The Bulgarian office of the ICOM Computers Company has significant know-how in the development of software and hardware for fleet management. Due to the expansion of its operations, new challenges arise, related to the amounts of data to be processed and the customer’s needs for new services. A potential new service was identified in the use of meteorological and air pollution data to provide options for optimization of traffic and decreasing the air pollution impact of the fleets.
The company has been developing software and hardware, related to fleet management. The goal of the project was to assess options for achieving “greener” fleet management, through the use of data about meteorology and air pollution in the big cities. The project was focused on methods for data acquisition, aggregation and processing, which enable data that is produced from researchers or publicly available from the municipalities to be combined with proprietary data, in order to enable clients to optimize their traffic point of view of potentially harmful emissions and impact on the environment within the city limits.
The idea of the project was to benefit from air quality simulations that have been performed in VI-SEEM and to test possibilities for integrating them within the company portfolio. VI-SEEM resources were provided at the Avitohol supercomputer system, which
Integrates 150 servers HP Cluster Platform SL250S GEN8. The servers provide not only significant compute power (more than 400 Teraflops) but also have a total of 9.6 TB of RAM, which is important for Big Data processing.
Through the use of VI-SEEM HPC resources and the air pollution datasets, the company was able to carry out extensive simulations. The tests showed that by integrating industry-standard middleware in the data processing pipeline there is sufficient compute and data processing power to achieve the required response times in order to be able to provide this service to the customers. The successful completion of this project increases the innovative capacity of the company and improves its competitiveness in this rapidly expanding sector of the economy.
The Apache Hadoop middleware and related technologies were used for the data processing. Different open source software packages dealing with GPS tracking data were tested. The simulations were carried out as a combination of jobs, where one job used 64 CPU cores.
Fig 1: Provision Realtime tracking and Routing
Links of company: