Driving successful brand strategy through customer driven innovation
User-Driven Cloud Transportation System for Smart Driving
-
Upload
amg93 -
Category
Engineering
-
view
189 -
download
2
Transcript of User-Driven Cloud Transportation System for Smart Driving
ABSTRACT
Traffic congestion is a major problem worldwide affecting millions of peoples daily
activities. Intelligent transportation system (ITS) has emerged as an effective way to
improving the performance of transportation systems, aiming to relieve the congestion
and maximize total social benefit. Key challenges of its in recent years include the per-
vasive data collection, data security, privacy preserving, large volume data processing,
and intelligent analytics. These challenges lead to a revolution in ITS development by
leveraging the crowd sourcing scheme and cloud computing architecture. A user-driven
Cloud Transportation system (CTS) employs a scheme of user-driven crowd sourcing
to collect user data for traffic model construction and congestion prediction including
data collection, filtering, modeling, intelligent computation and publish.
Contents
1 INTRODUCTION 1
2 INTELLIGENT TRANSPORTATION SYSTEM (ITS) 2
2.1 Intelligent transport technologies . . . . . . . . . . . . . . . . . . . . . . 3
2.1.1 Wireless communications . . . . . . . . . . . . . . . . . . . . . . . 3
2.1.2 Computational technologies . . . . . . . . . . . . . . . . . . . . . 4
2.1.3 Floating car data/floating cellular data . . . . . . . . . . . . . . . 4
2.1.4 Sensing technologies . . . . . . . . . . . . . . . . . . . . . . . . . 6
2.1.5 Inductive loop detection . . . . . . . . . . . . . . . . . . . . . . . 6
2.1.6 Video vehicle detection . . . . . . . . . . . . . . . . . . . . . . . . 6
2.1.7 Bluetooth detection . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.2 Intelligent transport applications . . . . . . . . . . . . . . . . . . . . . . 7
2.2.1 Emergency vehicle notification systems . . . . . . . . . . . . . . . 7
2.2.2 Automatic road enforcement . . . . . . . . . . . . . . . . . . . . . 8
2.2.3 Variable speed limits . . . . . . . . . . . . . . . . . . . . . . . . . 9
2.3 Challenges . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
3 USER-DRIVEN CLOUD TRANSPORTATION
SYSTEM 11
3.1 Cloud computing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
3.2 Application Scenario . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
3.3 Overview of User-Driven CTS . . . . . . . . . . . . . . . . . . . . . . . . 12
3.4 Core CTS Services . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
4 SYSTEM DESIGN AND IMPLEMENTATION 17
4.1 System Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
4.2 Prototype Implementation . . . . . . . . . . . . . . . . . . . . . . . . . . 23
4.3 Preliminary User Feedback . . . . . . . . . . . . . . . . . . . . . . . . . 24
5 CONCLUSION AND FUTURE WORK 25
References 26
i
List of Figures
1 RFID E-ZPass reader by using vehicle re-identification method . . . . . . 5
2 Saw cut loop detectors for vehicle detection . . . . . . . . . . . . . . . . 7
3 Automatic speed enforcement gantry . . . . . . . . . . . . . . . . . . . . . 9
4 Variable speed limit sign in the United States . . . . . . . . . . . . . . . . 9
5 Application Scenario and Workflow . . . . . . . . . . . . . . . . . . . . . 12
6 User-Driven CTS Review . . . . . . . . . . . . . . . . . . . . . . . . . . 13
7 User-Driven CTS Structure . . . . . . . . . . . . . . . . . . . . . . . . . 14
8 User-Driven CTS Service Model . . . . . . . . . . . . . . . . . . . . . . . 15
9 CTS Server Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
10 Components of IaaS Model . . . . . . . . . . . . . . . . . . . . . . . . . . 19
11 MapReduce Computing Model . . . . . . . . . . . . . . . . . . . . . . . . 19
12 System Interaction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
13 Screenshot of Mobile Application Prototype . . . . . . . . . . . . . . . . . 23
14 Screenshot of Background Management System Prototype . . . . . . . . . 24
ii
User-Driven Cloud Transportation System for Smart Driving
1 INTRODUCTION
Intelligent transportation systems (ITS) are advanced applications which, without
embodying intelligence as such, aim to provide innovative services relating to different
modes of transport and traffic management and enable various users to be better in-
formed and make safer, more coordinated, and ’smarter’ use of transport networks.In
the developing world, the migration from rural to urbanized habitats has progressing
without major development in transportation. Intelligent transportation system (ITS)
has emerged as an effective way to improving the performance of transportation sys-
tems, aiming to relieve the congestion and maximize total social benefit. ITS Intelligent
Transport Systems is a generic term for the integrated application of communications,
control and information processing technologies to the transportation system. The re-
sultant benefits save lives, time, money, energy and the environment. The term ITS is
flexible and capable of being interpreted in a broad or narrow way. Transport telem-
atics is a term used in Europe for the group of technologies that support ITS. ITS
World Congress is a world-wide annual event to promote and showcase ITS technolo-
gies. ERTICO ITS Europe, ITS America and ITS Japan work closely together in the
preparation of the annual ITS World Congress and Exhibition attracting over 8,000
people. Each year the event takes place in a different region (Europe, Americas or Asia-
Pacific) Many of the proposed ITS systems also involve surveillance of the roadways..A
user-driven pattern of ITS based on cloud computing technology named user-driven
cloud transportation system (CTS) to enhance data collection capability. CTS operates
around users, in the least help of external data source, to calculate the gathered data
and provide real time guidance back to them. User data is processed to reconstruct the
traffic model, based on which the prediction algorithm can be performed to guide an
optimized route for each user and the hole transportation system. The central process-
ing system applies the cloud computing architecture to support mass data storage and
distributed computing from user cloud.
