Carbon emission prediction and management under the coordinated operation of renewable energy and smart grid

To address urgent climate challenges, reducing carbon emissions is a core goal of global energy transformation.Renewable energy, such as wind and solar, is increasingly replacing fossil fuels.Smart grids facilitate this shift by enabling efficient distribution and large-scale integration of renewables.However, their growing share raises critical questions about optimal dispatch and emission reduction.This study employs big data analytics and machine learning to investigate carbon emission prediction and management through renewable energy and smart grid synergy.A data-driven prediction model was developed using decade-long energy consumption and emission data from Heilongjiang Province, China.Simulations show that introducing 30% renewable energy reduces carbon emissions by approximately 12%.With smart grid optimised scheduling, emissions decrease a further 8%, demonstrating its vital role in advancing low-carbon energy systems.