Efficient and Accurate Classification Enabled by a Lightweight CNN
Weiwei Miao, Zeng Zeng, Chuanjun Wang, Yueqin Chen, Chunhe Song · 2020 5th International Conference on Computer and Communication Systems (ICCCS) · 2020
With the rapid development of cloud computing technology, many applications such as image recognition and fault diagnosis are applied in the power grid, and the data is collected and uploaded to the cloud for processing. However, the amount of data and the amount of calculation required by the model are too large, so that the cloud computing model cannot solve the current problem well. Edge computing refers to processing data at the edge of the network, which can reduce request response time, improve battery life, and reduce network bandwidth while ensuring data security and privacy. However, existing edge devices are difficult to meet complex models' demands. In order to solve the above problems, this paper proposes a lightweight CNN model that can be operated on the edge device. Experiments prove that the model is a reliable method for fault diagnosis at the edge.