=Paper=
{{Paper
|id=Vol-1260/paper4
|storemode=property
|title=A Social-Aware Smart Parking Application
|pdfUrl=https://ceur-ws.org/Vol-1260/paper4.pdf
|volume=Vol-1260
|dblpUrl=https://dblp.org/rec/conf/woa/NoceraNR14
}}
==A Social-Aware Smart Parking Application==
https://ceur-ws.org/Vol-1260/paper4.pdf
A Social-Aware Smart Parking Application
Dario Di Nocera* Claudia Di Napoli Silvia Rossi
Dipartimento di Matematica e Applicazioni, Istituto di Calcolo e Reti Dipartimento di Ingegneria Elettrica
Università degli Studi di Napoli ad Alte Prestazioni e Tecnologie dell’Informazione,
“Federico II”, Napoli, Italy C.N.R., Napoli, Italy Università degli Studi di Napoli
dario.dinocera@unina.it claudia.dinapoli@cnr.it “Federico II”, Napoli, Italy
silvia.rossi@unina.it
Abstract—The problem of finding parking spaces in big urban also to take into account specific city needs that cannot always
areas is one of the unsolved challenges of Smart Cities causing been known in advance and that may change in time according
traffic congestion, increased carbon emission and time wasting. to volatile events effecting car circulation at specific time
Network and sensor technologies available today allow to foresee intervals. At this purpose in [2], we proposed a negotiation-
Smart Cities equipped with applications able to provide real-time based smart parking application in order to push motorists to
information on parking space availability, which can be used to
assist motorists in looking for a parking space. In the present
consider parking spaces they would have not selected as their
work, we propose a smart parking application that relies on the first choice, by making them a viable solution for parking.
use of software agent negotiation as a mechanism to automate the In this paper, we present a prototype implementation of
selection of parking spaces according to the user preferences, but a web-based application for smart parking, based on the
at the same time to take into account city needs in terms of areas
motorists should avoid, or car pars occupancy at a specific time.
negotiation-based approach presented in [2], and provide an
Both city needs and user’s preferences are dynamic information experimentation to assess the suitability of the designed mech-
managed by the negotiation mechanism at the time a user’s anism as a smart parking solution. In particular, we are inter-
request is processed, so providing a dynamic-based selection of ested in understanding if the adoption of negotiation together
a parking space. with a dynamic pricing mechanism, is a viable way to satisfy
both motorists and city needs, i.e. if it is possible to maximize
I. I NTRODUCTION social welfare represented by the utility values of both the user
and the city.
One of the big unsolved challenges to make Smart Cities
a reality is the provision of Smart Parking applications. The
II. A S MART PARKING A PPLICATION S CENARIO
overall objective of Smart Cities is to improve city life, so
the provision of smart and sustainable parking solutions is A smart parking system is a complex system composed
becoming a key priority. In fact, several studies made it of several hardware devices able to detect the city occupancy
evident how the problem of searching for a parking space in level of parking spaces, and software components integrated to
high populated urban areas is a source of traffic congestion, manage the allocation of these parking spaces by redirecting
increased carbon emission and, not least, a very frustrating and cars accordingly (see Figure 1). Usually, such systems are
time consuming experience for motorists [1]. designed to assist motorists in the localization of available
parking spaces, so that they can decide which space to select
Several industry efforts have already produced solutions
according to their own needs [3].
in this direction by making use of advanced Information and
Communication Technologies including vehicle sensors, wire- In the present work, we assume that Smart Cities will be
less communications, and data analytics in order to improve equipped with such a complex system, and we propose to
urban mobility. Some cities have adopted these solutions in extend it with a software module implementing an application
pilot areas installing wireless sensors able to detect parking that can make decisions on where to park on behalf of a mo-
space occupancy in real time. In addition, smart parking me- torist, taking into account not only his/her needs, but also the
ters, allowing for a wide variety of available payment methods, social benefit for the city. In the proposed approach, a decision
are being developed in conjunction with the dissemination of on where to park is the result of an automated negotiation
parking availability information. process between two software agents: the User Agent (UA)
acting on behalf of the motorist, and the Parking Manager
Based on the information that can be collected on parking
(PM) who is responsible for managing parking spaces belong-
spaces occupancy, location and directions, applications assist-
ing to different car parks located in the city, which are offered
ing users in selecting a parking space are being developed.
