Innovative resource intelligent configuration and scheduling system and method thereof

Abstract

The invention discloses an innovative resource intelligent configuration and scheduling system and method, and relates to the technical field of artificial intelligence, and the method comprises the following steps: data collection and integration; carrying out data modeling on the integrated data; performing resource optimization configuration on the prediction data; generating a scheduling plan according to the optimal configuration scheme; performing automatic execution based on the scheduling plan; an automatic execution result is fed back and optimized; performing intelligent decision adjustment according to an optimization result; and performing global resource coordination and scheduling according to the intelligent decision. According to the system, a self-adaptive deep learning framework based on a feedback mechanism is introduced. By combining real-time feedback information from the environment and the scheduling result of each decision-making unit in the agent system, the system can dynamically adjust the weight and the structure of the deep learning model, and the problem of overfitting in a traditional method is avoided. According to the system, resource optimization configuration is carried out by introducing a linear programming technology, so that resource waste is minimized, and the operation stability of the system is ensured.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an innovative resource intelligent configuration and scheduling system and method thereof. Background Art

[0002] With the rapid development of modern industry, energy, agriculture and other fields, resource allocation and scheduling issues are becoming increasingly complex. Especially in the face of variable factors such as equipment status, load demand, environmental changes, etc., how to optimize resource allocation and scheduling while ensuring efficient resource utilization has become a key issue that needs to be solved in various industries. Traditional resource scheduling methods rely on rule-based algorithms, optimization models and manual adjustments, but these methods often seem incapable of dealing with large-scale complex systems, high-dimensional data and dynamically changing environments.

[0003] In recent years, with the development of artificial intelligence (AI) technology, especially the application of deep learning and multi-agent systems (MAS), new solutions to resource scheduling problems have gradually emerged. Deep learning can learn high-level features from complex historical data to make efficient predictions and optimization decisions; while multi-agent systems can flexibly respond to the interactions between multiple resources, equipment, and goals by simulating the collaboration and feedback mechanism of multiple decision-making entities. However, existing technologies still have some shortcomings in practical applications, especially in the combined use of deep learning and multi-agent systems, which face some key challenges. In the existing technology, deep learning is usually applied to static data sets or relatively simple tasks, and often lacks sufficient adaptability when dealing with dynamic changes and complex systems. Although deep learning models can predict future trends in resource scheduling, they are prone to overfitting because they are not closely integrated with the real-time environment and system feedback, and cannot effectively deal with drastic changes in system status and short-term fluctuations in resource demand. In addition, existing deep learning models mostly rely on static training data and lack adaptive mechanisms to adjust model parameters to adapt to the changing environment. Summary of the invention

[0004] In view of the deficiencies of the prior art, the present invention provides an innovative resource intelligent configuration and scheduling method to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: In a first aspect, an embodiment of the present invention provides an innovative resource intelligent configuration and scheduling method, comprising the following steps: S1, data collection and integration; Collect resource data in the system in real time through sensors, integrate it through the cloud platform, unify the format and timestamp, and obtain integrated data; S2, perform data modeling on the integrated data; A prediction model for resource consumption is built through regression analysis technology in machine learning, and the integrated data input is used to calculate the prediction data using the model; S3. Optimize resource allocation for forecast data; Based on the forecast data, linear programming technology is used to optimize resource allocation and obtain the optimal allocation plan; S4. Generate a scheduling plan according to the optimized configuration plan; Based on the optimal configuration scheme, a heuristic algorithm is used to generate a scheduling plan; S5. Automated execution based on the scheduling plan; According to the scheduling plan, use the automation control system based on IoT devices to realize the automatic execution of resource scheduling plan and obtain feedback data to obtain the automatic execution results; S6. Provide feedback and optimize the automated execution results; Use data mining technology to analyze the feedback data in the automated execution results, and make optimization suggestions based on the analysis results to obtain optimization results; S7. Make intelligent decision adjustments based on the optimization results; Use deep learning algorithms to analyze and process optimization results, adjust resource allocation strategies, and make intelligent decisions; S8. Global resource coordination and scheduling based on intelligent decision-making; Based on intelligent decision-making, multi-agent system technology is used to coordinate and schedule global resources.

