摘要
粒子群优化算法在求解含有多维约束的多目标优化问题时,存在易陷入局部最优解或者全局收敛不唯一,从而造成优化结果的多样性。针对该问题,提出运用数据包络分析算法对采用改进粒子群求解的水火电多目标问题的优化结果进行效益评估,选取有效的决策单元,同时将多个有效单元进行排序,为决策者提供利用优化目标和超效率DEA值双重准则来选取决策方案。实例仿真证明该方法可有效减少多个目标追求下的决策盲目性,为决策者提供了决策选择。
In solving multi-objective optimization problems with multi-dimensional constraints,the particle swarm optimization(PSO) is easy to fall into local optimal solution or global convergence being not unique,that makes the optimization resultbeing diverse. Aiming at this problem,the data envelopment analysis( DEA) algorithm is proposed to evaluate the optimizationresult of improved PSO for hydro-thermal power system scheduling,then the effective scheduling schemes are selected andsorted,and finally the scheduling scheme is selected by decision makers based on the dual criteria of optimizing objective andsuper-efficiency DEA value. The example simulation proves that the method can effectively reduce the blindness of decision-making under multiple targets and provide final choice for decision-makers.
引文
[1]苏鹏,刘天琪,赵国波,等.基于改进粒子群算法的节能调度下多目标负荷最优分配[J].电网技术,2009,33(5):48-53.
[2]张晓花,朱昌平,陈星莺,等.计及节能减排的梯级水火电优化调度研究[J].华东电力,2012,40(7):1104-1106.
[3]张志刚,马光文.基于NSGA-Ⅱ算法的多目标水火电站群优化调度模型研究[J].水力发电学报,2010,29(1):213-218.
[4]刘文静,付传雄,吴杰康,等.基于节能环保的水火电多目标优化调度研究[J].水力发电,2014,40(2):83-87.
[5]魏权龄.评价相对有效性的数据包络分析模型[M].北京:中国人民大学出版社,2012.
[6]杜栋,庞庆华等.现代综合评价方法与案例精选[M].北京:清华大学出版社,2008.
[7]ANERSEN P,PETERSEN N C.A procedure for ranking efficient unit in data envelopmentanalysis[J].Management Science,1993(10):1261-1264.
[8]李盟.基于超效率DEA模型的电力行业环境绩效评价研究[D].镇江:江苏大学,2017.