Multimarket Trading Strategy of a Hydropower Producer Considering Active-Time Duration: A Distributional Regression Approach

This article presents a new approach for finding the optimal multimarket trading strategy of cascaded hydropower plants (HPPs) in the sequential electricity markets. These markets are day-ahead energy market, the market for frequency containment reserve in normal mode (FCR-N), and manual frequency r...

Full description

Saved in:
Bibliographic Details
Published in:IEEE systems journal 2023-06, Vol.17 (2), p.3343-3353
Main Authors: Khodadadi, Abolfazl, Hesamzadeh, Mohammad Reza, Soder, Lennart
Format: Article
Language:English
Subjects:
Cascaded hydropower plant
Cascaded hydropower plants (HPPs)
Deep learning
distributional regression
electricity market
Electricity supply industry
Europe
Hydroelectric plants
Hydroelectric power
Hydroelectric power generation
Hydroelectric power plants
Hydropower plants
Interactive computer systems
Learning algorithms
Machine learning
Mathematical models
Parameter uncertainty
Power markets
Predictive models
Production
Real - Time system
Real time systems
Regression analysis
Scheduling
Time duration
Uncertainty analysis
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This article presents a new approach for finding the optimal multimarket trading strategy of cascaded hydropower plants (HPPs) in the sequential electricity markets. These markets are day-ahead energy market, the market for frequency containment reserve in normal mode (FCR-N), and manual frequency restoration reserve markets for both energy production and capacity reserve. The active-time duration (ATD) of an mFRR energy offer is an important required parameter and it is uncertain at the time of day-ahead offer-function submission. Hence, we suggest a distributional regression approach for ATD modeling in an optimal multimarket setup. Also, a modified machine learning approach is proposed to generate price scenarios for the mFRR energy market taking into account uncertain ATD parameters. To illustrate our proposed approach, various numerical experiments are performed. Our numerical results show how proper modeling of ATD parameters can lead to a more realistic multimarket offer-function for cascaded HPPs. Furthermore, the results show how the inclusion of FCR-N and mFRR capacity markets change the optimal day-ahead offer-function.
ISSN:1932-8184
1937-9234
1937-9234
DOI:10.1109/JSYST.2022.3205142