to users as a global city facility. This means that different car
Many of the proposed approaches deal with the smart parking
parks owners agreed to subscribe to a City Parking System,
problem mainly as an optimization process from the drivers
managed by the Parking Manager, by delegating the selling
point of view. However, Smart City applications have to in-
of their parking spaces (partially or globally) to it. Hence, the
clude benefits and revenues for the city itself. In fact, effective
Parking Manager is the authority responsible for allocating
smart parking applications should be designed not only to
the parking spaces, virtually belonging to the City Parking
make it easy for motorists to search for parking spaces, but
System, but it is also responsible for collecting the information
*Ph.D. scholarship funded by Media Motive S.r.l, POR Campania FSE concerning specific city needs regarding transportation that
2007-2013. will be gathered from the city council offices managing it.
solutions that facilitate advance parking space reservation by
setting up dynamic pricing policies, as in [1], [5]. By making
such services available to motorists, operators may offer an
enhanced level of service to their customers, while at the same
time have the opportunity to increase their revenues. Parking
pricing strategies play a crucial role in a comprehensive
solution approach to the complex traffic congestion problems.
Dynamic pricing can serve a number of purposes. It can
be used to maximize revenues for parking operators by setting
higher fees during peak times and in more demanded areas
[6], or as a results of current demand and supply. For example,
traffic authorities, local governments and private sector could
introduce higher parking tariffs for single drivers, or for long-
term parkers in congested city areas, or they may provide
special parking discounts for parking in specific city areas.
Moreover, it may encourage motorists to use park-and-ride fa-
Figure 1. A general smart parking system. cilities. This may result in an increase of public transportation
use, and at the same time it may reduce traffic and parking
demands in city centers [1].
Negotiation is used in order to accommodate both users and
city needs that are different and, more importantly, conflicting. Obviously, parking pricing should be carefully studied in
In fact, the Parking Manager has the objective to sell parking the context of the considered city. In this work, it is assumed
spaces to make a profit, but to prevent, as much as possible, that the Parking Manager tries to incentive drivers to park
motorists to park in a specified area, while users would prefer far from areas that are either highly congested, or where
to save as much money as possible, and at the same time, to specific events affecting traffic take place, such as concerts,
park close to the city destination they require. demonstrations, road works, and so on. The use of negotiation
allows to consider these events at the time a parking request
is issued, so managing the dynamic nature of such type of
III. A S OCIAL -AWARE PARKING S PACE S ELECTION information.
In many decision-making situations in transportation, the In order to push users to avoid some city areas, a dynamic
competitive alternatives and their characteristics are reasonably cost model is associated to the City Parking System. Once a
well known in advance to the decision makers (passenger, specific zone to be avoided is selected by the Parking Manager,
driver). On the other hand, motorists usually discover different we refer to as a red zone, the area around this zone is divided
parking alternatives one by one in a temporal sequence. in several rings, referred to as sectors, that account for the
Clearly, this temporal sequence has a very strong influence on distance between a car park and the specific red zone. The first
the driver’s final decision about the parking space. In our work, sector, named sector 1, is centered in the red zone with a radius
the Parking Manager selects a set of car parks belonging to that can be set according to some criteria. The price associated
the City Parking System, but the temporal sequence in which to parking spaces depends on the sector the corresponding car
they are offered during negotiation privileges first car parks park belongs to, so the farther the car park is from the red
meeting also city needs requirements. zone, the cheaper it is. In addition, in order to incentivize
The goal of the negotiation between the User Agent and the the occupancy of less crowded car parks, a discount factor is
Parking Manager is to select a parking space that represents applied to each car park in accordance to its occupancy w.r.t.
a viable compromise between the driver’s and the city needs its total capacity.
