Large scale stream analytics using a resource-constrained edge

Autor: Henri E. Bal, Gabriele Di Bernardo, Roshan Bharath Das
Přispěvatelé: Computer Systems, Network Institute, High Performance Distributed Computing
Jazyk: angličtina
Rok vydání: 2018
Předmět:
Zdroj: Bharath Das, R, Di Bernardo, G & Bal, H 2018, Large scale stream analytics using a resource-constrained edge . in Proceedings-2018 IEEE International Conference on Edge Computing, EDGE 2018-Part of the 2018 IEEE World Congress on Services ., 8473389, Institute of Electrical and Electronics Engineers Inc., pp. 135-139, 2018 IEEE International Conference on Edge Computing, EDGE 2018, San Francisco, United States, 2/07/18 . https://doi.org/10.1109/EDGE.2018.00027
Proceedings-2018 IEEE International Conference on Edge Computing, EDGE 2018-Part of the 2018 IEEE World Congress on Services, 135-139
STARTPAGE=135;ENDPAGE=139;TITLE=Proceedings-2018 IEEE International Conference on Edge Computing, EDGE 2018-Part of the 2018 IEEE World Congress on Services
EDGE
DOI: 10.1109/EDGE.2018.00027
Popis: A key challenge for smart city analytics is fast extraction, accumulation and processing of sensor data collected from a large number of IoT devices. Edge computing has enabled processing of simple analytics, such as aggregation, geographically closer to the IoT devices to improve latency. However, the throughput of processing in the edge depends on the type of resources available, the number of IoT devices connected and the type of stream analytics performed in the edge. We introduce a framework called Seagull for building efficient, large scale IoT-based applications. Our framework distributes the stream analytics processing tasks to the nodes based on their proximity to the sensor data source as well as the amount of processing the nodes can handle. Our evaluation shows the effect of various stream analytics parameters on the maximum sustainable throughput for a resource-constrained edge device.
Databáze: OpenAIRE
Externí odkaz: