Efficiency of Data Preprocessing Application for Geographically Distributed Cyberphysical Systems Using WSNs

The concepts of fog and edge computing are currently applied in the construction of distributed cyber-physical systems in order to reduce the load on the network infrastructure, as well as to reduce the time of data processing. In this case, as a rule, the process of workload distribution on fog layer nodes at fixed labor intensity of computational tasks is investigated. In this study, the impact of the amount of data preprocessing on edge devices with sending the results to the data collector node are considered, taking into account the transit overhead costs. We propose a formalization in the form of an additional parameter, the type of task, which determines the dependence of the amount of data to be sent on the labor intensity. As an example, data on data compression rate and efficiency for the gzip archiver is used to generate discrete types of tasks. The modeling results allow us to draw a conclusion about the influence of the choice of the type of data processing algorithm on the key criteria of the system.