Abstract
Smart devices continue to proliferate as the Internet-of-Things expands. Collectively, Internet-of-Things devices generate massive amounts of data for processing, analysis, and implementation. However, most individual smart devices lack sufficient hardware resources to process collected data in an efficient or timely manner. Thus, most devices send their data to a remote server or other cloud-based computing system for processing because of the increased computational capacities of such remote locations. Although these remote locations can process the data faster and more efficiently, the increase in the number of smart devices accessing the remote locations increases the transmission traffic, and associated bottlenecks, on networks and other data-transmission systems. Many smart devices reside on local networks that feature other, more-powerful, computing devices, such as desktops, laptops, home servers, and gaming systems. Some of these additional computing devices could be tasked with processing data and other information for Internet-of-Things devices that lack sufficient computational capacity to process the data themselves.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Shankar, Karthik Ravi and Nagarajan, Gurunathan, "Distributed Placement of Machine-Learning Computing in an Edge Network", Technical Disclosure Commons, (July 20, 2018)
https://www.tdcommons.org/dpubs_series/1348