1
User-Driven Cloud Transportation System for Smart Driving
2 INTELLIGENT TRANSPORTATION SYSTEM
(ITS)
ITS is a synergy of related technologies including communications network, sens-
ing equipment and computational computing models. The communication technologies
adopted in ITS include radio frequency, IEEE 802.11p WAVE, WiMAX, GSM and
3G. ITU-T are developing a set of standards named CALM (Continuous Air-interface
for Long- and Medium-range communications), promise to provide the underlying glue
to make all types of communication happen in ITS application. Sensing systems for
ITS are networks of vehicle- and infrastructure-based sensors. For example, inductive
loop detection can be placed in a roadbed to detect vehicles pass through. Traffic flow
measurement and automatic incident detection using video cameras is another form of
vehicle detection. Floating Car Data (FCD) is a method for collecting position and
speed data from vehicles traveling. FCD provides the advantages of less expensive
device, more coverage, less maintenance and high usability. ITS applications can be
classified into four primary categories:
Table 1: ITS Application Classification
ITS Application Category Specific Applications
Travel Information SystemsNavigation SystemReal-Time Traffic InformationPoints of Interest Information
Transportation Management SystemsTraffic Operation CenterTraffic Signal ControlAutomatic Road Enforcement
Transportation Pricing Systems
Electronic Toll CollectionElectronic Road PricingVariable Parking FeesVehicle-Miles Travelled Usage Fees
Public Transportation SystemsReal-Time Public Transit Information SystemAutomatic Vehicle LocationEmergency Vehicle Notification System
2
User-Driven Cloud Transportation System for Smart Driving
2.1 Intelligent transport technologies
Recent governmental activity in the area of ITS specifically in the United States is
further motivated by an increasing focus on homeland security. Many of the proposed
ITS systems also involve surveillance of the roadways, which is a priority of homeland
security. Funding of many systems comes either directly through homeland security
organisations or with their approval. Further, ITS can play a role in the rapid mass
evacuation of people in urban centres after large casualty events such as a result of a
natural disaster or threat. Much of the infrastructure and planning involved with ITS
parallels the need for homeland security systems.
In the developing world, the migration from rural to urbanized habitats has progressed
differently. Many areas of the developing world have urbanised without significant mo-
torisation and the formation of suburbs. A small portion of the population can afford
automobiles, but the automobiles greatly increase congestion in these multimodal trans-
portation systems. They also produce considerable of air pollution, pose a significant
safety risk, and exacerbate feelings of inequities in the society. High-population den-
sity could be supported by a multimodal system of walking, bicycle transportation,
motorcycles, buses, and trains.
Other parts of the developing world, such as China, remain largely rural but are
rapidly urbanising and industrialising. In these areas a motorised infrastructure is being
developed alongside motorisation of the population. Great disparity of wealth means
that only a fraction of the population can motorise, and therefore the highly dense
multimodal transportation system for the poor is cross-cut by the highly motorised
transportation system for the rich. Intelligent transport systems vary in technologies
applied, from basic management systems such as car navigation, traffic signal control
systems, container management systems, variable message signs, automatic number
plate recognition or speed cameras to monitor applications, such as security CCTV
systems and to more advanced applications that integrate live data and feedback from
a number of other sources, such as parking guidance and information systems, weather
information, bridge de-icing (US deicing) systems, and the like.
2.1.1 Wireless communications
Various forms of wireless communications technologies have been proposed for intelli-
gent transportation systems. Radio modem communication on UHF and VHF frequen-
cies are widely used for short and long range communication within ITS. Short-range
communications of 350 m can be accomplished using IEEE 802.11 protocols, specifi-
cally WAVE or the Dedicated Short Range Communications standard being promoted
3
User-Driven Cloud Transportation System for Smart Driving
by the Intelligent Transportation Society of America and the United States Department
of Transportation. Theoretically, the range of these protocols can be extended using
Mobile ad hoc networks or Mesh networking.
Longer range communications have been proposed using infrastructure networks such
as WiMAX (IEEE 802.16), Global System for Mobile Communications (GSM), or 3G.
Long-range communications using these methods are well established, but, unlike the
short-range protocols, these methods require extensive and very expensive infrastructure
deployment. There is lack of consensus as to what business model should support this
infrastructure. Auto Insurance companies have utilised ad hoc solutions to support
eCall and behavioural tracking functionalities in the form of Telematics 2.0.
