DLAG-TA: Deep Learning-Based Adaptive Grid Builder for System-Level Thermal Analysis

2021 ◽  
Author(s):  
Wen-Sheng Lo ◽  
Hong-Wen Chiou ◽  
Shih-Chieh Hsu ◽  
Yu-Min Lee
Keyword(s):  
Thermal Analysis ◽  
Deep Learning ◽  
Adaptive Grid ◽  
System Level

scholarly journals RISC-V Virtual Platform-Based Convolutional Neural Network Accelerator Implemented in SystemC

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1514
Author(s):  
Seung-Ho Lim ◽  
WoonSik William Suh ◽  
Jin-Young Kim ◽  
Sang-Young Cho
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Network Model ◽  
Neural Network Model ◽  
Deep Neural Network ◽  
System Level ◽  
Neural Network Models ◽  
Data Set ◽  
Embedded Device ◽  
Virtual Platform

The optimization for hardware processor and system for performing deep learning operations such as Convolutional Neural Networks (CNN) in resource limited embedded devices are recent active research area. In order to perform an optimized deep neural network model using the limited computational unit and memory of an embedded device, it is necessary to quickly apply various configurations of hardware modules to various deep neural network models and find the optimal combination. The Electronic System Level (ESL) Simulator based on SystemC is very useful for rapid hardware modeling and verification. In this paper, we designed and implemented a Deep Learning Accelerator (DLA) that performs Deep Neural Network (DNN) operation based on the RISC-V Virtual Platform implemented in SystemC in order to enable rapid and diverse analysis of deep learning operations in an embedded device based on the RISC-V processor, which is a recently emerging embedded processor. The developed RISC-V based DLA prototype can analyze the hardware requirements according to the CNN data set through the configuration of the CNN DLA architecture, and it is possible to run RISC-V compiled software on the platform, can perform a real neural network model like Darknet. We performed the Darknet CNN model on the developed DLA prototype, and confirmed that computational overhead and inference errors can be analyzed with the DLA prototype developed by analyzing the DLA architecture for various data sets.

scholarly journals Systems biology informed deep learning for inferring parameters and hidden dynamics

2020 ◽  
Vol 16 (11) ◽  
pp. e1007575 ◽  
Author(s):  
Alireza Yazdani ◽  
Lu Lu ◽  
Maziar Raissi ◽  
George Em Karniadakis
Keyword(s):  
Deep Learning ◽  
Systems Biology ◽  
Differential Equations ◽  
Ordinary Differential Equations ◽  
Learning Algorithm ◽  
Optimization Procedure ◽  
System Level ◽  
Benchmark Problems ◽  
Model Parameters ◽  
Unknown Parameters

Mathematical models of biological reactions at the system-level lead to a set of ordinary differential equations with many unknown parameters that need to be inferred using relatively few experimental measurements. Having a reliable and robust algorithm for parameter inference and prediction of the hidden dynamics has been one of the core subjects in systems biology, and is the focus of this study. We have developed a new systems-biology-informed deep learning algorithm that incorporates the system of ordinary differential equations into the neural networks. Enforcing these equations effectively adds constraints to the optimization procedure that manifests itself as an imposed structure on the observational data. Using few scattered and noisy measurements, we are able to infer the dynamics of unobserved species, external forcing, and the unknown model parameters. We have successfully tested the algorithm for three different benchmark problems.

scholarly journals Massive MIMO Adaptive Modulation and Coding Using Online Deep Learning

2021 ◽  
Author(s):  
Evgeny Bobrov ◽  
Dmitry Kropotov ◽  
Hao Lu ◽  
Danila Zaev
Keyword(s):  
Deep Learning ◽  
Massive Mimo ◽  
Learning Algorithm ◽  
Adaptive Modulation ◽  
System Level ◽  
Adaptive Modulation And Coding ◽  
Q Learning ◽  
Deep Learning Algorithm ◽  
System Level Simulation ◽  
Fully Connected

The paper describes an online deep learning algorithm for the adaptive modulation and coding in 5G Massive MIMO. The algorithm is based on a fully connected neural network, which is initially trained on the output of the traditional algorithm and then is incrementally retrained by the service feedback of its output. We show the advantage of our solution over the state-of-the-art Q-Learning approach. We provide system-level simulation results to support this conclusion in various scenarios with different channel characteristics and different user speeds. Compared with traditional OLLA our algorithm shows 10% to 20% improvement of user throughput in full buffer case. <br>

