Journal ArticleDOI
Building modeling as a crucial part for building predictive control
Reads0
Chats0
TLDR
In this paper, the authors provide an overview of identification methods for buildings and analyze their applicability for subsequent predictive control, and propose a new methodology to obtain a model suitable for the use in a predictive control framework combining the building energy performance simulation tools and statistical identification.About:
This article is published in Energy and Buildings.The article was published on 2013-01-01. It has received 306 citations till now. The article focuses on the topics: Building science & Building automation.read more
Citations
More filters
Journal ArticleDOI
Generating Models for Model Predictive Control in Buildings
TL;DR: This paper focuses on the development of reliable models that can be used to support the deployment of (Distributive (Di) MPC application.
Journal ArticleDOI
Dynamic Neural Network Based Sensing and Controlling a Reactive Distillation Column Having Inverse Response
Gaurav Kataria,Kailash Singh +1 more
Abstract: The inverse response is one of the obstacles in control studies which leads to instability and causes difficulty in a control system. In this paper, a dynamic neural network based estimator and controller are studied for a reversible butyl acetate esterification reaction in a reactive distillation column showing inverse response. The product composition in the bottoms of the column has been estimated using a recurrent neural network (RNN) based soft sensor and controlled using a model predictive controller (MPC) containing a dynamic neural network based model. To study the closed loop response of the model, disturbances in the form of pseudo random binary sequence have been used for the regulatory response and step disturbances are taken for the servo response. The closed loop results of the MPC are then compared with those of the PI controlled closed loop using the performance index of integral errors. It is observed that the MPC performs better than the PI controller for the process with high nonlinearity and inverse characteristics.
Journal ArticleDOI
Comparative study of supervised algorithms for topology detection of sensor networks in building energy systems
TL;DR: In this paper , the authors used 200 weeks of data collected from eight temperature sensors of a heat pump and a heat exchanger in 5-min samples and used this data to auto-generate grey-box models to extend the data set with 500 weeks of simulated data.
Journal ArticleDOI
Deep Reinforcement Learning for Heat Pump Control
TL;DR: In this paper , the authors propose a solution to solve the problem of the problem: this paper ] of "uniformity" and "uncertainty" of the solution.
References
More filters
Book
The EM algorithm and extensions
TL;DR: The EM Algorithm and Extensions describes the formulation of the EM algorithm, details its methodology, discusses its implementation, and illustrates applications in many statistical contexts, opening the door to the tremendous potential of this remarkably versatile statistical tool.
Journal ArticleDOI
A review on buildings energy consumption information
TL;DR: In this article, the authors analyzed available information concerning energy consumption in buildings, and particularly related to HVAC systems, and compared different types of building types and end uses in different countries.
Journal ArticleDOI
Finding the Observed Information Matrix When Using the EM Algorithm
TL;DR: A procedure is derived for extracting the observed information matrix when the EM algorithm is used to find maximum likelihood estimates in incomplete data problems and a method useful in speeding up the convergence of the EM algorithms is developed.
Journal ArticleDOI
N4SID: subspace algorithms for the identification of combined deterministic-stochastic systems
TL;DR: Two new N4SID algorithms to identify mixed deterministic-stochastic systems are derived and these new algorithms are compared with existing subspace algorithms in theory and in practice.