Journals >Journal of Electronic Science and Technology
Contents
2025
Volume: 23 Issue 1
6 Article(s)
Export citation format
Adaptive multi-agent reinforcement learning for dynamic pricing and distributed energy management in virtual power plant networks
Jian-Dong Yao, Wen-Bin Hao, Zhi-Gao Meng, Bo Xie, Jian-Hua Chen, and Jia-Qi Wei
This paper presents a novel approach to dynamic pricing and distributed energy management in virtual power plant (VPP) networks using multi-agent reinforcement learning (MARL). As the energy landscape evolves towards greater decentralization and renewable integration, traditional optimization methods struggle to addresThis paper presents a novel approach to dynamic pricing and distributed energy management in virtual power plant (VPP) networks using multi-agent reinforcement learning (MARL). As the energy landscape evolves towards greater decentralization and renewable integration, traditional optimization methods struggle to address the inherent complexities and uncertainties. Our proposed MARL framework enables adaptive, decentralized decision-making for both the distribution system operator and individual VPPs, optimizing economic efficiency while maintaining grid stability. We formulate the problem as a Markov decision process and develop a custom MARL algorithm that leverages actor-critic architectures and experience replay. Extensive simulations across diverse scenarios demonstrate that our approach consistently outperforms baseline methods, including Stackelberg game models and model predictive control, achieving an 18.73% reduction in costs and a 22.46% increase in VPP profits. The MARL framework shows particular strength in scenarios with high renewable energy penetration, where it improves system performance by 11.95% compared with traditional methods. Furthermore, our approach demonstrates superior adaptability to unexpected events and mis-predictions, highlighting its potential for real-world implementation..
Journal of Electronic Science and Technology
- Publication Date: Mar. 25, 2025
- Vol. 23, Issue 1, 100290 (2025)
Stable computations of the spherically layered media theory with high lossy media by using scaled Bessel functions
Jia-Hui Wang, and Bo O. Zhu
The spherically layered media theory has wide applications for electromagnetic wave scattering analysis. Due to the involved Bessel functions, the conventional formulations of spherically layered media theory suffer from numerical overflow or underflow when the Bessel function’s order is large, the argument is small orThe spherically layered media theory has wide applications for electromagnetic wave scattering analysis. Due to the involved Bessel functions, the conventional formulations of spherically layered media theory suffer from numerical overflow or underflow when the Bessel function’s order is large, the argument is small or the argument has a large imaginary part. The first two issues have been solved recently by employing small-argument asymptotic formulas of Bessel functions, while the third issue remains unsolved. In this paper, the Bessel functions in the conventional formulation of the theory are replaced by scaled Bessel functions which have good numerical properties for high loss media, and stable formulas are derived. Numerical tests show that this approach can work properly with very high lossy media. Also, this approach can be seamlessly combined with the stable computation method for cases of small argument and large order of Bessel functions..
Journal of Electronic Science and Technology
- Publication Date: Mar. 25, 2025
- Vol. 23, Issue 1, 100291 (2025)
Compensation for topographic effect on P-band PolSAR data with a polarimetric decomposition technique
Yin Zhang, and Ding-Feng Duan
A P-band polarimetric synthetic aperture radar (PolSAR) sensor has deep penetration ability into and through the vegetation canopies in forested environments. Thus, the sensor is of great potential to accurately assess forest parameters such as coverage, stand density, and tree height. Unfortunately, the radar backscatA P-band polarimetric synthetic aperture radar (PolSAR) sensor has deep penetration ability into and through the vegetation canopies in forested environments. Thus, the sensor is of great potential to accurately assess forest parameters such as coverage, stand density, and tree height. Unfortunately, the radar backscatter from complex terrain can adversely impact the backscatter from trees or forests, and forest parameters assessed can be erroneous. Thus, reducing the topographic impact is an urgent must. In this study, a topographic compensation algorithm has been studied. To assess the algorithm’s validity and effectiveness, we applied it to P-band PolSAR datasets in four forested areas in the US. Trees in the forest stands have diverse species, and the topographic conditions of the terrain differ. Significant topographic impact on the P-band PolSAR data exists before the topographic compensation algorithm. After the algorithm, the impact decreases noticeably qualitatively and quantitatively. The algorithm is valid and effective in reducing the topographic influence on the PolSAR data and, consequently, provides a better chance of retrieving accurate forest parameters..
