Application optimization method of simulation technology in intelligent scheduling training
By building a multi-dimensional scheduling simulation model and adaptive strategy optimization, the problem that simulation technology cannot simulate complex factors is solved, and the authenticity and flexibility of scheduling training is improved, helping students to deal with changing scheduling tasks.
Patent Information
- Application Number
- CN202510504898.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-22
- Publication Date
- 2025-08-15
AI Technical Summary
Existing simulation technologies cannot fully simulate complex factors in reality, such as equipment failures and emergencies, which make it difficult for students to deal with in actual operations, with a single optimization strategy, and cannot flexibly respond to diversified and dynamically changing scheduling tasks, with poor results.
Build a multi-dimensional scheduling simulation model, combine dynamic strategy optimization and adaptive strategy evolution mechanism, introduce task priority, resource availability and environmental event trigger parameters, update strategies in real time, embed emergencies modeling, adopt multi-objective collaborative optimization method, assist in understanding scheduling behavior through visual modules, and generate personalized evaluation reports.
It realizes the real simulation of emergencies and environmental changes during the training process, improves students' response ability in a dynamic scheduling environment, adaptability and flexibility of scheduling strategies, and ensures the efficiency and rationality of scheduling decisions.
Smart Images
Figure CN120494646A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of simulation technology application optimization, and in particular to a method for optimizing the application of simulation technology in intelligent scheduling training. Background Art
[0002] The application of simulation technology in intelligent scheduling training helps trainees become familiar with and master scheduling strategies by simulating different scheduling scenarios and problems. The basic structure of the system consists of four core components: a system model, a data input module, a simulation execution engine, and a result feedback and analysis module. First, the system model uses mathematical modeling to describe the relationship between scheduling tasks and resources and models various constraints in the scheduling process. Trainees provide task information through the data input module, and the system performs scheduling calculations based on this data. The simulation execution engine is responsible for performing simulation calculations based on the selected strategy, simulating the effects of different scheduling strategies. Finally, the result feedback and analysis module visualizes the simulation results, helping trainees analyze the pros and cons of different strategies and adjust their plans based on this. The system principle is based on computer simulation of various scenarios in the scheduling process, helping trainees improve their ability to deal with practical problems without actual operation.
[0003] While simulation technology is widely used in intelligent scheduling training, it also has certain drawbacks. Because simulation technology cannot fully simulate the complexities of real-world situations, such as equipment failures and emergencies, trainees may struggle to cope with these unexpected situations in actual operations, which in turn affects their ability to handle real-world scenarios. The system's relatively simple optimization strategies are unable to flexibly address diverse and dynamically changing scheduling tasks, resulting in poor results when handling certain complex scheduling problems. Summary of the Invention
[0004] In response to the shortcomings of the existing technology, the present invention provides an optimization method for the application of simulation technology in intelligent scheduling training, which solves the problem that simulation technology cannot fully simulate various complex factors in reality, affecting its ability to cope with real scenarios; the optimization strategy adopted by the system is relatively single, and cannot flexibly respond to diverse and dynamically changing scheduling tasks, and is not effective in dealing with complex scheduling problems.
[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for optimizing the application of simulation technology in intelligent scheduling training, comprising:
[0006] a. Build a multi-dimensional scheduling simulation model, which covers multiple dimensions of tasks, resources, time, and emergency factors to reflect the dynamic changes in the real scheduling environment;
[0007] b. Establish simulation input parameters, including task priority parameters, resource availability parameters, and environmental event trigger parameters, dynamically generate simulation scenario combinations, and map them to the simulation engine;
[0008] c. Receive real-time data input from the user end or external interface;
[0009] d. Establish a scheduling evaluation objective function based on simulation input parameters;
[0010] e. Model emergencies as probabilistic disturbance variables and build a disturbance simulation module to embed into the core simulation process;
[0011] f. Apply dynamic policy optimization algorithms to update task sequencing and resource allocation strategies in real time, improving the adaptability and flexibility of scheduling results;
[0012] g. After each round of simulation, the scheduling strategy output is evaluated, and the average delay rate and resource utilization indicators are output and fed back to the optimization engine.
