181 ISSN 0361-7688, Programming and Computer Software, 2018, Vol. 44, No. 3, pp. 181–189. © Pleiades Publishing, Ltd., 2018. Towards a Cloud Computing Paradigm for Big Data Analysis in Smart Cities 1 R. Massobrio a, *, S. Nesmachnow a, **, A. Tchernykh b,c,d,f, ***, A. Avetisyan c,e,f, ****, and G. Radchenko d, ***** a Universidad de la Republica, Montevideo, 11200 Uruguay b CICESE Research Center, Carretera Tijuana-Ensenada 3918, Fraccionamiento Zona Playitas, Ensenada, BC, 22860 Mexico c Institute for System Programming of the RAS, Moscow, 109004 Russia d South Ural State University, Chelyabinsk, 454080 Russia e Lomonosov Moscow State University, Moscow, 119991 Russia f Moscow Institute of Physics and Technology, Dolgoprudny, Moscow oblast, 141701 Russia *e-mail: renzom@fing.edu.uy **e-mail: sergion@fing.edu.uy ***e-mail: chernykh@cicese.mx ****e-mail: arut@ispras.ru *****e-mail: gleb.radchenko@susu.ru Received January 13, 2017 Abstract—In this paper, we present a Big Data analysis paradigm related to smart cities using cloud comput- ing infrastructures. The proposed architecture follows the MapReduce parallel model implemented using the Hadoop framework. We analyse two case studies: a quality-of-service assessment of public transportation system using historical bus location data, and a passenger-mobility estimation using ticket sales data from smartcards. Both case studies use real data from the transportation system of Montevideo, Uruguay. The experimental evaluation demonstrates that the proposed model allows processing large volumes of data efficiently. Keywords: cloud computing, big data, smart cities, intelligent transportation systems DOI: 10.1134/S0361768818030052 1. INTRODUCTION One of Smart City challenges is to use information and communications technologies to manage cities’ assets with the goal of improving the quality and per- formance of urban services. By applying these tech- niques, it is possible to reduce infrastructure and oper- ational costs, increase efficiency in the use of resources, and facilitate the interaction between citi- zens and authorities [1]. Such techniques are often applied to transportation services due to the central role they play in modern cities. Nowadays, many complex activities, which impose serious challenges to the mobility of citizens are devel- oped in modern cities [2]. Public transportation plays a major role in the city transit system, especially in dense urban areas. However, many public transporta- tion systems are not able to cope with the growing mobility demand. In order to address this issue, authorities and decision-makers need to have a deep understanding of the overall picture and details of the people mobility, including up-to-date information on the use of public transportation [3]. Unfortunately, due to the lack of financial and human resources, pub- lic administration often has scarce and outdated mobility data. Frequently, data are gathered but are not analyzed and used to improve public/private transportation infrastructure. For this reason, improv- ing the decision-making processes related to urban mobility becomes mandatory in most modern cities. The adequate paradigm of smart cities allows to take advantage of data coming from a plethora of sources that can be processed to understand mobility in the cities. Intelligent Transportation Systems (ITS) are a key component of smart cities. ITS are defined as those systems that integrate synergistic technologies, computational intelligence, and engineering concepts applied to transport systems in order to improve traffic 1 The article is published in the original.