Dynamic Offloading Loading Optimization in distributed Fault Diagnosis system with Deep Reinforcement Learning Approach

TL;DR

This paper proposes a deep reinforcement learning-based framework for optimizing task offloading in distributed fault diagnosis systems, reducing delays and improving resource utilization in MEC environments.

Contribution

It introduces a novel RL-based approach with DQN and DDPG strategies for dynamic resource allocation and MEC server selection in fault diagnosis systems.

Findings

Both RL strategies outperform traditional non-learning schemes.

DQN effectively optimizes MEC selection with convex optimization for other variables.

DDPG handles all dynamic variables simultaneously for adaptive offloading.

Abstract

Artificial intelligence and distributed algorithms have been widely used in mechanical fault diagnosis with the explosive growth of diagnostic data. A novel intelligent fault diagnosis system framework that allows intelligent terminals to offload computational tasks to Mobile edge computing (MEC) servers is provided in this paper, which can effectively address the problems of task processing delays and enhanced computational complexity. As the resources at the MEC and intelligent terminals are limited, performing reasonable resource allocation optimization can improve the performance, especially for a multi-terminals offloading system. In this study, to minimize the task computation delay, we jointly optimize the local content splitting ratio, the transmission/computation power allocation, and the MEC server selection under a dynamic environment with stochastic task arrivals. The challenging dynamic joint optimization problem is formulated as a reinforcement learning (RL) problem, which is designed as the computational offloading policies to minimize the long-term average delay cost. Two deep RL strategies, deep Q-learning network (DQN) and deep deterministic policy gradient (DDPG), are adopted to learn the computational offloading policies adaptively and efficiently. The proposed DQN strategy takes the MEC selection as a unique action while using the convex optimization approach to obtain the local content splitting ratio and the transmission/computation power allocation. Simultaneously, the actions of the DDPG strategy are selected as all dynamic variables, including the local content splitting ratio, the transmission/computation power allocation, and the MEC server selection. Numerical results demonstrate that both proposed strategies perform better than the traditional non-learning schemes.