Can you forecast green energy in the future?
Welcome to Green - A country well known for its greenery and natural resources. Green is working towards the betterment of the environment, natural resources, and health of citizens. Over the past few years, Green has improvised its natural resources by enabling the technologies for a safer future.
The major investment happened to be in renewable energy. As of today, renewable energy contributes to 60% of the total energy capacity in the country. By 2030, the target is to generate 95% of the total energy through renewable energy.
In order to achieve this objective, the government of Green Energy would like to use Data Science to understand the total energy demand of the country in the near future. This will help the government to build the infrastructure and technologies to achieve 95% of the total energy capacity via renewable energy.
They have captured the estimated total energy demand from the past 12 years on an hourly basis. Now, the government of Green Energy is looking for a data scientist to understand the data and forecast the total energy demand for the next 3 years based on past trends.
Help Green! Save Nature! Stay Healthy!
Your task at hand is to build a machine learning/deep learning approach to forecast the total energy demand on an hourly basis for the next 3 years based on past trends.
You are provided with total energy demand on an hourly basis for the past 9 years from March 2008 to Dec 2018 in the training set. You need to forecast the total energy demand on an hourly basis for the next 3 years from 2019 to 2021 in the test set.
You are provided with 3 files: train set, test set, and sample submission file.
Train Set
| Variable | Description |
|---|---|
row_id |
Unique identifier of a row |
datetime |
Date and Time (yyyy-mm-dd hh:mm:ss) |
energy |
Outcome: Total Energy Demand for an hour |
Test Set
| Variable | Description |
|---|---|
row_id |
Unique identifier of a row |
datetime |
Date and Time (yyyy-mm-dd hh:mm:ss) |
Submission File Format
You need to submit the solution file that follows a format similar to that of the sample submission file. sample_submission.csv contains 2 variables - row_id and energy.
| Variable | Description |
|---|---|
row_id |
Unique identifier of a row |
energy |
Outcome: Total Energy Demand for an hour |
Evaluation metric
The evaluation metric for this hackathon would be RMSE.