Computer and Information Engineering | Article | Published 2022
Today, the growth of the flow of digital data requires unusual, specialized methods and tools for storing and processing it. The storage and processing of large volumes of data using a conventional single computing system are not efficient, neither in terms of storage nor processing speed. With that in mind, storing and processing large amounts of data using interconnected computing systems can have a number of benefits. One of the main tasks in the joint use of these computing systems is the correct choice of the scheme of interaction between them, as well as the software architecture. This research presents the efficiency and high-efficiency approach to storing and processing Big Data’s Fast Data and Big Analytics class data using distributed computing systems. In addition, this research analyzes the requirements for distributed computing systems in Big Data processing and storage, as well as the interconnection schemes and software architectures of distributed computing systems for Big Data processing and storage. As a result of this research, an optimized architecture for the Big Data processing and storage of a distributed computing system was developed.