Vehicular Traffic Detection, Scheduling,

and Simulation
Abdulmomn Kadhim {a.bluemix@gmail.com}
Supervised by:
Dr. Muayad Sadik Croock
Dr. Shaimaa Hameed Shaker
December 29, 2013

Contents
1 Magnetic sensors and vehicle detection
1.1 Wireless magnetic sensor networks [3] . . . . . . . . . . . . . . .
1.2 On-road sensors deployment . . . . . . . . . . . . . . . . . . . . .

2
2
3

2 Simulation of urban traffic

3 Swarm intelligence for traffic light scheduling [2]

3.1 Cycle program of traffic lights . . . . . . . . . . . . . . . . . . . .
3.2 Experiments and results . . . . . . . . . . . . . . . . . . . . . . .

5
6
7

Report outlines
Why ad-hoc sensor networks are can be preferred to infrastructure ones
How magnetic sensor nodes are deployed and used to detect vehicles
Simulating urban vehicular traffic using SUMO
How swarm intelligence approach used to find successful cycle programs
of traffic lights

Magnetic sensors and vehicle detection

The presence, direction, and speed of a vehicle can be determined by employing

magnetic sensors. The technique requires a magnetic field of known strength
and direction. A moving vehicle can disturb the distribution of the magnetic
field either by producing its own mag- netic field or simply by cutting across it.
As the magnitude and direction of the disturbance depends on the speed, size,
density, and permeability of the vehicle, it is possible to use magnetic sensors
to quantify the disturbance.
Sensors that can measure the Earths magnetic field comprise an alloy of
nickel and iron. Typical examples are anisotropic magnetoresistive (AMR) sensors whose resistive property changes according to the Earths magnetic field
strength. AMR sensors can measure both linear and angular positions and
displacement in the Earths magnetic field.
Almost all road vehicles, including those with polymer body panels, contain
a large mass of steel. Since the magnetic permeability of steel is much higher
than the surrounding air, it has the capacity to concentrate the flux lines of
the Earths magnetic field. The concentration of magnetic flux (disturbance) at
a particular location varies as the vehicle moves and can be detected from a
distance of up to 15 m. Fig. 7 demonstrates how an AMR sensor can be used
to measure the disturbance in the Earths magnetic field caused by a moving
vehicle. [1]
For detecting the presence of a vehicle, measurements of the (vertical) z-axis
is a better choice as it is more localized and the signal from vehicles on adjacent
lanes can be neglected. [4]

1.1

Wireless magnetic sensor networks [3]

Wireless magnetic sensor networks offer a very attractive alternative to inductive

loops for traffic surveillance on freeways and at intersections in terms of cost,
ease of deployment and maintenance, and enhanced measurement capabilities.
These networks consist of a set of sensor nodes (SN) and one access point (AP)1 .
A SN comprises a magnetic sensor, a microprocessor, a radio, and a battery.
Each SN is encased in a 5- diameter smart stud container that is glued to the
center of a lane.
1 This is an infrastructure arrangement, in an ad-hoc one, only sensor nodes exist, i.e.,
peer-to-peer communication

Figure 1: Detection of a moving vehicle with an AMR magnetic sensor

1.1.1

The use of ad-hoc sensor networks in vehicular traffic [5]

All nodes in a wireless ad-hoc network act as a router and host at the same time
(peer-to-peer communication), alongside, the network topology is dynamically
varying, because the connectivity between the nodes may vary with time due
to node departures (e.g., the node gets corrupted) and new node arrivals (e.g.,
placement of a new node instead of corrupted one, or extendign the coverage of
the netword). The special features about ad-hoc networks is that all the nodes
are responsible to organize themselves dynamically the communication between
each other and to provide the necessary network functionality in the absence of
a fixed infrastructure or we can call it ventral administration. It implies that
maintenance, routing and management, etc., have to be done between all the
nodes. This case called Peer level multi-hopping and that is the main building
block for ad-Hoc networks. In the end, we conclude that the ad-hoc nodes are
difficult and more complex than other wireless networks. Therefore, ad hoc
networks form sort of clustering for effective implementation and performance
of such a complex process.
In summary, here are some of the core benefits of ad-hoc networks:
Ad-hoc networks are simple to set up. Plug in your wireless network
sensors and youre off and running.
Ad-hoc networks are inexpensive. You save the cost of purchasing an
access point (the centralized device in infrastructure networks).
Ad-hoc networks are fast. Throughput rates between two wireless network adapters (nodes) are twice as fast as when you use an access point
(infrastructure networks cut the data transfer rate about in half, because
of the time it takes to send the signal to and from the access point rather
than directly to its destination, as in an ad-hoc network).

