89 results about "Job shop scheduling problem" patented technology

The invention discloses a flexible job shop scheduling method based on a graph neural network and deep reinforcement learning, and relates to the technical field of flexible job shop scheduling. The method at least comprises the following steps: S1, firstly, carrying out Markov Decision Process (MDP) on a flexible job shop scheduling problem, namely, FJSP, and initializing a scheduling state; and S2, representing a complex relationship between a job and a machine by using a heterogeneity graph, and effectively mapping different entities (the job, the machine, the operation and the like) of the problem and the relationship between the different entities into a graph structure, wherein the different entities (the job, the machine, the operation and the like) of the problem and the relationship between the different entities (the job, the machine, the operation and the like) of the problem are represented by the heterogeneity graph. According to the method, the graph neural network based on the meta-relationships is provided, different graph convolution modes are innovatively adopted for different meta-relationships to extract features, original semantic information is reserved, the global information capturing capability is enhanced, and a reinforcement learning agent is more accurate when making a scheduling decision.

The invention provides a workshop scheduling method and system fusing a decision tree and a genetic algorithm. The method comprises the following steps: firstly, collecting operation process and machine information through an ERP system and extracting related features; generating a scheduling scheme by using historical orders of an ERP system or manually added orders, and constructing a training set training decision tree to accurately judge machine allocation conflicts; constructing a multi-target flexible job shop scheduling model, and constructing a target function based on a hierarchical Pareto dominance relationship; and secondly, realizing job-shop scheduling scheme coding by adopting double-layer chromosome coding, carrying out selection, intersection and mutation operations in combination with a genetic algorithm, carrying out conflict detection and repair by utilizing a decision tree, solving an objective function, continuously iterating until a convergence condition is met, and outputting a Pareto optimal solution. According to the workshop scheduling method, the scheduling efficiency and feasibility are improved by establishing a data model of a multi-target flexible job workshop scheduling problem and through dynamic conflict detection, hierarchical multi-target optimization and a closed-loop feedback mechanism.

The invention discloses a dynamic scheduling optimization method based on deep reinforcement learning and a heterogeneous graph neural network. The method comprises the following steps: firstly, converting a flexible job shop scheduling problem into a Markov decision process, and setting a state, an action, a state transition and a reward function; then constructing a basic heterogeneous graph and an enhanced heterogeneous graph, and defining the types and the number of nodes and edges and a directed relationship between the edges; performing three-stage feature embedding by adopting a heterogeneous graph attention network to obtain machine node embedding, operation node embedding, distribution instance node embedding and global state features; and inputting an action state vector formed after each feature is processed, optimizing a decision network according to a reward function, updating parameters to obtain a flexible job shop scheduling model, and completing FJSP solving. The method can effectively consider the flexible job shop scheduling problem under transport time and machine reachability constraints, can also process scheduling problems of different scales, has good generalization ability, and shows excellent performance in large-scale application.

The invention discloses a multi-target flexible workshop scheduling method based on a double-attention network and deep reinforcement learning. The method comprises the following steps: 1, acquiring basic information in flexible job shop scheduling; 2, constructing a workshop scheduling mathematical model based on a target function and constraint conditions; 3, formalizing a flexible job shop scheduling problem into a Markov decision process, and defining state parameters, action parameters, state transition parameters and reward parameters in a deep reinforcement learning method; 4, constructing a double-attention network, and extracting feature information of procedures and machines; and 5, obtaining an optimal scheduling scheme by using a deep reinforcement learning algorithm. According to the invention, the scheduling scheme with shortest time consumption and minimum machine load can be obtained, direct learning from original data to decision can be realized, dependence on expert knowledge is reduced, production scheduling time is reduced, workshop generation efficiency is improved, and decision basis is provided for actual production scheduling.

The invention relates to a fuzzy flexible job shop scheduling method, a fuzzy flexible job shop scheduling system, fuzzy flexible job shop scheduling equipment and a storage medium, which are applied to a scene in which scheduling is required when disturbance occurs in a job shop operation process. Parameters of the genetic algorithm are initialized according to the real-time resource state of the current production environment, wherein the parameters comprise the maximum number of iterations; an initial population is generated according to the parameters, a weight vector is initialized, an external file is created, the external file is used for storing an optimal solution or an optimal solution in the algorithm, and the optimal solution is a solution capable of increasing population diversity; selecting an operation individual in the population and the external archive; and performing iterative optimization on the population based on the operation individuals until the maximum number of iterations is reached, outputting a non-dominated solution set, and after each iterative optimization, updating the external archive and the weight vector based on the generated non-dominated solution so as to optimize the fuzzy flexible job shop scheduling problem under the urgent order insertion and improve the production efficiency and the response flexibility.