2.1.2 Computational technologies
Recent advances in vehicle electronics have led to a move towards fewer, more capable
computer processors on a vehicle. A typical vehicle in the early 2000s would have be-
tween 20 and 100 individual networked microcontroller/Programmable logic controller
modules with non-real-time operating systems. The current trend is toward fewer, more
costly microprocessor modules with hardware memory management and Real-Time Op-
erating Systems. The new embedded system platforms allow for more sophisticated
software applications to be implemented, including model-based process control, artifi-
cial intelligence, and ubiquitous computing. Perhaps the most important of these for
Intelligent Transportation Systems is artificial intelligence.
2.1.3 Floating car data/floating cellular data
Floating car or probe data collection is a set of relatively low-cost methods for obtain-
ing travel time and speed data for vehicles travelling along streets, highways, motorways
(freeways), and other transport routes. Broadly speaking, three methods have been used
to obtain the raw data:
• Triangulation method
In developed countries a high proportion of cars contain one or more mobile
phones. The phones periodically transmit their presence information to the mobile
phone network, even when no voice connection is established. In the mid-2000s,
attempts were made to use mobile phones as anonymous traffic probes. As a car
moves, so does the signal of any mobile phones that are inside the vehicle. By
measuring and analysing network data using triangulation, pattern matching or
cell-sector statistics (in an anonymous format), the data was converted into traf-
fic flow information. With more congestion, there are more cars, more phones,
4
User-Driven Cloud Transportation System for Smart Driving
and thus, more probes. In metropolitan areas, the distance between antennas is
shorter and in theory accuracy increases. An advantage of this method is that no
infrastructure needs to be built along the road, only the mobile phone network
is leveraged. But in practice the triangulation method can be complicated, es-
pecially in areas where the same mobile phone towers serve two or more parallel
routes (such as a motorway (freeway) with a frontage road, a motorway (freeway)
and a commuter rail line, two or more parallel streets, or a street that is also a
bus line). By the early 2010s, the popularity of the triangulation method was
declining
• Vehicle re-identification
Vehicle re-identification methods require sets of detectors mounted along the road.
In this technique, a unique serial number for a device in the vehicle is detected at
one location and then detected again (re-identified) further down the road. Travel
times and speed are calculated by comparing the time at which a specific device
is detected by pairs of sensors. This can be done using the MAC (Machine Access
Control) addresses from Bluetooth devices, or using the RFID serial numbers from
Electronic Toll Collection (ETC) transponders (also called ”toll tags”).
Figure 1: RFID E-ZPass reader by using vehicle re-identification method
• GPS based methods
An increasing number of vehicles are equipped with in-vehicle satnav/GPS (satel-
lite navigation) systems that have two-way communication with a traffic data
provider. Position readings from these vehicles are used to compute vehicle speeds.
Modern methods may not use dedicated hardware but instead Smartphone based
solutions using so called Telematics 2.0 approaches.
5
User-Driven Cloud Transportation System for Smart Driving
2.1.4 Sensing technologies
Technological advances in telecommunications and information technology, coupled
with ultramodern/state-of-the-art microchip, RFID (Radio Frequency Identification),
and inexpensive intelligent beacon sensing technologies, have enhanced the technical
capabilities that will facilitate motorist safety benefits for intelligent transportation
systems globally. Sensing systems for ITS are vehicle- and infrastructure-based net-
worked systems, i.e., Intelligent vehicle technologies. Infrastructure sensors are inde-
structible (such as in-road reflectors) devices that are installed or embedded in the road
or surrounding the road (e.g., on buildings, posts, and signs), as required, and may be
manually disseminated during preventive road construction maintenance or by sensor
injection machinery for rapid deployment. Vehicle-sensing systems include deployment
of infrastructure-to-vehicle and vehicle-to-infrastructure electronic beacons for identifi-
cation communications and may also employ video automatic number plate recognition
or vehicle magnetic signature detection technologies at desired intervals to increase sus-
tained monitoring of vehicles operating in critical zones.
2.1.5 Inductive loop detection
Inductive loops can be placed in a roadbed to detect vehicles as they pass through
the loop’s magnetic field. The simplest detectors simply count the number of vehicles
during a unit of time (typically 60 seconds in the United States) that pass over the loop,
while more sophisticated sensors estimate the speed, length, and weight of vehicles and
the distance between them. Loops can be placed in a single lane or across multiple
lanes, and they work with very slow or stopped vehicles as well as vehicles moving at
high-speed.
2.1.6 Video vehicle detection
Traffic-flow measurement and automatic incident detection using video cameras is
another form of vehicle detection. Since video detection systems such as those used in
automatic number plate recognition do not involve installing any components directly
into the road surface or roadbed, this type of system is known as a ”non-intrusive”
method of traffic detection. Video from cameras is fed into processors that analyse the
changing characteristics of the video image as vehicles pass. The cameras are typically
mounted on poles or structures above or adjacent to the roadway. Most video detec-
tion systems require some initial configuration to ”teach” the processor the baseline
background image. This usually involves inputting known measurements such as the
distance between lane lines or the height of the camera above the roadway. A single
video detection processor can detect traffic simultaneously from one to eight cameras,
6
User-Driven Cloud Transportation System for Smart Driving
depending on the brand and model. The typical output from a video detection system is
lane-by-lane vehicle speeds, counts, and lane occupancy readings. Some systems provide
additional outputs including gap, headway, stopped-vehicle detection, and wrong-way
vehicle alarms.
