Aiming at the problem of the operation condition evaluation of distribution transformers, a practical evaluation method based on the fusion analysis of load rate, three-phase current unbalance rate and voltage differe...
详细信息
Time series anomaly detection often faces significant challenges due to the high dimensionality, interdependence, and label sparsity of the data. Traditional methods struggle to model the intricate relationships betwe...
详细信息
This paper presents a comprehensive implementation of a cybersecurity solution for smart grid network containers. The methodology utilises (i) Qualys API-based vulnerability scanning and reporting system for vulnerabi...
详细信息
ISBN:
(纸本)9798350360882;9798350360899
This paper presents a comprehensive implementation of a cybersecurity solution for smart grid network containers. The methodology utilises (i) Qualys API-based vulnerability scanning and reporting system for vulnerability identification, (ii) Docker deployment for security and isolation, (iii) advanced load balancing techniques for resource optimisation, and (iv) machine learning-powered anomaly detection for threat identification and vulnerability prioritisation. The implementation was used to create a dataset that continues the details of several simulated attacks, enabling effective training and evaluation of a robust machine-learning model. The paper provides a thorough description of the implemented system architecture, the Qualys API-based vulnerability scanning and reporting system, the data set creation process, simulated attacks in Docker implementation, the load balancing process, and the machine learning model used for vulnerability prioritisation. Theexperiments showed that the machine learning model performed exceptionally well across all conducted attacks i.e., Denial of Service, Remote-to-Local, User-to-Root, and Probes, achieving high scores in accuracy, precision, recall, and F1 scores.
This paper presents table structure recognition models based on PPLCNet, MobileNetV3, and ResNet, evaluated on the PubTabNet dataset. By incorporating residual structures and the CBAM attention mechanism into PPLCNet,...
详细信息
In order to improve the prediction accuracy of power line loss degree, this paper analyzes the structure of the artificial neural network model and proposes the quality checking method of line loss data, which lays th...
详细信息
Theenergy consumption problem in data centers is becoming increasingly severe, and energy consumption models can reveal the relationship between data center energy consumption and its corresponding factors, which is ...
详细信息
ISBN:
(纸本)9781665455336
Theenergy consumption problem in data centers is becoming increasingly severe, and energy consumption models can reveal the relationship between data center energy consumption and its corresponding factors, which is crucial for reducing energy consumption. Containerization is the current mainstream trend in data centers. Therefore, this paper proposes energy consumption models for physical hosts, containers, and containerized applications. First, we constructe a physical host energy consumption model based on polynomial regression with lasso. Then, by analyzing the resource utilization, we propose a simple and accurate method for modeling the container energy consumption. Finally, based on the container energy consumption model, we propose a method for constructing a parameter-based energy consumption models for containerized applications. Theexperimental results show that our modeling methods are valid. The advantages of our modeling method are that it can analyze data center energy consumption from different levels, such as physical hosts, containers, and applications, and it has the advantages of simplicity, high accuracy, ease of implementation.
Photovoltaic (PV) energy is the most vital renewableenergy sources, and it has appeared as a feasible solution to the world's energy issue. This paper proposes a sophisticated PV integrated architecture including...
详细信息
Aiming at the new working conditions of various new types of energy and high proportion of new energy sources connected to thegrid, as well as the operation of guaranteed energy co-generation with thermal power as th...
详细信息
With the development of society and the progress of science and technology, electricity has become an indispensable resource in our daily life. However, in the process of power use, abnormal power consumption behavior...
详细信息
grid-based simulations of hot fusion plasmas are often severely limited by computational and memory resources;thegrids live in four- to six-dimensional space and thus suffer the curse of dimensionality. However, high...
详细信息
暂无评论