The invention discloses a multi-rotating-speed flexible job shop scheduling method applied to double-resource constraint, and the method comprises the steps: taking the maximum completion time and minimum total energy consumption of a minimum machine as target functions, and constructing a flexible job shop scheduling model considering the rotating speed energy consumption of the machine and the production demands of a fine process; a machine speed gear constraint, a fine process constraint, a process sequence constraint, a completion time constraint, a machine processing constraint and a worker operation constraint are established as constraint conditions of the model; the flexible job shop scheduling problem is solved by adopting an improved artificial bee colony algorithm, bee colony search guided by excellent genes is adopted in bee learning operation in the improved artificial bee colony algorithm, and nectar source optimization is carried out based on the searched excellent genes; the following bee operation adopts a neighborhood structure which considers machine speed change and balances the working time of workers to carry out dynamic neighborhood search so as to optimize a nectar source. The effectiveness of the improved strategy is verified through experiments, and the superiority is verified through comparison of different algorithms on expansion standard examples.

The invention discloses a reconfigurable flexible job shop scheduling optimization method with secondary clamping constraint, and relates to the technical field of intelligent manufacturing and production optimization. The method comprises the following steps of: 1) establishing a mixed integer linear programming model considering a reconfigurable flexible job shop scheduling problem of secondary clamping by taking minimization of maximum completion time and minimum number of chemical workers as targets; 2) designing a three-segment coding mode and a decoding mode corresponding to the mixed integer linear programming model based on process sorting, machine selection and worker selection; and 3) based on the three-segment coding mode and the decoding mode, adopting an improved multi-target genetic algorithm to solve an optimal scheduling scheme of the mixed integer linear programming model. According to the method, processing machine selection, auxiliary module selection, processing sequence sorting and secondary clamping worker selection of a manufacturing workshop can be considered at the same time, the workshop production efficiency is improved, and the method has the advantages of being good in model performance, small in result fluctuation and high in stability.

The invention provides a distributed heterogeneous flexible job shop scheduling optimization method based on solution space conversion, which aims to solve the problem of energy-saving distributed heterogeneous flexible job shop scheduling, and comprises the following steps of: 1, preprocessing related data of factories and workpieces; 2, constructing a distributed heterogeneous flexible workshop scheduling problem model; 3, presetting value method related parameters; 4, the average machining time of each workpiece is calculated; step 5, constructing a workpiece group through a hierarchical clustering method of optimal leaf order constraint; step 6, constructing an initial scheme according to the workpiece group; and 7, solving the model through a distributed heterogeneous flexible job shop scheduling optimization method based on solution space conversion to obtain an optimal scheduling scheme. According to the method, the distributed heterogeneous flexible job shop scheduling problem can be quickly solved, a scheme of minimum maximum completion time and total energy consumption is provided for actual production scheduling, and the production efficiency and the resource utilization rate are improved.

The invention discloses a supply chain process job scheduling method and system based on a hybrid expert model, and the method comprises the steps: obtaining a target job shop scheduling problem, and selecting a target gated network from an expert selection gated network based on static similarity and a gated network based on weight learning according to a preset threshold value; when the target gated network is the gated network based on weight learning, constructing a scheduling graph according to the target job shop scheduling problem, and processing the scheduling graph based on a plurality of preset expert networks and the trained gated network based on weight learning to obtain a first target strategy; and when the target gated network is an expert selection gated network based on static similarity, selecting a target expert network from a plurality of preset expert networks according to the target job shop scheduling problem, and processing the target job shop scheduling problem through the target expert network to obtain a second target strategy. According to the invention, the job shop scheduling problem can be accurately processed.

The invention discloses a multi-target flexible job shop scheduling method based on a graph network and reinforcement learning, which can effectively characterize key features of a production model by using features of a double-graph attention network deep mining process and a machine. The depth characterization capability can not only improve the performance of the model, but also enhance the adaptability of the model to different production models, so that the model can flexibly cope with various unseen production scenes, and shows excellent generalization performance. Besides, in the field of multi-objective optimization, how to balance the relationship between different objectives is an important and challenging problem, so that the model can find an optimal balance point among the multiple objectives by distributing different weights for different optimization objectives, and the method not only can improve the solving efficiency, but also can improve the optimal balance point among the multiple objectives. And moreover, a high-quality Pareto frontier solution set can be generated, and an effective solution is provided for a multi-target flexible job shop scheduling problem.

