arXiv subjects

Jérôme Darmont

Publications and source records attributed to Jérôme Darmont.

At least 91 records · Page 5Linked to original sources

arXiv2008

Dynamic index selection in data warehouses

Analytical queries defined on data warehouses are complex and use several join operations that are very costly, especially when run on very large data volumes. To improve response times, data warehouse administrators casually use indexing techniques. This task is nevertheless complex and fastidious. In this paper, we present an automatic, dynamic index selection method for data warehouses that is based on incremental frequent itemset mining from a given query workload. The main advantage of this approach is that it helps update the set of selected indexes when workload evolves instead of recreating it from scratch. Preliminary experimental results illustrate the efficiency of this approach, both in terms of performance enhancement and overhead.

cs.DB↗

arXiv2008

Knowledge and Metadata Integration for Warehousing Complex Data

With the ever-growing availability of so-called complex data, especially on the Web, decision-support systems such as data warehouses must store and process data that are not only numerical or symbolic. Warehousing and analyzing such data requires the joint exploitation of metadata and domain-related knowledge, which must thereby be integrated. In this paper, we survey the types of knowledge and metadata that are needed for managing complex data, discuss the issue of knowledge and metadata integration, and propose a CWM-compliant integration solution that we incorporate into an XML complex data warehousing framework we previously designed.

cs.DB↗

arXiv2008

A Join Index for XML Data Warehouses

XML data warehouses form an interesting basis for decision-support applications that exploit complex data. However, native-XML database management systems (DBMSs) currently bear limited performances and it is necessary to research for ways to optimize them. In this paper, we propose a new join index that is specifically adapted to the multidimensional architecture of XML warehouses. It eliminates join operations while preserving the information contained in the original warehouse. A theoretical study and experimental results demonstrate the efficiency of our join index. They also show that native XML DBMSs can compete with XML-compatible, relational DBMSs when warehousing and analyzing XML data.

cs.DB↗

arXiv2007

Data Mining-based Materialized View and Index Selection in Data Warehouses

Materialized views and indexes are physical structures for accelerating data access that are casually used in data warehouses. However, these data structures generate some maintenance overhead. They also share the same storage space. Most existing studies about materialized view and index selection consider these structures separately. In this paper, we adopt the opposite stance and couple materialized view and index selection to take view-index interactions into account and achieve efficient storage space sharing. Candidate materialized views and indexes are selected through a data mining process. We also exploit cost models that evaluate the respective benefit of indexing and view materialization, and help select a relevant configuration of indexes and materialized views among the candidates. Experimental results show that our strategy performs better than an independent selection of materialized views and indexes.

cs.DB↗

arXiv2007

An Architecture Framework for Complex Data Warehouses

Nowadays, many decision support applications need to exploit data that are not only numerical or symbolic, but also multimedia, multistructure, multisource, multimodal, and/or multiversion. We term such data complex data. Managing and analyzing complex data involves a lot of different issues regarding their structure, storage and processing, and metadata are a key element in all these processes. Such problems have been addressed by classical data warehousing (i.e., applied to "simple" data). However, data warehousing approaches need to be adapted for complex data. In this paper, we first propose a precise, though open, definition of complex data. Then we present a general architecture framework for warehousing complex data. This architecture heavily relies on metadata and domain-related knowledge, and rests on the XML language, which helps storing data, metadata and domain-specific knowledge altogether, and facilitates communication between the various warehousing processes.

cs.DB↗

arXiv2007

Un index de jointure pour les entrepôts de données XML

XML data warehouses form an interesting basis for decision-support applications that exploit heterogeneous data from multiple sources. However, XML-native database systems currently bear limited performances and it is necessary to research ways to optimize them. In this paper, we propose a new index that is specifically adapted to the multidimensional architecture of XML warehouses and eliminates join operations, while preserving the information contained in the original warehouse. A theoretical study and experimental results demonstrate the efficiency of our index, even when queries are complex.

cs.DB↗

arXiv2007

Sélection simultanée d'index et de vues matérialisées

Indices and materialized views are physical structures that accelerate data access in data warehouses. However, these data structures generate some maintenance overhead. They also share the same storage space. The existing studies about index and materialized view selection consider these structures separately. In this paper, we adopt the opposite stance and couple index and materialized view selection to take into account the interactions between them and achieve an efficient storage space sharing. We develop cost models that evaluate the respective benefit of indexing and view materialization. These cost models are then exploited by a greedy algorithm to select a relevant configuration of indices and materialized views. Experimental results show that our strategy performs better than the independent selection of indices and materialized views.

