Anaylyzing Spatio-temporal patterns and Correlations in grid Carbon intensity data

Project Description:  

Students will work on understanding the basics of the electricity grid and carbon intensity – how the grid works, what carbon intensity represents, and how it changes across space and time. Students will then analyze the spatiotemporal correlations in historical carbon intensity data across multiple electricity grids. By understanding and analyzing this information, students will be able to answer questions such as: (i) How does carbon intensity vary by hour of day, day of week, and the seasons in a region? (ii) How different is the carbon intensity of various regions (e.g. Massachusetts compared to California) and why? (iii) Which regions exhibit similar temporal patterns and why? (iv) How can we efficiently predict these carbon intensities, and how do the predictions affect the decision-making process? To answer these and other relevant questions, students will develop skills in data retrieval (using REST API), analysis (using Python), and visualization (using Colab). Students will gain the necessary knowledge and skills through hands-on experience.

Learning Objectives:  

1. Understand the basics of the electricity grid and grid carbon intensity.

2. Understand spatio-temporal patterns and correlations in grid carbon intensity

3. Learn to process and analyze big data. 

4. Learn visualization techniques to communicate analysis results effectively.

5. Learn to build a reproducible pipeline for data retrieval, analysis, and visualization. 

6. Learn techniques for predicting time series data

Skills needed:  

• Python and related frameworks (Pandas, SciPy, NumPy)

• Data analysis and visualization using Colab Notebooks & Matplotlib.

• REST API (for data retrieval)

• Basics of time series data aggregation and analysis.