Documentation - Home

Engineering Science Building

Repository source

GitHub Mirror

Author: Ibrahim Ahmed

These files document research on smart control of HVAC systems using data-driven methods.

The purpose of this project is to analyze performance of HVAC systems - particularly chillers and cooling towers - in the Engineering Science Building (ESB) at Vanderbilt University to develop control approaches to maximize cooling and power efficiency.

The documentation is divided into a discussion of background concepts in physics, jargon in the HVAC industry, layout of air conditioning systems, and a description of the dataset specific to the system at ESB.

1. Thermodynamics concepts

2. Industry terms

3. Chillers - refrigeration

4. Chillers - Cooling towers

5. Data

   a.

   V1 Data

   Preprocessing

   b.

   V2 Data

6. Trends

7. Relationships

8. ESB Controller Deployment Notes

Installation

Requires python 3.7. However, python 3.5+ shoould work fine. To install dependencies:

conda env create -f dev.yml  # for development

One requirement is IPyVolume for 3D plots. See installation instructions here.

Saving GIFs using IPyVolume requires ImageMagick with legacy options (i.e. the convert.exe command) enabled.

Currently IPyVolume does not work with Jupyter Lab. Instead use Jupyter Notebook to view those plots.

Deployment

The controller is currently deployed for Engineering Science Building using a rudimentary feedback logic. This logic is contained in the controller.py script in the repository. This is the first step to gathering data to generate data-driven models. A log of various events during deployment is maintained here.

To read instructions on deployment, read the (you guessed it) README.