With the emergence of the Internet of Things (IoT), a new computing paradigm -Edge Computing- is evolving. Thanks to its horizontal scalability, this new paradigm leverages the rapid growth of devices and makes it in its favor. As a result, it improves scalability and reduces latency. However, simply adopting it does not necessarily guarantee meeting the Quality of Service (QoS), as many aspects need to be considered. To overcome this issue, there is a need for an intelligent Edge Computing. With machine learning abilities, the power of this paradigm can be extended to meet the IoT requirements. Motivated by this, in this paper, we present a tasks orchestration algorithm that is based on Fuzzy Decision Tree. It uses reinforcement learning that allows it to adapt to the unpredictable changes in the environment, and to provide better support for the heterogeneity of devices. The proposed algorithm has reduced the power consumption by 37% and failure rate by 57%, with a slightly shorter completion time compared to the existing solutions.
CITATION STYLE
Mechalikh, C., Taktak, H., & Moussa, F. (2020). A Fuzzy Decision Tree Based Tasks Orchestration Algorithm for Edge Computing Environments. In Advances in Intelligent Systems and Computing (Vol. 1151 AISC, pp. 193–203). Springer. https://doi.org/10.1007/978-3-030-44041-1_18
Mendeley helps you to discover research relevant for your work.