1.2

On-road sensors deployment

We [4] use intersections controlled by four traffic lights. Each traffic light is
responsible for controlling traffic on three lanes. We assume the right lane turns
3

Figure 2: Road intersection configuration

Figure 3: Deploying sensor networks at freeway (left), intersection (right)

right only, center lane goes straight or left and left lane goes left only. We deploy
sensor nodes on every lane (see Fig. 2). We place the sensor nodes where they
can monitor the traffic before entering the intersection and after leaving the
intersection. We use the nodes placed after the intersection to locally determine
the direction of the vehicle within one intersection.
Another general configuration proposed by [3], is show in Fig. 3.

Simulation of urban traffic

SUMO (Simulation of Urban MObility) is an open source, highly portable,

microscopic and continuous road traffic simulation package designed to handle large road networks. It is mainly developed by employees of the Institute
of Transportation Systems at the German Aerospace Center. SUMO is open

Figure 4: Flowchart showing the traffic model creation process.

source, licensed under the GPL.
The open-source SUMO simulation environment was chosen for a number
of reasons including portability, presence of an active development community
and availability of a graphical user interface [6].
A realistic traffic model based on a section of the downtown area of the
City of Ottawa was developed for use within the SUMO microscopic traffic
simulation environment, to demonstrate the effectiveness of an intelligent traffic
control system that system should be tested on realistic traffic scenarios [6].
Fig. 4, shows a flowchart of the traffic model creation process, which is
explained in [6].
Fig. 5 shows an example intersection with four groups (and thus four signal
sets) within a SUMO simulation [6].
And, finally, University of Technology road street map is shown in Fig. 6.2

Swarm intelligence for traffic light scheduling [2]

The growing number of traffic lights that control the vehicular flow requires a
complex scheduling, and hence, automatic systems are indispensable nowadays
for optimally tackling this task.
In this work, we propose a Swarm Intelligence approach to find successful
cycle programs of traffic lights. Using a microscopic traffic simulator, the solutions obtained by our algorithm are evaluated in the context of two large and
heterogeneous metropolitan areas located in the cities of Ma laga and Sevilla (in
Spain). In comparison with cycle programs predefined by experts (close to real
ones), our proposal obtains significant profits in terms of two main indicators:
2 This

map is being displayed in jsom, which can be converted to be used in SUMO.

Figure 5: Example of an intersection with four groups, showing the four corresponding signal sets. (a) Signal set for Group #1, (b) Signal set for Group #2,
(c) Signal set for Group #3 and (d) Signal set for Group #4.
the number of vehicles that reach their destinations on time and the global trip
time.

3.1

Cycle program of traffic lights

Cycle programs are refereed to the time span a set of traffic lights (in a junction)
keep their color states. At the same time, these programs have to coordinate
traffic lights in adjacent intersections with the aim of improving the global flow
of vehicles circulating according to traffic regulations. In this context, our main
objective is to find optimized cycle programs (OCP) for all the traffic lights
located in a given urban area.
In our approach, the OCP (optimized cycle program) is encoded by means of
a vector of integers (see Fig. 7) following the SUMO structure of programming
cycles, where each element represents a phase duration of one state of the traffic
6

Figure 6: University of Technology street map.

lights involved in a given intersection.
An example of this mechanism can be observed in Fig. 7 where the intersection with id =i contains seven phases with dura- tions 40, 5, 40, 10, 36, 6,
and 22 s (simulation steps). In these phases, the states have fourteen signals
(colors), corresponding each one of them to one of the fourteen traffic lights
located in the studied intersection. These states are the valid ones generated
by the simulator (SUMO in this work) attending to real traffic rules. In this
instance, the fifth phase contains the state rrrr GGr rrrr GGr meaning that
four traffic lights are in green (G), and the ten others are in red (r) during 36
s. The following phase changes the state of the four traffic lights to other valid
combination, for example, GGGG yyr GGGG yyr (y means yellow) during 6 s,
and so on.
The last phase is followed by the first one, and this cycle is repeated during
all the simulation time. All the intersections in the complete scenario perform
their own programming cycles of phases at the same time, hence conforming
the global schedule of traffic lights. As commented before, computing OCP
consists in optimizing the combination of phase durations of all traffic lights (in
all intersections) with the aim of improving the global flow of vehicles circulating
in a urban scenario instance.

3.2
3.2.1

Experiments and results

Instances

In Fig. 8, the selected areas of the two cities are shown with their corresponding
snapshots of Google Earth, OpenStreetMap, and SUMO. This figure illustrates
the process of generating the traffic network instances.

Figure 7: Cycle program (phase duration) of traffic lights within intersections.