[0006] To further optimize the technical solution, in step S1, integrating data includes: Voltage, current, power, electric energy, temperature, humidity, air pressure, equipment operating time, number of times equipment is used, and equipment operating status.

[0007] To further optimize the technical solution, in step S2, the regression analysis technique includes: Get the integrated data, perform a simple linear regression equation on the integrated data, and get the usage forecast of each resource. Define Y as the dependent variable, which represents the predicted consumption of this resource, and define X as the independent variable, which represents the various resource data in the integrated data. The regression equation is: ; in, It is calculated based on the least squares method; Represents the intercept, the initial value is 0; represents the error term.

[0008] To further optimize the technical solution, in step S3, the linear programming technology includes: Construct the objective function: ; Among them, n represents the type of resources, which is 10 according to the type of integrated data; T represents the total time range, 24 hours. The sum is calculated starting from the first hour, for a total of 24 hours; Indicates Resources in time Unit consumption cost or energy consumption; Indicates Resources in time The amount of distribution; Establish constraints.

[0009] To further optimize this technical solution, the setting constraints include: Constraints: Equipment constraints: The amount of demand that each device or task meets at each point in time, defining the In time The amount of resources required is

[0010] , then for each device and each resource, there must be: ;

[0011] in, Indicates Resources and The correlation coefficient of a device is set manually.

[0012] Resource availability constraint: The total consumption of each resource cannot exceed its available amount. The total available amount of this resource is ,but: ; Load balancing constraint: The allocation of each resource should ensure the load balance of the system to avoid excessive consumption or waste of resources. The load balancing requirement of the system is that the consumption of resources in the tth time period cannot exceed the predetermined load threshold. , the threshold is set artificially, then: .

[0013] To further optimize the technical solution, in step S4, the heuristic algorithm includes: Backtracking algorithm: The solution to the problem is constructed step by step through trial and error. If it is found that the selected solution cannot lead to a feasible solution, it will go back to the previous step and replace it with another solution until the solution is complete, that is, the plan is feasible.

[0014] To further optimize the technical solution, in step S6, data mining includes: Data cleaning: delete the wrong data in the feedback data; Data integration: classify the data in the feedback data and integrate the data of the same type; Anomaly detection: By calculating the average value of the feedback data, each feedback data is compared with the average value, and an error is reported if the difference is greater than 30%.

[0015] Visualization: Display feedback data in the form of charts for decision makers to view and analyze.

[0016] To further optimize the technical solution, the deep learning in step S7 includes: Define the input data: ; ; ; in, , is a vector, indicating the resources consumed at time t, including power, voltage, and current, reflecting the resource consumption status, where is the amount of power consumed by the i-th resource device at time t, and the maximum value of i is 3; , is a vector representing the equipment operating status at time t, where is the operating status of the jth device at time t; , is a vector representing the environmental factors data at time t, including temperature, humidity, and air pressure data. Represents the change of the kth environmental factor at time t, and the maximum value of k is 3.

[0017] Set up feedback mechanism: Based on the error and optimization results in the historical learning process, and through time steps Dynamic update of the adjustment strategy: ; in, represents the error at time t-1; represents the feedback resource consumption vector at time t; Represents the feedback function, which dynamically adjusts the input data by integrating historical data and errors to increase the prediction accuracy of future scheduling decisions.

