DE | EN
Home
About Us
Overview
Facts and Figures
Organization
Scientists
Contact
Approach
Situations offered
Research
Overview
Application Fields
Projects
Publications
Scientists
Preprints
Institutional Cooperation
Archiv 02-14
Transfer
Overview
Industry
References
MODAL-AG
Spin Offs
Software
Patents
Schools
Overview
MathInside
Matheathlon
Matheon-Kalender
What'sMath
Training for Teachers
Summer Schools
Events
Press
Overview
Releases
News
Overview
Matheon Head
Number of the week
News 2002 - 2014
Activities
Overview
Workshops
15 Years Matheon
Media
Overview
Photos
Videos
Audios
Booklets
Books
News from around the world

Prof. Dr. Vladimir Spokoiny

spokoiny@wias-berlin.de


Projects as a project leader

  • SE7

    Optimizing strategies in energy and storage markets

    PD Dr. John Schoenmakers / Prof. Dr. Vladimir Spokoiny

    Project heads: PD Dr. John Schoenmakers / Prof. Dr. Vladimir Spokoiny
    Project members: Roland Hildebrand
    Duration: -
    Status: completed
    Located at: Weierstraß-Institut

    Description

    The project aims at developing numerical methods for the solution of complex optimal control problems arising in energy production, storage, and trading on energy markets. As a first step, we implement a Monte-Carlo approach to a hydro-electricity production and storage problem coupled with a stochastic model of the electricity market. Further we develop algorithms for pricing of complex energy derivatives based on the dual martingale approach.

    http://www.wias-berlin.de/projects/ECMath-SE7/
  • SE22

    Decisions in energy markets via deep learning and optimal control

    PD Dr. John Schoenmakers / Prof. Dr. Vladimir Spokoiny

    Project heads: PD Dr. John Schoenmakers / Prof. Dr. Vladimir Spokoiny
    Project members: Dr. Alexandra Suvorikova
    Duration: 01.06.2017 - 31.12.2018
    Status: running
    Located at: Weierstraß-Institut

    Description

    One of the main goals in this project is a systematic numerical treatment of generic optimal decision problems in real-life applications that encounter in energy markets by incorporating ``deep Learning'', a recent concept for data analysis and prediction. Also it is intended to include principles of deep learning in methods for forecasting and estimating price distribution processes in a systematic way.

    https://www.wias-berlin.de/projects/ECMath-SE22/