With the emergence of various convolutional neural network (CNN)-based applications and the rapid growth of CNN model scale, the resource-constricted end devices can hardly deploy CNN-based applications. Current work optimizes the CNN model on edge servers and deploys the optimized model on devices in an edge computing environment. However, most of them only optimize the resource consumption within or across models solely, whereas neglecting the other side. In this article, we propose a novel CNN-based resource optimization approach (CroApp) that not only optimizes the resource consumption within the CNN model but also pays attention to resource optimization across the applications. Specifically, we adopt model compression as the “inner-model” optimization method, as well as computation sharing as the “intermodel” optimization method. First, during “inner-model” optimization, the CroApp prunes unnecessary parameters within the model on edge servers to reduce the scale of the model. Then, during “intermodel” optimization, the CroApp trains a set of shareable models based on the pruned model and sends these shareable models to end devices. Finally, the CroApp adaptively adjusts the shared models to reduce resource consumption. The experimental results show that the CroApp outperforms the state-of-the-art approaches in terms of resource reduction, scalability, and application performance.

中文翻译：

---

CroApp：边缘计算环境中基于 CNN 的资源优化方法


随着各种基于卷积神经网络（CNN）的应用的出现以及CNN模型规模的快速增长，资源有限的终端设备很难部署基于CNN的应用。目前的工作是在边缘服务器上优化 CNN 模型，并将优化后的模型部署在边缘计算环境中的设备上。然而，他们中的大多数只优化模型内部或模型之间的资源消耗，而忽略了另一面。在本文中，我们提出了一种新颖的基于 CNN 的资源优化方法（CroApp），该方法不仅优化 CNN 模型内的资源消耗，而且还关注跨应用程序的资源优化。具体来说，我们采用模型压缩作为“模型内”优化方法，并采用计算共享作为“模型间”优化方法。首先，在“内部模型”优化过程中，CroApp 会在边缘服务器上修剪模型内不必要的参数，以减少模型的规模。然后，在“模型间”优化过程中，CroApp 根据修剪后的模型训练一组可共享模型，并将这些可共享模型发送到终端设备。最后，CroApp自适应地调整共享模型以减少资源消耗。实验结果表明，CroApp 在资源减少、可扩展性和应用程序性能方面优于最先进的方法。