The invention relates to a flexible job shop scheduling method considering grouping characteristics, belongs to the technical field of flexible job shop production scheduling, solves the problem of poor comparison effect between a scheduling scheme and an actual processing situation in the prior art, and comprises the following steps: S1, determining a job switching type and executing grouping classification to obtain a grouping classification result; s2, determining decision variables and basic parameters considering grouping characteristics according to the obtained job switching types and grouping classification results; s3, constructing an objective function considering grouping characteristics; s4, establishing a flexible job-shop scheduling problem constraint condition considering the grouping characteristics, and obtaining a flexible job-shop scheduling mathematical model considering the grouping characteristics; s5, solving the flexible job shop scheduling mathematical model considering the grouping characteristics by using an improved genetic algorithm to obtain a scheduling scheme with the optimal fitness; and S6, outputting the obtained scheduling scheme with the optimal fitness as an optimal scheme.

The invention discloses a flexible job shop scheduling method and system based on an improved genetic algorithm, and the method comprises the steps: 1, problem modeling: defining parameters and constraint conditions of a flexible job shop scheduling problem, the parameters comprising a machine set, a workpiece set, process information, processing time and decision variables, 2, improved genetic algorithm design, and step 3, executing the scheduling scheme. According to the method, the initial population generation strategy and the multi-target fitness function of the genetic algorithm are improved, so that the global search capability and the convergence speed are improved, the maximum completion time is shortened, the target is optimized in combination with machine load balancing and cost, the resource utilization rate is improved, and the production cost is reduced; the system has flexibility and expansibility, can adapt to flexible workshops of different scales, and realizes real-time adjustment of a scheduling scheme through dynamic monitoring.

The invention relates to the technical field of industrial manufacturing, and discloses a flexible workshop scheduling optimization method based on deep reinforcement learning, and the method comprises the following steps: constructing a graph neural network model, and carrying out the modeling of a workshop operation process of a flexible workshop scheduling problem; the flexible job-shop scheduling problem is converted into a Markov decision process, a deep reinforcement learning algorithm is used for dynamic decision making, and the Markov decision process comprises a state space, an action space, a reward function and a state transfer function; and restraining the action space of the deep reinforcement learning algorithm in combination with a heuristic scheduling rule. The flexible workshop scheduling is optimized through the deep reinforcement learning algorithm, and the scheduling strategy can be dynamically adjusted in real time according to the actual production state and task requirements of the workshop. Compared with a traditional scheduling method, the method does not need to preset a fixed scheduling rule, autonomously learns and decides through the intelligent agent, and adapts to a complex and changeable production environment.

The present invention discloses a method for solving the job shop scheduling problem based on the NSGA-III algorithm. First, a multi-objective flexible job shop scheduling problem model is constructed. The method includes the following steps: describing the multi-objective flexible job shop scheduling problem and constructing the model; generating a set of evenly distributed reference points; encoding the parent population P using an equal-length three-segment encoding method; and t The individuals in the temporary population R are subjected to crossover and mutation operations based on adaptive operators. t An approximate dominant sorting based on the reference point is performed to determine whether the termination condition is met. Finally, a weighted method is used to select a solution from the optimal solution set as the optimal compromise solution and output it. The present invention solves the problem in the prior art that different rotational speeds affect the machining effect of the machine.

The invention discloses a dynamic distributed flexible job shop scheduling method based on hierarchical multi-agent deep reinforcement learning, and belongs to the technical field of distributed shop scheduling. Comprising the following steps: determining an initial state of a to-be-solved dynamic distributed flexible workshop scheduling problem; when a new workpiece arrives, constructing a global heterogeneous graph to represent a relationship between the new workpiece and the FMU; the upper-layer intelligent agent extracts features of a new workpiece and FMU through a process-level attention module, a workpiece-level attention module and FMU coding by using a hierarchical graph attention architecture, inputs the features into a decision network to obtain the probability of FMU action, and selects the FMU with the maximum probability; new workpieces are distributed to the designated FMU, and the original features of the FMU and the machine and process features in the FMU are updated; and constructing a bottom layer heterogeneous graph, predicting feasible actions by using a heterogeneous graph neural network, and selecting proper working procedures and machine combinations. According to the method, the problems of continuous arrival of dynamic workpieces, cooperative scheduling of multiple flexible manufacturing units and distributed workshop scheduling of real-time response can be efficiently solved.

