par Ugarte Caraball, Martin Ignacio ;Vansummeren, Stijn
Référence Alberto Mendelzon International Workshop on Foundations of Data Management (AMW)(12: May 21-25, 2018: Cali, Colombia), Proceedings of the 12th Alberto Mendelzon International Workshop on Foundations of Data Management (AMW), CEUR-WS.org, Vol. 2100
Publication Publié, 2018
Publication dans des actes
Résumé : The increasing number of applications that require processing and analyzing high-throughput information in real time has fostereda new field of study known as Complex Event Processing (CEP). The claimed objective of CEP is to develop techniques that are able to copewith the high-throughput requirements of modern Big Data applications. Also, it is commonly argued that CEP systems are different from relational reactive systems such as Active Database Management Systems (ADBMSs) or Data Stream Management Systems (DSMSs) because the latter see new data elements as database transactions (generally insertions or deletions) whose order is not relevant. On the contrary, CEPsystems see new data elements as events (e.g. sensor measurements) whose arrival time and order have a semantic meaning. Unfortunately,these differences come from a high-level description of the underlying applications, but do not reveal fundamental computational differencesbetween the requirements of CEP systems and relational systems. Moreover, recent developments in Dynamic Query Evaluation (DQE) showthat general techniques in the relational setting can be more efficient than current CEP algorithms. In this paper, we study whether there is a fundamental difference between the computational requirements of CEP and DQE. To answer this question, we identify two concrete assumptions of CEP and investigate their effects in terms of evaluation complexity. Concretely, we show a realistic CEP query that, if the Online Matrix-vector multiplication (OMv) conjecture holds, cannot be evaluated with sub-linear time per tuple followed by sub-linear-delay enumeration, but under the CEP assumptions can be evaluated with constant time per tuple followed by constant-delay enumeration. Sub-linear here means O(n^{1−ε})), where n is the size of the active domain.