Multi-objective optimization of steam system based on GPU acceleration

Abstract

The steam system is an important part of the utility systems in process industry. The energy consumption and operation cost of the existing plant were increased due to the inefficient configuration of the steam system. Meanwhile, the fossil fuels such as coal and oil were used to produce steam for the process industry, and the poisonous gases released from the burning process caused a lot of damage to the environments. Therefore, it is of great practical significance to reduce the operation cost and pollutant emissions simultaneously. This paper proposes an evolutionary multi-objective optimization (EMOO) algorithm to deal with this problems. But because of the complexity, higher dimension and rigid constraint conditions of the process industry, the computation time of EMOO algorithm can not meet the requirements of real-time optimization. Thus, Graphics Processing Unit (GPU) computing, which was running on the CUDA platform was introduced to shorten the running time of the algorithm. A constraint handling mechanism was presented to improve the performance of the algorithm. The case study indicates that the proposed GPU-based EMOO algorithm can obtain the Pareto optimal solution of the steam system in a minute-level time.