Title: Multistage Stochastic Portfolio Optimisation in Deregulated Electricity Markets Using Linear Decision Rules
Speaker: Paula Rocha
Affiliation: Department of Computing – Imperial College London
Location: Room 217-218 Huxley Building
Time: 5:00pm

Abstract. The deregulation of electricity markets often poses great financial risks to retailers who procure electric energy on the spot market to satisfy their customers’ electricity demand. To hedge against this risk exposure, retailers often hold a portfolio of electricity derivative contracts. In this talk, we present a multistage stochastic mean-variance optimisation model for the management of such a portfolio. To reduce computational complexity, we perform two approximations: stage-aggregation and linear decision rules (LDR). The LDR approach consists of restricting the space of recourse decisions to those affine in the history of the random parameters. When applied to mean-variance optimisation models, it leads to convex quadratic programs. Since their size grows typically only polynomially with the number of decision stages, they are amenable to efficient numerical solution. Our numerical experiments highlight the value of adaptivity inherent in the LDR method and its potential for enabling scalability to portfolio optimisation problems with many decision stages.

About the speaker.