[0018] Set up the deep neural network structure model: The model is based on the long short-term memory network LSTM model, which is processed by the convolutional neural network CNN and LSTM. The formula is: ;

[0019] in, is the time step The hidden state of ,represents the high-level feature representation of the system; The output of each layer is transformed nonlinearly through an activation function, allowing the model to better capture complex patterns in the data: ;

[0020] in, and is the weight matrix of the neural network for the previous hidden state and the current input ; is an activation function used to introduce nonlinearity; Output and optimization goals: Set the final output of the network to , indicating that at time When the optimal scheduling amount of each resource is used, the performance of the model is optimized through the loss function to minimize the prediction error. for: ; in, is the predicted scheduling amount of the i-th resource at time t; is the actual resource consumption value; Regularization parameter, which controls the complexity of the model; Adaptive optimization mechanism: Dynamically adjust the learning rate according to the feedback error, ; in, represents the learning rate at time t; Indicates the initial value of the parameter, which is set manually; It represents the adjustment parameter and determines the influence of error feedback on parameter adjustment; represents the error value at time t-1, the prediction error.

[0021] To further optimize the technical solution, the multi-agent system technology in step S8 includes: The multi-agent system simulates multiple independent intelligent agents and uses self-organization and collaboration to coordinate the configuration and scheduling of various resources on a global scale. Through the intelligent decision support system, each agent can dynamically adjust the resource scheduling strategy based on real-time data and prediction models.

[0022] To further optimize the present technical solution, the functional modules of the innovative resource intelligent configuration and scheduling system include data collection and integration module, resource consumption prediction and data modeling module, resource optimization configuration module, scheduling plan generation module, automated execution and resource scheduling module, feedback and optimization module, intelligent decision support module, and global coordination and resource optimization scheduling module.

[0023] In a second aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of an innovative resource intelligent configuration and scheduling system and method thereof as described in the first aspect of the present invention are implemented.

[0024] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of an innovative resource intelligent configuration and scheduling system and method thereof as described in the first aspect of the present invention are implemented.

[0025] Compared with the prior art, the present invention provides an innovative resource intelligent configuration and scheduling system and method thereof, which has the following beneficial effects: This innovative resource intelligent configuration and scheduling system introduces an adaptive deep learning framework based on a feedback mechanism. By combining real-time feedback information from the environment and the scheduling results of each decision-making unit in the agent system, the system can dynamically adjust the weight and structure of the deep learning model to avoid the overfitting problem in traditional methods. This mechanism enables the model to not only capture the rules in historical data during the training phase, but also optimize resource scheduling decisions through continuous learning in actual applications, and improve the model's prediction accuracy and responsiveness to future resource consumption and demand fluctuations. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 A schematic diagram of a process of an innovative resource intelligent configuration and scheduling method proposed by the present invention; Figure 2A schematic diagram of a module of an innovative resource intelligent configuration and scheduling system proposed by the present invention; Figure 3 This is a schematic diagram of a linear programming algorithm for an innovative resource intelligent configuration and scheduling method proposed in the present invention. DETAILED DESCRIPTION

[0028] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0029] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0030] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments. Example

[0031] Reference Figure 1 and Figure 3 , which is the first embodiment of the present invention, and provides an innovative resource intelligent configuration and scheduling method, comprising the following steps: S1, data collection and integration; The resource data in the system is collected in real time through sensors, integrated through the cloud platform, and unified in format and timestamp to obtain integrated data. The integrated data includes: voltage, current, power, electric energy, temperature, humidity, air pressure, equipment operating time, equipment usage times, and equipment operating status.

[0032] In this embodiment, in the resource intelligent configuration and scheduling system, data collection and integration are first required. This step mainly relies on the Internet of Things (IoT) technology to collect various types of resource data in the system in real time through sensors and smart devices. These data are integrated through the cloud platform, with unified formats and timestamps to ensure consistency and synchronization during subsequent processing. The collected data is preliminarily screened and cleaned through big data technology to remove noise and irrelevant data, providing accurate input for subsequent steps. This step is the basis of the entire intelligent configuration and scheduling process, and lays the foundation for subsequent optimization decisions and intelligent scheduling.

[0033] S2, perform data modeling on the integrated data; The prediction model of resource consumption is constructed through regression analysis technology in machine learning, and the integrated data input is used to calculate the prediction data using the model. Regression analysis technology includes: Get the integrated data, perform a simple linear regression equation on the integrated data, and get the usage forecast of each resource. Define Y as the dependent variable, which represents the predicted consumption of this resource, and define X as the independent variable, which represents the various resource data in the integrated data. The regression equation is: .