Journal of Electronic Science and Technology
- Publication Date: Mar. 25, 2025
- Vol. 23, Issue 1, 100292 (2025)
Grape Guard: A YOLO-based mobile application for detecting grape leaf diseases
Sajib Bin Mamun, Israt Jahan Payel, Md. Taimur Ahad, Anthony S. Atkins, Bo Song, and Yan Li
Grape crops are a great source of income for farmers. The yield and quality of grapes can be improved by preventing and treating diseases. The farmer’s yield will be dramatically impacted if diseases are found on grape leaves. Automatic detection can reduce the chances of leaf diseases affecting other healthy plants. SGrape crops are a great source of income for farmers. The yield and quality of grapes can be improved by preventing and treating diseases. The farmer’s yield will be dramatically impacted if diseases are found on grape leaves. Automatic detection can reduce the chances of leaf diseases affecting other healthy plants. Several studies have been conducted to detect grape leaf diseases, but most fail to engage with end users and integrate the model with real-time mobile applications. This study developed a mobile-based grape leaf disease detection (GLDD) application to identify infected leaves, Grape Guard, based on a TensorFlow Lite (TFLite) model generated from the You Only Look Once (YOLO) v8 model. A public grape leaf disease dataset containing four classes was used to train the model. The results of this study were relied on the YOLO architecture, specifically YOLOv5 and YOLOv8. After extensive experiments with different image sizes, YOLOv8 performed better than YOLOv5. YOLOv8 achieved 99.9% precision, 100% recall, 99.5% mean average precision (mAP), and 88% mAP50–95 for all classes to detect grape leaf diseases. The Grape Guard android mobile application can accurately detect the grape leaf disease by capturing images from grape vines..
Journal of Electronic Science and Technology
- Publication Date: Mar. 25, 2025
- Vol. 23, Issue 1, 100300 (2025)
On large language models safety, security, and privacy: A survey
Ran Zhang, Hong-Wei Li, Xin-Yuan Qian, Wen-Bo Jiang, and Han-Xiao Chen
The integration of artificial intelligence (AI) technology, particularly large language models (LLMs), has become essential across various sectors due to their advanced language comprehension and generation capabilities. Despite their transformative impact in fields such as machine translation and intelligent dialogue The integration of artificial intelligence (AI) technology, particularly large language models (LLMs), has become essential across various sectors due to their advanced language comprehension and generation capabilities. Despite their transformative impact in fields such as machine translation and intelligent dialogue systems, LLMs face significant challenges. These challenges include safety, security, and privacy concerns that undermine their trustworthiness and effectiveness, such as hallucinations, backdoor attacks, and privacy leakage. Previous works often conflated safety issues with security concerns. In contrast, our study provides clearer and more reasonable definitions for safety, security, and privacy within the context of LLMs. Building on these definitions, we provide a comprehensive overview of the vulnerabilities and defense mechanisms related to safety, security, and privacy in LLMs. Additionally, we explore the unique research challenges posed by LLMs and suggest potential avenues for future research, aiming to enhance the robustness and reliability of LLMs in the face of emerging threats..
Journal of Electronic Science and Technology
- Publication Date: Mar. 25, 2025
- Vol. 23, Issue 1, 100301 (2025)
Model and service for privacy in decentralized online social networks
George Pacheco Pinto, José Ronaldo Leles Jr., Cíntia da Costa Souza, Paulo R. de Souza, Frederico Araújo Durão, and Cássio Prazeres
Intensely using online social networks (OSNs) makes users concerned about privacy of data. Given the centralized nature of these platforms, and since each platform has a particular storage mechanism, authentication, and access control, their users do not have the control and the right over their data. Therefore, users Intensely using online social networks (OSNs) makes users concerned about privacy of data. Given the centralized nature of these platforms, and since each platform has a particular storage mechanism, authentication, and access control, their users do not have the control and the right over their data. Therefore, users cannot easily switch between similar platforms or transfer data from one platform to another. These issues imply, among other things, a threat to privacy since such users depend on the interests of the service provider responsible for administering OSNs. As a strategy for the decentralization of the OSNs and, consequently, as a solution to the privacy problems in these environments, the so-called decentralized online social networks (DOSNs) have emerged. Unlike OSNs, DOSNs are decentralized content management platforms because they do not use centralized service providers. Although DOSNs address some of the privacy issues encountered in OSNs, DOSNs also pose significant challenges to consider, for example, access control to user profile information with high granularity. This work proposes developing an ontological model and a service to support privacy in DOSNs. The model describes the main concepts of privacy access control in DOSNs and their relationships. In addition, the service will consume the model to apply access control according to the policies represented in the model. Our model was evaluated in two phases to verify its compliance with the proposed domain. Finally, we evaluated our service with a performance evaluation, and the results were satisfactory concerning the response time of access control requests..
Journal of Electronic Science and Technology
- Publication Date: Mar. 25, 2025
- Vol. 23, Issue 1, 100302 (2025)
