Data communication optimization for the evaluation of multivariate conditions in distributed scenarios

Abstract

The current technological landscape is characterized by the massive and efficient interconnection of heterogeneous devices. Sensor networks (SNs) are key elements of this paradigm; they support the local loop, the collection and early manipulation of information. Among the applications of SNs, event detection is a well-explored topic in which strategies such as collaboration, self-organization, and others have been developed in depth. In this topic, the simplest and also most used event concept approach is the threshold-based event, which is usually integrated as part of the local sensor process. This paper addresses a different perspective by discussing the evaluation of multivariate Boolean conditions with distributed variables. We propose a new algorithm (Data Retaining Algorithm for Condition Evaluation, DRACE) that reduces packet traffic while preserving time accuracy in event calculation on an adaptive approach. To facilitate understanding of DRACE, a case study is presented in the context of a logical simile titled The Problem of a Proper Defense. The algorithm supports parameters that affects the compromise between accuracy and traffic savings. To analyze its performance, 9000 executions of the algorithm have been performed. 9 configurations tested on a repository of 1000 triads of signals randomly generated. Focusing on the most accurate configuration, 99% of executions are error-free, and the number of packets is reduced by 40% on average, being between 30 and 50% in 68% of cases.