@inbook{54587,
  abstract     = {{<jats:p>With significant growth in RDF datasets, application developers demand online availability of these datasets to meet the end users’ expectations. Various interfaces are available for querying RDF data using SPARQL query language. Studies show that SPARQL end-points may provide high query runtime performance at the cost of low availability. For example, it has been observed that only 32.2% of public endpoints have a monthly uptime of 99–100%. One possible reason for this low availability is the high workload experienced by these SPARQL endpoints. As complete query execution is performed at server side (i.e., SPARQL endpoint), this high query processing workload may result in performance degradation or even a service shutdown. We performed extensive experiments to show the query processing capabilities of well-known triple stores by using their SPARQL endpoints. In particular, we stressed these triple stores with multiple parallel requests from different querying agents. Our experiments revealed the maximum query processing capabilities of these triple stores after which point they lead to service shutdowns. We hope this analysis will help triple store developers to design workload-aware RDF engines to improve the availability of their public endpoints with high throughput.</jats:p>}},
  author       = {{Khan, Hashim and Manzoor, Ali and Ngonga Ngomo, Axel-Cyrille and Saleem, Muhammad}},
  booktitle    = {{Studies on the Semantic Web}},
  issn         = {{1868-1158}},
  publisher    = {{IOS Press}},
  title        = {{{When is the Peak Performance Reached? An Analysis of RDF Triple Stores}}},
  doi          = {{10.3233/ssw210042}},
  year         = {{2021}},
}

@inproceedings{56485,
  abstract     = {{Over years, the Web of Data has grown significantly. Various interfaces such as SPARQL endpoints, data dumps, and Triple Pattern Fragments (TPF) have been proposed to provide access to this data. Studies show that many of the SPARQL endpoints have availability issues. The data dumps do not provide live querying capabilities. The TPF solution aims to provide a trade-off between the availability and performance by dividing the workload among TPF servers and clients. In this solution, the TPF server only performs the triple patterns execution of the given SPARQL query. While the TPF client performs the joins between the triple patterns to compute the final resultset of the SPARQL query. High availability is achieved in TPF but increase in network bandwidth and query execution time lower the performance. We want to propose a more intelligent SPARQL querying server to keep the high availability along with high query execution performance, while minimizing the network bandwidth. The proposed server will offer query execution services (can be single triple patterns or even join execution) according to the current status of the workload. If a server is free, it should be able to execute the complete SPARQL query. Thus, the server will offer execution services while avoiding going beyond the maximum query processing limit, i.e. the point after which the performance start decreasing or even service shutdown. Furthermore, we want to develop a more intelligent client, which keeps track of a server’s processing capabilities and therefore avoid DOS attacks and crashes.}},
  author       = {{Khan, Hashim}},
  booktitle    = {{International Semantic Web Conference}},
  keywords     = {{dice group_aksw hashim ngonga opal saleem simba}},
  title        = {{{Towards More Intelligent SPARQL Querying Interfaces}}},
  year         = {{2019}},
}