Back to search

Athens University Economics and Business (AUEB)

Demand forecasting and energy consumption recommendations for smart grid consumer engagement through deep learning and reinforcement learning

Abstract

dc:description

Consumers are crucial regarding the operation of Smart Grids, since their activities account for a large portion of the total energy demand. Therefore, utility companies, governmental agencies, and various other entities with environmental concerns aim at lowering and shaping energy consumption patterns to achieve peak load reduction, load smoothing, and hence carbon emission curtailment. Forecasting the energy demand of individual consumers is a vital component of future Smart Grids since it enables energy-saving mechanisms such as Demand Response (DR), activity scheduling, and prosumer energy markets. In addition, personalized device level energy consumption recommendations towards energy efficiency can have a notable impact both on electricity bills and on the overall energy supply-demand balance. However, end-user behavior regarding device activation is usually unknown a priori, thus giving rise to a highly dynamic environment. In this dissertation, we initially present an overview of approaches for engaging Smart Grid consumers and for offering them information, motivation, and recommendations for energy efficiency through mobile apps. Our focus is to bring machine learning approaches closer to Smart Grid mobile apps so as to optimally manage consumer flexibility and enhance energy savings through detailed consumer profiling and modeling, since an increasing amount of energy consumer data is becoming available. A novel survey of prior work in the area is conducted in order to identify gaps from this perspective, and a mobile application is developed to fill those gaps. In addition, we propose a single-model deep learning architecture named Deep4Ener for consumer-level energy demand forecasting, trained on data from multiple buildings and capable of making predictions for unseen consumers with scarce historical data that were not included in the training phase. Deep4Ener learns common energy demand characteristics among different consumers by utilizing a novel architecture for energy profiling, including clustering, and an encoder neural network for feature extraction. Moreover, we propose a Markov Decision Process (MDP) driven Reinforcement Learning (RL) framework for energy efficiency recommendations that jointly learns the user’s behavior for multiple devices. The proposed model is wrapped as an open-source customizable Gymnasium environment, named EMS-env, for multidevice energy efficiency recommendations. EMS-env can simulate different types of consumer behavior profiles based on the MDP model and supports different device types as well as user feedback. Finally, a Reinforcement Learning from Human Feedback (RLHF) approach with partially defined rewards is proposed and integrated into a residential energy efficiency recommendations pipeline. The proposed solution reduces energy costs while learning user preferences based on collected feedback instances, without needing a fully defined reward function.

Degree

thesis:*
Grantor dc:publisher
Athens University Economics and Business (AUEB)
Year dc:date
2025

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Chadoulos, Spyridon
  • Χαδουλός, Σπυρίδων

Subjects

dc:subject × 14

Rights

Language dc:language
eng

Identifiers

dc:identifier.*
Identifier
10.12681/eadd/59595

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

Chadoulos, Spyridon; Χαδουλός, Σπυρίδων. Demand forecasting and energy consumption recommendations for smart grid consumer engagement through deep learning and reinforcement learning. Athens University Economics and Business (AUEB), 2025. http://hdl.handle.net/10442/hedi/59595