Skip to Main content Skip to Navigation

Enhancing Stream Processing and Complex Event Processing Systems

Abstract : As more and more connected objects and sensory devices are becoming part of our daily lives, the sea of high-velocity information flow is growing. This massive amount of data produced at high rates requires rapid insight to be useful in various applications such as the Internet of Things, health care, energy management, etc. Traditional data storage and processing techniques are proven inefficient. This gives rise to Data Stream Management and Complex Event Processing (CEP) systems.This thesis aims to provide optimal solutions for complex and proactive queries. Our proposed techniques, in addition to CPU and memory efficiency, enhance the capabilities of existing CEP systems by adding predictive feature through real-time learning. The main contributions of this thesis are as follows:We proposed various techniques to reduce the CPU and memory requirements of expensive queries. These operators result in exponential complexity both in terms of CPU and memory. Our proposed recomputation and heuristic-based algorithm reduce the costs of these operators. These optimizations are based on enabling efficient multidimensional indexing using space-filling curves and by clustering events into batches to reduce the cost of pair-wise joins.We designed a novel predictive CEP system that employs historical information to predict future complex events. We proposed a compressed index structure, range query processing techniques and an approximate summarizing technique over the historical space.The applicability of our techniques over the real-world problems presented has produced further customize-able solutions that demonstrate the viability of our proposed methods.
Complete list of metadatas

Cited literature [133 references]  Display  Hide  Download
Contributor : Abes Star :  Contact
Submitted on : Wednesday, February 5, 2020 - 4:04:07 PM
Last modification on : Saturday, February 8, 2020 - 1:21:08 AM
Long-term archiving on: : Wednesday, May 6, 2020 - 6:03:17 PM


Version validated by the jury (STAR)


  • HAL Id : tel-02468246, version 1


Abderrahmen Kammoun. Enhancing Stream Processing and Complex Event Processing Systems. Networking and Internet Architecture [cs.NI]. Université de Lyon, 2019. English. ⟨NNT : 2019LYSES012⟩. ⟨tel-02468246⟩



Record views


Files downloads