Application of stochastic evolutionary optimization techniques to environmental processes

Abstract Optimization studies can lead to considerable benefits to environmental engineering systems in terms of efficiency improvement, energy reduction, and pollution control. The environmental processes usually exhibit nonlinear dynamics and are associated with uncertainty in data. Design, modeling, and optimization studies are more and more pursued to understand and improve the performance of environmental processes. A variety of optimization approaches are used for the solution of environmental problems in the areas of air pollution, solid, liquid and industrial waste management, and energy management. Conventional optimization methods may not be effective in solving complex environmental problems. This chapter mainly focuses on various stochastic evolutionary and artificial intelligence–based strategies for optimization of environmental processes. Fixed-bed reactors with naturally attached biofilms are increasingly used for anaerobic treatment of industry wastewaters. The complex nature of biological reactions in biofilm reactors often poses difficulty in analyzing and optimizing the biofilm reactors. The wastewater treatment processes in biofilm reactors serve as useful case studies for design and application of advanced optimization algorithms. In this study, various optimization strategies based on ant colony optimization, tabu search, and artificial neural networks coupled with rigorous mathematical models are designed and applied to different industry wastewater treatment processes in fixed-bed biofilm reactors. The results demonstrate the usefulness of stochastic global optimization methods for solving complex optimization problems concerning to wastewater treatment processes.