Integrated Thermal Analysis of Natural Convection Air Cooled Electronic Enclosure

1999 ◽  
Vol 121 (2) ◽  
pp. 108-115 ◽  
Author(s):  
L. Tang ◽  
Y. K. Joshi
Keyword(s):  
Heat Transfer ◽  
Thermal Analysis ◽  
Boundary Condition ◽  
Natural Convection ◽  
Thermal Analyses ◽  
Heat Fluxes ◽  
Global Model ◽  
System Level ◽  
Integrated Analysis ◽  
Component Level

In the present paper, a methodology is described for the integrated thermal analysis of a laminar natural convection air cooled nonventilated electronic system. This approach is illustrated by modeling an enclosure with electronic components of different sizes mounted on a printed wiring board. First, a global model for the entire enclosure was developed using a finite volume computational fluid dynamics/heat transfer (CFD/CHT) approach on a coarse grid. Thermal information from the global model, in the form of board and component surface temperatures, local heat transfer coefficients and reference temperatures, and heat fluxes, was extracted. These quantities were interpolated on a finer grid using bilinear interpolation and further employed in board and component level thermal analyses as various boundary condition combinations. Thus, thermal analyses at all levels were connected. The component investigated is a leadless ceramic chip carrier (LCCC). The integrated analysis approach was validated by comparing the results for a LCCC package with those obtained from detailed system level thermal analysis for the same package. Two preferred boundary condition combinations are suggested for component level thermal analysis.

A System Level Thermal Analysis of Large Telecommunication Racks

2003 ◽  
Author(s):  
L. T. Yeh
Keyword(s):  
Thermal Analysis ◽  
Flow Rate ◽  
Printed Circuit Boards ◽  
System Level ◽  
Circuit Boards ◽  
Air Flow Rate ◽  
Printed Circuit ◽  
Computational Fluid Dynamics Cfd ◽  
Cfd Method ◽  
Level Analysis

A system level thermal analysis is performed by employing the computational fluid dynamics (CFD) method on a large telecommunication rack. Each rack consists of two identical shelves located on the top-to-bottom orientation. Each shelf includes one fan tray with 6 fans, 3 card cages with a total of 50 printed circuit boards (PCBs). Air enters from the front of the shelf, and then makes a 90-degree turn upwards through PCBs, and finally turns another 90-degree to exit the system from the back of the shelf. The system level analysis is performed independently on each shelf. The main purpose of the analysis is to determine the air flow rate to individual printed circuit boards as well as the air temperature distribution in the system. The computed flow rate for individual PCBs is then used for a detailed board analysis to predict the component temperatures of individual boards.

scholarly journals Multi-Scale Thermal Analysis for Design of SiC-Based Medium Voltage Motor Drive

2019 ◽  
Author(s):  
J. Emily Cousineau ◽  
Kevin Bennion ◽  
Karun Potty ◽  
He Li ◽  
Risha Na ◽  
...  
Keyword(s):  
Thermal Analysis ◽  
System Level ◽  
Motor Drive ◽  
Cfd Simulations ◽  
Medium Voltage ◽  
Pin Fin ◽  
Multi Scale ◽  
Fea Model ◽  
Fast Running ◽  
Time Required

Abstract This paper describes a multi-scale thermal analysis approach for the design of an air-cooled 1.7-kV SiC MOSFET-based medium-voltage variable-speed motor drive. The scope of the models and required efficient and flexible thermal models to be developed. Two modeling techniques are described that significantly reduced model run time and enabled more complex models to be run faster while retaining needed accuracy. The first technique uses the effectiveness-NTU method to extract convection boundary conditions from a CFD model that can be applied to a fast-running FEA model. The second is a porous media technique that enables system-level CFD simulations that incorporate effects from heat exchangers (e.g., pin fin heat sinks) that run in a fraction of the time required for fully resolved CFD simulations. The multi-scale approach to the thermal analysis enabled fast and accurate simulation for the converter design ranging from the die level up to the full system with 36 submodules. The modeling results were validated against experimental data from system tests performed by OSU.

Sign in / Sign up

Export Citation Format

Share Document