09-08-2012, 02:53 PM
Cloud Computing for Agent-Based Urban Transportation Systems
[attachment=30785]
Agent-based traffi c management systems can
use the autonomy, mobility, and adaptability
of mobile agents to deal with dynamic traffi c environments.
Cloud computing can help such systems
74 www.computerintelligent IEEE INTELLIGENT SYSTEMS
agents were proposed to handle this
vexing problem. Only requiring a
runtime environment, mobile agents
can run computations near data
to improve performance by reducing
communication time and costs.
This computing paradigm soon drew
much attention in the transportation
field. From multiagent systems and
agent structure to ways of negotiating
between agents to control agent strategies,
all these fields have had varying
degrees of success.
Now, the IT industry has ushered
in the fifth computing paradigm:
cloud computing. Based on the Internet,
cloud computing provides ondemand
computing capacity to individuals
and businesses in the form of
heterogeneous and autonomous services.
With cloud computing, users
do not need to understand the details
of the infrastructure in the “clouds;”
they need only know what resources
they need and how to obtain appropriate
services, which shields the
computational complexity of providing
the required services.
In recent years, the research and
application of parallel transportation
management systems (PtMS), which
consists of artificial systems, computational
experiments, and parallel
execution, has become a hot spot in
the traffic research field.2,3 Here, the
term parallel describes the parallel
interaction between an actual transportation
system and one or more of
its corresponding artificial or virtual
counterparts.4
Such complex systems make it difficult
or even impossible to build accurate
models and perform experiments,
so PtMSs use artificial transportation
systems (ATS) to compensate for this
defect. Moreover, ATSs also help optimize
and evaluate large amounts of
traffic-control strategies. Cloud computing
caters to the idea of “local
simple, remote complex” in parallel
traffic systems. Such systems can take
advantage of cloud computing to organize
computing experiments, test
the performance of different traffic
strategies, and so on. Thus, only the
optimum traffic strategies will be used
in urban-traffic control and management
systems. This helps enhance
Figure 1. Relationship between the shifts in the computing and traffic management
paradigms.
Mainframe (1940s–1950s)
PC (1960s)
LAN (1970s)
Internet (1980s–1990s)
Cloud computing (2000s) Parallel transportation management systems (2010s)
Actual
transportation
systems
ATS
Mobile agent
Mobile agent
Traffic management systems
based on agents (2000s)
Internet
Traffic management systems
in distributed model (1980s–1990s)
Coordinator Coordinator Coordinator
Organizer
Traffic management systems
with single points (1970s–1980s)
Traffic management systems in
centralized model (1960s)
Detector
Detector Detector Detector
Executor
Executor
Executor
Executor
Executor
Executor
January/February 2011 www.computerintelligent 75
urban-traffic management system
performance and minimizes the system’s
hardware requirements to accelerate
the popularization of parallel
traffic systems.
Agent-Based Traffic Management Systems
Agent technology was used in trafficmanagement
systems as early as
1992, while multiagent trafficmanagement
systems were presented
later.5 However, all these systems focus
on negotiation and collaboration
between static agents for coordination
and optimization.6–8 In 2004,
mobile agent technology began to attract
the attention of the transportation
field. The characteristics of
mobile agents—autonomous, mobile,
and adaptive—make them suitable
to handling the uncertainties and inconstant
states in a dynamic environment.
9 The mobile agent moves
through the network to reach control
devices and implements appropriate
strategies in either autonomous or
passive modes. In this way, traffic devices
only need to provide an operating
platform for mobile traffic agents
working in dynamic environments,
without having to contain every traffic
strategies. This approach saves
storage and computing capacity in
physical control devices, which helps
reduce their update and replacement
rates. Moreover, when faced with the
different requirements of dynamic
traffic scenes, a multiagent system
taking advantage of mobile agents
will perform better than any static
agent system.
In 2005, the Agent-Based Distributed
and Adaptive Platforms for
Transportation Systems (Adapts) was
proposed as an hierarchical urbantraffic-
management system.10 The
three layers in Adapts are organization,
coordination, and execution, respectively.
Mobile agents play a role
as the carrier of the control strategies
in the system.
In the follow-up articles, both the
architecture and the function of mobile
traffic control agents were defined
clearly. The static agents in each layer
were also depicted in detail. What’s
more, a new traffic signal controller
was designed to provide the runtime
environment for mobile agent.