[0034] In this embodiment, the model can provide a forecast of the use of various resources in the future based on different environmental changes, equipment status and demand fluctuations. The goal of this step is to provide accurate basic data for scheduling decisions through the data model to avoid excess or insufficient resources during the scheduling process.

[0035] S3. Optimize resource allocation for forecast data; Based on the forecast data, linear programming technology is used to optimize resource allocation and obtain the optimal allocation plan. Linear programming technology includes: Construct the objective function: ; in, n represents the type of resource, which is obtained based on the type of integrated data and is 10; T represents the total time range, 24 hours. The sum is calculated starting from the first hour, for a total of 24 hours; Indicates Resources in time Unit consumption cost or energy consumption; Indicates Resources in time The amount of distribution; Set up constraints: Equipment constraints: The amount of demand that each device or task meets at each point in time, defining the In time The amount of resources required is , then for each device and each resource, there must be: ; in, Indicates Resources and The correlation coefficient of a device is set manually.

[0036] Resource availability constraint: The total consumption of each resource cannot exceed its available amount. The total available amount of this resource is ,but: ; Load balancing constraint: The allocation of each resource should ensure the load balance of the system to avoid excessive consumption or waste of resources. The load balancing requirement of the system is that the consumption of resources in the tth time period cannot exceed the predetermined load threshold. , the threshold is set artificially, then: .

[0037] In this embodiment, the use of the formula is explained as: Objective Function: Our goal is to minimize energy waste and costs by minimizing the total consumption cost while ensuring that equipment needs are met and resources do not exceed available amounts.

[0038] Device demand constraints: Ensure that the resource requirements of each device or task at different time points are met, that is, to ensure the basic requirements for system operation.

[0039] Resource availability constraints: Ensure that the consumption of each resource at each point in time does not exceed its maximum available amount, avoiding resource shortages due to excessive consumption.

[0040] Load balancing constraint: ensures that the system load does not exceed the predetermined load threshold to avoid system failure or resource waste due to overload.

[0041] Dynamically adjust constraints: Through feedback mechanisms (such as equipment failure, real-time energy consumption, etc.), the model can dynamically adjust resource allocation, making resource configuration more flexible and adaptive.

[0042] In traditional linear programming, optimization objectives and constraints are usually static, but in this scenario, resource consumption and demand are time-sensitive, so it is necessary to introduce time-varying parameters (such as load demand and resource availability) to make the optimization more realistic.

[0043] S4. Generate a scheduling plan according to the optimized configuration plan;

[0044] Based on the optimal configuration scheme, a heuristic algorithm is used to generate a scheduling plan. The heuristic algorithm includes: Backtracking algorithm: The solution to the problem is constructed step by step through trial and error. If it is found that the selected solution cannot lead to a feasible solution, it will go back to the previous step and replace it with another solution until the solution is complete, that is, the plan is feasible.

[0045] In this embodiment, an algorithm takes into account the time sensitivity of resources, the periodic demand for equipment operation, and changes in the external environment to automatically generate a detailed resource scheduling plan. This plan ensures that each resource can be supplied and scheduled as planned, while avoiding over-scheduling or under-scheduling of resources. During the generation of the scheduling plan, emergency situations are also simulated, such as equipment failure or sudden increase in demand, so as to adjust the scheduling plan and ensure the continuity and stability of system operation. Through the application of simulation algorithms, the system can dynamically respond to different operating environments and improve the flexibility of scheduling.

[0046] S5. Automated execution based on the scheduling plan; According to the scheduling plan, an automated control system based on IoT devices is used to automatically execute the resource scheduling plan and obtain feedback data to obtain automated execution results.

[0047] In this embodiment, through seamless connection with IoT devices, the automated control system can automatically adjust resource allocation based on real-time feedback, so that the resource scheduling plan can be accurately implemented. The system can adjust the scheduling strategy according to changes in real-time data, such as device status, environmental changes, etc., to ensure maximum resource utilization and avoid any waste of resources. The key to this step is to reduce human intervention through automation and improve the scheduling efficiency of the system.

