Multi-Criteria Decision-Making for Smart Grid Energy Scheduling and Demand Response: A Sustainability and Financial Approach

Abstract

The transition toward sustainable, reliable, and economically viable energy systems requires innovative approaches to manage energy scheduling and demand response (DR) in smart grids. Multi-Criteria Decision-Making (MCDM) techniques, combined with Artificial Intelligence (AI), provide a structured approach to addressing conflicting objectives across economic, environmental, technical, and financial dimensions. This study proposes an integrated framework for optimizing smart grid energy scheduling and DR strategies by employing the Analytic Hierarchy Process (AHP) for weight elicitation, the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) for ranking alternatives, and AI-based forecasting to enhance demand prediction accuracy. A synthetic case study demonstrates the framework’s effectiveness, showing that hybrid renewable integration strategies outperform conventional single-resource scheduling in terms of sustainability, cost-efficiency, and system resilience. The results underscore the importance of integrating MCDM and AI for informed decision-making in smart grid management, offering actionable insights for policymakers and energy operators.