期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2020
卷号：11
期号：8
DOI：10.14569/IJACSA.2020.0110846
出版社：Science and Information Society (SAI)
摘要：Scalability is an utter compulsory for the success of the IoT’s unprecedentedly growing network. The operational and financial bottlenecks allied with growth can be overwhelming for those peeping to integrate IoT solutions. As the IoT technology proceeds, so is the scale of operations desired to arrive at a wider target region. Breakdown may take place not because of device’s ability to scale, but due to data scale. As more devices are being incorporated, more data/information will be amassed, stored, processed, and scrutinized. The volume of this collection simply cannot be managed from a single edge device by deploying vertical approach. When starting small, it’s important to peep into the future and anticipate growth. Companies that can’t adapt to unpredictable market changes will fold without the right IoT architecture in place. Therefore, a scalable IOT framework has been proposed in the paper, which will provide load balancing or scalability by deploying the provisions of horizontal scalability for the system. The framework will be utilizing SOM for the purpose of classifying applications (whether delay sensitive or delay insensitive), so that proper decisions can be made based on the incoming data (typically signals) and if edge gets over flooded with the data, then edge is scaled to instigate the other edge for computing additional requests . The proposed system is termed as intelligent because its algorithm empowers the edge to take decision and classify applications based on the type of requirement of the application.
关键词：Scalability; internet of things; self organizing map; edge; horizontal scalability