[0048] S6. Provide feedback and optimize the automated execution results; Use data mining technology to analyze the feedback data in the automated execution results, and make optimization suggestions based on the analysis results to obtain optimization results. Data mining includes: Data cleaning: delete the wrong data in the feedback data; Data integration: classify the data in the feedback data and integrate the data of the same type; Anomaly detection: By calculating the average value of the feedback data, each feedback data is compared with the average value, and an error is reported if the difference is greater than 30%.

[0049] In this embodiment, data mining not only helps to find problems, but also provides optimization suggestions for future resource allocation. Based on these feedback results, the system can automatically or manually adjust the optimization parameters to improve the performance of the entire system.

[0050] S7. Make intelligent decision adjustments based on the optimization results; Use deep learning algorithms to analyze and process optimization results, adjust resource allocation strategies, and make intelligent decisions. Deep learning includes: Define the input data: ; ; ; in, , is a vector, indicating the resources consumed at time t, including power, voltage, and current, reflecting the resource consumption status, where is the amount of power consumed by the i-th resource device at time t, and the maximum value of i is 3; , is a vector representing the equipment operating status at time t, where is the operating status of the jth device at time t; , is a vector representing the environmental factors data at time t, including temperature, humidity, and air pressure data. Represents the change of the kth environmental factor at time t, and the maximum value of k is 3.

[0051] Set up feedback mechanism: Based on the error and optimization results in the historical learning process, and through time steps Dynamic update of the adjustment strategy: ; in, represents the error at time t-1; represents the feedback resource consumption vector at time t; Represents the feedback function, which dynamically adjusts the input data by integrating historical data and errors to increase the prediction accuracy of future scheduling decisions.

[0052] The general expression of the feedback function is: ; in, Represents the weight coefficient, which is set by experts.

[0053] Set up the deep neural network structure model: The model is based on the long short-term memory network LSTM model, which is processed by the convolutional neural network CNN and LSTM. The formula is: ; in, is the time step The hidden state of ,represents the high-level feature representation of the system; The output of each layer is transformed nonlinearly through an activation function, allowing the model to better capture complex patterns in the data: ; in, and is the weight matrix of the neural network for the previous hidden state and the current input ; is the activation function, which is used to introduce nonlinearity. The expression is ; Output and optimization goals: Set the final output of the network to , indicating that at time When the optimal scheduling amount of each resource is used, the performance of the model is optimized through the loss function to minimize the prediction error. for: ; in, is the predicted scheduling amount of the i-th resource at time t; is the actual resource consumption value; is the regularization parameter, which controls the complexity of the model; Adaptive optimization mechanism: Dynamically adjust the learning rate according to the feedback error, ; in, represents the learning rate at time t; Indicates the initial value of the parameter, which is set manually; It represents the adjustment parameter and determines the influence of error feedback on parameter adjustment; represents the error value at time t-1, the prediction error.

[0054] In this embodiment, the model can dynamically adjust the learning process according to error feedback to improve the accuracy of prediction and the adaptive ability of the system.

[0055] The usage of the formula model is explained as follows: Input data: Input data (such as resource consumption history, equipment status, and environmental changes) are adjusted through a feedback mechanism to ensure data timeliness and prediction accuracy.

[0056] Deep neural network: Use convolutional neural networks and LSTM models to process multi-dimensional time series data, capture spatial features and temporal dependencies in the data, and learn the laws of resource scheduling.

[0057] Output prediction: The output layer predicts the consumption of each resource in the future time period. These prediction results will serve as the basis for optimization decisions.

[0058] Loss function and optimization: The error between model prediction and actual consumption is minimized through the loss function to optimize the performance of the deep learning model. At the same time, an adaptive learning rate mechanism is used to improve the stability and convergence speed of the model.

[0059] Adaptive adjustment: The adaptive mechanism ensures that the model can automatically adjust the learning process according to environmental changes and feedback information to maintain the efficiency and flexibility of prediction.

