从智能优化的角度而言，针对性研究一般类型MOPOP的成果很少，仅有张仁

From the perspective of intelligent optimization, the results of targeted research on general types of MOPOP are few. Only Zhang Renchong et al. [26] designed MOPOP with adaptive sample allocation strategy based on MC random simulation for MOPOP under the opportunity constraint. The optimization algorithm (MOIOA) solves its obvious advantages in efficiency, but its evolution ability and noise suppression effect still need to be improved. In fact, MOPOP has been widely used in specific engineering optimization design, mainly focusing on the use of intelligent optimization algorithms in static sampling to solve, but the efficiency is low and the calculation overhead is large, which can not meet the actual needs of engineering applications and is difficult to promote. For example, literature [1-5] establishes a MOPOP model for airborne breakthrough decision-making, reservoir resource scheduling and other issues, and the weighted objective function is transformed into a single-objective probability optimization model, which is then obtained by means of neural networks, random (or fuzzy) simulation, and compromise algorithms Single objective improved genetic algorithm solution; many scholars [6-8] aimed at engineering optimization of the MOPOP model of automobile charging station planning, with the help of membership function, a single objective planning model was obtained by weighted form, using the improved single objective bat algorithm, discrete (Or continuous) particle swarm optimization. For the study of multi-objective intelligent optimization algorithms to solve MOPOP, literature [9-10] uses fuzzy simulation or random simulation, Latin hypercube sampling to suppress noise, and then uses the traditional fast non-dominated sorting genetic algorithm (NSGA-II) to solve uncertain Industrial grinding processing of parameters, optimal load reduction of power grid; literature [11-12] for the problem of cooperative scheduling of service resources, etc., using random simulation, BP neural network to suppress noise, using multi-objective particle swarm algorithm or multi-objective difference algorithm to solve . In the research of solving the deterministic transformation model, the literature [13-14] establishes an uncertain multi-objective programming model for multi-water source joint scheduling and other problems, and transforms the model into an analytical single-objective optimization model through complex transformation and linear weighting . In addition, for the optimization of wind and fire joint scheduling described as MOPOP, the literature [15-16] uses the dual interior point method, the normal boundary crossing method, and the hybrid interactive fuzzy programming method to solve, and selects the compromise solution through the sequential preference approximate ideal solution technology .

From the point of view of intelligent optimization, the results of targeted research on the general type of MOPOP are very few, only Zhang Renchong and so on, based on THE OPPORTUNITy constraints of MOPOP, based on MC random simulation, designed with adaptive sample allocation strategy of multi-target immunooptimization algorithm (MOIOA) solution, its efficiency advantages are obvious, but the evolutionary ability, noise suppression effect still needs to be improved. In fact, MOPOP has been widely used in the specific engineering optimization design, mainly focusing on the use of intelligent optimization algorithms in static sampling to solve, but the efficiency is low, the computing overhead is large, can not meet the actual needs of engineering applications, difficult to promote. For example, the literature, for such issues as airborne breakthrough point decision-making, reservoir resource scheduling, established MOPOP model, weighted target function into a single-target probability optimization model, and then obtained a single-target improved genetic algorithm with the help of neural network, random (or fuzzy) simulation, compromise algorithm; The algorithm for discrete (or continuous) particle groups is solved. For the study of multi-target intelligent optimization algorithm to solve MOPOP, the literature uses fuzzy simulation or random simulation, Latin super cubic sampling to suppress noise, and then uses the traditional fast non-dominant sequencing genetic algorithm (NSGA-II) to solve the problem of industrial grinding processing with uncertain parameters, optimal load reduction of the power grid; The multi-target particle group algorithm or multi-target differential algorithm are used to solve the problem. In the study of deterministic conversion model solving, the literature, 13-14, establishes an uncertain multi-target planning model for the problems of multi-water joint scheduling, and transforms the model into a single-target optimization model with analytical method through complex transformation and linear weighting. In addition, in view of the problems such as the optimization of wind-fire joint scheduling described as MOPOP, the literature, using the method of coupling inner point method, cross-crossing of common line boundary, and mixed interaction fuzzy planning method, is solved by the sequential preference approximate ideal solution technique.

From the point of view of intelligent optimization, there are few results of targeted research on general types of mopop, only Zhang renchong et al. [26] designed a multi-objective immune optimization algorithm (moioa) with adaptive sample allocation strategy based on MC random simulation for mopop under chance constraints. Its efficiency advantage is obvious, but the evolution ability and noise suppression effect still need to be improved. In fact, mopop has been widely used in the specific engineering optimization design, mainly focusing on the use of intelligent optimization algorithm in the static sampling, but the efficiency is low, the calculation cost is large, can not meet the actual needs of engineering applications, it is difficult to promote. For example, in reference [1-5], mopop model is established for the decision-making of air drop breakthrough point, reservoir resource scheduling and other problems. The weighted objective function is transformed into a single objective probability optimization model, and then a single objective improved genetic algorithm is obtained by means of neural network, stochastic (or fuzzy) simulation and compromise algorithm. Many scholars [6-8] mopop model for engineering optimization such as vehicle charging station planning, With the help of membership function, the single objective programming model is obtained by weighted form, and solved by improved single objective bat algorithm and discrete (or continuous) particle swarm optimization algorithm. For the study of solving mopop with multi-objective intelligent optimization algorithm, in reference [9-10], fuzzy simulation or random simulation and Latin hypercube sampling are used to suppress noise, and then the traditional fast non dominated sorting genetic algorithm (NSGA-II) is used to solve the problem of industrial grinding with uncertain parameters and optimal load reduction of power grid; in reference [11-12], the collaborative scheduling of service resources and other problems are solved Stochastic simulation and BP neural network are used to suppress noise, and multi-objective particle swarm optimization algorithm or multi-objective difference algorithm are used to solve the problem. In the research on the solution of the deterministic transformation model, literature [13-14] established the uncertain multi-objective programming model for the joint operation of multiple water sources, and transformed the model into a single objective optimization model with analytical formula through complex transformation and linear weighting. In addition, for the optimization of the combined scheduling of air and fire described as mopop, literature [15-16] uses dual interior point method, normal boundary crossing method, hybrid interactive fuzzy programming method to solve the problem, and selects the compromise solution through the order preference approximate ideal solution technology.<br>