cs.DB↗

arXiv2007

DWEB: A Data Warehouse Engineering Benchmark

Data warehouse architectural choices and optimization techniques are critical to decision support query performance. To facilitate these choices, the performance of the designed data warehouse must be assessed. This is usually done with the help of benchmarks, which can either help system users comparing the performances of different systems, or help system engineers testing the effect of various design choices. While the TPC standard decision support benchmarks address the first point, they are not tuneable enough to address the second one and fail to model different data warehouse schemas. By contrast, our Data Warehouse Engineering Benchmark (DWEB) allows to generate various ad-hoc synthetic data warehouses and workloads. DWEB is fully parameterized to fulfill data warehouse design needs. However, two levels of parameterization keep it relatively easy to tune. Finally, DWEB is implemented as a Java free software that can be interfaced with most existing relational database management systems. A sample usage of DWEB is also provided in this paper.

cs.DB↗

arXiv2007

DOEF: A Dynamic Object Evaluation Framework

cs.DB↗

arXiv2007

Decision tree modeling with relational views

Data mining is a useful decision support technique that can be used to discover production rules in warehouses or corporate data. Data mining research has made much effort to apply various mining algorithms efficiently on large databases. However, a serious problem in their practical application is the long processing time of such algorithms. Nowadays, one of the key challenges is to integrate data mining methods within the framework of traditional database systems. Indeed, such implementations can take advantage of the efficiency provided by SQL engines. In this paper, we propose an integrating approach for decision trees within a classical database system. In other words, we try to discover knowledge from relational databases, in the form of production rules, via a procedure embedding SQL queries. The obtained decision tree is defined by successive, related relational views. Each view corresponds to a given population in the underlying decision tree. We selected the classical Induction Decision Tree (ID3) algorithm to build the decision tree. To prove that our implementation of ID3 works properly, we successfully compared the output of our procedure with the output of an existing and validated data mining software, SIPINA. Furthermore, since our approach is tuneable, it can be generalized to any other similar decision tree-based method.

cs.DB↗

arXiv2007

Warehousing Web Data

In a data warehousing process, mastering the data preparation phase allows substantial gains in terms of time and performance when performing multidimensional analysis or using data mining algorithms. Furthermore, a data warehouse can require external data. The web is a prevalent data source in this context. In this paper, we propose a modeling process for integrating diverse and heterogeneous (so-called multiform) data into a unified format. Furthermore, the very schema definition provides first-rate metadata in our data warehousing context. At the conceptual level, a complex object is represented in UML. Our logical model is an XML schema that can be described with a DTD or the XML-Schema language. Eventually, we have designed a Java prototype that transforms our multiform input data into XML documents representing our physical model. Then, the XML documents we obtain are mapped into a relational database we view as an ODS (Operational Data Storage), whose content will have to be re-modeled in a multidimensional way to allow its storage in a star schema-based warehouse and, later, its analysis.

cs.DB↗

arXiv2007

Web data modeling for integration in data warehouses

In a data warehousing process, the data preparation phase is crucial. Mastering this phase allows substantial gains in terms of time and performance when performing a multidimensional analysis or using data mining algorithms. Furthermore, a data warehouse can require external data. The web is a prevalent data source in this context, but the data broadcasted on this medium are very heterogeneous. We propose in this paper a UML conceptual model for a complex object representing a superclass of any useful data source (databases, plain texts, HTML and XML documents, images, sounds, video clips...). The translation into a logical model is achieved with XML, which helps integrating all these diverse, heterogeneous data into a unified format, and whose schema definition provides first-rate metadata in our data warehousing context. Moreover, we benefit from XML's flexibility, extensibility and from the richness of the semi-structured data model, but we are still able to later map XML documents into a database if more structuring is needed.

cs.DB↗

arXiv2007

VOODB: A Generic Discrete-Event Random Simulation Model to Evaluate the Performances of OODBs

Performance of object-oriented database systems (OODBs) is still an issue to both designers and users nowadays. The aim of this paper is to propose a generic discrete-event random simulation model, called VOODB, in order to evaluate the performances of OODBs in general, and the performances of optimization methods like clustering in particular. Such optimization methods undoubtedly improve the performances of OODBs. Yet, they also always induce some kind of overhead for the system. Therefore, it is important to evaluate their exact impact on the overall performances. VOODB has been designed as a generic discrete-event random simulation model by putting to use a modelling approach, and has been validated by simulating the behavior of the O2 OODB and the Texas persistent object store. Since our final objective is to compare object clustering algorithms, some experiments have also been conducted on the DSTC clustering technique, which is implemented in Texas. To validate VOODB, performance results obtained by simulation for a given experiment have been compared to the results obtained by benchmarking the real systems in the same conditions. Benchmarking and simulation performance evaluations have been observed to be consistent, so it appears that simulation can be a reliable approach to evaluate the performances of OODBs.