[0060] S8. Global resource coordination and scheduling based on intelligent decision-making; Based on intelligent decision-making, multi-agent system technology is used to coordinate and schedule global resources. Multi-agent system technology includes: The multi-agent system simulates multiple independent intelligent agents and uses self-organization and collaboration to coordinate the configuration and scheduling of various resources on a global scale. Through the intelligent decision support system, each agent can dynamically adjust the resource scheduling strategy based on real-time data and prediction models.

[0061] In this embodiment, the multi-agent system technology includes: In a multi-agent system, assume that each agent Represents a resource scheduling unit in the system, and its goal is to predict the results of deep learning based on local information and global sharing , adjust its resource allocation to minimize resource consumption while meeting task requirements Agent’s decision making process: When making decisions, each agent selects its resource scheduling strategy based on the local information at the current time step t and the feedback from other agents, combined with the output of the deep learning model. The agent's goal is to select an action To maximize its benefits or minimize its costs. This decision process can be expressed as: ; in, Representation Agent The cost (e.g., resource consumption) of choosing an action at time t.

[0062] represents the regularization parameter, which is used to control the balance between global and local objectives.

[0063] Representation Agent For Agents The weight coefficient of the feedback.

[0064] Represents the error feedback from the deep learning model, reflecting the deviation between the predicted and actual consumption.

[0065] Collaborative optimization mechanism: Each agent not only relies on its own goals when making decisions, but also needs to adjust its strategy based on the feedback from other agents to maximize the overall benefits of the system. A collaborative optimization mechanism is introduced, which is expressed as: ; in, Prediction output from deep learning models; Represents resource availability data, indicating the availability status of each resource in the current system; Representation Agent Status information (such as device load, current resource consumption, etc.); is the feedback function.

[0066] Information exchange and feedback between agents: In a multi-agent system, agents collaborate through information exchange and feedback mechanisms. According to its decision-making process and resource allocation, it transmits its status information and scheduling results to other agents. The feedback mechanism can be expressed as: ; in, Representation Agent State information at time t.

[0067] Explanation of the formula: Agent decision-making process: Each agent selects an appropriate resource scheduling strategy based on its local goals and the prediction results of the deep learning model, with the aim of minimizing local resource consumption and meeting its needs.

[0068] Collaborative optimization mechanism: Each agent not only considers its own resource needs, but also makes adjustments based on feedback from other agents to ensure the optimization of global resource allocation.

[0069] Information exchange and feedback: Agents collaborate to optimize decisions by transmitting feedback information, enhance global coordination, and improve the overall efficiency of the system.

[0070] Global objective function: The global optimization goal takes into account the local decision results of all agents and their mutual influence, and achieves the optimal resource scheduling of the system by minimizing the total cost and coordination error.

[0071] Embodiment 2: Reference Figure 2 , which is the second embodiment of the present invention, the functional modules of the innovative resource intelligent configuration and scheduling system include data collection and integration module, resource consumption prediction and data modeling module, resource optimization configuration module, resource optimization configuration module, scheduling plan generation module, automatic execution and resource scheduling module, feedback and optimization module, intelligent decision support module, global coordination and resource optimization scheduling module.

[0072] In this embodiment, the data collection and integration module collects various resource usage data (such as electricity, gas, temperature and humidity, equipment status, etc.), and integrates the data. The data is cleaned and denoised, converted into a unified format, provides high-quality data input for subsequent modules, and synchronizes the collected real-time data and historical data to the cloud platform to provide support for subsequent data modeling and optimization; through the resource consumption prediction and data modeling module, the collected data is modeled using regression analysis and other technologies to predict the consumption trend of various resources. Build and train machine learning models to predict the consumption of various resources in the future. Provide accurate prediction data support for subsequent resource optimization configuration; through the resource optimization configuration module, the generated resource consumption prediction data is used to configure resources using optimization algorithms such as linear programming; through the scheduling plan generation module, the optimized resource configuration scheme is automatically generated using a heuristic algorithm to generate a scheduling plan; through the automatic execution and resource scheduling module, the resource scheduling operation is automatically executed; through the feedback and optimization module, feedback data after execution is collected, including equipment status, resource consumption, and fault reports, etc., and data mining and statistical analysis techniques are used to conduct in-depth analysis of the feedback data to discover potential problems or optimization opportunities in resource use. Based on the analysis results, optimization plans or adjustment suggestions are provided to provide support for subsequent decision-making and scheduling. Through the intelligent decision support module, the feedback data is deeply analyzed to automatically identify the optimization mode of resource allocation. Finally, through the global coordination and resource optimization scheduling module, a multi-agent system is used to perform global resource scheduling and coordination.