The invention relates to a factory job shop scheduling control optimization method and device, equipment and a medium, and the method comprises the steps: classifying workpieces irrelevant to all MPBPO sets into a first workpiece set, classifying the workpieces corresponding to each MPBPO set into one set to determine a second workpiece set, independently generating job task sorting sub-chromosome segments, and generating a job task sorting sub-chromosome segment; corresponding operation machine numbers and operation time are respectively filled into corresponding gene positions of the operation machine sub-chromosomes and the operation time sub-chromosomes, and the operation task sorting sub-chromosomes, the operation machine sub-chromosomes and the operation time sub-chromosomes are combined to obtain initial chromosomes so as to generate initial population individuals; genetic manipulation is carried out on the initial population individuals, and population individuals with the high fitness and the number of the population individuals being the population scale are selected as a next-generation initial population; and repeatedly executing, and outputting the production scheduling scheme with the optimal earliest completion time. According to the method, algorithm premature convergence can be avoided in a generalized job-shop scheduling problem with a forced parallel batch processing procedure.

The invention discloses an adaptive multi-group interaction PSO flexible workshop AGVs integrated scheduling optimization method, which comprises the steps of dividing three functional populations, namely elite, exploration and development, and realizing global exploration and local mining of a solution space through multi-group interaction. A task matrix and a resource matrix are constructed to represent the correlation essence of the position of a task processing machine and AGVs transportation time, and a matrix updating mechanism based on local feature reconstruction and global trajectory avoidance is proposed and used for extracting an excellent solution gene mode and guiding search of a foreground area. The proposed method is verified on two standard data sets of FJSP and EX, and the result shows that the proposed method can effectively improve the scheduling solution quality, has relatively strong convergence capability and adaptability, has wide application potential in solving the AGVs scheduling problem of the complex flexible job shop, and has a wide application prospect. And efficient and feasible technical support can be provided for scheduling optimization of the intelligent manufacturing workshop.

The invention discloses a flexible job shop scheduling method considering fuzzy factors. The method comprises the following steps: constructing a flexible production process model with fuzzy features; initializing a differential evolution algorithm; defining a differential evolution algorithm as a Markov decision process; and strategy optimization is carried out by using deep reinforcement learning, and flexible job shop scheduling is realized. According to the method, the fuzzy set theory and the flexible job shop scheduling problem are combined, uncertain factors in the production process are represented by fuzzy numbers, scheduling imbalance caused by changes of production and processing parameters can be prevented, the anti-interference performance of a scheduling scheme is improved, an optimization algorithm can better cope with a complex and changeable flexible production environment, and the production efficiency is improved. And a more reasonable and effective production scheduling scheme is obtained. And deep reinforcement learning is introduced to learn the variation strategy and the variation rate, and the algorithm is guided to be optimized in a more promising direction, so that the optimization process is more efficient, the solution performance is stronger, the solution result distribution is more concentrated, and the solution quality is higher.

The invention provides a job shop scheduling method based on decomposition type multi-objective reinforcement learning, and solves the problems that multi-objective optimization is difficult to balance, the strategy is unstable and the optimization efficiency is low in a complex scheduling environment. According to the method, weight configuration is dynamically adjusted, target values of candidate weights are predicted by using a hyperbolic tangent model, model complexity is reduced in combination with regularization, a comprehensive evaluation index is introduced to screen a solution set, and adaptive learning of features and stable updating of a strategy are realized. By optimizing the weight selection and strategy updating mechanism, a plurality of conflict targets can be efficiently balanced, the efficiency and accuracy of scheduling decision making are improved, the energy consumption is reduced, and the production efficiency is improved. In the industrial automation and intelligent manufacturing process, the multi-target job shop scheduling problem can be effectively solved, and technical support is provided for production optimization.