Figure 2: Saw cut loop detectors for vehicle detection
2.1.7 Bluetooth detection
Bluetooth is an accurate and inexpensive way to measure travel time and make ori-
gin/destination analysis. Bluetooth is a wireless standard used to communicate between
electronic devices like mobile/smart phones, headsets, navigation systems, computers
etc. Bluetooth road sensors are able to detect Bluetooth MAC addresses from Bluetooth
devices in passing vehicles. If these sensors are interconnected they are able to calculate
travel time and provide data for origin/destination matrices. Compared to other traffic
measurement technologies.
2.2 Intelligent transport applications
2.2.1 Emergency vehicle notification systems
The in-vehicle eCall is an emergency call generated either manually by the vehicle
occupants or automatically via activation of in-vehicle sensors after an accident. When
activated, the in-vehicle eCall device will establish an emergency call carrying both
voice and data directly to the nearest emergency point (normally the nearest E1-1-2
7
User-Driven Cloud Transportation System for Smart Driving
Public-safety answering point, PSAP). The voice call enables the vehicle occupant to
communicate with the trained eCall operator. At the same time, a minimum set of data
will be sent to the eCall operator receiving the voice call.
The minimum set of data contains information about the incident, including time,
precise location, the direction the vehicle was traveling, and vehicle identification. The
pan-European eCall aims to be operative for all new type-approved vehicles as a stan-
dard option. Depending on the manufacturer of the eCall system, it could be mobile
phone based (Bluetooth connection to an in-vehicle interface), an integrated eCall de-
vice, or a functionality of a broader system like navigation, Telematics device, or tolling
device. eCall is expected to be offered, at earliest, by the end of 2010, pending stan-
dardization by the European Telecommunications Standards Institute and commitment
from large EU member states such as France and the United Kingdom.Congestion pric-
ing gantry at North Bridge Road, Singapore. The EC funded project SafeTRIP is
developing an open ITS system that will improve road safety and provide a resilient
communication through the use of S-band satellite communication. Such platform will
allow for greater coverage of the Emergency Call Service within the EU.
2.2.2 Automatic road enforcement
A traffic enforcement camera system, consisting of a camera and a vehicle-monitoring
device, is used to detect and identify vehicles disobeying a speed limit or some other
road legal requirement and automatically ticket offenders based on the license plate
number. Traffic tickets are sent by mail. Applications include:
• Speed cameras that identify vehicles traveling over the legal speed limit. Many
such devices use radar to detect a vehicle’s speed or electromagnetic loops buried
in each lane of the road.
• Red light cameras that detect vehicles that cross a stop line or designated stopping
place while a red traffic light is showing.
• Bus lane cameras that identify vehicles traveling in lanes reserved for buses. In
some jurisdictions, bus lanes can also be used by taxis or vehicles engaged in car
pooling.
• Level crossing cameras that identify vehicles crossing railways at grade illegally.
• Double white line cameras that identify vehicles crossing these lines.
• High-occupancy vehicle lane cameras that identify vehicles violating HOV require-
ments.
8
User-Driven Cloud Transportation System for Smart Driving
• Turn cameras at intersections where specific turns are prohibited on red. This
type of camera is mostly used in cities or heavy populated areas.
Figure 3: Automatic speed enforcement gantry
2.2.3 Variable speed limits
Recently some jurisdictions have begun experimenting with variable speed limits that
change with road congestion and other factors. Typically such speed limits only change
to decline during poor conditions, rather than being improved in good ones. One exam-
ple is on Britain’s M25 motorway, which circumnavigates London. On the most heavily
traveled 14-mile (23 km) section (junction 10 to 16) of the M25 variable speed limits
combined with automated enforcement have been in force since 1995. Initial results
indicated savings in journey times, smoother-flowing traffic, and a fall in the number of
accidents, so the implementation was made permanent in 1997. Further trials on the
M25 have been thus far proven inconclusive.
Figure 4: Variable speed limit sign in the United States
9
User-Driven Cloud Transportation System for Smart Driving
2.3 Challenges
• Many of the proposed ITS systems focused on surveillance of the roadways. The
high cost and low mobility of monitoring equipment limit the deployment scale
and density. Data from auxiliary instruments such as traffic detectors also cannot
meet the requirements of more complex and accurate calculation and reduction.
• Pervasive data from transportation has not been collected. The vehicles, as the
main component of traffic flow, need to be monitored for their position, direction,
velocity and even destination. More comprehensive collection of information will
facilitate intelligent analytics.
• Large-scale of user leads to the requirements of enormous computing and storage
resources. Furthermore, It needs to apply the more intelligent prediction model
and approach to make full use of pervasive traffic data.
• User-driven Scheme: User-driven is a crowd sourcing process that involves out-
sourcing tasks to a distributed group of agent. In ITS, pervasive data can be
collected by user-driven architecture for traffic model construction and prediction.
