The growing adoption of renewable energy sources 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. Adaptive Large Neighborhood Search (ALNS) 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 ALNS provides faster execution time and greater constraint flexibility. Our results indicate a 22% reduction in consumers’ expenses when group transactions are possible, compared to the initial case, where consumers transact only with the grid.