HIFUN is a high-level query language for expressing analytic queries of big datasets, offering a clear separation between the conceptual layer, where analytic queries are defined independently of the nature and location of data, and the physical layer, where queries are evaluated. In this paper, we present a methodology based on the HIFUN language, and the corresponding algorithms for the incremental evaluation of continuous queries. In essence, our approach is able to process the most recent data batch by exploiting already computed information, without requiring the evaluation of the query over the complete dataset. We present the generic algorithm which we translated to both SQL and MapReduce using SPARK; it implements various query rewriting methods. We demonstrate the effectiveness of our approach in temrs of query answering efficiency. Finally, we show that by exploiting the formal query rewriting methods of HIFUN, we can further reduce the computational cost, adding another layer of query optimization to our implementation.
The technology landscape has been dynamically reshaped by the rapid growth of the Internet of Things, introducing an era where everyday objects, equipped with smart sensors and connectivity, seamlessly interact to create intelligent ecosystems. IoT devices are highly heterogeneous in terms of software and hardware, and many of them are severely constrained. This heterogeneity and potentially constrained nature creates new challenges in terms of security, privacy, and data management. This work proposes a Monitoring-as-a-Service platform for both monitoring and management purposes, offering a comprehensive solution for collecting, storing, and processing monitoring data from heterogeneous IoT networks for the support of diverse IoT-based applications. To ensure a flexible and scalable solution, we leverage the FIWARE open-source framework, also incorporating blockchain and smart contract technologies to establish a robust integrity verification mechanism for aggregated monitoring and management data. Additionally, we apply automated workflows to filter and label the collected data systematically. Moreover, we provide thorough evaluation results in terms of CPU and RAM utilization and average service latency.