• Context-aware Publish/Subscribe Mechanism: Publish Subscribe user informa-
tion collection mechanism based on SOA (Service-Oriented Architecture) gener-
ally provides a way for user information collection by perfectly connect the mobile
platform, center cloud processing system and background management system
• Cloud Computing infrastructure: Cloud computing is the delivery of computing
and storage capacity as a service to a community of end-recipients. With the
help of cloud computing platform, big data processing and complicated intelligent
analyses can be supported elastically. ITU-T anticipates the Cloud Computing
a next revolutionary technology and has formed a focus group on various cloud
computing researches.
10
User-Driven Cloud Transportation System for Smart Driving
3 USER-DRIVEN CLOUD TRANSPORTATION
SYSTEM
3.1 Cloud computing
Cloud computing is internet-based computing in which large groups of remote servers
are networked to allow the centralized data storage, and online access to computer ser-
vices or resources. Clouds can be classified as public, private or hybrid.Cloud computing
relies on sharing of resources to achieve coherence and economies of scale, similar to a
utility (like the electricity grid) over a network. At the foundation of cloud computing
is the broader concept of converged infrastructure and shared services.
Cloud computing, or in simpler shorthand just ”the cloud”, also focuses on maximiz-
ing the effectiveness of the shared resources. Cloud resources are usually not only shared
by multiple users but are also dynamically reallocated per demand. This can work for
allocating resources to users. For example, a cloud computer facility that serves Euro-
pean users during European business hours with a specific application (e.g., email) may
reallocate the same resources to serve North American users during North America’s
business hours with a different application (e.g., a web server). This approach should
maximize the use of computing power thus reducing environmental damage as well since
less power, air conditioning, rackspace, etc. are required for a variety of functions. With
cloud computing, multiple users can access a single server to retrieve and update their
data without purchasing licenses for different applications.
The term ”moving to cloud” also refers to an organization moving away from a tra-
ditional CAPEX model (buy the dedicated hardware and depreciate it over a period
of time) to the OPEX model (use a shared cloud infrastructure and pay as one uses
it).Proponents claim that cloud computing allows companies to avoid upfront infras-
tructure costs, and focus on projects that differentiate their businesses instead of on in-
frastructure. Proponents also claim that cloud computing allows enterprises to get their
applications up and running faster, with improved manageability and less maintenance,
and enables IT to more rapidly adjust resources to meet fluctuating and unpredictable
business demand. Cloud providers typically use a ”pay as you go” model. This can
lead to unexpectedly high charges if administrators do not adapt to the cloud pric-
ing model.The present availability of high-capacity networks, low-cost computers and
storage devices as well as the widespread adoption of hardware virtualization, service-
oriented architecture, and autonomic and utility computing have led to a growth in
cloud computing.
11
User-Driven Cloud Transportation System for Smart Driving
3.2 Application Scenario
Workflow of ITS application generally involves three phases, namely Route Decision,
Vehicle Travelling and Finish Driving.
Figure 5: Application Scenario and Workflow
Three groups of participants are involved in this workflow, including user (P1), vehicle
(P2) and system (P3). In the stage of Route Decision, user can select the destination
(S1) and send it to the server. The system receives the message (S2) and the user starts
to drive (S3). The vehicle uploads its information (S4) in the Vehicle Travelling stage.
The system receives the user data (S5) and predicts the traffic condition (S6). Results
will be push to the user automatically. User can decide whether to change his route
(S7). In the last stage, Finishing Driving, the vehicle, user and system finish their work
successively (S8-S10).
3.3 Overview of User-Driven CTS
Traditional ITS which relies on sensing devices such as CCTV cameras, infrared radar
detector and optical detectors is restricted by their mobility for a widely deployment
to collect pervasive traffic information and transportation system optimization. A user-
driven pattern of ITS based on cloud computing technology named user-driven cloud
transportation system (CTS) to enhance data collection capability. The user-driven
CTS has unique features in the following aspects:
• CTS operates around users, in the least help of external data source, to calculate
the gathered data and provide real time guidance back to them. From the systems
point of view, the users are treated as cloud services and discovered and invoked
using a cloud computing methodology.
12
User-Driven Cloud Transportation System for Smart Driving
• User data is processed to reconstruct the traffic model, based on which the pre-
diction algorithm can be performed to guide an optimized route for each user and
the hole transportation system.
• The central processing system applies the cloud computing architecture to support
mass data storage and distributed computing from user cloud. Traffic data can
be naturally divided by area which perfectly fits the MapReduce pattern in cloud
computing applications.
Figure 6: User-Driven CTS Review
Figure 6 depicts a CTS application scenario when a driver uses the system to guide
his driving route. The user data including location and velocity are calculated using
the GPS receiver and positioning techniques. After that the mobile application sends
message to the cloud server for storage and computing. The communication between
server and user is implemented through the cellular network or other technology in-
cluding wireless network and WAVE. Each client needs to register in the system and
provides username and password for authentication. The server collects data, processes
them and reconstructs a traffic model. According to this traffic model, the server should
be able to send to each client personalized and dynamic information about traffic. The
information is consisted of average travel time to the desired destination and real-time
13
User-Driven Cloud Transportation System for Smart Driving
route guidance about the optimal route to avoid the congestion. Additionally, other
information such as customized points of interest (POIs) are also sent and displayed on
the user’s device according to users habits.
