针对原油调度过程存在的资源规模庞大、约束条件复杂、多时间尺度决策衔接困难等问题,提出一种基于多时间尺度协同的进化算法(MTCEA)。首先,根据炼油企业的规模结构和实际需求,建立了一种大规模多时间尺度原油调度优化模型,该模型由面...针对原油调度过程存在的资源规模庞大、约束条件复杂、多时间尺度决策衔接困难等问题,提出一种基于多时间尺度协同的进化算法(MTCEA)。首先,根据炼油企业的规模结构和实际需求,建立了一种大规模多时间尺度原油调度优化模型,该模型由面向资源的中长期调度模型和面向操作的短期调度模型构成,通过引入原油资源动态分组策略,实现原油资源的合理配置,以满足不同的调度规模、多时间尺度的特征和精细化生产的要求;其次,为促进不同时间尺度调度决策的融合衔接,设计基于多时间尺度协同的进化算法,并针对不同时间尺度调度模型中的连续决策变量构造子问题进行求解,以实现不同时间尺度调度决策之间的协同优化;最后,在3个实际工业案例进行了算法性能验证。结果表明,与3种具有代表性的大规模进化优化算法(即竞争性粒子群优化算法(CSO)、基于多轨迹搜索的自适应差分进化算法(SaDE-MMTS)和基于混合模型的进化策略(MMES))以及3种高性能混合整数非线性规划(MINLP)数学求解器(即ANTIGONE(Algorithms for coNTinuous/Integer Global Optimization of Nonlinear Equations)、SCIP(Solving Constraint Integer Programs)和SHOT(Supporting Hyperplane Optimization Toolkit))相比,MTCEA的求解最优性指标和稳定性指标分别提高了30%和25%以上。这些显著的性能提升验证了MTCEA在大规模多时间尺度原油调度决策中的实际应用价值和优势。展开更多
By integrating the cooperative approach with the fast annealing coevolutionary algorithm (FAEA), a so-called cooperative fast annealing coevolutionary algorithm (CFACA) is presented in this paper for the purpose of so...By integrating the cooperative approach with the fast annealing coevolutionary algorithm (FAEA), a so-called cooperative fast annealing coevolutionary algorithm (CFACA) is presented in this paper for the purpose of solving high-dimensional problems. After the partition of the search space in CFACA, each smaller one is then searched by a separate FAEA. The fitness function is evaluated by combining sub-solutions found by each of the FAEAs. It demonstrates that the CFACA outperforms the FAEA in the domain of function optimization, especially in terms of convergence rate. The current algorithm is also applied to a real optimization problem of protein motif extraction. And a satisfactory result has been obtained with the accuracy of prediction achieving 67.0%, which is in agreement with the result in the PROSITE database.展开更多
文摘针对原油调度过程存在的资源规模庞大、约束条件复杂、多时间尺度决策衔接困难等问题,提出一种基于多时间尺度协同的进化算法(MTCEA)。首先,根据炼油企业的规模结构和实际需求,建立了一种大规模多时间尺度原油调度优化模型,该模型由面向资源的中长期调度模型和面向操作的短期调度模型构成,通过引入原油资源动态分组策略,实现原油资源的合理配置,以满足不同的调度规模、多时间尺度的特征和精细化生产的要求;其次,为促进不同时间尺度调度决策的融合衔接,设计基于多时间尺度协同的进化算法,并针对不同时间尺度调度模型中的连续决策变量构造子问题进行求解,以实现不同时间尺度调度决策之间的协同优化;最后,在3个实际工业案例进行了算法性能验证。结果表明,与3种具有代表性的大规模进化优化算法(即竞争性粒子群优化算法(CSO)、基于多轨迹搜索的自适应差分进化算法(SaDE-MMTS)和基于混合模型的进化策略(MMES))以及3种高性能混合整数非线性规划(MINLP)数学求解器(即ANTIGONE(Algorithms for coNTinuous/Integer Global Optimization of Nonlinear Equations)、SCIP(Solving Constraint Integer Programs)和SHOT(Supporting Hyperplane Optimization Toolkit))相比,MTCEA的求解最优性指标和稳定性指标分别提高了30%和25%以上。这些显著的性能提升验证了MTCEA在大规模多时间尺度原油调度决策中的实际应用价值和优势。
基金the National Natural Science Foundation of China (Grant Nos. 20475068 and 20575082)the Natural Science Foundation of Guangdong Province (Grant No. 031577)the Scientific Technology Project of Guangdong Province (Grant No. 2005B30101003)
文摘By integrating the cooperative approach with the fast annealing coevolutionary algorithm (FAEA), a so-called cooperative fast annealing coevolutionary algorithm (CFACA) is presented in this paper for the purpose of solving high-dimensional problems. After the partition of the search space in CFACA, each smaller one is then searched by a separate FAEA. The fitness function is evaluated by combining sub-solutions found by each of the FAEAs. It demonstrates that the CFACA outperforms the FAEA in the domain of function optimization, especially in terms of convergence rate. The current algorithm is also applied to a real optimization problem of protein motif extraction. And a satisfactory result has been obtained with the accuracy of prediction achieving 67.0%, which is in agreement with the result in the PROSITE database.
