EnergyPLUS

Inspiration

As Malaysians concerned for our country's ability to commit to the Paris Agreement on climate change, we aim to apply our computer science and electrical engineering skills to provide actionable solutions to make renewable energy more sustainable.

What it does

Energy PLUS provides data-driven insights to energy users to participate in controlling energy demand, preventing grid stress on power grids incorporating a hybrid of renewables like solar and wind energy, as renewable energy generation fluctuates throughout the day.

How we built it

We used XG Boost machine learning to train and test our data sets.

Challenges we ran into

Our biggest challenge was finding comprehensive data sets from reliable environmental organizations to train and test our machine learning models.

Accomplishments that we're proud of

Our machine learning model was able to achieve accuracies with errors of approximately 40 Megawatts.

What we learned

How to use Machine Learning, how to search for data sets, and learned about energy demand and use in California

What's next for EnergyPLUS

We aim to continue developing EnergyPLUS to provide real-time updates every 5 minutes, based on solar and wind energy generation as these renewable energy sources are affected by weather, as well as providing more realistic compensation schemes for energy users, in step with the insights received from our machine learning models.

Built With

• jupyter
• machine-learning
• python
• xgboost