The CTS is composed of three main components, namely cloud server, user cloud and
background management system. Figure 7 illustrates the user-driven CTS structure.
Figure 7: User-Driven CTS Structure
The cloud server is responsible for the receiving, processing, querying, pushing and
other functions on traffic information. Cloud server is a cluster of virtualized resources
providing services. The server listens and receives traffic data submitted by the mobile
agents, and audit the legality of contents. Data processing algorithm was adapted
to aggregate the data into distributed cloud database with specific standard, such as
position, time-stamp and event type. The cloud server calculates the results and pushes
them to the user with the information of POI, activities and user information. The
cloud server structure and service model will be discussed in detail in section IV. The
mobile agents in user cloud include smart phone and sensing device. The basic functions
of the mobile device is sending and receiving traffic data. Other related functions such
as map and information demonstration can be provided by mobile devices. Background
management system includes the management interface for central cloud server, which
implements the function of system performance monitoring, information querying, user
management, etc.
14
User-Driven Cloud Transportation System for Smart Driving
3.4 Core CTS Services
The proposed CTS operates by means of interactions between its components in
providing services, as shown in Figure 8.
Figure 8: User-Driven CTS Service Model
Services implemented to support intelligent transportation include the following core
functions:
1. Service Discovery
Along with the popularity of the web services, how to discover the service quickly,
automatically and accurately is a key research issue. The Service Discovery (SD)
keeps an up-to-date database of services. This work is usually done in Cloud and
Grid systems by using data replication techniques. Although a lot of approaches
have been proposed to solve this problem like Enterprise Service Bus (ESB) and
Universal Description Discovery and Integration (UDDI), these approaches are
designed for restricted area or scale. Things are different and need further discuss
when the web services outbreaks in scale.
2. Routing Service
Routing Service (RS) is responsible for the computing of best route from current
position to the destination inputted by mobile agent. The RS receives messages
and replies the best route and also the time expected for driving with the Timing
Service (TS).
3. Timing Service
Timing Service (TS) is responsible for the computing of time expected to spend on
the giving route from the Routing Service (RS). The RS and TS will be recalled
when the user change route according to the suggestion replied by Prediction
Service (PS).
15
User-Driven Cloud Transportation System for Smart Driving
4. Prediction Service
Prediction Service (PS) pushes message of real-time traffic situation and location-
specific alerts. The function is implemented with algorithm to fuse and analyze
the pervasive traffic data collected anonymously from user. PS is aware of the
road network topology and aims to optimize traffic flow on users perspective and
also on a macro scale.
5. Communication Service
A Communication Service (CS) is a service wrapper for message conveys be-
tween cloud server and vehicles mobile devices. CS uses the structure of pub-
lish/subscribe to push real-time message between server and user bi-directionally
according to the subscriptions of user-interested topic.
6. Other Services
Besides the core CTS services, system allows other types of services implemented
easily. Examples of additional services could include:
• POI Service: A service finding POI closest to the selected area or the current
position.
• Emergency Service: Vehicles could be registered to submit emergency signal
for a higher priority to pass through.
• Social Service: Social service maintains a social network in CTS allowing
user to share information between friends.
16
User-Driven Cloud Transportation System for Smart Driving
4 SYSTEM DESIGN AND IMPLEMENTATION
4.1 System Architecture
Based on CTS model , a three layers structure of cloud application system is designed
and a prototype system has been implemented.
1. Infrastructure as a Service (IaaS)
In IaaS model, cloud providers offer storage resources, network resources and com-
puting resources. A unified source layer is constructed above the fabric layer with
the help of virtual machines and their monitoring system. IaaS clouds providers
supply these unified resources on demand for cloud storage and computing. Net-
work resources link the user cloud, central cloud server, background management
system and digital map to a whole system. Storage resources is provided for data
storage and management. The cloud server centralizes all kinds of traffic informa-
tion from the terminal and other system information. It uses the traditional SQL
database to store the system information such as registration, configuration and
social networks data. NoSQL database, a class of database management system
identified by its non-adherence to the widely used relational database management
system model, is applied for traffic data cloud storage . NoSQL is often highly
optimized for retrieve and append operations and often offer little functionality
beyond record storage (e.g. key-value stores) which is useful when working with
a huge quantity of data and the data’s nature does not require a relational model
for the data structure. Traffic data can be naturally divided by area which fits
the NoSQL and MapReduce pattern in cloud storage and computing. The system
components of IaaS model, as shown in Figure 9, include: Hadoop, a framework
for running applications on large clusters of commodity hardware, MapReduce,
a programming model for distributed large data sets processing on clusters of
computers, HBase, a non-relational, distributed database, Hive, a data warehouse
infrastructure built on top of Hadoop providing data summarization, query, and
analysis, Chukwa, a data collection system for monitoring large distributed sys-
tems, Pig, a platform for analyzing large data sets, ZooKeeper, a centralized
service for maintaining configuration information, naming, providing distributed
synchronization, and providing group services.Commodity hardware is a term for
affordable devices that are generally compatible with other such devices. In a pro-
cess called commodity computing or commodity cluster computing, these devices
are often networked to provide more processing power when those who own them
cannot afford to purchase more elaborate supercomputers, or want to maximize
savings in IT design.