[0013] h. Introducing an adaptive strategy evolution mechanism to automatically adjust strategy parameters based on historical simulation results and current feedback to adapt to changing mission requirements;
[0014] i. The visualization module presents task flow diagrams, resource usage diagrams, and scheduling performance indicator diagrams in real time to help users understand the behavior of the scheduling system;
[0015] j. Start the next round of training tasks and generate new scheduling simulation scenarios based on the strategy evolution results to achieve iterative training;
[0016] k. Adopt multi-objective collaborative optimization methods to balance task completion time and resource efficiency;
[0017] I. Generate personalized evaluation reports based on the strategy evolution logs and simulation trajectory records output by the system for training effect tracking and strategy comparative analysis.
[0018] Preferably, the real-time data input includes equipment status, task progress, and personnel scheduling, and the interference variables include equipment failure rate, personnel leave probability, and resource delay.
[0019] Preferably, the optimization function of the multi-objective collaborative optimization method is:
[0020] F(x)=α·E(x)+β·R(x);
[0021] Among them, F(x) is the comprehensive optimization target value, E(x) is the task completion efficiency function, R(x) is the resource utilization function, α and β are weight factors, which are adjusted according to the training objectives.
[0022] Preferably, the scheduling evaluation objective function is defined as minimizing the weighted task completion time:
[0023]
[0024] Among them, Z is the optimization target value, w i represents the weight of task i, T i represents the actual completion time of task i, and n is the total number of tasks.
[0025] Preferably, the priority weight wi is dynamically set according to task urgency, customer level or delay penalty factor.
[0026] Preferably, the personalized assessment report also includes a rationality score of the scheduling decision and an assessment result of the trainee's ability to respond to emergencies.
[0027] Preferably, the strategy evolution log includes parameter adjustments, task execution time and resource consumption of each decision, and the decision effect is evaluated through data analysis.
[0028] Preferably, the simulation engine supports adjusting task priorities, resource allocation rules and emergency simulations through user interaction, so that users can test and evaluate the effects in different scheduling environments.
[0029] The present invention provides an optimization method for applying simulation technology in intelligent scheduling training. It has the following beneficial effects:
[0030] This simulation technology optimization method for intelligent scheduling training builds a multi-dimensional scheduling simulation model, combined with dynamic policy optimization and adaptive policy evolution mechanisms. This method can reflect real-world emergencies and environmental changes in real time during training, thereby more realistically simulating various interference factors in scheduling tasks. In particular, when faced with complex factors such as equipment failures and personnel absences, the simulation system can automatically adjust based on historical data and real-time feedback, helping trainees improve their ability to cope with dynamic scheduling environments.
[0031] The multi-objective collaborative optimization method employed in this paper comprehensively considers multiple factors, such as task completion time and resource efficiency, and can flexibly adjust scheduling strategies based on varying task priorities and resource constraints. This not only improves the adaptability of the scheduling system but also increases its flexibility, enabling participants to cope with a variety of changing scheduling tasks. This optimization method ensures that scheduling decisions remain efficient and reasonable despite ever-changing scheduling requirements. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION
[0033] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.
[0034] Example 1
[0035] like Figure 1 As shown, an embodiment of the present invention provides an optimization method for the application of simulation technology in intelligent scheduling training, including: a. constructing a multi-dimensional scheduling simulation model, constructing a multi-dimensional scheduling simulation model covering multiple dimensions such as tasks, resources, time and emergency factors to reflect the dynamic changes in the real scheduling environment.
[0036] b. Establish simulation input parameters, including task priority parameters, resource availability parameters, and environmental event trigger parameters, dynamically generate simulation scenario combinations, and map them to the simulation engine. The simulation engine supports adjusting task priorities, resource allocation rules, and emergency event simulations through user interaction, allowing users to test and evaluate the effects in different scheduling environments.
[0037] c. Receive real-time data input from the user end or external interface. Real-time data input includes equipment status, task progress, and personnel scheduling. Interference variables include equipment failure rate, personnel leave probability, and resource delay.
[0038] d. Establish a scheduling evaluation objective function based on the simulation input parameters. The scheduling evaluation objective function is defined as minimizing the weighted task completion time:
[0039]
[0040] Among them, Z is the optimization target value, w i represents the weight of task i, T i represents the actual completion time of task i, n is the total number of tasks, and the priority weight wi is dynamically set according to the task urgency, customer level or delay penalty factor.
[0041] e. Model emergencies as probabilistic disturbance variables and build a disturbance simulation module to embed into the core simulation process.
[0042] f. Apply dynamic strategy optimization algorithms to update task sequencing and resource allocation strategies in real time to improve the adaptability and flexibility of scheduling results.
[0043] g. After each round of simulation, the scheduling strategy output results are evaluated, and the average delay rate and resource utilization indicators are output and fed back to the optimization engine.