(represented by the Parking Manager preferences), so reaching
a sort of utilitarian social welfare. In other words, we propose B. The Negotiation-based Parking Space Selection
to find an allocation of parking spaces that is viable from In the present work, we adopt the negotiation mechanism
a global social benefit point of view. The concept of social reported in [2], whose protocol is based on the FIPA Iterated
welfare, as studied in welfare economics, is an attempt to Contract Net Protocol, that is frequently used to mime the
characterize the well-being of a society in relation to the human contract negotiation process. The protocol is organized
welfare enjoyed by its individual members [4]. The proposed in negotiation rounds, each one consisting of interactions
negotiation mechanism relies on the utilitarian interpretation of between the UA, that is the initiator of the negotiation, and
the concept of social welfare in multi agent systems literature, the PM, that is the agent proposing offers.
i.e. whatever increases the average welfare of the agents
inhabiting a society is taken to be beneficial for society as At the first negotiation round, the UA issues a request (i.e.
well. According to the utilitarian concept, social welfare is a call for proposal) for a parking space specifying his/her
interpreted as the sum of individual utilities. destination location, the time interval he/she needs to park for,
and the importance level (weight) for the considered parking
A. The City Parking Cost Model space attributes. The PM may either reject the call, if there
are not offers available, or it sends back an offer consisting
The possibility to monitor parking availability in real time in a parking space solution selected from the set of available
opens up an opportunity for the provision of smart parking offers. The PM calculates, at the first negotiation round, the
entire set of available offers by selecting a set of car parks Here the same utility functions presented in [2] are used.
within an area centered around the user’s requested destination The PM utility function depends on the car park occupancy
location, and whose dimensions are set according to some percentage, at the moment the request is received, and on the
criteria (e.g. a small area if the user wants to park far from distance of the car park from the current red zone (if any),
the red, and wider in the opposite case). Once the set of car normalized with respect to the maximum considered distance
parks is selected, the PM calculates the corresponding prices to by the PM, that determines the area for the selection of car
offer according to the price model previously described. Then, parks. The UA utility function depends on the parking space
it ranks the offers according to its own preference criteria that price, on the car park walking distance from the requested
take into account the city needs. The offers are sent one by one, destination, and on the corresponding travel time distance
at each negotiation round, in their ranking decreasing order. with public transportation. The values of these attributes are
When receiving an offer, the UA evaluates it, according to specified for each parking space in the offer sent by the
its own evaluation criteria, to decide whether to accept or to PM. Each attribute value is normalized for the UA with the
reject it. In the case of rejection it can iterate the negotiation maximum parking space cost, and the maximum walking
process by sending another call for proposal. It should be noted distance and travel time between the parking space and the
that an offer proposed by the PM in a negotiation round is motorist’s actual destination, that are specified as requirements
not considered available in future rounds once it is rejected. in the user request [9].
This assumption models the possibility that a rejected parking
space may be offered to another user in the meantime, or its IV. A P ROTOTYPE I MPLEMENTATION
price may change according to the parking market trends as
in [7]. Of course, it is difficult for the negotiating agent to In order to provide Smart Cities with an intelligent smart
evaluate whether to accept an offer to minimize the expected parking solution to be integrated in a more complex City
cost of communication (at the risk of getting a sub-optimal Parking System, we designed and implemented a web-based
result for the specific application), or to keep on negotiating multi-agent application to automatically select parking spaces
to maximize its expected utility (at the risk of increasing the in reply to user’s requests. The application was tested in a case
cost of negotiation and ending with a conflict deal). In our study based on both real and simulated information, to assess
approach this aspect is modeled by associating to the UA an the suitability of software agent negotiation in the context
acceptance threshold value (in the interval [0, 1]) representing of intelligent parking. The architecture of the implemented
the user’s attitude to reach a compromise. prototype is shown in Figure 2 reporting its main components.
The negotiation module is implemented by using the JADE
Both the PM and UA preference criteria on a parking space framework [10] to implement the UA and the PM, and relying
offer are modeled through utility functions based on the Multi- on its messaging primitives to implement the adopted negoti-
Attribute Utility Theory defined on independent issues [8], ation protocol. JADE is an open source software framework
over the attributes to be negotiated upon. In particular, utilities for developing applications that implements agent and multi-
are defined both for the UA and the PM, as weighted sum of agent systems. It is a Java based agent development environ-
specific normalized attributes that sum to one as follows: ment providing libraries designed to support communication
between agents in compliance with Foundation for Intelligent
n
Physical Agents (FIPA) specifications. The multi-agent system
X attri is composed of the UAs and the PM. The PM is enveloped
UP M/U A (of f erP M (k)) = (wi ∗ ) (1) in an application server, more specifically Apache Web Server
i=1
normf actori
extended with Tomcat, and it is able to communicate with
external services and information sources:
where n is the number of considered parking space attributes
attri , normf actori is the corresponding normalization factor, • Google Map Server [11] to retrieve walking distance
Pn and travel time from a selected car park to the user’s
and wi is the corresponding weight, with wi = 1. destination location,
i=1
• the Car Park Database to retrieve information on the
available car parks,
• City Manager facilities to retrieve information regard-
ing roads accessibility-related information.
