Difference between revisions of "Deep Learning and Energy Forecasting"

From REU@MU
Jump to: navigation, search
(Created page with "Title: Deep Learning and Energy Forecasting Host: GasDay Laboratory Responsible faculty: Richard Povinelli, George Corliss, Ron Brown, Tom Quinn Description: How much natur...")
 
 
(2 intermediate revisions by one other user not shown)
Line 1: Line 1:
Title: Deep Learning and Energy Forecasting
+
'''Host''':  GasDay Laboratory
Host:  GasDay Laboratory
+
Responsible faculty: Richard Povinelli, George Corliss, Ron Brown, Tom Quinn
+
  
Description:
+
'''Mentors''': [http://www.marquette.edu/electrical-computer-engineering/povinelli-richard.php Dr. Richard Povinelli], [http://www.marquette.edu/mscs/facstaff-corliss.shtml Dr. George Corliss], [http://www.marquette.edu/electrical-computer-engineering/brown-ronald.php Dr. Ron Brown], Tom Quinn
  
How much natural gas is needed each day for the next week?
+
'''Description''':  How much natural gas is needed each day for the next week?
  
 
At GasDay we answer this question for over 30 local distribution
 
At GasDay we answer this question for over 30 local distribution
Line 26: Line 24:
 
probabilistic forecasting.
 
probabilistic forecasting.
  
Wish list of skills: Computer programming (MATLAB)
+
'''Preferred skills''': Computer programming (MATLAB)

Latest revision as of 17:32, 31 January 2017

Host: GasDay Laboratory

Mentors: Dr. Richard Povinelli, Dr. George Corliss, Dr. Ron Brown, Tom Quinn

Description: How much natural gas is needed each day for the next week?

At GasDay we answer this question for over 30 local distribution companies. Each day, we help forecast about 20% of the natural gas delivered to residential, industrial, and commercial customers in the US. We use modern software architecture and tools, including databases, multi-tiered systems, distributed computing, automated testing, and user interface design.

We offer research opportunities in mathematical modeling, statistical analysis of data, and software engineering. Previous REU participants' projects have involved water demand forecasting, high performance computing, data mining, hourly natural gas demand forecasting, electricity demand forecasting using model trees, and evaluating strategies for weather-normalizing natural gas demand. If you work with GasDay, your interests and skills will be matched with a suitable project, you will have plentiful attention from your mentor(s), and you will enjoy working in an active community of scholars. Current projects will focus on deep learning and probabilistic forecasting.

Preferred skills: Computer programming (MATLAB)