[0073] Embodiment three: This embodiment also provides a computer device, which is suitable for an innovative resource intelligent configuration and scheduling system and method thereof, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement an innovative resource intelligent configuration and scheduling system and method thereof as proposed in the above embodiment.

[0074] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, an innovative resource intelligent configuration and scheduling system and method thereof are implemented as proposed in the above embodiment.

[0075] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0076] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0077] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0078] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk case (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0079] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit with a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit with a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0080] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An innovative resource intelligent configuration and scheduling method, characterized in that: The following steps are involved: S1, data collection and integration; Collect resource data in the system in real time through sensors, integrate it through the cloud platform, unify the format and timestamp, and obtain integrated data; S2, perform data modeling on the integrated data; A prediction model for resource consumption is built through regression analysis technology in machine learning, and the integrated data input is used to calculate the prediction data using the model; S3. Optimize resource allocation for forecast data; Based on the forecast data, linear programming technology is used to optimize resource allocation and obtain the optimal allocation plan; S4. Generate a scheduling plan according to the optimized configuration plan; Based on the optimal configuration scheme, a heuristic algorithm is used to generate a scheduling plan; S5. Automated execution based on the scheduling plan; According to the scheduling plan, use the automation control system based on IoT devices to realize the automatic execution of resource scheduling plan and obtain feedback data to obtain the automatic execution results; S6. Provide feedback and optimize the automated execution results; Use data mining technology to analyze the feedback data in the automated execution results, and make optimization suggestions based on the analysis results to obtain optimization results; S7. Make intelligent decision adjustments based on the optimization results; Use deep learning algorithms to analyze and process optimization results, adjust resource allocation strategies, and make intelligent decisions; S8. Global resource coordination and scheduling based on intelligent decision-making; Based on intelligent decision-making, multi-agent system technology is used to coordinate and schedule global resources.

2. According to claim 1, a method for intelligent configuration and scheduling of innovative resources is characterized in that: In step S1, integrating data includes: Voltage, current, power, electric energy, temperature, humidity, air pressure, equipment operating time, number of times equipment is used, and equipment operating status.

3. The method for intelligent configuration and scheduling of innovative resources according to claim 1, characterized in that: In step S2, the regression analysis technique includes: Get the integrated data, perform a simple linear regression equation on the integrated data, and get the usage forecast of each resource. Define Y as the dependent variable, which represents the predicted consumption of this resource. Define X as the independent variable, which represents the various resource data in the integrated data. The regression equation is: ; in, It is calculated based on the least squares method; Represents the intercept, the initial value is 0; represents the error term.

4. The method for intelligent configuration and scheduling of innovative resources according to claim 1, characterized in that: In step S3, the linear programming technique includes: Construct the objective function: ; in, n represents the type of resource, which is obtained based on the type of integrated data and is 10; T represents the total time range, 24 hours, starting from the first hour and totaling 24 hours; Indicates Resources in time Unit consumption cost or energy consumption; No. Resources in time The amount of distribution; Establish constraints.

