摘要
把Pareto解集应用到电梯群控系统多目标权重值确定的研究中,采用随机权重法,一次生成多组不同权重值,并对各权重值下生成的派梯方案求取Pareto最优解,能够一次得到多组不同最优派梯方案,为研究人员决策提供了更多直观的数据;根据优缺点互补特性,将梯度下降算子加入克隆选择算法,加快其后期收敛速度,以随机层间均衡交通流为乘客流,将混合算法与克隆选择算法应用于电梯群控系统中寻找节能策略,混合算法一定程度上优于克隆选择算法。
The pareto solution set is applied to the research of choosing weight values, and the random weight method is used. Several groups of different weight values is obtained, then the optimal Pareto solution is gained according to the elevator dispatching strategies generated by different weight values. The algorithm can provide several groups of different and optimal elevator dispatching strategies, and provide more useful data for researchers to refer. According to the advantages and disadvantages of each algorithm, gradient descent algorithm is joined with the clonal selection algorithm. The convergence rate is speeded up in later period, random balanced traffic flow between layers is defined as passengers flow, and the hybrid algorithm and the clonal selection algorithm are combined and applied to elevator group control system to find the saving energy policy. To some extent, the hybrid algorithm has much more superiority than the clonal selection algorithm.
出处
《数据采集与处理》
CSCD
北大核心
2012年第3期353-357,共5页
Journal of Data Acquisition and Processing
基金
河南省国际科技合作(114300510029)资助项目
关键词
多目标优化
电梯群控
克隆选择算法
梯度下降算法
PARETO解集
multi-objective optimization
elevator group control
clonal selection algorithm
gradient descent algorithm
Pareto solution set
