Sustainable energy management requires the integration of renewable energy sources like solar and wind into smart grids, but this is difficult because of their intermittent and unpredictable nature. Conventional optimi- -sation techniques, such as linear and convex programming, offer deterministic answers but are not flexible enough to deal with uncertainty. Although metaheuristic algori- -ithms are flexible, they frequently have issues with scalability and convergence. In order to reduce operating costs, maximise renewable utilisation, and preserve grid stability, this research suggests a hybrid optimisation framework that blends deterministic optimisation with metaheuristic techniques. The hybrid model outperforms traditional approaches, yielding cost reductions of up to 20% and better renewable integration, according to simulation studies using realworld datasets. In order to advance sustainable energy systems, the findings provide policymakers and industry stakeholders fresh perspectives.