Accurate detection of surface defects on railway tracks is critical for safe railway operation. Most existing models rely solely on Red–Green–Blue (RGB) images, limiting their ability to capture structural information. Incorporating depth features provides richer spatial cues, significantly improving detection accuracy. However, current Red–Green–Blue and Depth (RGB-D) dual-stream models suffer from high computational complexity and hardware dependencies, making them impractical for real-world deployment. To address these limitations, we propose DAHNet, an asymmetric knowledge distillation model with a teacher–student architecture. DAHNet-T serves as the teacher network, taking RGB-D inputs and integrating a cross-modal attention feature enhancement (CAFE) module to capture contextual information, along with a depth feature interaction block (DFIB) for efficient cross-modal fusion. DAHNet-S is the student network, a lightweight single-stream RGB model employing depthwise separable convolutions to reduce computation. We introduce a multi-level distillation strategy with dynamic temperature scaling to balance coarse-grained and fine-grained knowledge transfer, while incorporating contrastive learning and structural loss to improve pixel-level accuracy. Extensive experiments on the NEU RSDDS-AUG dataset demonstrate that our distilled model DAHNet-KD outperforms state-of-the-art methods. Compared to DAHNet-T, the number of parameters is reduced from 87.72 MParams to 13.97 MParams, and the computational cost decreases from 19.79 GFLOPs to 5.41 GFLOPs. The proposed model achieves superior performance across various evaluation metrics and also generalizes well on other public datasets. Therefore, the model provides a lightweight and high-accuracy solution for deployment on mobile devices in real-world industrial scenarios.

The rapid development of the Internet of Vehicles (IoV) and sixth-generation (6G) technology has made traditional cloud computing architectures inadequate for vehicular networks. With ultra-low latency, high bandwidth, and massive connectivity, 6G networks provide essential support for task offloading in mobile edge computing. Task offloading transfers computational tasks from vehicles to edge base stations or cloud servers. However, traditional methods struggle to adapt to diverse user tasks and dynamic network environments. These limitations increase offloading delays. Digital twin (DT) offers real-time simulation to reflect system dynamics and address these challenges. In this paper, we propose a task offloading framework that combines DTs with deep reinforcement learning. We propose a multi-layer dynamic framework with an error-reward feedback mechanism to handle complexity, dynamic changes, and errors. This approach enables the conclusion of task offloading strategies that minimize latency. The framework includes a threshold-based warning mechanism to effectively manage edge base station loads. By monitoring load in real time, the system evaluates base station status and adjusts task allocation to maintain stability. We propose a multi-dimensional state encoder architecture, comprising environment encoders, base station state encoders, and task state encoders to effectively extract critical features. The proposed architecture enables the conclusion of task offloading strategies that minimize latency. Experimental results demonstrate that the proposed algorithm can accurately and quickly conclude the task offloading strategy to minimize energy consumption and latency.

With the development of the Internet of energy, more and more participants share data by different types of edge devices. However, such multi-source heterogenous data typically contain low-quality data, e.g., missing values, which may result in potential risks. Besides, resource-constrained devices incur large latency in edge computing networks. To alleviate such latency, distributed task offloading schemes are designed to share the computation burden between edge nodes and nearby servers. However, there are three main drawbacks of such schemes. First, low-quality data are not carefully evaluated by constraints under scenarios, which may result in slow convergence in distributed computation. Second, multi-source data including sensitive information are computed and shared among edge nodes without privacy protection. Third, distributed tasks on low-quality data may result in low-quality results even with an optimal offloading scheme. To address the problems above, a task offloading framework for edge computing based on consortium blockchain and distributed reinforcement learning is proposed in this paper, which can provide high-quality task offloading policies with data privacy protected. This framework consists of three key components: data quality evaluation (DQ) with multiple data quality dimensions, data repairing (DR) with a repairing algorithm based on a novel repairing consensus mechanism and distributed reinforcement learning for task arrangement (DELTA) with a distributed reinforcement learning algorithm based on a novel low-quality data distributing strategy. Numeric results are presented to illustrate the effectiveness and efficiency of the proposed task offloading framework for edge computing on low-quality data in the IoE.

Currently, the integration of distributed energy generators through virtual power plants in the Internet of Energy is a mainstream method. The complex structure of virtual power plants and the characteristics of distributed energy make it difficult to solve the economic dispatch problems of virtual power plants. In addition, the load of a virtual power plant is unstable and uncertain and thus requires a robust economic dispatch strategy. Because the selection of the set of uncertain conditions is conservative, the traditional robust economic dispatch strategies cannot effectively reduce the cost of virtual power plants. In addition, the traditional methods for solving robust strategies cannot directly solve nonlinear and nonconvex problems. In this article, we propose a scenario-based robust economic dispatch strategy for virtual power plants, aiming to reduce the operational costs of virtual power plants. First, to reduce the conservatism of the strategy, scenario-based data augmentation is adopted for data generation. Through a generative adversarial network, a large amount of scene data are generated to extend the set of uncertain conditions. The scene data cannot only reduce the conservatism but also can be used in the determination of robust strategies. Second, deep reinforcement learning is adopted for historical data training, directly solving nonlinear and nonconvex problems to obtain a robust economic dispatch strategy. As experiments show, with the accurate generation of scene data, the proposed economic dispatch strategy is robust and effectively reduces the cost of virtual power plants.

Nowadays, microgrids (MG) have attracted much attention, as a key technology of the Internet of Energy (IoE). A great deal of research have shown that the hierarchical microgrid is a more novel structure of IoE. Although the hierarchical microgrid model solves the problem of weak power scheduling capability across microgrids, it suffers from severe communications uncertainty, which can lead to communication delay and fluctuation. To obtain the accurate result of the renewable energy accommodation assessment capacity, a hierarchical microgrid model considering communication uncertainty is proposed in this article. The solution to solve the problem of the assessment renewable energy accommodation capacity for hierarchical MG is a hybrid control based on distribution deep reinforcement learning. The temporal difference (TD) generation adversarial network (TD-GAN) is proposed as a value-based method. Compared with the policy-based method, it can better solve the distributed problem in hybrid control with a generation adversarial network (GAN). Moreover, the challenge that the method cannot handle a continuous action space is solved by using a normalized advantage function (NAF). The method similar with the TD error method is employed to train the GAN network. Simulation results using real power grid data demonstrate the effectiveness and accuracy of the proposed method.

With the high penetration of large-scale distributed renewable energy generation, the power system is facing enormous challenges in terms of the inherent uncertainty of power generation of renewable energy resources. In this regard, virtual power plants (VPPs) can play a crucial role in integrating a large number of distributed generation units (DGs) more effectively to improve the stability of the power systems. Due to the uncertainty and nonlinear characteristics of DGs, reliable economic dispatch in VPPs requires timely and reliable communication between DGs, and between the generation side and the load side. The online economic dispatch optimizes the cost of VPPs. In this article, we propose a deep reinforcement learning (DRL) algorithm for the optimal online economic dispatch strategy in VPPs. By utilizing DRL, our proposed algorithm reduced the computational complexity while also incorporating large and continuous state space due to the stochastic characteristics of distributed power generation. We further design an edge computing framework to handle the stochastic and large-state space characteristics of VPPs. The DRL-based real-time economic dispatch algorithm is executed online. We utilize real meteorological and load data to analyze and validate the performance of our proposed algorithm. The experimental results show that our proposed DRL-based algorithm can successfully learn the characteristics of DGs and industrial user demands. It can learn to choose actions to minimize the cost of VPPs. Compared with the deterministic policy gradient algorithm and DDPG, our proposed method has lower time complexity.