Cost efficient cloud-based service oriented architecture for water pollution prediction

River water quality nowadays represents a major concern. Performing water monitoring, in order to detect the pollutant with wireless sensor networks is not enough. Furthermore, the solution to place more sensors for monitoring is not cost efficient as this type of sensors are very expensive. In the case of a pollution accident on a river, it is mandatory to alert people and, more important, to predict the evolution of pollutant concentration, downstream. Also, it is essential to minimize the time-frame to send the alert to the possibly affected people. In this paper, we propose a cost-efficient cloud-based service oriented architecture for water pollution prediction and alert system. The cost efficiency of our approach comes from the three main directions. The first way is represented by the usage of less water monitoring specific sensors due to the usage of complex hydraulic models. The second direction is represented by the construction of a knowledge-base with pre-run scenarios of pollution propagation events. The third direction is represented by the usage of cloud computing services which are proven to be cost effective. The novelty of our approach comes from the integration of different Cloud computing platforms and services, in order achieve scalability, provisioning of resources in real time, to have a simplified deployment and management of resources and applications, and to get a better cost/performance ratio.