Description

A large portion of buildings total energy use is caused by chilled water systems (CHW). As a result, it can drastically affect the energy cost. Usually there is no holistic approach to optimize the whole CHW as most of the efforts that have been made are limited to optimization of different components of CHW. It’s crucial to find optimal methods to design a more efficient CWS and develop holistic optimization tools to reduce the energy consumption by incorporating system models and genetic algorithm technics, using real time data from the chilled water system. The proposed optimization technique can reduce the energy consumption by analyzing the data, generated by the building automation system (BAS) and developing a model that can predict the behavior of the system. It can also assess the performance of the system and tune the model if necessary to increase the efficiency of the system by using optimization algorithms. This paper proposes an integrated optimization method to determine controller’s set points and the sequence of control of different components for different chilled water system configurations. It also develops a data driven system model by using machine learning techniques to predict the energy consumption of the system. An optimization algorithm is also created that can be incorporated with the system model to produce the integrated optimization method and find the optimal solution. The objective function for this algorithm is the total energy consumption for different components of chilled water systems, using the two main variables of: controller’s set points and sequence of operation. The integration of the optimization algorithm with the system model is the other objective of the proposed model. The result of using different machine learning testing methods to predict the chiller power shows that the model can capture and predict the performance of the chiller with a high level of accuracy. The initial result of the optimization shows that optimization technique can reduce the energy consumption of the chilled water system.

Citation: 2019 Annual Conference, Kansas City, MO, Extended Abstracts

Product Details

Published:

2019

Number of Pages:

4

Units of Measure:

Dual

File Size:

1 file , 1.1 MB

Product Code(s):

D-KC-19-A027