17
User-Driven Cloud Transportation System for Smart Driving
Vehicle velocity data is stored in key-value pair < V ehicleID, V elocity > after
pre-processing. A key-value pair represents a vehicles speed in a certain times-
tamp. Average velocity of each vehicle can be mapped into the corresponding
road velocity. Obviously, each task of the procedure is independent, only need
to ensure that data of a vehicle allocated into same processing job. Therefore,
MapReduce computing model is suitable for traffic data processing.
Figure 9: CTS Server Architecture
Figure 11 depicts the MapReduce computing model proposed. The model is
consist of two parts namely Map and Reduce. MapReduce master uses hash
function (Hash(V ehicleID)modM) to split data into M Map jobs. When map
worker received the job data, user-defined Map function will be called to calculate
the average velocity for each vehicle < V ehicleID, avg > and the mapping from
vehicle to corresponding RoadID into intermediate result in the collection of <
RoadID, avg >. Intermediate result will be copy and merge into R Reduce jobs
in < RoadID, [avg1, avg2, ...] > by the same hash function. Reduce function
will return the final result < RoadID, avg >.The algorithm of average velocity
18
User-Driven Cloud Transportation System for Smart Driving
computing are described in Algorithm 1. Leveraging the MapReduce computing
framework, user only need to define a Map function and a Reduce function. Job
allocation and result collection will be implemented automatically. This high-
level abstraction allows user to develop parallel and distributed algorithm without
professional experience.
Figure 10: Components of IaaS Model
Figure 11: MapReduce Computing Model
2. Platform as a Service (PaaS)
In the PaaS model, system deliver a storage and computing service from IaaS
platform for higher level functions including web service framework, data access
object framework, Internet service and publish/subscribe mechanism. With PaaS
offers, the underlying computer and storage resources scale automatically to match
platform services demand.
19
User-Driven Cloud Transportation System for Smart Driving
• Web Service Framework: Different functions are linked through well-defined
interface by SOA-based lightweight web service framework. The definition
of interface is independent of the hardware platforms, operating systems and
programming languages. This makes the interaction in system performs in a
unified and common way.
• Data Access Object Framework: A data access object (DAO) is an object that
provides an abstract interface to some type of database or other persistence
mechanism. By mapping application calls to the persistence layer, DAO pro-
vide some specific data operations without exposing details of the database.
This isolation supports the Single responsibility principle. It separates what
data accesses the application needs, in terms of domain-specific objects and
data types (the public interface of the DAO), from how these needs can be
satisfied with a specific DBMS, database schema, etc. (the implementation
of the DAO).ADO .NET entity framework is integrated to provide solution
of high-speed access on large amounts data while reducing the dependence
of the service layer to facilitate data migration and maintenance.
• Publish/Subscribe Mechanism:In software architecture, publishsubscribe is a
messaging pattern where senders of messages, called publishers, do not pro-
gram the messages to be sent directly to specific receivers, called subscribers.
Instead, published messages are characterized into classes, without knowl-
edge of what, if any, subscribers there may be. Similarly, subscribers express
interest in one or more classes, and only receive messages that are of interest,
20
User-Driven Cloud Transportation System for Smart Driving
without knowledge of what, if any, publishers there are.This pattern provides
greater network scalability and a more dynamic network topology, with a re-
sulting decreased flexibility to modify the Publisher and its structure of the
data published.In the pub/sub model, subscribers typically receive only a
subset of the total messages published. The process of selecting messages for
reception and processing is called filtering. There are two common forms of
filtering: topic-based and content-based.
In a topic-based system, messages are published to ”topics” or named logical
channels. Subscribers in a topic-based system will receive all messages pub-
lished to the topics to which they subscribe, and all subscribers to a topic
will receive the same messages. The publisher is responsible for defining the
classes of messages to which subscribers can subscribe. In a content-based
system, messages are only delivered to a subscriber if the attributes or con-
tent of those messages match constraints defined by the subscriber. The
subscriber is responsible for classifying the messages.Some systems support
a hybrid of the two publishers post messages to a topic while subscribers
register content-based subscriptions to one or more topics.In many pub/sub
systems, publishers post messages to an intermediary message broker or event
bus, and subscribers register subscriptions with that broker, letting the broker
perform the filtering. The broker normally performs a store and forward func-
tion to route messages from publishers to subscribers. In addition, the broker
may prioritize messages in a queue before routing.Subscribers may register
for specific messages at build time, initialization time or runtime. In GUI
systems, subscribers can be coded to handle user commands (e.g., click of a
button), which corresponds to build time registration. Some frameworks and
software products use xml configuration files to register subscribers. These
configuration files are read at initialization time. The most sophisticated
alternative is when subscribers can be added or removed at runtime. This
latter approach is used, for example, in database triggers, mailing lists, and
RSS.Most Data Distribution Service (DDS) do not use a broker in the mid-
dle. Instead, each publisher and subscriber in the pub/sub system shares
meta-data about each other. The publisher and the subscribers cache this
information locally and route messages based on the discovery of each other
in the shared cognizance.
