Carleton University
Modeling and Learning Prosumer Preferences in Peer-to-Peer Energy Sharing Using Federated Techniques
Abstract
dc:description.abstractThis research proposes a federated, preference-aware framework to tackle preference heterogeneity in decentralized Peer-to-Peer (P2P) energy-sharing systems. Traditional centralized methods pose privacy risks and fail to support multi-objective preferences. To address this, the framework introduces three customizable preference models that enable prosumers to express trade-offs across energy-sharing attributes. A three-layer federated learning (FL) architecture is then employed to implement these models in a privacy-preserving and scalable manner, avoiding centralization of raw consumer data. The system incorporates key techniques such as preference-based clustering, similarity-weighted aggregation, and representative model distillation to personalize recommendations for diverse prosumer groups. This design addresses cold-start and data sparsity issues while enhancing model interpretability and adaptability. Experimental results show that the proposed framework outperforms standard FL baselines, achieving up to a 32% improvement in preference alignment and an 11% gain in NDCG, while maintaining stable scalarized rewards.
Degree
thesis:*- Name thesis:degree_name
- Master of Information Technology (M.I.T.)
- Level thesis:degree_level
- Master's
- Discipline thesis:degree_discipline
- Data Science, Analytics, and Artificial Intelligence
- Grantor dc:publisher
- Carleton University
- Year dc:date.issued
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Abolhasanzadeh, Bahareh
Subjects
dc:subject × 3Rights
dc:rights- Statement dc:rights
-
- Copyright © 2025 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner.
- Language dc:language.iso
- en