GithubHelp home page GithubHelp logo

emmxl / -machine-learning-to-predict-energy-consumption Goto Github PK

View Code? Open in Web Editor NEW
0.0 1.0 0.0 2.24 MB

This a machine learning model to predict electricity consumption, the dataset used was from Finland.

License: MIT License

Jupyter Notebook 100.00%

-machine-learning-to-predict-energy-consumption's Introduction

Energy Consumption Prediction using Machine Learning

Time Series Forecasting (LSTM)

This research was done as part of a research seminar course at LAB University of Applied Science (fall 2022). The report was written using the thesis template of LAB University.

Abstract

The purpose of this research was to predict energy consumption using the data of Finland's transmission system operator. The objective of this project was to test if a machine learning model can yield good enough results in a complex forecasting problem, exploring machine learning techniques and developing a data-driven model for forecasting energy. The data contained 6-year hourly electrical consumption in Finland, and it is a univariate time series, as it is seasonal. We used a long-short term memory (LSTM) model to train the data. The model was evaluated using root mean squared error (RMSE) to be directly comparable to energy readings in the data. The result shows that electricity consumption can be predicted using machine learning algorithms so we can use the results to deploy renewable energy, plan for high/low load days, and reduce wastage from polluting on reserve standby generation.

Model Implementation

The data was imported from Finland's transmission system operator as a CSV file and then exported to a GitHub repository. There was a total number of 52965 observations and 5 variables in this dataset and no missing values were found. The minimum load volume is 5341 MWh, and the maximum load volume is 15105 MWh along with an average volume of 9488.750519 MWh. The data is univariate time series, where there is a need for one column to present time and another one to present energy consumption. For predicting day consumption, data were down-sampled using resample function. This function changed the data from hourly frequency to daily frequency. Training the LSTM model was done using the training set and the validation dataset for testing the results through the training process. The learning algorithm worked through the entire training dataset 60 times (Epoch), and the model weights were updated after each batch where the batch size is 20.

-machine-learning-to-predict-energy-consumption's People

Contributors

emmxl avatar

Watchers

 avatar

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.