基于改进模拟退火遗传算法的高速公路服务区自洽能源系统高能效优化

Optimization of High Energy Efficiency for Self-Consistent Energy System in Highway Service Area via Simulated Annealing Algorithm-Genetic Algorithm

针对高速公路自洽能源系统高能效优化的问题,基于改进模拟退火遗传算法(SA-GA),提出了一种综合考虑经济目标和环保目标的自洽能源系统高能效优化运行策略。首先根据高速公路服务区自洽能源系统中各电力单元特性,建立一种综合考虑系统经济性和环保性的能效目标函数;其次根据高速公路服务区自洽能源系统的分类,建立了不同类型系统对应的约束条件;为避免遗传算法易陷入局部最优的缺陷,引入模拟退火算法,对改进后的SA-GA算法采用降温函数,寻找全局最优解;利用新疆某高速公路服务区自洽能源系统发电和负荷数据,并在传统服务区负荷的基础上进一步考虑新能源汽车充电站的影响。测试函数测试结果表明:SA-GA算法在求解速度和稳定性方面有明显提升,改进SA-GA算法对夏季、冬季典型日能效优化的结果,相较于遗传算法,在寻优精度提升约为20.33%。

To solve the problem of high-efficiency optimization of highway self-consistent energy system(SCES)by utilizing an improved simulated annealing genetic algorithm(SA-GA)with a comprehensive consideration on the economic and environmental targets based on an energy-efficient optimization strategy for SCES.Firstly,an objective function is established to consider the energy efficiency from economic and environmental perspectives,taking into account the characteristics of each power unit within the SCES in the highway service area.Secondly,constraints corresponding to different types of systems are established based on the classification of SCES in highway service areas.The simulated annealing algorithm is incorporated into the solution of the objective function to avoid the defect that the genetic algorithm tends to fall into the local optimum.The improved SA-GA algorithm incorporates a cooling function,allowing for the accurate identification of the global optimal solution.By leveraging the generation and load data of the SCES in the highway service area in Xinjiang,China,along with considering the influence of new energy vehicle charging stations in addition to the load from traditional service areas.Finally,the test results show that the evaluation of various test functions demonstrates that the SA-GA algorithm significantly improves both solution speed and stability.The SA-GA algorithm is employed to compute energy efficiency optimization results for typical days in summer and winter,to obtain an effective operation strategy for the service area.Simulation results demonstrate that the proposed SA-GA algorithm improves optimization accuracy by 20.33%in comparison to the genetic algorithm.