Investigation and improvement of intelligent evolutionary algorithms for the energy cost optimization of an industry crude oil pipeline system

Based on the simulation predication of an industry crude oil pipeline system, a novel energy cost optimization model combining discrete grid points and a penalty factor is proposed. Combined with the optimization model, the optimization performance of four representative intelligent evolutionary algorithms is compared and analysed. The comparative results indicate that the improved differential evolution (DE) algorithm obtains a lower energy cost and exhibits better optimization performance than the other three representative algorithms. Compared with the lowest energy cost of the actual field, an energy cost saving of 4.62% can be made. To further improve the performance of intelligent evolutionary algorithms for energy cost optimization, hybrid coding and selection schemes of the algorithms are researched. The hybrid coded DE algorithms can more easily obtain stable optimal energy costs. The modified genetic algorithm with a greedy selection scheme exhibits excellent optimization performance, and can obtain the optimal energy cost more quickly than DE.