Towards Sustainability in Incentive Allocation for Renewable Energy Projects: A hybrid AHP-ML Methodology

The global expansion of RE projects faces significant financial, technological, and environmental challenges. Although a plethora of incentive categories exist, ranging from R&D funding, fiscal tools, feed-in tariffs, and soft loans to grants, policymakers struggle to allocate targeted incentive strategies to RE projects. This decision-making process is compounded by the huge volume of RE projects’ production data, the need to align with multi-dimensional sustainability objectives, and the distinct local policy priorities and policymakers’ perspectives. This study aims to develop a segmentation methodology for a tailored allocation of incentives for RE projects based on their production and sustainability metrics.The proposed methodology combines machine learning (ML) algorithms, data analytics techniques, and multi-criteria decision-making (MCDM) to allocate tailored incentives within the RE sector. ML and data analytics are leveraged to identify the projects’ segments with similar characteristics, while MCDM facilitates an adjustable weighting of the sustainability-related criteria. Our contribution offers a practical decision-making methodology for policymakers seeking to effectively allocate incentive strategies, ultimately stimulating the RE sector and pursuing sustainability objectives toward a resilient energy transition.