traffic Management: Challenges and Solutions Ke Han Lecturer (Assistant Professor) Center for Transport Studies Department of Civil and Environmental Engineering, Imperial College London [email protected] www.imperial.ac.uk/people/k.han

Upload: institute-for-transport-studies-its

Post on 18-Jan-2017

110 views

Category:

Automotive


1 download

TRANSCRIPT

Real-Time Traffic Management: Challenges and Solutions

Ke HanLecturer (Assistant Professor)

Center for Transport StudiesDepartment of Civil and Environmental Engineering, Imperial College London

[email protected]/people/k.han

Outline

1. Overview

2. The CARBOTRAF Project

3. Decision Rule Approach for Real-Time Operation

Real-Time Traffic Management

v Challenges

Ø Timeliness of decisionsØ Nonlinear and nonconvex objectiveØ Multiple objectivesØ Insufficient telecom capacity (centralized vs. distributed)Ø Uncertainties and insufficient data coverage

v New Opportunities (more challenges?)Ø Multi-source and heterogeneous data (e.g. mobile data, social media)Ø New collection/communication methods (e.g. crowd sourcing)Ø Need for more robust and fundamentally new theories and methods

Outline

1. Overview

2. The CARBOTRAF Project

3. Decision Rule Approach for Real-Time Operation

The CARBOTRAF Project

“A Decision Support System for reduced emissions of CO2 and Black Carbon through Adaptive Traffic Management”

Ø Scenario evaluation using traffic and environmental modelling tools

Ø Online status updates and decision support

Ø Ambient monitoring for evaluation, feedback and learning

Ø Two “Pilot Cities” (Glasgow and Graz)

Ø Decision Support System with GUI for Traffic Operators

Work Flow of The CARBOTRAF Project

Offline modelling

& simulation

Decision Support System

Online Database

Inte

rfac

e to

rea

l-tim

e da

ta Real-time

traffic data

ITS actions

Catalogue of ITS actions

Traffic simulation

Emission models

Air quality models

Look-up table &

database of traffic and emission scenarios

Real-time pollutant concentration

Real-time air quality data

Real-time meteorology data

Offline module Online module

Off-Line Modeling

Microsimulation

Emission Model

Dispersion Model

• Network model• Traffic flows• Signal plans• Vehicle composition• Vehicle dynamics

• Vehicle emissioncategories

• Road elevation

• Weather data• Building heights

S-Paramics,VISSIM

AIRE

IFDM

Test Site in West Glasgow

Key Performance Indicators

v TrafficØ Travel timeØ SpeedØ Delay

v Environment

Ø Black CarbonØ CO2Ø Nox

v Spatial referencesØ Network wideØ CorridorØ Junction

Great Western Rd.

Kel

vin

Way

University Av.

VMS

TSC

city center

The CARBOTRAF Project

Reduction of BC Concentration with ITS Actions

BC conc (µg/m3) ITS – Base Scenario Boundary condition 1

BC conc (µg/m3) ITS – Base Scenario Boundary condition 2

Managerial Insights Gained from Offline Modeling & Simulation

v The effectiveness of ITS actions depends on many factors, which need to be determined and telecommunicated in real timeØ Dynamic demand profileØ Weather conditionØ Fleet composition

v Benefits of the ITS actions are more pronounced at the local levelØ Network level: below 3%Ø Corridor/junction level: 5-30%

v In an urban environment, emission is closely related to Ø Traffic flow dynamics (not merely “flow” or “volume”)Ø Fleet composition (bus/LGV/HGV)

Decision Support System

v The DSS combines streaming data and the off-line LUT to rank different candidate ITS actions

v Input:Ø Current ITS action deployedØ Probability distributions of KPIs for the complete set of alternative actions

(LUT)Ø Operational constraints on the set of ITS actions

v Minimization problem (in real time):

v Potential issues:Ø Resolution of the Look-Up TableØ Expectation highly susceptible to outliers and errorsØ Computationally expensive, with additional lags -- Traffic Prediction Tool (Min and

Wynter, 2011)

Outline

1. Overview

2. The CARBOTRAF Project

3. Decision Rule Approach for Real-Time Operation

Analytical/closed-form

transformation

Decision Rule Approach for Real-Time Traffic Management

v Real-time control: Challenges- Timeliness- Nonlinear and nonconvex objective- Distributed vs. centralized control- Uncertainties

v Heuristic (genetic algorithm, fuzzy logic), inexact and sub-optimal

v Decision Rule (DR) approach for real-time traffic management

ü Historical and real-time dataü Within-day and day-to-day variationsü Distributionally Robust Optimization (DRO) to ensure

performance in the most adversarial situationü Efficient on-line operationü Compatible with analytical computations and microsimulation

Real-timesystem state

Controlparameters

Not optimal?

Decision rule

Decision Rule: ConceptOff-line moduleOn-line module

Analytical/ closed-form

transformation

Real-time traffic state

Real-time decision

Decision rule

Offline training

Real-time traffic state Historical

traffic state

Look-up table

Traffic prediction

tool

Real-time decision

Historical traffic state

Offline simulation

Decision rule approach CARBOTRAF approach

Stochastic optimization

Offline simulation

-- real-time information (flow, count, speed, queue)

-- Analytical transformation with undetermined coefficients x

-- Projection onto feasible control set

--Network performance measure (minimize) (congestion, emission, fuel consumption)

Real-timeInformation

q

Controlu

Decision Rule

Network performance

measure(simulation)

Φ(q,u)

f (x,q)u = PΩ[ f (x,q)]

Decision Rule: Deterministic Formulation

q

Deterministic Formulation

Given real-time information q, find the best decision rule (x):

u = PΩ[ f (x,q)]

Linear Decision Rule

Time

Location/data type

past Tobservations

REAL-TIME DATA

CONTROL

COEFFICIENT

Nonlinear Decision Rule (Artificial Neural Network)

REAL-TIME DATA

CONTROLANN . . . . . .

