An Approach to Aggregation of Security Events in Internet-of-Things Networks Based on Genetic Optimization

Nowadays, the Internet-of-Things (IoT) networks find more, more wide distribution in many areas. IoT peculiarities do rather actual the problem of parallel processing of big arrays of the collected data, including data on security events. It is possible to solve this problem by realization of security event data preprocessing "on the fly" on the basis of the complex event processing (CEP) technology. However, issue of parallel processing of CEP queries is poorly addressed in the current literature. This paper presents an approach to solving this problem based on the principles of parallelization of CEP operators in IoT, using genetic algorithms. The genetic algorithm is used for finding the optimum scheme of the distribution of CEP operators on IoT network hosts. Experimental results showed that the usage of the offered approach allows to receive a gain in throughput to 50 percent. At the same time, the operation of the genetic algorithm does not violate the real-time scale.