@inproceedings {pub6147,
	title = {Adaptive Large Neighborhood Search for Optimal Clustering of Prosumers into Energy Communities},
	author = {Ehsan Aliyan AND Jose  Almeida AND Steffen Limmer AND Sergio Ramos AND Joao Soares},
	year = {2026},
	month = {January},
	abstract = {The growing adoption of renewable energy sources (RES) is transforming sustainable energy systems and economies, driven by their environmental benefits and steadily decreasing costs. The increasing integration of renewable energy sources in local energy systems necessitates efficient clustering of prosumers to enhance economic benefits and grid stability. This paper presents a method for clustering prosumers into energy communities based on their demand and photovoltaic (PV) production. The clustering process ensures that the maximum distance between prosumers in a group does not exceed a specified value and that total PV production remains below a specified threshold. The problem is formulated as a combinatorial optimization challenge, where prosumers with complementary energy generation and consumption patterns are grouped. The Large Neighborhood Search (LNS) heuristic is employed to efficiently explore the solution space and enhance clustering performance, aiming to maximize prosumer benefits and reduce energy costs. Computational experiments on simulated datasets demonstrate the effectiveness of the proposed approach compared to a previously published mathematical approach, as LNS provides faster execution time and greater constraint flexibility.},
	publisher = {Springer, LNCS, LNAI, LNBI},
	booktitle = {International Conference on Machine Learning, Optimization, and Data Science (LOD) 2025}
}