Machine Learning Forecasting (University of New Brunswick)

EE6673
Closed
JC
Associate Professor
1
General
  • Graduate; 2nd year
  • 15 learners; teams of 3
  • 40 hours per learner
  • Dates set by experience
  • Learners self-assign
Preferred companies
  • 1 projects wanted
  • Anywhere
  • Academic experience
  • Any company type
  • Energy, Technology
Categories
Engineering & manufacturing Data modelling Electrical engineering Environmental sustainability Machine learning Artificial intelligence
Skills
collaboration computer engineering machine learning innovation electrical engineering data analysis mentorship forecasting
Project timeline
  • February 19, 2024
    Experience start
  • March 5, 2024
    Forecasting and Literature review.
  • March 19, 2024
    Discussion of methods and initial model development.
  • March 26, 2024
    Model refinement and presentation preparation.
  • April 2, 2024
    Model implementation and testing.
  • April 11, 2024
    Final presentation and project report submission.
  • April 12, 2024
    Experience end
Overview
Details

Are you looking to empower the next generation of Electrical Engineers while advancing your projects? Join the Riipen Experience in collaboration with the University of New Brunswick's Department of Electrical and Computer Engineering. Our course, "Data Analytics for the Smart Grid", is designed to equip future electrical engineers with the skills needed to navigate the complexities of smart grid analytics.


Ideal Employer Profile:

We are seeking industry partners committed to fostering innovation in the energy sector. Employers who value the potential of emerging talent, possess expertise in data analytics, and can guide students through real-world applications are ideal collaborators.


Steps to Collaboration:

  1. Submit a match request through the Riipen platform with a well-defined project proposal.
  2. Engage in a video call to discuss potential collaborations and ensure mutual alignment.
  3. If both parties agree, accept the match on the Riipen platform.
  4. Students will be assigned to collaborate with you, and you'll provide mentorship and support.
  5. Upon project completion, provide feedback on the Riipen platform to showcase the valuable work experience gained by students.


Learner skills
Collaboration, Computer engineering, Machine learning, Innovation, Electrical engineering, Data analysis, Mentorship, Forecasting
Deliverables

Partnering with us opens the door to valuable deliverables:


Machine Learning-Based Forecasting Model:

  • Integrating multiple data sources for accurate forecasting.

Detailed Evaluation:

  • Assessing model accuracy, speed, and robustness.

Schedule:

  • Weeks 1-2: Forecasting and Literature review.
  • Weeks 3-4: Discussion of methods and initial model development.
  • Week 5: Model implementation and testing.
  • Week 6: Model refinement and presentation preparation.
  • Week 7: Final presentation and project report submission.


Project Examples

Is your project a perfect fit for our students?


Consider the following project idea aligned with the course objectives:


Project Name: Energy Price Forecasting

Develop a model to forecast energy prices in a smart grid, considering factors such as market trends, supply-demand dynamics, and regulatory changes.


Project Name: Renewable Energy Generation Prediction

Build a forecasting model to predict the generation of renewable energy sources (solar, wind) in a smart grid, incorporating weather forecasts, historical generation data, and grid conditions.


Project Name: Load Forecasting for Smart Grids

Develop a machine learning model to forecast electrical load demand in smart grids, considering historical usage patterns, weather conditions, and real-time data from smart meters.

Additional company criteria

Companies must answer the following questions to submit a match request to this experience:

How does your project align with advancing skills in smart grid analytics for future electrical engineers?

Can you provide substantial amount of data in the beginning?

Can you provide support to guide students through real-world applications of data analytics?

In what ways do you see your project contributing to the efficiency and reliability of power systems?

How comfortable are you with engaging in regular communication with students, answering questions, and providing necessary documentation?

Can you provide references for my students who participated in your project?

Are you open to collaborating with emerging talent and contributing to their growth in the field of data analytic electrical engineering?