The invention discloses a multi-agent dynamic flexible job shop scheduling solving method based on a D3QN network, and belongs to the technical field of agent deep reinforcement learning and production scheduling. According to the method, the dynamic change of the machined workpiece and the machine can be monitored in real time, a real-time scheduling decision is given timely and efficiently according to different emergencies such as workpiece emergency insertion and machine damage, and the time cost and the resource cost of production are effectively reduced. The method comprises the steps that in the actual production process of a dynamic flexible workshop, machining information in the dynamic flexible workshop is obtained in real time, and the machining information comprises machining workpiece information and machining machine information; when it is determined that a rescheduling event occurs based on the processing information, a rescheduling strategy is generated according to the real-time states of workpieces and machines at the rescheduling point of the dynamic event based on the mathematical model of the dynamic flexible job shop scheduling problem, and rescheduling is executed until the production process is completed.

The invention discloses a multi-target-interval flexible job shop scheduling method and a related device, and relates to the technical field of shop scheduling, and the method comprises the steps: constructing a multi-target-interval flexible job shop scheduling problem model, the problem model comprises interval maximum completion time, interval machine total load, interval total energy consumption, constraint conditions and interval number correlation operation rules related to the multi-target interval flexible job shop scheduling problem; and based on the interval number correlation operation rule, solving the multi-target interval flexible job shop scheduling problem model by utilizing an interval chameleon group algorithm to obtain a global optimal scheduling solution, and realizing multi-target interval flexible job shop scheduling. According to the method, the problem that multi-objective optimization is difficult to carry out on interval flexible job shop scheduling in the prior art can be solved.

This invention discloses a method for solving the job shop scheduling problem based on the red deer algorithm, belonging to the field of shop scheduling. The method decodes the job shop schedule using a random key, explores and utilizes a balancing algorithm of roaring, fighting, and pairing operations, and uses the Euclidean distance to measure the distance between male and female deer to solve the job shop scheduling problem. This invention is the first to attempt to apply the red deer algorithm to the job shop scheduling problem. Compared with traditional mathematical programming methods, this method can obtain satisfactory scheduling solutions for large-scale scheduling problems in polynomial time, while maintaining low computational complexity and high robustness.

The invention belongs to the technical field of job shop scheduling, and particularly relates to a self-learning job shop scheduling method meeting waiting time constraint, which comprises the following steps: S0, constructing a job shop scheduling problem model with waiting time constraint; the method comprises the following steps: S1, acquiring job shop scheduling problem data, a configuration algorithm and operation parameters; s2, constructing chromosome individuals, generating chromosomes and initializing a population; s3, calculating the fitness value of each chromosome individual; s4, forming a new generation of population; s5, combining the fitness information of the current population, dynamically selecting a crossover rate Pc through a Q learning algorithm, and performing crossover operation on the population; s6, dynamically determining a mutation rate Pm in the same parameter combination space by using a Q learning algorithm, and performing mutation operation on the crossover progeny to generate an updated population; and S7, judging whether an iteration termination condition is met or not. According to the method, a feasible and near-optimal scheduling scheme can be efficiently generated on the premise of ensuring that the inter-process waiting time constraint is met.

The present invention discloses a flexible job scheduling method for cloud-based resources based on an improved chimp optimization algorithm, and the method comprises the following steps: (1) adjusting the convergence factor of the chimp algorithm and setting its position update strategy according to the chimp algorithm; (2) designing a cloud-based resource scheduling scheme according to the chimp algorithm obtained in step (1) to provide data reference. The present invention can solve the flexible job shop scheduling problem. The present invention provides a new initialization method combining GS, LS and random search, which improves the quality of the initial solution of the population and speeds up the convergence rate of the genetic algorithm. By comparing with the test results of other genetic algorithms in the prior art, the calculation results are further improved, and at the same time, the calculation time is shortened to a certain extent, verifying the feasibility and effectiveness of the proposed initialization method.

The invention provides a deep reinforcement learning job shop scheduling method based on customer agent multi-bidding, which solves the problem that a multi-agent job shop cannot be scheduled in the prior art, and comprises the following steps: modeling a multi-agent job shop scheduling problem; obtaining a client agent intelligent agent corresponding to the client agent and a job shop agent intelligent agent corresponding to the job shop, and obtaining a scheduling state of the job shop; obtaining feature representation of each process node, and outputting a process set participating in bidding in each round of bidding; obtaining the feature representation of each process node, and outputting a calibration decision sequence; and collecting a bidding process set of all client agents by the job shop agent to perform a calibration decision, and continuously repeating a bidding process until a final scheduling scheme is generated. According to the method, on the premise that the private preferences of all client agents can be well protected, a plurality of agents with personalized targets jointly participate in scheduling decision making, so that a scheduling scheme which can be accepted by all parties is formed.

