The growing smart devices (SDs) in the Industrial Internet of Things (IIoT) generate complex computations that strain the performance and energy of local processing. Mobile Edge Computing (MEC) addresses this by providing nearby computing resources for low-latency offloading. However, achieving efficient computation offloading under massive device concurrency and densely distributed computation offloadings remains a key challenge. To address this, this paper constructs a multi-server MEC system model for IIoT and introduces Mean-Field Game (MFG) theory to model the offloading competition among SDs. This effectively reduces the dimensionality and complexity of multi-agent interactions. A novel Mean-Field Computation Offloading (MFCO) algorithm is proposed, which combines MFG with Rainbow Deep Q-Network under a Multi-Agent Deep Reinforcement Learning framework. By incorporating advanced components such as distributional value estimation, prioritized experience replay, multi-step learning, and dueling architecture, each SD acts as an autonomous agent, optimizing its policy based on local observations and mean-field approximations. Further enhancements include Boltzmann exploration, adaptive learning rates, and a mean Q-network structure, which improve convergence speed and training stability. Extensive simulations on a large-scale IIoT platform (100 SDs, 9 MEC servers) demonstrate that MFCO reduces computation latency and improves long-term rewards while maintaining robust server performance.
Xinmin Cheng, Chengquan Yu, Lu Gao et al.· IEEE Transactions on Green C...· 0 citations
: The rapid growth of the Industrial Internet of Things (IIoT) has become a cornerstone of high-quality global economic development. By integrating sensor networks, edge computing, and cloud intelligence, IIoT has emerged as a key enabler for smart manufacturing and digital transformation across industries. However, this technological advancement introduces significant cybersecurity challenges that render traditional intrusion detection systems inadequate for IIoT environments. To address this critical gap, we propose a deep spiking Q-network (DSQN)-based intrusion detection system (DSQN-IDS) for the IIoT, formulating unknown intrusion detection as a Markov decision process (MDP). The system employs a hierarchical multi-stage decision-making framework integrating conditional variational autoencoders (CVAE) for feature extraction, deep Q-networks (DQN) for reinforcement learning-based decision-making, and spiking neural networks (SNNs) for energy-efficient classification. We train the DSQN using a multi-layer perceptron (MLP) to approximate the state-action value function, and leverage the event-driven nature of SNNs—where neurons only spike when their membrane potential exceeds a threshold—to minimize energy consumption. Extensive experiments on IIoT datasets demonstrate that our approach achieves superior performance in balancing detection accuracy, energy efficiency, and model stability when identifying unknown attacks compared to state-of-the-art methods.
Yimeng Liu, Xinyu Xu, Wangting Xue et al.· Computers, Materials & C...· 0 citations