Bi-Level Optimal Control Based on Similarity Clustering for Wastewater Treatment Process with Greenhouse Gas Emissions

There is a global consensus on reducing greenhouse gas (GHG) emissions to slow down global warming. GHG emissions from the wastewater treatment process (WWTP) have also received extensive attention. Therefore, how to reduce GHG emissions without increasing the operating cost and ensuring water quality standards for WWTP is a challenging problem. To cope with the issue, a bi-level optimal control strategy based on similarity clustering (BLOC-SC) for WWTP with GHG emissions is proposed. First, a bi-level optimization (BLO) model for WWTP is established based on the key process variables. Then, the model can describe the relationship among water quality, operating costs, and GHG emissions. Second, a multi-task optimization algorithm, based on similarity clustering, is designed to solve the BLO problem. Then, the algorithm can save computing resources and quickly solve the BLO problem to obtain the optimal set values for WWTP. Third, a fuzzy neural network controller is proposed to achieve accurate tracking of optimal set values. Finally, the simulation results, based on benchmark simulation model 2-GHG, indicate that BLOC-SC can achieve energy saving and emission reduction in WWTP.