The contents of the Car Park Database are retrieved from the
OpenStreetMap application [12], and it is implemented using
PostgreSQL, an object-relational database management sys-
tem, and PostGIS an open source software providing support
for geographic objects to the PostgreSQL database. The user’s
application also queries OpenStreetMap to obtain maps for the
interface it interacts with.
A. A Special Event Case Study: The Football Match
In order to assess how software agent negotiation can be
Figure 2. The prototype architecture of the smart parking application. used in the selection of parking spaces in a urban area, a set
Figure 3. Queries distribution in sectors 1, 2 and 3. Figure 4. Selected parking spaces for the UA queries with negotiation.
of experiments were carried out considering the city of Naples values for the selected parking space increase when users’
as the target area. The negotiation mechanism is proposed destination locations are far from the red zone. Furthermore,
as a means to incentive motorists to consider parking space the negotiation length increases when users want to park in the
solutions that are related not only to their own preferences. red zone, since it is more difficult to find a compromise. In
fact, when users require destination locations far from the red
Our reference scenario consists of a set of users that make
zone the social welfare (last column of Table I) increases since
requests to park in different zones of Naples on the day a
the needs of both the PM and the UA are easily satisfied. The
football match will take place. For this reason, it is considered
distribution of the selected parking spaces for the considered
beneficial for the city to make motorists to avoid the area
queries is reported in Figure 4, showing that the parking
around the football stadium for parking, in order to limit traffic
spaces are selected in accordance with the objective to prevent
congestion. So, the red zone is represented by the city sector
motorists from parking in the red zone.
(sector 1) centered in the location of the football stadium, with
a radius set to 500m (the radius value can be set by the PM In order to evaluate the benefit in using negotiation to find
according to several factors such as viability conditions in the a compromise between the PM and the UA, we also evaluated
surrounding area, the number of car parks available in the the attribute values of parking spaces chosen respectively by
surrounding areas, and so on). The rest of the city is split in the PM and the UA without negotiation. In this case, the PM
sectors as well, starting from sector 1, with an exponential and the UA select respectively the best parking space that
increased radius. The experiments simulate 60 queries (qi ) maximizes their own utility functions. Of course, in order for
with destination locations distributed in sectors 1, 2 and 3 (20 the PM and the UA to chose the best parking space, it is
queries in each sector), as shown in Figure 3. The sectors are assumed that they both share the same information concerning
determined with respect to the red zone (target t), and the the available parking spaces.
destination locations are randomly generated. The threshold
value for all users is set to 0.7 in all the experiments. In Table II the same attributes described in Table I are
reported for the best parking space for the UA (U Abest ). As
expected, in this case, the UA preferences are privileged while
B. Experimental Results
the PM utility value increases only for locations far from the
For each generated query the negotiation process between red zone. Note that the ranking position of the selected parking
the UA and the PM takes place. In Table I we report, for each space for the PM is in average 20, meaning that in case of
set of queries (respectively for sector 1, sector 2 and sector negotiation such parking space would be offered to the UA
3), the mean value together with the standard deviation of the only after 20 rounds, so requiring a longer (and hence more
following attributes of the parking space (si ) selected after costly) negotiation w.r.t. the case reported in Table I, where
the negotiation: the UA and PM utilities (UU A and UP M ), the average number of rounds is 5.5. Finally, the price of the
its distance from the red zone (Dist(t)), its walking distance U Abest is in the average higher then the price of the si because
(Dist(qi )) and travel time distance with public transportation it corresponds to parking spaces nearer to the query locations
(T ime(qi )) from the query destination location, its offered and, hence, nearer, in average, to the red zone.
