Back to search

University of Patras

AI - enabled price and system imbalance forecasting for the optimal participation of flexible industrial loads in the Day-ahead and balancing market

Abstract

dc:description

This doctoral dissertation investigates the participation of industrial consumers in modern electricity markets. The increasing need for flexibility in power systems, the transition of European electricity markets to a 15-minute market time resolution, and the growing volatility of electricity prices necessitate the development of advanced forecasting and decision-support tools. The dissertation proposes an integrated framework that combines ML techniques with mathematical optimization to support the participation of industrial loads in both the Day-Ahead Market (DAM) and the Balancing Market (BM). For DAM price forecasting, a hybrid model combining machine learning and neural network techniques is developed. For the BM, a probabilistic forecasting framework is implemented to predict both system imbalance and imbalance prices. The forecasts are then integrated into a Mixed-Integer Linear Programming (MILP) model that represents the operation of a steel production industry, considering technological constraints, process interdependencies, and production requirements. Through the evaluation of different operational scenarios, the economic value of flexibility and the impact of forecasting accuracy on market outcomes are assessed. The dissertation contributes to the areas of electricity price forecasting and operational optimization, providing a scalable decision-support framework for the participation of industrial facilities in electricity markets.

Degree

thesis:*
Grantor dc:publisher
University of Patras
Year dc:date
2026

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Plakas, Konstantinos
  • Πλάκας, Κωνσταντίνος

Subjects

dc:subject × 14

Rights

Language dc:language
eng

Identifiers

dc:identifier.*
Identifier
10.12681/eadd/62094

Chain of custody

source
Harvested from
Greek National Archive of PhD Theses
Base URL
phdtheses.ekt.gr/eadd_oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Plakas, Konstantinos; Πλάκας, Κωνσταντίνος. AI - enabled price and system imbalance forecasting for the optimal participation of flexible industrial loads in the Day-ahead and balancing market. University of Patras, 2026. http://hdl.handle.net/10442/hedi/62094