QBF: A Query Broker Framework for Adaptable Query Evaluation

Collet, Christine; Vu, Tuyet-Trinh

doi:10.1007/978-3-540-25957-2_29

Cited by 16 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, persistence could be configured at different levels [48] memory, cache or disk and it could cooperate with fault tolerance protocols for providing, for example, different levels of atomic persistent data management. Other frameworks for building query optimizers are the ones described in [89], Cascades [54], and EROC (Extensible Reusable Optimization Components) [80] and [34,107]. Framboise [46] and ODAS [33,105] are frameworks for layering active database functionality on top of passive DBMS.…”

Section: Configuring and Unbundling Data Managementmentioning

confidence: 99%

Big Data Management: What to Keep from the Past to Face Future Challenges?

2017

View full text Add to dashboard Cite

The emergence of new hardware architectures, and the continuous production of data open new challenges for data management. It is no longer pertinent to reason with respect to a predefined set of resources (i.e., computing, storage and main memory). Instead, it is necessary to design data processing algorithms and processes considering unlimited resources via the ''pay-as-you-go'' model. According to this model, resources provision must consider the economic cost of the processes versus the use and parallel exploitation of available computing resources. In consequence, new methodologies, algorithms and tools for querying, deploying and programming data management functions have to be provided in scalable and elastic architectures that can cope with the characteristics of Big Data aware systems (intelligent systems, decision making, virtual environments, smart cities, drug personalization). These functions, must respect QoS properties (e.g., security, reliability, fault tolerance, dynamic evolution and adaptability) and behavior properties (e.g., transactional execution) according to application requirements. Mature and novel system architectures propose models and mechanisms for adding these properties to new efficient data management and processing functions delivered as services. This paper gives an overview of the different architectures in which efficient data management functions can be delivered for addressing Big Data processing challenges.

show abstract

Section: Configuring and Unbundling Data Managementmentioning

confidence: 99%

Big Data Management: What to Keep from the Past to Face Future Challenges?

2017

View full text Add to dashboard Cite

show abstract

“…These methods are classified in four types (i) Replacement,(ii) Scheduling [15], (iii): Reoptimization [1,2,12], and (iv) Uses of dynamic operators [23,24]. Each dynamic optimization method is able in adapting the execution plans in order to react to one or several events: (i) Estimation errors [15],(ii) Memory available [7,8,28,30], (iii): Delays in data arrival rates [1,2], and (iv) Users Preferences.…”

Section: Related Workmentioning

confidence: 99%

Mobile Join Algorithms based on Mobiles Agents for Large Scale Distributed Query Optimization

Hussein¹

2012

IJAIS

View full text Add to dashboard Cite

In the large scale distributed environment, the query optimization presents new problems because of the data unavailability, the estimations inaccuracies and environment instability. In this paper, we address the sub-optimality of executions plans caused by these problems. We propose to extend the join algorithms based on mobile agents in order to correct the sub-optimality. This extension allows the join to change their execution site. Indeed, the mobile agent executing a join adapts to changes in characteristics of the execution environment (e.g. network bandwidth, available memory) and responds to the estimations inaccuracies (e.g. size of intermediate relations). The performance evaluation shows that the proposed algorithms improve the response time whatever the variation of estimations errors.

show abstract

“…The adaptive methods can be classified according to nature of the decision making about adaptation: centralized and decentralized methods. In the centralized methods [2,19,20,21,41], a main process is in charge of monitoring and changing, at runtime, the execution plans, whereas correcting sub-optimality is done in operator or subquery level in decentralized methods [1,8,29,30,37].…”

Section: Related Workmentioning

confidence: 99%

“…On the other hand, we observe decentralized methods [8,19,37] that try to improve the cost of local processing by adapting the use of the CPU, I/O and memory to the changes in execution environment. Whereas [1,30] take into account the cost of local processing together with network resources.…”

Section: Introductionmentioning

confidence: 99%