price (P rice), its position in the PM ranking (RankP M ), and
In Table III the same information as Table II is reported,
the social welfare value (SW ), obtained as the sum of UA
but considering the best parking space for the PM (P Mbest ).
and PM utilities. The ranking position of si corresponds to
In this case the PM preferences are privileged, while the UA
the number of the negotiation round at which the offer was
utility value increases only for locations far from the red zone.
sent by the PM, so representing the length of the negotiation
Of course, the ranking value of the best parking space for the
(i.e., the number of rounds necessary to reach an agreement
PM is 1, because it represents the best choice for the PM,
between the UA and the PM).
whose utility value is 1 because it is normalized w.r.t. the max
The obtained results show that the PM and UA utility values of the parking attributes available for each query.
si UU A UP M Dist(t) m Dist(qi ) m P rice e T ime(qi ) s RankP M SW
sector 1 0.75 ± 0.04 0.83 ± 0.22 1089 ± 255 866 ± 228 2.8 ± 0.4 269 ± 109 11 ± 10 1.59 ± 0.23
sector 2 0.75 ± 0.05 0.91 ± 0.09 1650 ± 304 1053 ± 167 2.2 ± 0.7 212 ± 77 3.8 ± 3.3 1.66 ± 0.11
sector 3 0.83 ± 0.04 0.93 ± 0.11 2399 ± 377 1145 ± 219 0.9 ± 0.8 213 ± 59 2.2 ± 2.1 1.76 ± 0.13
total 0.78 ± 0.07 0.89 ± 0.15 1713 ± 624 1021 ± 234 1.9 ± 1.0 232 ± 87 5.5 ± 7.1 1.67 ± 0.18
Table I. E XPERIMENTAL DATA OF PARK SELECTION (si ) W. R . T THE QUERIES qi AFTER THE NEGOTIATION .
U Abest UU A UP M Dist(t) m Dist(qi ) m P rice e T ime(qi ) s RankP M SW
sector 1 0.91 ± 0.06 0.21 ± 0.20 390 ± 163 339 ± 232 4.5 ± 1.0 101 ± 86 34 ± 5 1.12 ± 0.18
sector 2 0.98 ± 0.06 0.66 ± 0.17 1114 ± 217 473 ± 106 2.8 ± 0.4 115 ± 62 17 ± 6 1.64 ± 0.20
sector 3 0.99 ± 0.05 0.75 ± 0.14 1830 ± 463 616 ± 282 1.5 ± 1.0 114 ± 63 9±6 1.74 ± 0.16
total 0.96 ± 0.06 0.54 ± 0.29 1112 ± 666 476 ± 244 2.9 ± 1.5 110 ± 70 20 ± 12 1.50 ± 0.33
Table II. DATA OF UA BEST CHOICES (U Abest ) W. R . T. THE QUERIES qi WITHOUT NEGOTIATION .
P Mbest UU A UP M Dist(t) m Dist(qi ) m P rice e T ime(qi ) s RankP M SW
sector 1 0.44 ± 0.18 1±0 1332 ± 153 1496 ± 362 2.5 ± 0.0 385 ± 109 1±0 1.44 ± 0.18
sector 2 0.56 ± 0.21 1±0 1875 ± 241 1656 ± 920 1.9 ± 0.9 240 ± 85 1±0 1.56 ± 0.21
sector 3 0.57 ± 0.26 1±0 2580 ± 350 2006 ± 1057 1.5 ± 1.0 114 ± 63 1±0 1.57 ± 0.26
total 0.52 ± 0.22 1±0 1929 ± 576 1720 ± 849 1.6 ± 1.0 294 ± 123 1±0 1.52 ± 0.22
Table III. DATA FOR THE PM BEST CHOICES (P Mbest ) W. R . T. THE QUERIES qi WITHOUT NEGOTIATION .