Currently, Adapts is part of PtMS,
which can take advantage of mobile
traffic strategy agents to manage a
road map. The organization layer,
which is the core of our system, has
four functions: agent-oriented task
decomposition, agent scheduling,
encapsulating traffic strategy, and
agent management (see Figure 2).
The organization layer consists of a
management agent (MA), three databases
(control strategy, typical traffic
scenes, and traffic strategy agent), and
an artificial transportation system. As
one traffic strategy has been proposed,
the strategy code is saved in the traffic
strategy database. Then, according to
the agent’s prototype, the traffic strategy
will be encapsulated into a traffic
strategy agent that is saved in the traffic
strategy agent database. Also, the
traffic strategy agent will be tested by
the typical traffic scenes to review its
performance. Typical traffic scenes,
which are stored in a typical intersections
database, can determine the performance
of various agents. With the
support of the three databases, the
MA embodies the organization layer’s
intelligence.
Figure 2. Overview of the main functional elements in the organization layer of
Adapts.
Traffic-strategy
database Traffic-strategy
agent database
Database of
knowledge
Traffic data
Modified
agent-distribution
map
Agent-distribution
map
Traffic task and state of
transportation
Agent
performance
Ask agent
to move
Combination of
traffic agents
Agent prototype
Traffic-strategy
developers
Agent performance
Traffic
strategies
Agent storage and
generation module
Agent deployment and support module
Actual traffic management system Artificial transportation system
Agent testing and training module
Typical traffic
scenes testbed
Agent performance
76 www.computerintelligent IEEE INTELLIGENT SYSTEMS
The function of the
agents’ scheduling and
agent-oriented task decomposition
is based on
the MA’s knowledge
base, which consists of
the performances of different
agents in various
traffic scenes. If the urban
management system
cannot deal with a transportation
scene with its
existing agents, it will
send a traffic task to the
organization layer for help. The traffic
task contains the information
about the state of urban transportation,
so a traffic task can be decomposed
into a combination of several
typical traffic scenes. With knowledge
about the most appropriate traffic
strategy agent to deal with any
typical traffic scene, when the organization
layer receives the traffic
task, the MA will return a combination
of agents and a map about the
distribution of agents to solve it. This
way, this system takes advantage
of the strategy agent to manage a
road map.
Lastly, we set up an ATS to test performance
of the urban-traffic management
system based on the map
showing the distribution of agents.
ATS is modeled from the bottom up,
and it mirrors the real urban transportation
environment.11 Because the
speed of the computational experiments
is faster than the real world, if
the performance is unsatisfactory, the
agent-distribution map in both systems
will be modified.
New Challenges
During the runtime of Adapts, we
need to send the agent-distribution
map and the relevant agents to ATS
for experimental evaluation, so we
tested the cost of this operation. In
our test, traffic-control agents must
communicate with ATS to get trafficdetection
data and send back lampcontrol
data. Both running load
and communication volumes increase
with the number of intersections.
If the time to complete the experimental
evaluation exceeds a certain
threshold, the experimental results
become meaningless and useless. As
a result, the carry capacity for experimental
evaluation of one PC is
limited.
In our test, we used a 2.66-GHz
PC with a 1-Gbyte memory to run
both ATS and Adapts. The experiment
took 3,600 seconds in real
time. The number of intersections
we tested increased from two to 20,
and Figure 3 shows the time cost of
each experiment. When the number
of traffic-control agents is 20,
the experiment takes 1,130 seconds.
If we set the time threshold to 600
seconds, the maximum number of
intersections in one experiment is
only 12. This is insufficient to handle
model major urban areas such as Beijing,
where the central area within
the Second Ring Road intersection
contains up to 119 intersections. We
would need several PCs or a highperformance
server to handle the experimental
scale of several hundreds
of intersections.
Furthermore, a complete urbantraffic
management system also
requires traffic control,
detection, guidance, monitoring,
and emergency
subsystems. To handle
the different states in a
traffic environment, an
urban-traffic management
system must provide appropriate
traffic strategy
agents. And to handle
performance improvements
and the addition
of new subsystems, new
traffic strategies must be
introduced continually. So future
urban-traffic management systems
must generate, store, manage, test,
optimize, and effectively use a large
number of mobile agents. Moreover,
they need a decision-support system
to communicate with traffic managers.
A comprehensive, powerful decision-
support system with a friendly
human-computer interface is an inevitable
trend in the development of
urban-traffic management systems.
