Bi-Level Optimization Method for Frequency Regulation Performance of Industrial Extraction Heating Units Under Deep Peak Shaving Conditions

This paper proposes a multi-objective collaborative optimization method based on a two-layer optimization framework to address the problem of difficult coordinated optimization of multi-parameter coupling in the frequency regulation performance of heating units under deep peak shaving conditions. The upper-level optimization of this method focuses on the dynamic performance of primary frequency modulation and improves the fast response capability through multi-objective optimization of overshoot and adjustment time. Lower-level optimization is based on the optimal control parameter set output by the upper level, with comprehensive power deviation as the indicator, focusing on suppressing the deviation of frequency modulation power and the steady-state deviation of heating power. Propose a comprehensive quantitative index for frequency modulation performance and characterize the optimization effect of frequency modulation performance. Introducing a dynamic perturbation factor mechanism to generate an improved HO algorithm for dual-layer optimization solutions, preventing it from getting stuck in local optima and solving the problem of global search capability imbalance. The effectiveness of the method was verified based on actual unit calculations, and the obtained control parameter set met the objectives of optimal primary frequency regulation dynamic performance and optimal comprehensive power deviation performance, significantly improving the frequency regulation performance of heating units under deep peak shaving. After optimization, the overshoot performance score of the unit increased by 16.9%, the regulation time performance score increased by 25.1%, the frequency modulation power deviation score increased by 14.2%, the heating power deviation score increased by 17.7%, and the total frequency modulation performance score increased from 75.26 to 95.95, with a comprehensive optimization range of 27.5%.