Artificial Neural Network

v : a neural network with m hidden layers and n neurons

v Activation function pre-determined (e.g. sigmoid functions)

v x represents the weights of the connections between neurons

Decision Rule: Stochastic Extension

v In reality, q is stochastic, subject to within-day & day-to-day variations

v Stochastic programming – exact probability distribution required

v Ambiguous information on the distribution with finite samples

v Distributionally robust optimization (DRO)

Ø Worst-case scenario (‘max’),

Ø among all candidate distributions

Ø Subsumes stochastic optimization

Ø Data-driven calibration of

Distributionally Robust Formulation

Given stochastic input q, find the best

decision rule coefficient x:

“Uncertain distributions (DRO) instead of uncertain parameters (RO)”

Advantages of the Decision Rule Approach

v Finding the best responsive signal strategy è Finding x

v Feasible and efficient on-line operation

- Off-line: Distributionally robust optimization (expensive)- On-line: Linear transformation and projection (inexpensive)

v Flexible sensor location, data type, and control resolution

v User-defined feasible set for signal control parameters

v Two solution procedures for the off-line problem:

- Mixed integer linear program- Metaheuristic search

Distributionally Robust Optimization

v Kolmogorov-Smirnov (K-S) goodness-of-fit test (Massey, 1951; Bertsimas et al., 2013):

v Random variable: ,parameterized by

v Uncertainty set: ,parameterized by

v Fix ,and consider K samples (historical data)

v Does a distribution well capture a finite set of sampled data?

v Reject H0 at the level α if

Data-Driven Calibration of the Uncertainty Set

Set of candidate distributions

Formulation of the Uncertainty Set

Evaluating the Objective Function

v Random Variable (objective): , parameterized by

v Lower and upper bounds of : , partitioned into W intervals

v Fix (control),

g1Lf Ufg2 gi-1 gi

. . . . . .

K-S test

Numerical Study, Part 1

Great Western Rd

Great Western Rd

Byre

s Rd

City Center

University of Glasgow

§ West end of Glasgow§ 5 signalized intersections§ 35 directed links§ LWR network model

Network

Data§ Turn-by-turn flow count§ 8-9 am, 7 June 2010§ Daily variations are

generated synthetically,using a variety of distributions

Benchmarks§ Fixed signal timing

(deterministic & DRO)§ Field signal parameters

(Glasgow City Council)

Numerical Study: Part 1

Particle Swarm Optimization Great Western Rd

Great Western Rd

Byres

Rd

City Center

University of Glasgow

§ Zeroth-order information on the objective and constraints

§ LWR-based network simulation model§ Flexible trade-off between solution

quality and computational cost§ Off-line computational time: 24h§ On-line computational time: negligible

Criteria DeterministicFixed timing

DROFixed timing

Field parameter(Glasgow City)

LDR-DRO NDR-DRO

Objective (maximize) 1.61 3.81 4.14 4.28 4.34

Throughput 1498 (veh) 3382 (veh) 3576 (veh) 3910 (veh) 3951

CPU time (offline/online)

24h/- 24h/- -/- 24h/0.01s 24h/0.03s

Numerical Study: Part 2

v 4-by-4 grid network in S-Paramicsv 8 zones, 56 O-D pairsv Dynamic route assignmentv Fleet: passenger car, LGV, MGV, HGV, coachv 4-stage signal plan at all four junctionsv 30 random seeds for generating samples

72

74

76

78

80

82

1

Ave

rage

Del

ay (s

)

3.0% improvement

210 215 220 225 230 235 240 245 2500

1

2

3

4

5

6

7

Average Vehicle Delay (s)

Coun

t

215

220

225

230

235

240

245

1 2

Ave

rage

Veh

icle

Del

ay (s

)

Numerical Study: Part 3

v West Glasgow in S-Paramicsv 21 zones, 420 O-D pairsv Dynamic route assignmentv Fleet: passenger car, LGV, MGV, HGV, coachv 30 random seeds for generating samplesv 80 PSO major iterationsv Signal optimization at the key junction

Byres Rd. &University Ave.

NDR-DRO Webster

1.3% improvement

Numerical Study: Part 4

v The decision rule approach combined with metaheuristic methods allow for sufficiently nonlinear and non-analytical objective functions, such as

v Emission (hydrocarbon, HC) is calculated based on vehicle speed, density, and acceleration/deceleration derived from the kinematic wave model, and the instantaneous HC emission model (Ahn et al., 2002)

f = w×Throughput - (1−w)×Total Emission w ∈ [0,1]

Great Western Rd

Great Western Rd

Byres

Rd

City Center

University of Glasgow

3100 3200 3300 3400 3500 3600 3700 3800 3900 40003.1

3.15

3.2

3.25

3.3

3.35

3.4

3.45x 107

Throughput (veh)

Tota

l HC

Emiss

ion

(µg)

w=0.1

w=1.0(no emissionconsideration)

Thank [email protected]