cs.DB↗

arXiv2007

OCB: A Generic Benchmark to Evaluate the Performances of Object-Oriented Database Systems

We present in this paper a generic object-oriented benchmark (the Object Clustering Benchmark) that has been designed to evaluate the performances of clustering policies in object-oriented databases. OCB is generic because its sample database may be customized to fit the databases introduced by the main existing benchmarks (e.g., OO1). OCB's current form is clustering-oriented because of its clustering-oriented workload, but it can be easily adapted to other purposes. Lastly, OCB's code is compact and easily portable. OCB has been implemented in a real system (Texas, running on a Sun workstation), in order to test a specific clustering policy called DSTC. A few results concerning this test are presented.

cs.DB↗

arXiv2007

Performance Evaluation for Clustering Algorithms in Object-Oriented Database Systems

It is widely acknowledged that good object clustering is critical to the performance of object-oriented databases. However, object clustering always involves some kind of overhead for the system. The aim of this paper is to propose a modelling methodology in order to evaluate the performances of different clustering policies. This methodology has been used to compare the performances of three clustering algorithms found in the literature (Cactis, CK and ORION) that we considered representative of the current research in the field of object clustering. The actual performance evaluation was performed using simulation. Simulation experiments we performed showed that the Cactis algorithm is better than the ORION algorithm and that the CK algorithm totally outperforms both other algorithms in terms of response time and clustering overhead.

cs.DB↗

arXiv2007

Dynamic Clustering in Object-Oriented Databases: An Advocacy for Simplicity

We present in this paper three dynamic clustering techniques for Object-Oriented Databases (OODBs). The first two, Dynamic, Statistical & Tunable Clustering (DSTC) and StatClust, exploit both comprehensive usage statistics and the inter-object reference graph. They are quite elaborate. However, they are also complex to implement and induce a high overhead. The third clustering technique, called Detection & Reclustering of Objects (DRO), is based on the same principles, but is much simpler to implement. These three clustering algorithm have been implemented in the Texas persistent object store and compared in terms of clustering efficiency (i.e., overall performance increase) and overhead using the Object Clustering Benchmark (OCB). The results obtained showed that DRO induced a lighter overhead while still achieving better overall performance.

cs.DB↗

arXiv2007

Une plate-forme dynamique pour l'évaluation des performances des bases de données à objets

In object-oriented or object-relational databases such as multimedia databases or most XML databases, access patterns are not static, i.e., applications do not always access the same objects in the same order repeatedly. However, this has been the way these databases and associated optimisation techniques such as clustering have been evaluated up to now. This paper opens up research regarding this issue by proposing a dynamic object evaluation framework (DOEF). DOEF accomplishes access pattern change by defining configurable styles of change. It is a preliminary prototype that has been designed to be open and fully extensible. Though originally designed for the object-oriented model, it can also be used within the object-relational model with few adaptations. Furthermore, new access pattern change models can be added too. To illustrate the capabilities of DOEF, we conducted two different sets of experiments. In the first set of experiments, we used DOEF to compare the performances of four state of the art dynamic clustering algorithms. The results show that DOEF is effective at determining the adaptability of each dynamic clustering algorithm to changes in access pattern. They also led us to conclude that dynamic clustering algorithms can cope with moderate levels of access pattern change, but that performance rapidly degrades to be worse than no clustering when vigorous styles of access pattern change are applied. In the second set of experiments, we used DOEF to compare the performance of two different object stores: Platypus and SHORE. The use of DOEF exposed the poor swapping performance of Platypus.

cs.DB↗

arXiv2007

Conception d'un banc d'essais décisionnel

We present in this paper a new benchmark for evaluating the performances of data warehouses. Benchmarking is useful either to system users for comparing the performances of different systems, or to system engineers for testing the effect of various design choices. While the TPC (Transaction Processing Performance Council) standard benchmarks address the first point, they are not tuneable enough to address the second one. Our Data Warehouse Engineering Benchmark (DWEB) allows to generate various ad-hoc synthetic data warehouses and workloads. DWEB is fully parameterized. However, two levels of parameterization keep it easy to tune. Since DWEB mainly meets engineering benchmarking needs, it is complimentary to the TPC standard benchmarks, and not a competitor. Finally, DWEB is implemented as a Java free software that can be interfaced with most existing relational database management systems.

cs.DB↗