Description:
Peak Electric Load Prediction
Princeton Docket # 24-4155-1
In today's energy landscape, commercial and industrial users face escalating peak demand charges, which can significantly impact their operating costs. These charges, determined by the highest levels of energy consumption during peak periods, can account for 10% to 40% of a customer's electricity bill, as established by the Federal Energy Regulation Commission (FERC). Companies often struggle to predict peak demand times, typically relying on external consultancy forecasts that can be limited in accuracy and timeliness. This innovative predictive technology, which was developed by Princeton University researchers, offers a robust solution to this challenge. Utilizing a stochastic modeling approach, this process is designed to forecast Coincidence Peak events by analyzing historical load data and calibrating with publicly available datasets. This flexible model can be tailored to align with various ISO and RTO frameworks, allowing companies to anticipate peak demand periods with greater accuracy. By leveraging this technology, businesses can strategically manage their electricity usage, significantly reducing their peak demand charges and, consequently, their overall energy expenses.
Applications
- Predict Coincident Peak (CP) events
- Optimize energy usage at peak hours for any sector
- Inform Demand Response processes
Advantages
- Sharp reduction in peak demand charges
- Energy efficient and sustainable
- Improved management of storage facilities
Stage of development
This simulation has been trained using publicly available data and results have been shown to be valuable for commercial applications.
Publication
https://arxiv.org/abs/2407.04081
Inventors
Rene Carmona Ph.D. is a Paul Wythes ’55 Professor of Engineering and Finance at Princeton University. He achieved a These d'Etat in Probability from the University of Marseille. His research interests include stochastic analysis, financial mathematics and signal analysis.
Xinshuo Yang Ph.D. received his doctorate from the University of Colorado Boulder in Applied Mathematics. He is currently working as a postdoctoral research associate at Princeton University researching stochastic models and how they can reduce risks associated with power grids.
Claire Zeng is a 4th year PhD candidate in the department of Operations Research and Financial Engineering at Princeton University. Her research interests are stochastic analysis and mathematical finance.
Intellectual Property & Development status
Patent protection is pending.
Princeton is currently seeking commercial partners for the further development and commercialization of this opportunity.
Contact
Prabhpreet Gill
Princeton University Office of Technology Licensing • (609)258-3653 • psgill@princeton.edu