The average values of social welfare, reported in the last negotiation is used to optimize traffic management relying
rows of Tables II and III, are lower than the one obtained with on shared knowledge between drivers and network operators
negotiation, since in these cases only the needs of one agent about routing preferences. In [14] a negotiation algorithm
(respectively the UA and the PM) are taken into consideration. is designed for negotiating routes based on the calculation
By the way, the average values of SW in the three tables are of routes utility, while in [15] agent negotiation is used for
very close, but the values relative to each sector differ, so dynamic parking allocation, focusing on satisfying driver’s
showing that negotiation is useful to improve social welfare preferences on prices and distances. Negotiation in smart
when users want to park close to a red zone (i.e., for sector parking application was used in [16] to determine the price
1), while for sector 2 and 3 the social welfare is comparable. of a car park. In our work, the price of a car park is not
negotiable, but it is dynamically set so to incentive users to
The distribution of the best parking spaces for the UA,
select parking spaces located in specific urban areas.
reported in Figure 5, is similar to the distribution of query
locations, meaning that without negotiation users are not Dynamic pricing mechanisms are being used in the context
prevented from parking in the red zone. While the distribution of parking applications. In [6] the authors presented, as in
of the best parking spaces for the PM, reported in Figure 6, is our case, a smart parking solution that tries to find a trade-
similar to the distribution of the parking spaces selected with off between benefits of both drivers and parking providers.
negotiation since in this case the PM needs are considered. To balance the needs of involved parties, they use a dynamic
parking price mechanism, and utility functions for the drivers,
V. R ELATED W ORKS to balance the convenience and cost in terms of parking price
Multi-agent negotiation was already used in Intelligent and parking distance from the user’s destination. Differently
Transportation System applications. In [13] cooperative agent from our approach, in [6] the parking selection is obtained
Figure 5. Distribution of U Abest parking space without negotiation. Figure 6. Distribution of P Mbest parking space without negotiation.
from a maximization of such utility with all the informa- project (ORganization of Cultural HEritage for Smart Tourism
tion available. In our case, we showed that a negotiation and Real-time Accessibility).
process may be more effective, in terms of social welfare
maximization, than a simple one-sided utility maximization. R EFERENCES
Dynamic price mechanisms were also explored in [5], where
[1] E. Polycarpou, L. Lambrinos, and E. Protopapadakis, “Smart parking
the objective was to set up prices for available parking spaces solutions for urban areas.” in World of Wireless, Mobile and Multimedia
to prompt the most efficient allocation, in terms of social Networks (WoWMoM), 2013 IEEE 14th International Symposium and
welfare, intended as the total utility value of all agents who are Workshops on a. IEEE, June 2013, pp. 1–6.
allocated to a parking space. Hence, while the social welfare in [2] C. Di Napoli, D. Di Nocera, and S. Rossi, “Agent negotiation for
our approach is a result of a mediation of the conflicting needs different needs in smart parking allocation,” in Advances in Practi-
of a user and the city management, in their work it consists in cal Applications of Heterogeneous Multi-Agent Systems., ser. LNCS.
Springer International Publishing, 2014, vol. 8473, pp. 98–109.
an optimal allocation of parking spaces to different users.
[3] Z. Faheem, S. Mahmud, G. Khan, M. Rahman, and Z. H., “A survey of
The optimal allocation of cars in car parks was also studied intelligent car parking system,” Journal of applied research technology,
vol. 11, no. 5, pp. 714–726, 2013.
in [9], where the authors propose a semi-centralized approach
[4] K. Arrow, A. Sen, and K. Suzumura, Handbook of Social Choice &
for optimizing the parking space allocation, and improving the Welfare, ser. Handbooks in Economics. Elsevier Science, 2010.
fairness among parking zones by balancing their occupancy-
[5] R. Meir, Y. Chen, and M. Feldman, “Efficient parking allocation as
load. In this approach, parking coordinators process the user online bipartite matching with posted prices,” in Proceedings of the
requests and may communicate with the neighbor coordinators. 2013 International Conference on Autonomous Agents and Multi-agent
In [17] the parking space allocation strategy, implemented Systems, ser. AAMAS ’13, 2013, pp. 303–310.
through the use of a Mixed Integer Linear Program, is based [6] H. Wang and W. He, “A reservation-based smart parking system,” in
on the user’s objective function that combines proximity to Computer Communications Workshops (INFOCOM WKSHPS), 2011
IEEE Conference on, April 2011, pp. 690–695.
destination and parking cost, while ensuring that the overall
parking capacity is efficiently utilized. In our work, a more [7] P. R. Lewis, P. Marrow, and X. Yao, “Resource allocation in de-
centralised computational systems: an evolutionary market-based ap-
efficient allocation of parking spaces is not the main goal. proach,” Autonomous Agents and Multi-Agent Systems, vol. 21, no. 2,
However, it may be obtained as a side effect of the negotiation pp. 143–171, 2010.
because of the adopted dynamic price strategy. [8] M. Barbuceanu and W.-K. Lo, “Multi-attribute utility theoretic negotia-
tion for electronic commerce,” in Agent-Mediated Electronic Commerce
III, Current Issues in Agent-Based Electronic Commerce Systems.
