The smart grids make the electricity power systems automated and intelligent by using advanced technologies such as IoT smart sensors and meters, and communication technologies. This automation and intelligent process...
详细信息
ISBN:
(纸本)9798350369229;9798350369236
The smart grids make the electricity power systems automated and intelligent by using advanced technologies such as IoT smart sensors and meters, and communication technologies. This automation and intelligent processing render the power systems more vulnerable to different types of severe cyberattacks like DDoS, man-in-the-middle and desynchronization attacks. Making smart grids robust against attacks requires to use strong access control and encryption techniques. The existing access control models in smart grids focus on user authentication and data encryption, limiting the model's ability to respond effectively to various types of known and unknown cyberattacks. To bridge this research gap, in this paper, we propose a software-defined (SD) access control model in smart grids. SD-access programmatically deploys an appropriate access control model in the edge routers/devices based on the user and their endpoint authentication and context, leveraging CISCO's digital network architecture and identity services engine. To the best of our knowledge, SD-access control has not been applied in smart grids yet. The security group policy is formulated considering the application and network security contexts. The efficacy of the proposed model is analyzed with the scenarios of electrical smart grids. Access control based on SD-access will make the smart grids more reliable, resilient and robust against known and unknown cyberattacks.
The knowledge base learning site's objective is to arrange the training materials and provide the trainee with a "Role-based learning"path. Students can access resources to meet various learning needs by...
详细信息
In response to the lack of relevant high-quality Q&A (question and answer) datasets in some specific domain Q&A systems, this paper proposes a large language model Q&A Method based on specific domain regul...
详细信息
ISBN:
(纸本)9798400718144
In response to the lack of relevant high-quality Q&A (question and answer) datasets in some specific domain Q&A systems, this paper proposes a large language model Q&A Method based on specific domain regulation documents. The paper adopts natural language processing technology combined with a large language model. Firstly, data processing is performed on regulatory documents to extract text that meets the requirements. Then extracting the information of interest from the text and structuring it, and performing vector transformation to store it in a vector database for building a knowledge base. At the same time, performing vector transformation on user's question, and using cosine similarity to calculate the distance between the problem vector and the vector in the knowledge base. Finally, a random method is proposed to form the problem context, and the Lang Chain tool is used to return the Q&A results, which are then displayed in the front-end. Through system design and engineering application, this paper proposes a large language model Q&A method based on specific domain regulation documents, which can accurately obtain Q&A results.
In order to support query-based learning, this research focuses on the applications of an AI tool named *** in the instruction of computer science and engineering students in Structured Query Language (SQL). As the fo...
详细信息
Event-driven architecture is one of the common software architecture patterns. In the process of software evolution, the deviation and corrosion often occur to architecture, which leads to larger deviation between act...
详细信息
Current crises illustrate the responsibility of the education system to educate its students with the knowledge and skills needed to meet the requirements of an increasingly complex, digital, and volatile world. The e...
详细信息
This paper investigates the potential of Deep Learning in the area of speech production. The purpose is to study whether algorithms are able to classify the spoken content based only on images of the oral region. With...
详细信息
Federated Learning enables collaboration among parties without the need for external data sharing, achieving knowledge sharing without data sharing. However, existing federated learning algorithms still encounter issu...
详细信息
The identification of real and fake news has become difficult task in the recent years due to more similar feature between them. As the issues of fake news are leading the miscommunication to the reads, various automa...
详细信息
The proceedings contain 51 papers. The topics discussed include: identifying similar top-k household electricity consumption patterns;detecting greenwashing in the environmental, social, and governance domains using n...
ISBN:
(纸本)9789897586712
The proceedings contain 51 papers. The topics discussed include: identifying similar top-k household electricity consumption patterns;detecting greenwashing in the environmental, social, and governance domains using natural language processing;speech detection of real-time MRI vocal tract data;a flexible approach for retrieving geometrically similar finite element models using point cloud autoencoders;fine-tuning and aligning question answering models for complex information extraction tasks;closeness centrality detection in homogeneous multilayer networks;subject classification of software repository;recommendation system for product test failures using BERT;and an explainable knowledge graph-based news recommendation system.
暂无评论