[0044] h. Introduce an adaptive strategy evolution mechanism to automatically adjust strategy parameters based on historical simulation results and current feedback to adapt to changing task requirements.
[0045] i. The visualization module presents task flow diagrams, resource usage diagrams, and scheduling performance indicator diagrams in real time to help users understand the behavior of the scheduling system.
[0046] j. Start the next round of training tasks and generate new scheduling simulation scenarios based on the strategy evolution results to achieve iterative training.
[0047] k. Use a multi-objective collaborative optimization method to balance task completion time and resource efficiency. The optimization function of the multi-objective collaborative optimization method is:
[0048] F(x)=α·E(x)+β·R(x);
[0049] Among them, F(x) is the comprehensive optimization target value, E(x) is the task completion efficiency function, R(x) is the resource utilization function, α and β are weight factors, which are adjusted according to the training objectives.
[0050] I. Generate personalized evaluation reports based on the strategy evolution log and simulation trajectory records output by the system for training effect tracking and strategy comparison analysis. The personalized evaluation reports also include the rationality score of the scheduling decision and the assessment results of the trainee's ability to respond to emergencies. The strategy evolution log includes the parameter adjustments, task execution time, and resource consumption of each decision, and the decision effectiveness is evaluated through data analysis.
[0051] Experimental Examples
[0052] The application of the target collaborative optimization method in intelligent scheduling systems focuses on testing how the method balances task completion time and resource efficiency, and verifies its optimization effect in actual scheduling tasks. This experiment simulates a logistics distribution system involving multiple delivery tasks and limited distribution resources. The goal is to reduce task completion time and improve resource utilization by optimizing the scheduling strategy.
[0053] Purpose of the experiment
[0054] Verify the effectiveness of multi-objective collaborative optimization methods in scheduling tasks, especially balancing task completion time and resource efficiency.
[0055] The impact of dynamic adjustment of test task priorities and resource allocation strategies on overall scheduling performance.
[0056] Analyze the effectiveness of the optimization plan, including resource utilization, task completion time, and delay rate indicators.
[0057] Experimental equipment
[0058] Simulation scheduling system: includes simulation engine, task scheduling module, resource allocation module, data acquisition and feedback system.
[0059] Hardware resources: A simulated distribution resource pool, including 10 distribution vehicles and 20 distribution personnel.
[0060] Experimental dataset: includes data on 50 delivery tasks, including task priority, required time, and required vehicle type.
[0061] Experimental procedures
[0062] Set up the experimental scene:
[0063] Create a logistics distribution simulation model that contains 50 delivery tasks with different priorities, time requirements, and resource requirements (such as required vehicles and personnel).
[0064] Configure 10 delivery vehicles and 20 delivery personnel, set the cargo capacity of each vehicle and the working time limit of each delivery personnel.
[0065] Define the objective function:
[0066] Task completion time and resource efficiency are the two optimization goals, and the objective function form is:
[0067] Among them, E(x) is the task completion efficiency function, R(x) is the resource utilization function, and α and β are the weight factors of task completion time and resource utilization, respectively.
[0068] E(x) is calculated as the average of all task completion times;
[0069] R(x) is the resource utilization rate, which is the ratio of the total working time of delivery vehicles and personnel to the available time.
[0070] Set the initial scheduling policy:
[0071] The initial scheduling strategy adopts the simplest scheduling method, that is, scheduling according to the arrival order of tasks, without considering the optimization of task priority and resource allocation.
[0072] Apply multi-objective optimization algorithms:
[0073] The scheduling strategy is optimized using a multi-objective collaborative optimization method that combines genetic algorithm and particle swarm optimization algorithm. During the optimization process, the dynamic adjustment of task priorities and the real-time changes of resource allocation strategies are considered.
[0074] Dynamically adjust the priority of tasks and automatically set the task priority based on the urgency of the task and the delay penalty factor.
[0075] Performance Evaluation:
[0076] After each round of simulation, the following indicators are calculated and evaluated:
[0077] Task completion time: the total time from the start to the completion of all tasks;
[0078] Resource utilization: the ratio of effective working time of distribution vehicles and personnel to total working time;
[0079] Delay rate: The ratio of the difference between the task completion time and the expected completion time.
[0080] Result feedback and adjustment:
[0081] Based on the results of each simulation round, task delays and resource usage are fed back to the optimization engine, adjusting the scheduling strategy in real time. Through multiple rounds of optimization, task completion efficiency and resource utilization are gradually improved.
