Clay Campaigne

Energy Optimization / Data Science Consultant Oakland, CA Contact clay.campaigne@gmail.com

Bio

I am an independent data science consultant specializing in green energy modeling -- most recently buildings, battery storage, and renewables. I finished my PhD in Industrial Engineering and Operations Research at UC Berkeley in 2016, where my research focused on the economics of electricity markets, particularly incentives and private information in the context of demand response and renewables integration. After grad school I worked as a senior energy modeler at Ascend Analytics for a few years. I mostly work in Python, but am interested in Julia as well.

Selected Publications

• Clay Campaigne, "On Demand Response in Electricity Markets," PhD Thesis. (Including joint work with Maximilian Balandat and Lilian Ratliff.)
  [pdf]
  

• Donghan Feng, Chang Liu, Zeyu Liu, Liang Zhang, Yangzhi Ding, and Clay Campaigne, "A Constraint Qualification based Detection Method for Nodal Price Multiplicity in Electricity Markets," IEEE Transactions on Power Systems.
  

• Clay Campaigne, Maximilian Balandat, and Lillian Ratliff, "Welfare Effects of Dynamic Electricity Pricing," working paper.
  [pdf]
  

• Clay Campaigne and Shmuel Oren, "Firming Renewable Power with Demand Response: An End-to-end Aggregator Business Model," Journal of Regulatory Economics.
  [pre-final-review, final, slides]

Presentations

• INFORMS Annual Meeting, San Francisco, CA, Nov 2014. "A Mechanism Design Model for Firming Intermittent Renewable Generation with Curtailable Demand." Joint work with Shmuel Oren.

Course projects, notes, etc.

• CS 281a, Statistical Learning Theory, Fall 2014: An online linear decision rule for dual-source energy procurement by a daily deadline.
  [video link: set to 0.25 speed and see description there.]

• Scribed notes on policy gradients, from CS 294, Deep Reinforcement Learning. Not very polished, but some people have told me they found them helpful.