Designing a Multi Agent System Architecture based on IOT Middleware for Smart Parking Khaoula Hassoune Wafaa Dachry Fouad Moutaouakkil Systems Architecture Systems Architecture Systems Architecture Hassan II University, ENSEM Hassan II University, ENSEM Hassan II University, ENSEM Casablanca, Morocco Casablanca, Morocco Casablanca, Morocco Khaoula.hassoune@gmail.com wafaa.dachry@gmail.com fmoutaouakkil@hotmail.com Hicham Medromi Systems Architecture Hassan II University, ENSEM Casablanca, Morocco hmedromi@yahoo.fr Abstract— this paper presents a dynamic smart parking architecture that offers many services to the driver based on multi-agent, expert systems and IOT Middleware. We have integrated the different technologies together in order to achieve a system which is the most efficient, reliable, secure and inexpensive. The Cloud Computing paradigm has been selected for designing and developing the mentioned architecture, since it exhibits interesting features, such as cost reduction, agility, scalability and elasticity, among others. And to improve intelligence of our system it is necessary to integrate the learning aspect in our agents to ensure services with a maximum degree of accuracy, efficiency and good performance. Agents are sophisticated computer programs that act autonomously on behalf of their users, across open and distributed environments, to solve a growing number of complex problems. Keywords—Smart Parking System; Multi-Agent Systems; Expert Systems; IOT Middelware. I. INTRODUCTION Cities noticed that their drivers had real problems to find a parking space easily especially during peak hours, the difficulty roots from not knowing where the parking spaces are available at the given time. Even if this is known, many vehicles may pursue a small number of parking spaces which in turn leads to traffic congestion. Smart parking system provides a suitable solution to these problems. Smart-parking system is one of essential aspect in realizing smart-city. It is one of the low hanging fruits because it gives drivers a quick solution to the nagging problem of getting parking occupancy in real time as well as helps city officials reduce congestion and air pollution [1]. The parking problem in big cities, especially the mega-cities, has become one of the key causes of the city traffic congestion, driver frustration and air pollution. So researchers are recently turned to applying technologies for management of parking area by designing and implementation of a prototype system of smart parking that allows vehicle drivers to effectively find the free parking places. The traditional way of smart-parking development would have been complex, time consuming and prohibitive. In this paper we will design a cloud and multi agent based architecture that enables the deployment of smart parking systems. The paper is organized as follows: Section 2 surveys the parking systems in academic publications. Section 3 presents technologies, hardware and software modules that have been used in this work; together with the cloud and multi agent based architecture for smart parking systems. The last section concludes our work and draws some perspectives. II. RELATED WORKS Smart parking is a way to help drivers find satisfied parking places efficiently through information and communications technology [2]. Various approaches and researches are made to overcome the difficulties of parking area. The author in [3] presents the design and implementation of a smart parking system based on wireless sensor networks that allow vehicle drivers to find the free parking places. The scheme is based on WSNs, Embedded Web-Server, Central Web-Server and Mobile phone application. The driver can detect the state of the parking slot using mobile devices thanks to sensor node in each parking slot which detect the state of this one and report it to embedded web-server and finally the information is sent to central web-server using Wi-Fi networks in real time. This paper [4] presents an invention that could be applied to monitor and manage vehicles in a parking garage by informing drivers about the number of available parking spaces and in which area should they be directed to. The scheme is based on the modification of the original WSN and use of RFID and ZigBee technology. To evaluate other meaningful metrics such as time etc. The information obtained