5. The method for intelligent configuration and scheduling of innovative resources according to claim 4, characterized in that: The establishment constraints include: Constraints: Equipment constraints: The amount of demand that each device or task meets at each point in time, defining the In time The amount of resources required is , then for each device and each resource, there must be: ; in, Indicates Resources and The correlation coefficient of each device is set manually; Resource availability constraint: The total consumption of each resource cannot exceed its available amount. The total available amount of this resource is ,but: ； Load balancing constraint: The allocation of each resource should ensure the load balance of the system to avoid excessive consumption or waste of resources. The load balancing requirement of the system is defined as follows: the consumption of resources in the tth time period cannot exceed the predetermined load threshold. , the threshold is set artificially, then: .

6. The method for intelligent configuration and scheduling of innovative resources according to claim 1, characterized in that: In step S4, the heuristic algorithm includes: Backtracking algorithm: Through trial and error, the solution to the problem is gradually constructed. If it is found that the solution that has been selected cannot lead to a feasible solution, it will go back to the previous step and replace it with another solution until the solution is complete, that is, the plan is feasible.

7. The method for intelligent configuration and scheduling of innovative resources according to claim 1, characterized in that: In step S6, data mining includes: Data cleaning: delete the wrong data in the feedback data; Data integration: classify the data in the feedback data and integrate the data of the same type; Anomaly detection: By calculating the average value of the feedback data, each feedback data is compared with the average value, and an error is reported if the difference is greater than 30%; Visualization: Display feedback data in the form of charts for decision makers to view and analyze.

8. The method for intelligent configuration and scheduling of innovative resources according to claim 1, characterized in that: The deep learning in step S7 includes: Define the input data: ； ； ； in, , is a vector, indicating the resources consumed at time t, including power, voltage, and current, reflecting the resource consumption status, where is the amount of power consumed by the i-th resource device at time t, and the maximum value of i is 3; , is a vector representing the equipment operating status at time t, where is the operating status of the jth device at time t; , is a vector representing the environmental factors data at time t, including temperature, humidity, and air pressure data. represents the change of the kth environmental factor at time t, and the maximum value of k is 3; Set up feedback mechanism: Based on the error and optimization results in the historical learning process, and through time steps Dynamic update of the adjustment strategy: in, represents the error at time t-1; represents the feedback resource consumption vector at time t; represents the feedback function, which dynamically adjusts the input data by integrating historical data and errors to increase the prediction accuracy of future scheduling decisions; Set up the deep neural network structure model: The model is based on the long short-term memory network LSTM model, which is processed by the convolutional neural network CNN and LSTM. The formula is: in, is the time step The hidden state of ,represents the high-level feature representation of the system; The output of each layer is transformed nonlinearly through an activation function, allowing the model to better capture complex patterns in the data: in, and is the weight matrix of the neural network for the previous hidden state and the current input ; is an activation function used to introduce nonlinearity; Output and optimization goals: Set the final output of the network to , indicating that at time When the optimal scheduling amount of each resource is used, the performance of the model is optimized through the loss function to minimize the prediction error. for: in, is the predicted scheduling amount of the i-th resource at time t; is the actual resource consumption value; Regularization parameter, which controls the complexity of the model; Adaptive optimization mechanism: Dynamically adjust the learning rate according to the feedback error, ； in, represents the learning rate at time t; Indicates the initial value of the parameter, which is set manually; It represents the adjustment parameter and determines the influence of error feedback on parameter adjustment; represents the error value at time t-1, the prediction error.

9. The method for intelligent configuration and scheduling of innovative resources according to claim 1, characterized in that: The multi-agent system technology in step S8 includes: The multi-agent system simulates multiple independent intelligent entities and uses self-organization and collaboration to coordinate the configuration and scheduling of various resources on a global scale. Through the intelligent decision support system, each agent can dynamically adjust the resource scheduling strategy based on real-time data and prediction models.

10. An innovative resource intelligent configuration and scheduling system, used to implement an innovative resource intelligent configuration and scheduling method according to any one of claims 1 to 9, characterized in that: The functional modules of the system include data collection and integration module, resource consumption prediction and data modeling module, resource optimization configuration module, scheduling plan generation module, automated execution and resource scheduling module, feedback and optimization module, intelligent decision support module, and global coordination and resource optimization scheduling module.

Images