RESUMEN
With the development of intelligent IoT applications, vast amounts of data are generated by various volume sensors. These sensor data need to be reduced at the sensor and then reconstructed later to save bandwidth and energy. As the reduced data increase, the reconstructed data become less accurate. Usually, the trade-off between reduction rate and reconstruction accuracy is controlled by the reduction threshold, which is calculated by experiments based on historical data. Considering the dynamic nature of IoT, a fixed threshold cannot balance the reduction rate with the reconstruction accuracy adaptively. Aiming to dynamically balance the reduction rate with the reconstruction accuracy, an autonomous IoT data reduction method based on an adaptive threshold is proposed. During data reduction, concept drift detection is performed to capture IoT dynamic changes and trigger threshold adjustment. During data reconstruction, a data trend is added to improve reconstruction accuracy. The effectiveness of the proposed method is demonstrated by comparing the proposed method with the basic Kalman filtering algorithm, LMS algorithm, and PIP algorithm on stationary and nonstationary datasets. Compared with not applying the adaptive threshold, on average, there is an 11.7% improvement in accuracy for the same reduction rate or a 17.3% improvement in reduction rate for the same accuracy.
RESUMEN
In order to effectively apply BranchyNet, a DNN with multiple early-exit branches, in edge intelligent applications, one way is to divide and distribute the inference task of a BranchyNet into a group of robots, drones, vehicles, and other intelligent edge devices. Unlike most existing works trying to select a particular branch to partition and deploy, this paper proposes a genetic algorithm (GA)-based online partitioning approach that splits the whole BranchyNet with all its branches. For this purpose, it establishes a new calculation approach based on the weighted average for estimating total execution time of a given BranchyNet and a two-layer chromosome GA by distinguishing partitioning and deployment during the evolution in GA. The experiment results show that the proposed algorithm can not only result in shorter execution time and lower device-average energy cost but also needs less time to obtain an optimal deployment plan. Such short running time enables the proposed algorithm to generate an optimal deployment plan online, which dynamically meets the actual requirements in deploying an intelligent application in the edge.