Giter VIP home page Giter VIP logo

energybuild's Introduction

Energy Usage of an office building

Big Data and Digital Modelling - Priv.Doz. Dr. techn. Mag. MA MA Gerald Schweiger

Predicting the energy consumption of an office building

Presentation Slides

Paper

Authors :

  • Calixto, Ian
  • Doblas Florido, Maria Angeles
  • Dogliani, Matias
  • Nord, Nathan Thomas

Model training and testing

Datasets

Energy consumption dataset used

Energy consumption Preprocessed Plot

Historical weather dataset used

Historical Weather Plot

Notebooks

Models

4 Models were tested and compared.

Models output

Perfomance comaparison

Models perfomance analysis

Energy consumption prediction

4 days

4 days prediction

Hourly

hourly one day prediction

To short:

In order to predict the future energy usage of a building using machine learning, a data set of historical energy usage was given. This data set had to be preprocessed before it could be useful. The major steps of preprocessing included cleaning the data, analysing the data, and detecting and replacing outliers. We then determined the inputs of the data for the machine learning model. Our inputs were weekdays, holidays, and temperature and our target variables was energy usage.

Historical weather data corresponding to the time of our data was retrieved via API to interface with our data. This weather data was also preprocessed. Next, the model was trained and tested with 4 different models.

After analysis of each model it was determined that the Tree Decision Regressor produced the best results for our use case, yileding an R2 value of 0.89. The Tree Decision Regressor was used to forecast the next 4 days of energy usage.

The 4 day forecast produced results that our group determined to be a reasonable prediction, validating the success of our model.

energybuild's People

Contributors

matias-dogliani avatar

Stargazers

 avatar  avatar

Watchers

 avatar

Forkers

tominord13

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.