UROP Project

Building AI-Ready Datasets for Power and Energy Systems

Artificial Intelligence; Data Engineering; Power Systems; Energy Systems; Machine Learning

Research Mentor: Dr., Prof. Ravikumar Gelli, He, His,
Department, College, Affiliation: Florida State University, FAMU-FSU College of Engineering
Contact Email: rgelli@fsu.edu
Research Assistant Supervisor (if different from mentor):
Research Assistant Supervisor Email:
Faculty Collaborators:
Faculty Collaborators Email:

Looking for Research Assistants: Yes
Number of Research Assistants: 2
Relevant Majors: Electrical Engineering, Computer Engineering, Computer Science, Data Science, Statistics, Applied Mathematics, Information Technology, or related disciplines. Students from other majors with an interest in data and artificial intelligence are also encouraged to apply.
Project Location: 2000 Levy Ave, Tallahassee, FL 32310. Center for Advanced Power Systems (CAPS)
Research Assistant Transportation Required: FSU Seminole Express provides service between the FSU main campus and the FAMU-FSU College of Engineering.
Remote or In-person: Partially Remote
Approximate Weekly Hours: 5 to 8 hours per week, Flexible schedule (Combination of business and outside of business. TBD between student and research mentor.)
Roundtable Times and Zoom Link:

• Day: Tuesday, September 1
  Start Time: 1:00
  End Time: 2:00
  Zoom Link: https://fsu.zoom.us/j/6540925978

Project Description

Power and energy systems generate large amounts of data from sensors, simulations, smart meters, renewable energy resources, weather measurements, communication systems, and other sources. However, raw data are often incomplete, inconsistent, noisy, poorly labeled, or stored in formats that are difficult to use directly for artificial intelligence and machine learning.

This project will explore how raw power and energy system data can be transformed into high-quality, AI-ready datasets. Undergraduate researchers will learn how to collect, organize, clean, visualize, label, and document different types of engineering data. Students will investigate common data-quality problems such as missing values, inconsistent timestamps, measurement errors, duplicated records, incompatible formats, and insufficient metadata.

The project will also explore how dataset design affects the performance and reliability of downstream AI and machine-learning applications. Students will work with real or simulated power and energy datasets while developing broadly applicable skills in Python, data analysis, data engineering, visualization, and responsible dataset preparation.

No prior experience in artificial intelligence, machine learning, or electric power systems is required. The project is designed as an accessible introduction to research for first-year and early undergraduate students.

Research Tasks: 1) Review introductory materials on datasets, data quality, and the role of data in artificial intelligence and machine learning.
2) Explore power and energy datasets from simulations, sensors, renewable energy systems, weather sources, or other publicly available resources.
3) Use Python-based tools to organize, visualize, and understand different types of data.
4) Identify data-quality problems such as missing values, duplicate records, inconsistent timestamps, outliers, noise, and incompatible data formats.
5) Develop and test procedures for data cleaning, synchronization, normalization, labeling, and transformation.
6) Organize datasets into consistent structures suitable for machine-learning and deep-learning applications.
7) Develop metadata and documentation describing the dataset, variables, units, sources, processing steps, and limitations.
8) Evaluate dataset quality and investigate how different data-preparation choices affect simple AI or machine-learning models.
9) Document the research process and prepare results for presentation at the Undergraduate Research Symposium.

Skills that research assistant(s) may need: Required:
-- Interest in artificial intelligence, data, or engineering
-- Willingness to learn programming and data-analysis tools
-- Attention to detail
-- Ability to organize information carefully
-- Willingness to communicate progress and work consistently

Recommended but not required:
-- Basic familiarity with Python, MATLAB, Excel, or another computational tool
-- Introductory programming experience
-- Basic mathematics or statistics
-- Experience working with spreadsheets or structured data

Prior experience with machine learning, deep learning, data engineering, or electric power systems is not required.