CTS provides solution to push message between central server and mobile
agent using MQTT protocol. MQTT is a publish/subscribe, extremely simple
and lightweight messaging protocol, designed for constrained devices and low-
bandwidth or unreliable networks. These principles make the protocol ideal
21
User-Driven Cloud Transportation System for Smart Driving
of the emerging Internet of Things world of connected devices, and for mobile
applications where bandwidth and battery power are at a premium.
3. Software as a Service (SaaS)
In SaaS model, application software in the cloud and cloud users access the soft-
ware from cloud clients. The cloud users do not manage the cloud infrastructure
and platform on which the application is running. That makes a cloud application
different from other applications in its elasticity. SaaS model in CTS provides the
core business logic of applications including traffic, living, social and user infor-
mation services. All event information is packed in the form of JSON (JavaScript
Object Notation) string. Central server accepts the JSON message to response
according to the different business logic. It use a scene of information subscrip-
tion and push to describe the interaction flow of the system (Figure 12). Mobile
user calls the service of message broker Subscribe() to subscribe the topic inter-
ested. Message broker declares the interface and implements it with WebInvoke()
in cloud server when it receives the subscription. Cloud server uses readDB() and
writeDB() to interact with database for MapReduce calculation. CTS uses an
open source message broker Mosquitto to push message to mobile user. Manage-
ment personnel acquires background information through interface of database for
system maintenance.
Figure 12: System Interaction
22
User-Driven Cloud Transportation System for Smart Driving
4.2 Prototype Implementation
An application prototype is implemented based the system design. The mobile ap-
plication is implemented on Android platform and the central server is built with .NET
framework on a private cloud structure. It presents a screenshot of mobile application
for prototype system in Figure 13. The interface of the Android application displays
current traffic conditions by different color mark. Green represents the traffic is smooth,
while yellow represents a slow traffic and red is congestion. The server will predict traffic
congested and feedback to the user in real-time also with the information about road
construction and accident.
Figure 13: Screenshot of Mobile Application Prototype
Figure 14 depicts a screenshot of background management system prototype. This
application is mainly focused on the traffic event showing, traffic data management and
auxiliary information management. The upper panel is able to mark events on the map
display. The lower panel is responsible for traffic data details display. Events before
audit is on the left side while audited data on the right panel.
23
User-Driven Cloud Transportation System for Smart Driving
4.3 Preliminary User Feedback
This prototype is developed for smart driving. The Application implements the func-
tion of traffic date collection and real-time traffic information dissemination. Based on
the smart phone platform, it can provide user dynamic event display, parking slot in-
formation, social network and other functions which cannot be provided by traditional
GPS devices. The function of data collection, event audit, automatic aggregation, traffic
model construction and prediction are implemented in cloud central server. The appli-
cation still has many features to be improved, such as intelligent prediction algorithm,
automatic learning of user behaviour, traffic abnormality detection, etc. According
to the preliminary system prototype, user driven CTS is an effective model to inte-
grate crowd sourcing scheme, context-aware publish/subscribe mechanism and cloud
computing technology. CTS has theoretically solved the defects of sparse deployment
density, incomprehensive data collection and low data processing ability in traditional
ITS. Through underlying cloud platform interface package, CTS shields the complex be-
haviours of virtual resource management, distributed scheduling with easy-to-use web
service interface to upper layer user. The architecture takes advantage of the pervasive
user data to establish a precise traffic model, supporting the behavior of the traffic pre-
diction calculation. The application has a user-friendly and smooth GUI implemented
on Android platform. More future works of CTS remain to be extended.
Figure 14: Screenshot of Background Management System Prototype
24
User-Driven Cloud Transportation System for Smart Driving
5 CONCLUSION AND FUTURE WORK
Intelligent transportation systems (ITS) are advanced applications which, without
embodying intelligence as such, aim to provide innovative services relating to different
modes of transport and traffic management and enable various users to be better in-
formed and make safer, more coordinated, and ’smarter’ use of transport networks. ITS
relies on sensing devices such as CCTV cameras, infrared radar detector and optical
detectors is restricted by their mobility for a widely deployment to collect pervasive
traffic information and transportation system optimization. A user- driven pattern of
ITS based on cloud computing technology named user-driven cloud transportation sys-
tem (CTS) to enhance data collection capability. It employs a scheme of user-driven
crowdsourcing to collect user data for traffic model construction and congestion pre-
diction which includes data collection, filtering, modeling,intelligent computation and
publish.In this paper its application scenario, system architecture, and core CTS services
model were described.
25
User-Driven Cloud Transportation System for Smart Driving
References
[1] Meng Ma, Yu Huang, Chao-Hsien Chu, Ping Wang,User−Driven Cloud Trans-
portation System for Smart Driving,2012 IEEE 4th International Conference on
Cloud Computing Technology and Science.
[2] J.P. Zhang, F.Y. Wang, K.F. Wang, W.H. Lin, C. Chen , Data-driven Intelli-
gent Transportation Systems: A Survey,, IEEE Transactions on , vol.12, no.4,
pp.1624-1639, Dec. 2011.
26