VI. C ONCLUSION Springer-Verlag, 2001, pp. 15–30.
Smart parking applications should make it easier for mo- [9] N. Mejri, M. Ayari, and F. Kamoun, “An efficient cooperative parking
slot assignment solution,” in UBICOMM 2013, The Seventh Interna-
torist to find a parking space, and so help in reducing traffic tional Conference on Mobile Ubiquitous Computing, Systems, Services
congestion, carbon emission, and users frustrations and time and Technologies. IARIA, 2013, pp. 119–125.
wasting, leading to a benefit for the whole city as a side effect. [10] F. Bellifemine, G. Caire, A. Poggi, and G. Rimassa, “Jade: A software
But in order to really improve the living conditions of city framework for developing multi-agent applications. lessons learned,”
life, Smart Cities should rely also on the contribution of local Inf. Softw. Technol., vol. 50, no. 1-2, pp. 10–21, Jan. 2008.
authorities providing information regarding city regulations [11] B. Pan, J. C. Crotts, and B. Muller, “Developing web-based tourist in-
and decisions that, if shared, could help to design smarter formation tools using google map,” in Information and Communication
Technologies in Tourism 2007, M. Sigala, L. Mich, and J. Murphy, Eds.
applications. Typically, this type of information is very dy- Springer Vienna, 2007, pp. 503–512.
namic depending also on unforeseen events. For these reasons, [12] M. Haklay and P. Weber, “Openstreetmap: User-generated street maps,”
we proposed a smart parking application having as a main Pervasive Computing, IEEE, vol. 7, no. 4, pp. 12–18, 2008.
objective to reach a social benefit as well as helping users. The [13] J. L. Adler and V. J. Blue, “A cooperative multi-agent transportation
implemented mechanism aims to maximize the social welfare management and route guidance system,” Transportation Research Part
of users and city managers finding a compromise between their C: Emerging Technologies, vol. 10, no. 56, pp. 433 – 454, 2002.
goals sometimes in conflict. The classical way to achieve such [14] W. Longfei and C. Hong, “Coorporative parking negotiation and guid-
a compromise is through negotiation, that we propose as the ance based on intelligent agents,” in Computational Intelligence and
Natural Computing, 2009. CINC ’09. International Conference on,
underling mechanism of a smart parking application. vol. 2, June 2009, pp. 76–79.
In this paper, we described a first prototype of the negoti- [15] S.-Y. Chou, S.-W. Lin, and C.-C. Li, “Dynamic parking negotiation and
ation process in order to assess its suitability in the context of guidance using an agent-based platform,” Expert Syst. Appl., vol. 35,
no. 3, pp. 805–817, Oct. 2008.
smart parking. The experimental results, obtained in testing the
[16] W. Longfei, C. Hong, and L. Yang, “Integrating mobile agent with
application, showed that negotiation may improve the social multi-agent system for intelligent parking negotiation and guidance,” in
welfare mainly when the goals are conflicting. In future works Industrial Electronics and Applications, 2009. ICIEA 2009. 4th IEEE
we plan to extend the experimentation to evaluate the possibil- Conference on, May 2009, pp. 1704–1707.
ity of achieving optimal social welfare by varying the values [17] Y. Geng and C. Cassandras, “A new smart parking system based on
of parameters that characterize the negotiation mechanism. optimal resource allocation and reservations,” in Intelligent Transporta-
tion Systems (ITSC), 2011 14th International IEEE Conference on, Oct
2011, pp. 979–984.
ACKNOWLEDGMENT
The research leading to these results has received funding
from the EU FP7-ICT-2012-8 under the MIDAS Project, Grant
Agreement no. 318786, and the Italian Ministry of University
and Research and EU under the PON OR.C.HE.S.T.R.A.