Electricity demand forecasting is an essential tool for energy management, maintenance scheduling and investment decisions in the energy markets. Electricity demand for a region depends on economic variables – oil prices, stock prices, exchange rates; demographic circumstances – holidays, population and most importantly climatic conditions – temperatures, humidity etc. In this project we want to measure how daily temperatures affect electricity demand for a region. We will also investigate how accurately temperature can be used to forecast the demand in mid-term (8 weeks/2 months)
Read this writeup for more info
Head over to Demand Forecasting and explore the notebooks
- Add holiday and weekday data
- Add humidity
- Try BSTS/1-D CNN/RNN
Please reach out to arsaikia@iu.edu for questions and feedback.