Triple-partition Network: Collaborative Neural Network based on the ‘End Device-Edge-Cloud’

Gao, Zhipeng; Miao, Dong; Zhao, Langcheng; Mo, Zijia; Qi, Guangpeng; Yan, Liang

doi:10.1109/wcnc49053.2021.9417243

Cited by 3 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One is that the model's convolutional layer is dealt with using low-rank decomposition, followed by the full connection layer using singular value decomposition method, and the other is that processed network is segmented into fine granularity for minimum execution delay. cloud-edge neural network model segmentation method composed of three outlets to transmit data, which greatly reduces end-to-end transmission delay compared to pure cloud computing[24]. Xue et al presented a novel DNN partition method that segments the neural network model to minimize delay, cost, and energy consumption and escaped the failure caused by networks and other factors in the transmission process of large-scale computing data…”

mentioning

confidence: 99%

A cloud-edge collaborative task scheduling method based on model segmentation

Zhang,

Chen,

et al. 2024

J Cloud Comp

View full text Add to dashboard Cite

With the continuous development and combined application of cloud computing and artificial intelligence, some new methods have emerged to reduce task execution time for training neural network models in a cloud-edge collaborative environment. The most attractive method is neural network model segmentation. However, many factors affect the segmentation point, such as resource allocation, system energy consumption, load balancing, and network Bandwidth allocation. Some segmentation methods consider the shortest task execution time, which ignores the utilization of resources at the edge and can result in resource waste. Additionally, these factors are difficult to measure, which presents a challenge in calculating the best segmentation point to achieve the goal of maximum resource utilization and minimum task execution time. To solve this problem, this paper proposes a cloud-edge collaborative task scheduling method based on model segmentation (CECMS). This method first analyzes the factors affecting the segmentation point of the model and then obtains accurate factors that affect the segmentation point calculation through the pre-execution method. Furthermore, a multi-objective solution algorithm is improved to calculate the optimal model segmentation point. And tasks are separately offloaded to the edge and cloud based on the optimal model segmentation point. Finally, the experiments are conducted to verify the effectiveness of this method. Finally, the effectiveness of the CECMS method was verified through simulation experiments. Compared with the Dynamic Adaptive DNN Surgery (DADS) method and an adaptive DNN inference acceleration framework algorithm with end–edge–cloud collaborative computing algorithm (ADC), CECMS achieves the same effectiveness as DADS and ADC in optimizing task execution time by comprehensively considering the utilization of edge resources and minimizing task execution time, while also effectively ensuring resource utilization.

show abstract

mentioning

confidence: 99%