Thus, future systems must have the
following capabilities.
[attachment=30785]
Agent-based traffi c management systems can
use the autonomy, mobility, and adaptability
of mobile agents to deal with dynamic traffi c environments.
Cloud computing can help such systems
74 www.computerintelligent IEEE INTELLIGENT SYSTEMS
agents were proposed to handle this
vexing problem. Only requiring a
runtime environment, mobile agents
can run computations near data
to improve performance by reducing
communication time and costs.
This computing paradigm soon drew
much attention in the transportation
field. From multiagent systems and
agent structure to ways of negotiating
between agents to control agent strategies,
all these fields have had varying
degrees of success.
Now, the IT industry has ushered
in the fifth computing paradigm:
cloud computing. Based on the Internet,
cloud computing provides ondemand
computing capacity to individuals
and businesses in the form of
heterogeneous and autonomous services.
With cloud computing, users
do not need to understand the details
of the infrastructure in the “clouds;”
they need only know what resources
they need and how to obtain appropriate
services, which shields the
computational complexity of providing
the required services.
In recent years, the research and
application of parallel transportation
management systems (PtMS), which
consists of artificial systems, computational
experiments, and parallel
execution, has become a hot spot in
the traffic research field.2,3 Here, the
term parallel describes the parallel
interaction between an actual transportation
system and one or more of
its corresponding artificial or virtual
counterparts.4
Such complex systems make it difficult
or even impossible to build accurate
models and perform experiments,
so PtMSs use artificial transportation
systems (ATS) to compensate for this
defect. Moreover, ATSs also help optimize
and evaluate large amounts of
traffic-control strategies. Cloud computing
caters to the idea of “local
simple, remote complex” in parallel
traffic systems. Such systems can take
advantage of cloud computing to organize
computing experiments, test
the performance of different traffic
strategies, and so on. Thus, only the
optimum traffic strategies will be used
in urban-traffic control and management
systems. This helps enhance
Figure 1. Relationship between the shifts in the computing and traffic management
paradigms.
Mainframe (1940s–1950s)
PC (1960s)
LAN (1970s)
Internet (1980s–1990s)
Cloud computing (2000s) Parallel transportation management systems (2010s)
Actual
transportation
systems
ATS
Mobile agent
Mobile agent
Traffic management systems
based on agents (2000s)
Internet
Traffic management systems
in distributed model (1980s–1990s)
Coordinator Coordinator Coordinator
Organizer
Traffic management systems
with single points (1970s–1980s)
Traffic management systems in
centralized model (1960s)
Detector
Detector Detector Detector
Executor
Executor
Executor
Executor
Executor
Executor
January/February 2011 www.computerintelligent 75
urban-traffic management system
performance and minimizes the system’s
hardware requirements to accelerate
the popularization of parallel
traffic systems.
Agent-Based Traffic Management Systems
Agent technology was used in trafficmanagement
systems as early as
1992, while multiagent trafficmanagement
systems were presented
later.5 However, all these systems focus
on negotiation and collaboration
between static agents for coordination
and optimization.6–8 In 2004,
mobile agent technology began to attract
the attention of the transportation
field. The characteristics of
mobile agents—autonomous, mobile,
and adaptive—make them suitable
to handling the uncertainties and inconstant
states in a dynamic environment.
9 The mobile agent moves
through the network to reach control
devices and implements appropriate
strategies in either autonomous or
passive modes. In this way, traffic devices
only need to provide an operating
platform for mobile traffic agents
working in dynamic environments,
without having to contain every traffic
strategies. This approach saves
storage and computing capacity in
physical control devices, which helps
reduce their update and replacement
rates. Moreover, when faced with the
different requirements of dynamic
traffic scenes, a multiagent system
taking advantage of mobile agents
will perform better than any static
agent system.
In 2005, the Agent-Based Distributed
and Adaptive Platforms for
Transportation Systems (Adapts) was
proposed as an hierarchical urbantraffic-
management system.10 The
three layers in Adapts are organization,
coordination, and execution, respectively.
Mobile agents play a role
as the carrier of the control strategies
in the system.
In the follow-up articles, both the
architecture and the function of mobile
traffic control agents were defined
clearly. The static agents in each layer
were also depicted in detail. What’s
more, a new traffic signal controller
was designed to provide the runtime
environment for mobile agent.