[0082] Experimental data
[0083] In this experiment, a total of 5 rounds of simulation were conducted, and the performance of the scheduling strategy in each round was recorded. The following are the main data results of each round:
[0084]
[0085] Experimental results analysis
[0086] Optimization of task completion time:
[0087] In the initial strategy of the experiment, the average task completion time was 8.5 hours. After five rounds of optimization, the task completion time gradually dropped to 6.8 hours, a reduction of about 20%.
[0088] Improved resource utilization:
[0089] Resource utilization increased from 65% in the initial strategy to 82%. This improvement was primarily due to the optimization strategy's real-time adjustment of resource allocation, which significantly reduced idle time for vehicles and personnel, resulting in more efficient use of resources.
[0090] Reduction in delay rate:
[0091] The delay rate was reduced from 20% in the initial strategy to 5%, indicating that the proportion of tasks completed on time was significantly improved under the effect of multi-objective optimization.
[0092] Improved task completion efficiency:
[0093] The task completion efficiency (number of tasks / hour) increased from the initial 5 tasks / hour to 7.35 tasks / hour, indicating that by optimizing the scheduling strategy, the system can complete more tasks in the same time.
[0094] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.
Claims
1. A method for optimizing the application of simulation technology in intelligent scheduling training, characterized in that: include: a. Build a multi-dimensional scheduling simulation model, which covers multiple dimensions of tasks, resources, time and emergency factors; b. Establish simulation input parameters, including task priority parameters, resource availability parameters, and environmental event trigger parameters, dynamically generate simulation scenario combinations, and map them to the simulation engine; c. Receive real-time data input from the user end or external interface; d. Establish a scheduling evaluation objective function based on simulation input parameters; e. Model emergencies as probabilistic disturbance variables and build a disturbance simulation module to embed into the core simulation process; f. Apply dynamic strategy optimization algorithms to update task sequencing and resource allocation strategies in real time; g. After each round of simulation, the scheduling strategy output is evaluated, and the average delay rate and resource utilization indicators are output and fed back to the optimization engine. h. Introducing an adaptive strategy evolution mechanism to automatically adjust strategy parameters based on historical simulation results and current feedback; i. The visualization module presents task flow diagrams, resource usage diagrams, and scheduling performance indicator diagrams in real time to help users understand the behavior of the scheduling system; j. Start the next round of training tasks and generate new scheduling simulation scenarios based on the strategy evolution results to achieve iterative training; k. Adopt multi-objective collaborative optimization methods to balance task completion time and resource efficiency; I. Generate a personalized evaluation report based on the strategy evolution log and simulation trajectory records output by the system.
2. The method for optimizing the application of simulation technology in intelligent scheduling training according to claim 1 is characterized by: The real-time data input includes equipment status, task progress, and personnel scheduling, and the interference variables include equipment failure rate, personnel leave probability, and resource delay.
3. The method for optimizing the application of simulation technology in intelligent scheduling training according to claim 1 is characterized in that: The optimization function of the multi-objective collaborative optimization method is: F(x)=α·E(x)+β·R(x); Among them, F(x) is the comprehensive optimization target value, E(x) is the task completion efficiency function, R(x) is the resource utilization function, α and β are weight factors, which are adjusted according to the training objectives.
4. The method for optimizing the application of simulation technology in intelligent scheduling training according to claim 1 is characterized in that: The scheduling evaluation objective function is defined as minimizing the weighted task completion time: Among them, Z is the optimization target value, w i represents the weight of task i, T i represents the actual completion time of task i, and n is the total number of tasks.
5. The method for optimizing the application of simulation technology in intelligent scheduling training according to claim 4 is characterized in that: The priority weight wi is dynamically set according to the task urgency, customer level or delay penalty factor.
6. The method for optimizing the application of simulation technology in intelligent scheduling training according to claim 1 is characterized by: The personalized assessment report also includes a rationality score for the scheduling decision and an assessment result of the trainee's ability to respond to emergencies.
7. The method for optimizing the application of simulation technology in intelligent scheduling training according to claim 1 is characterized by: The strategy evolution log includes parameter adjustments, task execution time, and resource consumption for each decision.
8. The method for optimizing the application of simulation technology in intelligent scheduling training according to claim 1 is characterized by: The simulation engine supports adjusting task priorities, resource allocation rules and emergency simulation through user interaction, allowing users to test and evaluate the effects in different scheduling environments.