Industry 4.0 aims to create a modern industrial system by introducing technologies such as cloud computing, intelligent robotics and wireless sensor networks. In this paper we consider the multi-channel access and task offloading problem in mobile edge computing (MEC) enabled industry 4.0, and describe this problem in multi-agent environment. To solve this problem, we propose a novel multi-agent deep reinforcement learning (MADRL) scheme. The solution enables edge devices (EDs) to cooperate with each other, which can significantly reduce computation delay and improve channel access success rate. Extensive simulation results with different system parameters reveal that the proposed scheme could reduce computation delay by 33.38% and increase the channel access success rate by 14.88% and channel utilization by 3.24% compared to the traditional single agent reinforcement learning method.
The electromagnetic parameter retrieval method based on scattering ( ) parameters is widely used because parameters are easy to obtain. As a classic parameters retrieval method, the Nicolson–Ross–Weir (NRW) algorithm has problems such as half-wave resonance, phase angle jump, and multivaluedness. In this work, an electromagnetic parameter retrieval method based on deep learning is proposed, which aims to solve the multivaluedness problem in the traditional NRW method. The method we proposed is suitable for retrieval of inhomogeneous medium that satisfies the theory of effective medium. The simulation shows that the electromagnetic parameter retrieval method based on deep learning has high calculation accuracy without the multivaluedness problem.