Nowadays, big data processing systems are evolving to be more stream-oriented; where each data record is processed as it arrives by distributed and low latency computational frameworks [18]. Data streams have been extensively used in several fields of computational analytics such as data mining, business intelligence etc. [17]. In every field, the data stream can be considered as an ordered sequence of data items, as they continuously arrive over the period. Due to this characteristic, streaming data analytics is a challenging area of research [5, 11]. This paper aims to present data stream processing as a growing research field , along with streaming analytics frameworks as a rich focus area. The paper also contributes to evaluate the efficacy of available stream analytics frameworks. One of the Industry 4.0 use case - predictive maintenance rail transportation - has been illustrated here as a case study design mapped with streaming analytics framework.
Multi-Objective Reinforcement Learning for Reconfiguring Data Stream Analytics on Edge Computing
