NSGA-II-based Multi-objective Intelligent Scheduling Optimization System for Hybrid Oil-Gas Heating Furnaces

To address the challenge of coordinating economic costs and carbon emissions in scheduling hybrid oil-gas pipeline heating furnaces, this study proposes a multi-objective intelligent decision-making framework based on the Non-dominated Sorting Genetic Algorithm II (NSGA-II). Considering practical constraints including equipment heterogeneity (with partial furnaces operating exclusively on oil) and disparities in carbon emission intensities, we formulate a mixed-integer nonlinear programming model aiming to minimize both the carbon-to-economy ratio and operational costs. The NSGA-II algorithm is leveraged to identify equilibrium points among conflicting objectives, generating a set of Pareto-optimal solutions that enable efficient exploration of retrofitting strategies. Simulation experiments on heating furnace allocation optimization at a pipeline station validate the effectiveness and superiority of the proposed methodology. These findings provide theoretical foundations for low-carbon retrofitting of heating furnace systems.