scholarly journals Performance prediction of deep learning applications training in GPU as a service systems

2022 ◽  
Author(s):  
Marco Lattuada ◽  
Eugenio Gianniti ◽  
Danilo Ardagna ◽  
Li Zhang
Keyword(s):  
Deep Learning ◽  
Performance Prediction ◽  
Service Systems

scholarly journals Dynamic access control and security performance prediction for IoT networking using a novel deep learning technique

2021 ◽  
Author(s):  
Sriramya P. ◽  
A.K. Reshmy ◽  
R. Subhashini ◽  
Korakod Tongkachok ◽  
Ajay Prakash Pasupulla ◽  
...  
Keyword(s):  
Deep Learning ◽  
Access Control ◽  
Real Time ◽  
Performance Prediction ◽  
Dynamic Models ◽  
Security Risk ◽  
Time Data ◽  
Iot Security ◽  
Area Of Interest ◽  
Dynamic Access Control

Abstract Internet of things (IoT) has increased an importance for an area of interest in many devices. Then, the applications such as sensitive home sensors, medical devices, wireless sensors,and other devices are related to IoT network. The transmission of big data is subject to a possible attack that could cause network interruptions and problems with security. The security performance prediction is important for IoT networks to address complicated security issues in real-time which one of the attacks can freely threaten its global performance. Initially,investigate the safety performance of security intelligent prediction techniques is linking with deep learning algorithms into the IoT security risks. This contribution provides a CNN model that improves IoT security risk assessment (SRA) performance. Then, the access control techniques are changed with IoT-like dynamic systems with the number of items spread all over the place. Therefore, dynamic access control models are necessary. Thesedesign not individual use strategies of access but incorporate environmental and real-time data to predict the decision on access. The risk-based access control approach is one of those dynamic models. To decide the access decision, this model assesses the security risk value associated with the access request. This assessment of the model proposed results from the performance and accuracy of IoT networks.

Aerodynamic Prediction on the Off-Design Performance of a S-CO2 Turbine Based on Deep Learning

2021 ◽  
Author(s):  
Yuqi Wang ◽  
Tianyuan Liu ◽  
Di Zhang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Performance Prediction ◽  
Aerodynamic Performance ◽  
Operating Conditions ◽  
Training Data ◽  
Brayton Cycle ◽  
Data Set ◽  
Set Size ◽  
The Mean

Abstract The research on the supercritical carbon dioxide (S-CO2) Brayton cycle has gradually become a hot spot in recent years. The off-design performance of turbine is an important reference for analyzing the variable operating conditions of the cycle. With the development of deep learning technology, the research of surrogate models based on neural network has received extensive attention. In order to improve the inefficiency in traditional off-design analyses, this research establishes a data-driven deep learning off-design aerodynamic prediction model for a S-CO2 centrifugal turbine, which is based on a deep convolutional neural network. The network can rapidly and adaptively provide dynamic aerodynamic performance prediction results for varying blade profiles and operating conditions. Meanwhile, it can illustrate the mechanism based on the field reconstruction results for the generated aerodynamic performance. The training results show that the off-design aerodynamic prediction convolutional neural network (OAP-CNN) has reduced the mean and maximum error of efficiency prediction compared with the traditional Gaussian Process Regression (GPR) and Artificial Neural Network (ANN). Aiming at the off-design conditions, the pressure and temperature distributions with acceptable error can be obtained without a CFD calculation. Besides, the influence of off-design parameters on the efficiency and power can be conveniently acquired, thus providing the reference for an optimized operation strategy. Analyzing the sensitivity of AOP-CNN to training data set size, the prediction accuracy is acceptable when the percentage of training samples exceeds 50%. The minimum error appears when the training data set size is 0.8. The mean and maximum errors are respectively 1.46% and 6.42%. In summary, this research provides a precise and fast aerodynamic performance prediction model in the analyses of off-design conditions for S-CO2 turbomachinery and Brayton cycle.

Deep Learning for Multi-Step Performance Prediction in Operational Optical Networks

2020 ◽  
Author(s):  
Ameni Mezni ◽  
Douglas W. Charlton ◽  
Christine Tremblay ◽  
Christian Desrosiers
Keyword(s):  
Deep Learning ◽  
Optical Networks ◽  
Performance Prediction

scholarly journals Off-Design Performance Prediction of a S-CO2 Turbine Based on Field Reconstruction Using Deep-Learning Approach

2020 ◽  
Vol 10 (14) ◽  
pp. 4999
Author(s):  
Dongbo Shi ◽  
Lei Sun ◽  
Yonghui Xie
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Performance Prediction ◽  
Learning Approach ◽  
Processing Unit ◽  
Design Performance ◽  
Deep Model ◽  
Physical Fields ◽  
Turbine Design ◽  
Prediction Approach

The reliable design of the supercritical carbon dioxide (S-CO2) turbine is the core of the advanced S-CO2 power generation technology. However, the traditional computational fluid dynamics (CFD) method is usually applied in the S-CO2 turbine design-optimization, which is a high computational cost, high memory requirement, and long time-consuming solver. In this research, a flexible end-to-end deep learning approach is presented for the off-design performance prediction of the S-CO2 turbine based on physical fields reconstruction. Our approach consists of three steps: firstly, an optimal design of a 60,000 rpm S-CO2 turbine is established. Secondly, five design variables for off-design analysis are selected to reconstruct the temperature and pressure fields on the blade surface through a deconvolutional neural network. Finally, the power and efficiency of the turbine is predicted by a convolutional neural network according to reconstruction fields. The results show that the prediction approach not only outperforms five classical machine learning models but also focused on the physical mechanism of turbine design. In addition, once the deep model is well-trained, the calculation with graphics processing unit (GPU)-accelerated can quickly predict the physical fields and performance. This prediction approach requires less human intervention and has the advantages of being universal, flexible, and easy to implement.

Sign in / Sign up

Export Citation Format

Share Document