Currently, Adapts is part of PtMS,
which can take advantage of mobile
traffic strategy agents to manage a
road map. The organization layer,
which is the core of our system, has
four functions: agent-oriented task
decomposition, agent scheduling,
encapsulating traffic strategy, and
agent management (see Figure 2).
The organization layer consists of a
management agent (MA), three databases
(control strategy, typical traffic
scenes, and traffic strategy agent), and
an artificial transportation system. As
one traffic strategy has been proposed,
the strategy code is saved in the traffic
strategy database. Then, according to
the agent’s prototype, the traffic strategy
will be encapsulated into a traffic
strategy agent that is saved in the traffic
strategy agent database. Also, the
traffic strategy agent will be tested by
the typical traffic scenes to review its
performance. Typical traffic scenes,
which are stored in a typical intersections
database, can determine the performance
of various agents. With the
support of the three databases, the
MA embodies the organization layer’s
intelligence.
Figure 2. Overview of the main functional elements in the organization layer of
Adapts.
Traffic-strategy
database Traffic-strategy
agent database
Database of
knowledge
Traffic data
Modified
agent-distribution
map
Agent-distribution
map
Traffic task and state of
transportation
Agent
performance
Ask agent
to move
Combination of
traffic agents
Agent prototype
Traffic-strategy
developers
Agent performance
Traffic
strategies
Agent storage and
generation module
Agent deployment and support module
Actual traffic management system Artificial transportation system
Agent testing and training module
Typical traffic
scenes testbed
Agent performance
76 www.computerintelligent IEEE INTELLIGENT SYSTEMS
The function of the
agents’ scheduling and
agent-oriented task decomposition
is based on
the MA’s knowledge
base, which consists of
the performances of different
agents in various
traffic scenes. If the urban
management system
cannot deal with a transportation
scene with its
existing agents, it will
send a traffic task to the
organization layer for help. The traffic
task contains the information
about the state of urban transportation,
so a traffic task can be decomposed
into a combination of several
typical traffic scenes. With knowledge
about the most appropriate traffic
strategy agent to deal with any
typical traffic scene, when the organization
layer receives the traffic
task, the MA will return a combination
of agents and a map about the
distribution of agents to solve it. This
way, this system takes advantage
of the strategy agent to manage a
road map.
Lastly, we set up an ATS to test performance
of the urban-traffic management
system based on the map
showing the distribution of agents.
ATS is modeled from the bottom up,
and it mirrors the real urban transportation
environment.11 Because the
speed of the computational experiments
is faster than the real world, if
the performance is unsatisfactory, the
agent-distribution map in both systems
will be modified.
New Challenges
During the runtime of Adapts, we
need to send the agent-distribution
map and the relevant agents to ATS
for experimental evaluation, so we
tested the cost of this operation. In
our test, traffic-control agents must
communicate with ATS to get trafficdetection
data and send back lampcontrol
data. Both running load
and communication volumes increase
with the number of intersections.
If the time to complete the experimental
evaluation exceeds a certain
threshold, the experimental results
become meaningless and useless. As
a result, the carry capacity for experimental
evaluation of one PC is
limited.
In our test, we used a 2.66-GHz
PC with a 1-Gbyte memory to run
both ATS and Adapts. The experiment
took 3,600 seconds in real
time. The number of intersections
we tested increased from two to 20,
and Figure 3 shows the time cost of
each experiment. When the number
of traffic-control agents is 20,
the experiment takes 1,130 seconds.
If we set the time threshold to 600
seconds, the maximum number of
intersections in one experiment is
only 12. This is insufficient to handle
model major urban areas such as Beijing,
where the central area within
the Second Ring Road intersection
contains up to 119 intersections. We
would need several PCs or a highperformance
server to handle the experimental
scale of several hundreds
of intersections.
Furthermore, a complete urbantraffic
management system also
requires traffic control,
detection, guidance, monitoring,
and emergency
subsystems. To handle
the different states in a
traffic environment, an
urban-traffic management
system must provide appropriate
traffic strategy
agents. And to handle
performance improvements
and the addition
of new subsystems, new
traffic strategies must be
introduced continually. So future
urban-traffic management systems
must generate, store, manage, test,
optimize, and effectively use a large
number of mobile agents. Moreover,
they need a decision-support system
to communicate with traffic managers.
A comprehensive, powerful decision-
support system with a friendly
human-computer interface is an inevitable
trend in the development of
urban-traffic management systems.
Thus, future systems must have the
following capabilities.