Processamento de consultas em redes de sensores sem fio : uma abordagem de detecção de novidades para o controle da qualidade dos serviços de consultas / Processamento de Consultas em Redes de Sensores sem Fio: Uma Abordagem de Detecção de Novidades para o Controle da Qualidade dos Serviços das Consultas

AUTOR(ES)
DATA DE PUBLICAÇÃO

2009

RESUMO

Wireless Sensor Networks (WSNs) are communication networks composed of geographically distributed devices (sensor nodes) which can be used to monitor a variety of physical phenomena in real time. Due to the nature of these devices, WSNs have computational restrictions in terms of data processing and storage, and they are usually prone to failures. The main critical point of these networks, however, is in the way the levels of energy available in the sensor nodes are consumed; if this is done properly, the operational lifetime of the WSN can be well prolonged. This work presents an approach for adapting query processing in WSNs based on notions of quality of query services and novelty detection (ND). While the former concept captures the idea of possibly having different queries serviced in different ways by the same WSN, the latter relates to a machine learning technique embedded in the WSN components that allows them to modify their query processing behaviour in a dynamic fashion. This approach aims at the intelligent consumption of the limited resources available in these networks while still delivering the data quality as expected by their users. In this context, four classes of quality of query services have been specified having in mind distinct levels of requirements in terms of accuracy and temporal behaviour of the sensed data. Moreover, a new ND-based algorithm, named as AdaQuali (ADAptive QUALIty control for query processing in wireless sensor networks), is introduced in detail as a way to control the sensor node activities through the adjustment of their rates of data collection and transmission. For validation purposes, experiments with a prototype have been conducted over real data, and the results achieved so far point to gains in terms of energy consumption reduction that vary from 1.73% to 42.99% for different classes of quality of query service in the experiment that varies the number of sensor nodes of the network. KEY WORDS: Wireless Sensor Networks. Query processing. Novelty detection. Quality of query services.

ASSUNTO(S)

sistema de comunicaÇÃo sem fio banco de dados - dissertaÇÕes sistemas de informacao

ACESSO AO ARTIGO

Documentos Relacionados