Advancements in artificial intelligence algorithms and models, along with embedded device support, have resulted in the issue of high energy consumption and poor compatibility when deploying artificial intelligence models and networks on embedded devices becoming solvable. In response to these problems, this paper introduces three aspects of methods and applications for deploying artificial intelligence technologies on embedded devices, including artificial intelligence algorithms and models on resource-constrained hardware, acceleration methods for embedded devices, neural network compression, and current application models of embedded AI. This paper compares relevant literature, highlights the strengths and weaknesses, and concludes with future directions for embedded AI and a summary of the article.

Insulators are an important part of transmission lines; failure may threaten the operation of these transmission lines. For insulator defect detection, an optical image detection method based on deep learning and morphological detection is proposed. First of all, the Faster RCNN is used to locate the insulator and extract its target image from the detection image. In the second place, a segmentation method of insulator image is proposed to remove the background of the target image. In order to simplify insulator defect detection, an insulator shape transformation method is proposed to unify all types of insulator detection. Finally, a mathematical model is established in the binary image to describe the defect of the insulator. Experiments show that our proposed Faster RCNN can accurately detect the insulators in the image. Its AP is as high as 0.9175, and its Recall rate is as high as 0.98, which is higher than the common insulator recognition algorithm. The accuracy of the proposed defect detection method is 0.98, which can accurately locate the defect position of the insulator. In order to prove the efficiency of the proposed method, we compared several common detection methods.

With the rapid growth in the number of EVs, a huge number of EVs are connected to the power grid for charging, which places a great amount of pressure on the stable operation of the power grid. This paper focuses on the development of V2G applications, based on the current research status of V2G technology. Firstly, the standards on V2G applications and some pilot projects involving more representative V2G systems are introduced. Comparing V2G applications with ordered charging and unordered charging, the social and economic benefits of V2G applications are highlighted. Analysis of the social benefits of V2G applications concerns three points: the grid demand response, personalized charging, and the coordination of renewable energy sources. And analysis of the economic benefits of V2G applications is divided into three parties: the grid, the aggregator, and individuals. From the perspective of innovative EVs expanding the application scenarios through V2G technology, V2G applications for commercial EVs, emergency power applications, and vehicle-to-vehicle energy trading are introduced. The current challenges related to V2G applications are presented: users’ willingness to participate in V2G applications, battery loss, charging and discharging tariffs, privacy and security, and power loss. Finally, some research recommendations for the development of V2G applications are given and the current state of research in regard to those recommendations is presented.

Bounding box regression is a crucial step in object detection, directly affecting the localization performance of the detected objects. Especially in small object detection, an excellent bounding box regression loss can significantly alleviate the problem of missing small objects. However, there are two major problems with the broad Intersection over Union (IoU) losses, also known as Broad IoU losses (BIoU losses) in bounding box regression: (i) BIoU losses cannot provide more effective fitting information for predicted boxes as they approach the target box, resulting in slow convergence and inaccurate regression results; (ii) most localization loss functions do not fully utilize the spatial information of the target, namely the target’s foreground area, during the fitting process. Therefore, this paper proposes the Corner-point and Foreground-area IoU loss (CFIoU loss) function by delving into the potential for bounding box regression losses to overcome these issues. First, we use the normalized corner point distance between the two boxes instead of the normalized center-point distance used in the BIoU losses, which effectively suppresses the problem of BIoU losses degrading to IoU loss when the two boxes are close. Second, we add adaptive target information to the loss function to provide richer target information to optimize the bounding box regression process, especially for small object detection. Finally, we conducted simulation experiments on bounding box regression to validate our hypothesis. At the same time, we conducted quantitative comparisons of the current mainstream BIoU losses and our proposed CFIoU loss on the small object public datasets VisDrone2019 and SODA-D using the latest anchor-based YOLOv5 and anchor-free YOLOv8 object detection algorithms. The experimental results demonstrate that YOLOv5s (+3.12% Recall, +2.73% mAP@0.5, and +1.91% mAP@0.5:0.95) and YOLOv8s (+1.72% Recall and +0.60% mAP@0.5), both incorporating the CFIoU loss, achieved the highest performance improvement on the VisDrone2019 test set. Similarly, YOLOv5s (+6% Recall, +13.08% mAP@0.5, and +14.29% mAP@0.5:0.95) and YOLOv8s (+3.36% Recall, +3.66% mAP@0.5, and +4.05% mAP@0.5:0.95), both incorporating the CFIoU loss, also achieved the highest performance improvement on the SODA-D test set. These results indicate the effectiveness and superiority of the CFIoU loss in small object detection. Additionally, we conducted comparative experiments by fusing the CFIoU loss and the BIoU loss with the SSD algorithm, which is not proficient in small object detection. The experimental results demonstrate that the SSD algorithm incorporating the CFIoU loss achieved the highest improvement in the AP (+5.59%) and AP75 (+5.37%) metrics, indicating that the CFIoU loss can also improve the performance of algorithms that are not proficient in small object detection.

Functioning as a smart aggregation entity that combines distributed energy resources, energy storage systems, and flexible loads, virtual power plants (VPPs) serve as a pivotal technology in advancing the decarbonization and flexibility enhancement of modern power systems. Initially, we summarize the developmental context, evolutionary trajectory, and conceptual framework of VPPs. The architecture is functionally partitioned into three tiers: the aggregation layer, communication layer, and dispatch optimization layer (central layer). The dispatch optimization layer of VPPs serves as the “intelligent brain” connecting physical resources with electricity markets, whose core lies in achieving “controllable, adjustable, and optimizable” distributed resources through algorithmic and data-driven approaches, driving the energy system transition towards low-carbon, flexible, and efficient directions. Next, we critically examine core technologies in the dispatch optimization layer, particularly the response capacity assessment and optimal resource scheduling. Its content mainly focuses on the latest research on the aggregated resource response capability evaluation, virtual power plant dispatching optimization models, and dispatching strategies. Conclusively, we analyze prevailing technical bottlenecks and summarize significant advancements, concluding with prospective insights into future research frontiers and developmental priorities for VPPs. In the future energy system transition, VPPs will play an increasingly important role. It is foreseeable that the utilization efficiency of renewable energy will be significantly enhanced, and the energy market will become more diverse and vibrant. We look forward to VPPs integrating more quickly and effectively into daily life, transforming lifestyles and helping people collectively step into a low-carbon, green future.