The present application relates to the technical field of intelligent manufacturing production scheduling and combination optimization, in particular to a distributed flexible job shop scheduling method considering process dependency, comprising: initializing algorithm parameters, alternately using a heuristic method and a random method to generate an initial population; selecting a parent solution from the current population through an adaptive adjustment strategy, sequentially executing a crossover operator, a mutation operator and a local search on the parent solution, updating the population; calculating the current optimal solution of the current population, judging whether the termination time is reached, if yes, terminating evolution, outputting the current optimal solution and the maximum completion time, otherwise, continuing iteration. The present application solves the problems of existing solving methods, such as significant time consumption increase and search into local optimum when the scale of the distributed flexible job shop scheduling problem considering process dependency is expanded, and achieves the positive effects of reducing the maximum completion time and improving the search efficiency and solution quality of large-scale instances.

The present application relates to the technical field of intelligent manufacturing and industrial artificial intelligence, in particular to a man-machine cooperation flexible job shop scheduling method based on offline reinforcement learning, which firstly standardizes mathematical modeling of man-machine cooperation double-resource flexible job shop scheduling problem; constructs a heterogeneous scheduling graph containing three types of heterogeneous nodes of process, machine and worker; designs a multi-attention feature extractor; constructs a quantile alignment Actor-Critic offline reinforcement learning framework based on uncertainty control to complete robust offline policy training; and finally realizes end-to-end real-time scheduling decision through the trained model. The present application can complete model training without online environment interaction, has high solution accuracy, strong generalization ability, low deployment cost and high decision robustness, and is suitable for man-machine cooperation flexible production scene in the industrial 5.0 environment.

The invention proposes a multi-agent flexible job-shop scheduling method based on graph deep learning and evolutionary neural topology, and the method comprises the steps: firstly building a multi-agent flexible job-shop scheduling model, initializing a multi-agent flexible job-shop scheduling problem, then converting a mathematical model into a Markov decision process, constructing a heterogeneous graph model, and carrying out the optimization of the multi-agent flexible job-shop scheduling model. The multi-agent flexible job shop environment information is represented; secondly, state features of procedures and machines are extracted in a layered mode according to the information of the customer agency, wherein the state features comprise a node-level attention mechanism and a semantic-level attention mechanism; finally, constructing and training an actor-commentator model as a scheduling decision model; and solving the multi-agent flexible job shop scheduling problem by using the scheduling decision model to obtain a multi-agent flexible job shop scheduling scheme. According to the method, the limitation that an existing model only pays attention to global efficiency optimization is broken through, and the problems of high subjectivity, high trial and error cost, limited generalization ability and the like existing in artificial design of a neural network structure and hyper-parameters are solved.

This invention provides a dynamic flexible job shop scheduling method based on the Kepler optimization algorithm. Its main purpose is to solve the dynamic scheduling problem of flexible jobs shops, offering a solution to the uncertainty of events. The steps are as follows: 1. Modeling the job shop scheduling problem; 2. Presetting relevant parameters for the Kepler optimization algorithm; 3. Driving the Kepler optimization algorithm to solve for the scheduling scheme; 4. Dynamically rescheduling for sudden uncertain events to obtain a new production plan. This invention can fully utilize equipment, improve production efficiency, and provide a decision-making basis for actual production scheduling.

The invention belongs to the technical field of intelligent manufacturing and production scheduling, and particularly relates to a construction method and a scheduling method of a flexible job shop scheduling model based on a heterogeneous graph neural network and deep reinforcement learning. Constructing heterogeneous graph representation of a flexible job shop scheduling problem; constructing a deep reinforcement learning scheduling framework based on the heterogeneous graph representation; extracting machine node features by adopting a graph attention mechanism, and extracting process node features by adopting a heterogeneous graph Transform; designing a scale sensing module, and fusing problem scale information into node features; training a scheduling strategy model by adopting a near-end strategy optimization algorithm; and on-line scheduling decision making is carried out based on the trained model. According to the method, through heterogeneous graph representation and a scale perception mechanism, scheduling of different scales and dynamic disturbance scenes can be adapted through one-time training, and the generalization ability, the solving quality and the real-time performance of a scheduling strategy are remarkably improved.