Skip to Main content Skip to Navigation

Knowledge graph management and streaming in the context of edge computing

Abstract : Edge Computing proposes to distribute computation and data storage closer to original data sources. This technology is becoming an important trend in IT. This is mainly due to the emergence of the Internet of Things and its set of compact devices, eg sensors, actuators or gateways, whose computing and storing capacities are ever-increasing. Different from Cloud Computing, which targets large data centers, Edge Computing's computation distribution strategy can potentially reduce network pressure and make full use of computation power of edge devices.In order to support smart data processing at the edge of the network, a knowledge representation strategy is needed. In 2021, technologies belonging to the so-called Semantic Web are mature and robust enough to bring intelligence to Edge computing. These technologies correspond to the RDF (Resource Description Framework) data model, the RDFS (RDF Schema) and OWL (Web ontology Language) ontology languages and their associated reasoning services, the SPARQL query language. A cornerstone of such an approach is an Edge device compliant RDF database management system. However, most RDF stores are designed for powerful servers or Cloud Computing. These systems partly owe their efficiency to costly indexing strategies, ie based on multiples indexes.In the context of Edge computing, characterised by relatively limited memory footprint and computing power, it is not reasonable to use any of these RDF stores. Hence, a novel kind of RDF store is needed. In this work, we consider that some of its features must be an in-memory approach, low-memory footprint for both the system and its managed data, adapted query optimization techniques to make query processing as fast as possible. Moreover, reasoning at query run-time and stream processing are required by several of the use cases that we have identified in real-world situations.For the aim of compressing RDF data while maintaining querying speed, we make an extensive use of Succinct Data Structure (SDS) data structures to benefit from its data compression and high data retrieving speed simultaneously. This help us to get a self-indexed compact RDF store which does not require decompression operation. Our query processing approach is adapted to our storage layout and to standard SDS operations, namely access, rank and select. We prove the efficiency of our approach with thorough evaluation.In order to help the acceleration of RDFS reasoning, we have designed our system based on a semantic-aware encoding strategy named LiteMat. This encoding scheme, which has been developed and maintained by our research team, has been extended in the PhD thesis to support multiple inheritance, transitive and inverse properties. It thus extends the expressive power of addressed ontologies.In real IoT use cases, data are usually continuously coming from sensors or actuators. To address this issue, an extension of SuccinctEdge has been designed to handle those streaming data. This extension includes an extra data structure in our RDF store to process numeric data with time-based aggregations and an adapted streaming-SPARQL extension processor to permit the querying of streaming data. With the help of this extra data structure and the adapted query processor, one can easily query the dynamic RDF graph by a streaming-SPARQL query. However, query execution on a dynamic graph may have many repeating graph searching, which may heavily slow down the system. In order to solve this problem, we separate a query into dynamic part and static part. The result of the static part is computed once and stored all along the duration of the continuous query processing. Concerning the dynamic part, the corresponding result is combined with the static part result to generate the final result of each query execution. We prove that our streaming extension system is of low latency and of high throughput with good robustness and correctness properties
Document type :
Complete list of metadata
Contributor : ABES STAR :  Contact
Submitted on : Thursday, June 16, 2022 - 3:43:25 PM
Last modification on : Friday, June 24, 2022 - 4:05:30 AM


Version validated by the jury (STAR)


  • HAL Id : tel-03697222, version 1



Weiqin Xu. Knowledge graph management and streaming in the context of edge computing. Artificial Intelligence [cs.AI]. Université Gustave Eiffel, 2021. English. ⟨NNT : 2021UEFL2030⟩. ⟨tel-03697222⟩



Record views


Files downloads