Using Gurobi to Optimize Distributed Energy Storage Assets


Many organizations use optimization within some part of their business. Some companies, such as Advanced Microgrid Solution (AMS), use optimization as an integral part of their solution. AMS provides a software-as-a-service product that optimizes the operation of a clients’ energy storage assets in order to reduce their electric bill, while also meeting contractual obligation to provide capacity to the electric utility. AMS aggregates a number of distributed assets to provide the utility with a virtual power plant that can be used to reduce system peak load. Given the dynamic nature of the electric grid, the problem needs to be solved every 5-10 minutes, requiring a robust, reliable, and scalable solution to manage continual growth.

Join us for an hour-long joint webinar with Gurobi and AMS, which will focus on how AMS integrates Gurobi into their software solutions. Topics will include:

  • The business case from a high level
  • The problem formulation as a Mixed Integer Program using Gurobi’s Python API
  • Use of Gurobi server to allow for scaling
  • Tips and tricks for building production level models

There will be time for questions at the end of the webinar. This webinar will be presented by Andrew Martinez from Advanced Microgrid Solutions.

Presenting this webinar is Andrew Martinez. He is a member of the Data Science and Optimization Team at Advanced Microgrid Solutions (AMS). Prior to joining AMS, he was building optimization models to size generation equipment for campus-scale microgrids as well as large-scale optimization models to answer energy policy questions. He holds a MS in Mechanical Engineering from Stanford University and a BS in Mechanical Engineering from Purdue University.

There are two sessions, presented in English, to choose from:

Tuesday, November 13th at 8:00am PDT (GMT -7)

Wednesday, November 14th at 3pm CEST (GMT +2)

Click on the "Show in My Time Zone" link at the top of the registration page for each webinar to see the start time in your local timezone.