The Industrial Internet of Things (IIoT) is a crucial research field spawned by the Internet of Things (IoT). IIoT links all types of industrial equipment through the network; establishes data acquisition, exchange, and analysis systems; and optimizes processes and services, so as to reduce cost and enhance productivity. The introduction of edge computing in IIoT can significantly reduce the decision-making latency, save bandwidth resources, and to some extent, protect privacy. This paper outlines the research progress concerning edge computing in IIoT. First, the concepts of IIoT and edge computing are discussed, and subsequently, the research progress of edge computing is discussed and summarized in detail. Next, the future architecture from the perspective of edge computing in IIoT is proposed, and its technical progress in routing, task scheduling, data storage and analytics, security, and standardization is analyzed. Furthermore, we discuss the opportunities and challenges of edge computing in IIoT in terms of 5G-based edge communication, load balancing and data offloading, edge intelligence, as well as data sharing security. Finally, we introduce some typical application scenarios of edge computing in IIoT, such as prognostics and health management (PHM), smart grids, manufacturing coordination, intelligent connected vehicles (ICV), and smart logistics.

In the Industrial Internet of Things (IIoT), Multi-access Edge Computing (MEC) emerges as a transformative paradigm for managing computation-intensive tasks, where task offloading plays an important role. However, due to the complex environment of IIoT, existing deep reinforcement learning-based schemes suffer from significant shortcomings in accuracy and convergence speed during model training when addressing the issue of task offloading. In this paper, to solve this problem, we propose an online task offloading scheme based on reinforcement learning, leveraging the double deep Q network (DQN) and dueling DQN with a prioritized experience replay mechanism, called the P rioritized experience-based D ouble D ueling DQN task offloading scheme (P-D3QN). P-D3QN enhances action selection accuracy using double DQN and mitigates Q-value overestimation by decomposing state and advantage using dueling DQN. Additionally, we adopt the prioritized experience replay mechanism to enhance the convergence speed of model training by selecting transitions that induce a higher training error between the evaluation network and the target network. Experimental results demonstrate that P-D3QN outperforms several state-of-the-art schemes, achieving a reduction of 21.0% in the average cost of the task and improving the completion rate of the task by 19.5%.

The Industrial Internet of Things (IIoT) integrates diverse wireless and heterogeneous devices to enable time-sensitive applications. Multi-access edge computing (MEC) offers computing services for nearby tasks to meet their time requirements. However, offloading a large number of tasks to servers with minimal time is a challenging issue. Existing approaches typically allocate tasks into equal-length timeslots for offloading based on optimization or heuristic methods, overlooking the time-varying nature of task arrival density. This neglect significantly increases task execution time. To address this problem, we propose an Adaptive Task Offloading scheme with two-stage hybrid Matching (ATOM). In ATOM, a global buffer with an adjustable threshold is employed to store task information, enabling it to adapt to the time-varying arrival density and execute different offloading stages accordingly. In the online matching stage, if the threshold is not reached, tasks in the buffer are promptly offloaded to the most suitable server. In the offline matching stage, when the threshold is exceeded, all tasks in the buffer are optimally matched with servers and offloaded in batches. Experimental results demonstrate that ATOM outperforms state-of-the-art schemes in terms of average execution time and timeout rate, achieving reductions of 23.3% and 10.4%, respectively.

In the Multi-access Edge Computing (MEC)-based Industrial Internet of Things (IIoT), a key challenge is to make an efficient task-offloading decision. Machine learning methods have emerged as popular solutions to address this issue. However, in IIoT, it is common for the feature distribution of data to change significantly over time, i.e., data drift, and existing machine learning-based schemes struggle to frequent data drift, failing to maintain consistent high accuracy of task-offloading decisions. This struggle arises because they require extended retraining or extensive model adjustments, which involve significant delays and increased computational overhead due to the complex network structure. In this paper, we propose a B road learning-based task OFF loading scheme (BOFF). In BOFF, a data drift detection method based on statistical features and a sliding window is established to determine the occurrence of data drift in the system, while utilizing the Gini coefficient to enhance feature extraction and improve accuracy of task-offloading decision model under data drift. When data drift is detected, BOFF leverages its fast training and redeployment capabilities based on feature-enhanced broad learning to update the task offloading model and maintain accuracy. In the absence of significant data drift, minor changes in data distribution are addressed through incremental updates to slow the decline in model accuracy. Numerical results demonstrate that BOFF significantly improves the adaptability of data drift, ensuring high accuracy and efficiency of task offloading in dynamic IIoT environments.

Fifth-generation mobile communication technology (5G) is a powerful driving force for the Industrial Internet of Things (IIoT). In the 5G-based IIoT, multi-access edge computing (MEC) can move traffic and service computing from the centralized cloud to the edge networks, thus effectively improving the real-time performance of task processing. In this context, it is crucial to assign real-time tasks generated by numerous edge devices to MEC servers. Existing schemes usually schedule tasks in batches within time slots and ignore the situations where edge tasks arrive with time-varying density. However, the problem is that these schemes can lead to extra waiting delay in the slots with sparse tasks, thus resulting in additional latency in task processing. To solve this problem, we propose a task scheduling scheme based on two-stage hybrid matching. The proposed scheme measures the time-varying density of tasks and switches between two stages, offline and online matching stages, according to the different task densities. Experimental results show that our scheme has a lower task execution time compared with other state-of-the-art schemes.