Corporate renewable power purchase agreements (PPAs) are long-term agreements that enable companies to source renewable energy without having to build and operate their own renewable energy projects. Typically, producers and consumers agree on a fixed price at which power is purchased. The value of the PPA to the buyer then depends on the difference between the fixed price and the expected price at which the produced volume is expected to sell the future. To model this so-called capture price, practitioners often use either fundamental models or statistical approaches, each with their inherent weaknesses. We propose a new approach that blends the logic of fundamental electricity market models with statistical learning techniques. In particular, we use regularized inverse optimization of a quadratic programming formulation of a bid stack model to estimate the marginal costs of different technologies as a parametric function of exogenous factors. We compare the out-of-sample performance using market data from three European countries and demonstrate that our approach outperforms established statistical learning benchmarks. We then discuss the case of a photovoltaic plant in Spain to illustrate how to use the model to value a PPA from the buyer's perspective.
Roozbeh Qorbanian: Valuation of Power Purchase Agreements 7 December 2023 16:00 - 17:00
About Roozbeh Qorbanian: Valuation of Power Purchase Agreements
Starting date
- 7 December 2023
Time
- 16:00 - 17:00
Location
- VU Main Building
Address
- De Boelelaan 1105
- 1081 HV Amsterdam
Organised by
- Operations Analytics
Language
- English
Roozbeh Qorbanian
Roozbeh Qorbanian received the B.Sc. degree in industrial engineering from the Isfahan University of Technology, Isfahan, Iran, in 2013, and the master’s degree in industrial engineering from the University of Tehran, Tehran, Iran, in 2015. He is currently pursuing the Ph.D. degree with the Luxembourg Centre for Logistics and Supply Chain Management, University of Luxembourg. He was ranked in the top 1% in the university entrance exams in Iran for both the bachelor’s and master’s degrees. He received a merit-based fellowship for his undergraduate education. He worked as a Research Scholar in the Scientific Research Project “Scheduling Algorithms for Wireless Communication” with Yaşar University, İzmir, Turkey. His Ph.D. thesis is supported by FNR (Luxembourg National Research Fund) under the BRIDGES program for an academic-industry partnership. His current research interests include scheduling, decision making under uncertainty, and machine learning.
Interested in attending the seminar or in giving a talk?
Please send an email to Tim Oosterwijk