Distributed Processing Method for Deep Learning in Wireless Sensor Networks

Abstract

In wireless sensor networks, distributed processing technology for deep learning that utilizes edge computing and mobile terminals has been attracting interest; however, with the expansion of the use of wireless sensor networks, the amount of data and the increase in server load are issues, especially for deep learning. Although the existing studies which improve the data processing speed and latency reduction of distributed processing, there is still a problem in which the amount of communication and the load on the server increase. In this paper, we propose load balancing algorithm for deep learning to reduce the communication volume and server load.