Search

Your search keyword '"Dong, Weizhen"' showing total 2 results
Start Over Author "Dong, Weizhen" Topic artificial neural network
2 results on '"Dong, Weizhen"'

1. Control of a Buck DC/DC Converter Using Approximate Dynamic Programming and Artificial Neural Networks.

Author

Dong, Weizhen, Li, Shuhui, Fu, Xingang, Li, Zhongwen, Fairbank, Michael, and Gao, Yixiang

Subjects
*ARTIFICIAL neural networks, *DYNAMIC programming, *RECURRENT neural networks, *PREDICTIVE control systems, *ONLINE education, *COST functions, *TIME perspective
Abstract

This paper proposes a novel artificial neural network (ANN) based control method for a dc/dc buck converter. The ANN is trained to implement optimal control based on approximate dynamic programming (ADP). Special characteristics of the proposed ANN control include: 1) The inputs to the ANN contain error signals and integrals of the error signals, enabling the ANN to have PI control ability; 2) The ANN receives voltage feedback signals from the dc/dc converter, making the combined system equivalent to a recurrent neural network; 3) The ANN is trained to minimize a cost function over a long time horizon, making the ANN have a stronger predictive control ability than a conventional predictive controller; 4) The ANN is trained offline, preventing the instability of the network caused by weight adjustments of an on-line training algorithm. The ANN performance is evaluated through simulation and hardware experiments and compared with conventional control methods, which shows that the ANN controller has a strong ability to track rapidly changing reference commands, maintain stable output voltage for a variable load, and manage maximum duty-ratio and current constraints properly. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

2. Energy management and demand response with intelligent learning for multi-thermal-zone buildings.

Author

Gao, Yixiang, Li, Shuhui, Fu, Xingang, Dong, Weizhen, Lu, Bing, and Li, Zhongwen

Subjects
*ENERGY demand management, *SMART power grids, *VENTILATION, *ENERGY consumption of buildings, *BUILDING operation management, *AIR conditioning
Abstract

This paper presents an optimal building energy management strategy for the demand response of multi-thermal-zone buildings in the smart electricity grid environment. The proposed method includes a machine learning model, based on a neural network, for a building heating ventilation and air conditioning system. The learned model is then applied to an optimization problem to determine the optimal management scheduling of building loads. The goal of the optimization problem is to minimize building electricity costs and reduce the overall building energy consumption during peak load hours while satisfying human comfort demand. To overcome the coupling issue between the building internal-heat-gain loads and the building heating ventilation and air conditioning system, an iterative algorithm is proposed to solve the optimization problem. In each iteration, a mixed-integer linear programming technique is used to solve a sub-optimization problem for the building internal-heat-gain loads and its results are then applied to another sub-optimization problem, solved by using a particle swarm technique, for the building heating ventilation and air conditioning system. The iterative optimization algorithm stops when convergence between the optimization for the building heating ventilation and air conditioning system and the optimization for the building internal-heat-gain loads is properly reached. EnergyPlus is used to build and simulate complex buildings with multiple-thermal zones according to real-life conditions. The simulation model is also used to test and evaluate the effectiveness of the proposed machine-learning model and the iterative optimization algorithm and the improvement of building energy management in terms of energy consumption efficiency, cost saving, and satisfaction of human comfort. • A Machine-learning based strategy for energy management of multi-thermal zone buildings. • A combination of machine learning and optimization techniques for buildings. • A consideration of human comfort demands into learning-based energy optimization. • An integration of building energy management with demand response for smart grid. [ABSTRACT FROM AUTHOR]

Published
2020
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results