Integer codification inside a PSO tentative solution.
3.2.2

Results and comparisons

In this section, we are first interested to analyze the internal performance of our
PSO (particle swarm optimization). Graphically, Fig. 9 plots the trace progress
of the obtained in 30 independent runs of our technique when solving the Ma
laga instance.
In this figure, we can observe that for all executions our algorithm practically
converged after the first 200 iterations (20,000 evaluations), using the remaining
time to only slightly refine solutions. In addition, all the computed solutions
are close each other in quality, but different among them. They are almost all
in the range of fitness values between 1 and 3. In terms of convergence and
robustness, these are desirable features since we can offer to the expert a varied
set of accurate cycle programs in a first stage of optimization.
3.2.3

Analysis of resulting traffic light schedules

In this section we focus on the cycle programs obtained by our PSO, and the
possible profits they can offer to the actual users in this field. Then we show
the real impact of using our optimization technique, able of computing realistic

Figure 8: Process of creation of real-world instances for study. Urban centre of

Sevilla and Malaga instance views. After selecting our area of interest (Google
Earth view), it is interpreted by means of the OpenStreetMap tool, and then
exported to SUMO format.
and comprehensive traffic light cycle programs.
A representative example can be observed in the optimization process of the
Ma laga instance. First, in Fig. 10 we can see the trace of the number of vehicles
that did reach their destinations (upper continuous curve) versus the number
of vehicles that did not reach their destinations (lower dotted curve) for each
iteration step in a run of PSO. The overlapped curves show the mean number of
vehicles (out of 30 independent runs) that did arrive and did not arrive to their
destinations. In addition, this figure also shows the results (in dotted straight
lines) of the SCPG for this same instance.
From a different point of view, Fig. 11 plots the trace of the average trip
time employed by the vehicles in the resulted solutions of PSO through all the
iterations of an example run. In this case, the trip time becomes shorter as the
algorithm approaches the stop condition. We must notice that, in the calculation
of the trip time, the vehicles that did not arrive to their destinations took 500
s, the complete simulation time. For this reason, SCPG solutions showed an
averaged trip time of 660 s while PSO solutions obtained a trip duration of 557
s, which represents an improvement of 15.7% respect to the SCPG (SUMO cycle
program generator) solution.
Finally, with the aim of better understanding the final implica- tions of using
9

Figure 9: Trace progress of the best fitness values in 30 independent runs of

PSO tackling the Malaga instance.
(or not using) an optimized cycle program, Fig. 12 shows the simulation traces
of the traffic flow resulted from solutions generated by both, SCPG (left) and
PSO (right). The pictures were captured at the final of the simulation time,
and correspond to two simulation procedures of a selected area of the Ma laga
instance including: Andaluc a avenue, Aurora avenue, and Guadalmedina street.
As we can observe, the traffic density of the SCPG cycle program is clearly higher
than the one of PSO, even showing the former several intersections with traffic
jams. As to the PSO cycle program, all intersections are unblocked at the end
of the study.

10

Figure 10: Number of vehicles that did reach their destinations (continuous
lines) versus vehicles that did not reach their destinations (dotted lines). Overlapped curves show the mean number of vehicles (out of 30 independent runs)
that did arrive and did not arrive to their destinations. SCPG results are also
showed with dotted straight lines.

11

Figure 11: Mean trip time of vehicles calculated for each one of the simulations
performed through a representative run of PSO. SCPG (SUMO cycle program
generator) results are also showed with a dotted straight line. Y axis represents
the trip time in seconds.

Figure 12: Simulation traces of the traffic flow (cars in white) resulting from
the cycle programs generated by both, SCPG (left) and PSO (right) in Ma laga.
The pictures show snapshots at the end of the simulation time. The reader can
notice that the SCPG leaves a dense traffic while PSO has cleaned the routes
and the traffic is very fluid and sparse.

References
[1] Fundamentals of Wireless Sensor Networks - Theory and Practice - Dargie,
Waltenegus;( WILEY, 2010)
[2] Swarm intelligence for traffic light scheduling: Application to real urban
areas (Elsevier, 2011).

12

[3] Traffic Surveillance with Wireless Magnetic Sensors, Sing Yiu Cheung,
Sinem Coleri Ergen and Pravin Varaiya University of California, Berkeley,
CA 94720-1770, USA
[4] Adaptive Traffic Light Control with Wireless Sensor Networks: Malik
Tubaishat, Yi Shang and Hongchi Shi; Department of Computer Science
University of Missouri - Columbia; Columbia, MO 65211-2060
[5] An overview of mobile ad-hoc networks for the existing protocols and
applications; Saleh Ali K.Al-Omari , Putra Sumari; School of Computer
Science, Universiti Sains Malaysia, 11800 Penang, Malaysia. (International
journal on applications of graph theory in wireless ad hoc networks and
sensor networks, Vol.2, No.1, March 2010)
[6] Distributed and adaptive traffic signal control within a realistic traffic
simulation; Dave McKenney, Tony White (Elsevier 2012)

13