Resource management method, device and equipment based on neural network model

Abstract

The present invention relates to the field of data analysis, and in particular to a resource management method, device, equipment and storage medium based on a neural network model, the method comprising: constructing a neural network model, obtaining resource training data, inputting the resource training data into a module corresponding to the neural network model, simulating the demand data of the next year corresponding to the resource training data, and obtaining resource simulation training data; inputting the resource training data and resource simulation training data into a corresponding module, obtaining resource error data, and performing several training and error verification on the corresponding module according to the resource error data to obtain a target module of the neural network model. Compared with the prior art, it is possible to configure resources from multiple aspects, realize the reasonable configuration of resources, improve the efficiency of resource configuration, prevent resource waste, and enhance the benefit effect obtained by using resource configuration.

Description

Technical Field

[0001] The present invention relates to the field of data analysis, and in particular to a resource management method, device, equipment and storage medium based on a neural network model. Background Art

[0002] At present, the control of carbon emissions is becoming more and more stringent. In order to achieve the rational allocation of resources, a method for rational allocation of resources is urgently needed. However, the resource allocation method in the existing technology is too single and cannot reasonably allocate resources well, resulting in waste of resources and reduced benefits. Summary of the invention

[0003] Based on this, the purpose of the present invention is to provide a resource management method, device, equipment and storage medium based on a neural network model, which can configure resources from multiple aspects by integrating multiple constraint algorithms, realize reasonable allocation of resources, improve the efficiency of resource allocation, prevent waste of resources, and enhance the benefits obtained by utilizing resource allocation.

[0004] In a first aspect, an embodiment of the present application provides a resource management method based on a neural network model, comprising the following steps:

[0005] Constructing a neural network model, wherein the neural network model includes a water resource module, an energy module, a waste module and a planning module;

[0006] Obtaining resource training data, wherein the resource training data includes water resource training data, energy training data, and waste training data of several years;

[0007] Input the resource training data into the corresponding module of the neural network model, simulate the demand data of the next year corresponding to the resource training data, and obtain resource simulation training data;

[0008] Input the resource training data and resource simulation training data into the corresponding module, obtain resource error data, perform several training and error verification on the corresponding module according to the resource error data, and obtain the target module of the neural network model;

[0009] In response to the user's pipe arrangement instruction, obtaining the resource data input by the user and the operation cost data of the waste treatment facility, inputting the resource data into the corresponding target module of the neural network model, and obtaining the resource simulation data output by the target module;

[0010] The resource simulation data is input into the planning model, and the resource simulation data is analyzed in combination with the constraint algorithm corresponding to the resource simulation data in the planning model and the operation cost data of the waste treatment facility to obtain a resource allocation plan.

[0011] In a second aspect, an embodiment of the present application provides a resource management device based on a neural network model, including:

[0012] A construction module, used to construct a neural network model, wherein the neural network model includes a water resource module, an energy module, a waste module and a planning module;

[0013] An acquisition module, used to obtain resource training data, wherein the resource training data includes water resource training data, energy training data and waste training data of several years;

[0014] A simulation module, used for inputting the resource training data into a module corresponding to the neural network model, simulating the demand data of the next year corresponding to the resource training data, and obtaining resource simulation training data;

[0015] A training module, used to input the resource training data and resource simulation training data into a corresponding module, obtain resource error data, perform several training and error verification on the corresponding module according to the resource error data, and obtain a target module of the neural network model;

[0016] A response module, for responding to a user's pipe arrangement instruction, obtaining resource data input by the user and operation cost data of the waste treatment facility, inputting the resource data into a target module corresponding to the neural network model, and obtaining resource simulation data output by the target module;

[0017] A processing module is used to input the resource simulation data into the planning model, analyze the resource simulation data in combination with the constraint algorithm corresponding to the resource simulation data in the planning model and the operating cost data of the waste treatment facility, and obtain a resource management solution.

[0018] In a third aspect, an embodiment of the present application provides a device comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, the steps of the resource management method based on the neural network model as described in the first aspect are implemented.

[0019] In a fourth aspect, an embodiment of the present application provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the resource management method based on the neural network model as described in the first aspect.

[0020] In an embodiment of the present application, a resource management method, apparatus, device and storage medium based on a neural network model are provided, which can configure resources from multiple aspects by integrating multiple constraint algorithms, thereby achieving reasonable allocation of resources, improving the efficiency of resource allocation, preventing waste of resources, and enhancing the benefits obtained by utilizing resource allocation.

[0021] For better understanding and implementation, the present invention is described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic diagram of a process flow of a resource management method based on a neural network model provided in the first embodiment of the present application;

[0023] Figure 2 A schematic diagram of the process of S3 in the process of the resource management method based on the neural network model provided in the first embodiment of the present application;

[0024] Figure 3 A schematic diagram of the process of S6 in the resource management method based on a neural network model provided in the first embodiment of the present application;

[0025] Figure 4 A schematic diagram of the process of S6 in the resource management method based on a neural network model provided in the second embodiment of the present application;

[0026] Figure 5 A schematic diagram of the process of S6 in the resource management method based on a neural network model provided in the third embodiment of the present application;

[0027] Figure 6 A schematic diagram of the process of S6 in the resource management method based on a neural network model provided in the fourth embodiment of the present application;

[0028] Figure 7 A schematic diagram of the structure of a resource management device based on a neural network model provided in the fifth embodiment of the present application;

[0029] Figure 8 A schematic diagram of the structure of the device provided in the sixth embodiment of the present application. DETAILED DESCRIPTION

[0030] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0031] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0032] It should be understood that, although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" / "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determination".

[0033] See also Figure 1 , Figure 1 The flowchart of the resource management method based on the neural network model provided in the first embodiment of the present application includes the following steps:

[0034] S1: Constructing a neural network model, wherein the neural network model includes a water resource module, an energy module, a waste module and a planning module.

[0035] The executor of the resource management method based on the neural network model is the management device of the resource management method based on the neural network model (hereinafter referred to as the management device). In an optional embodiment, the management device can be a computer device, a server, or a server cluster composed of multiple computer devices.

[0036] A neural network is a computing model that is composed of a large number of nodes (or neurons) connected to each other. In this embodiment, the pipe matching device constructs a BP (back propagation) neural network model as a training model for the resource pipe matching method, wherein the BP neural network includes a water resource module, an energy module, a waste module, and a planning module, and initializes the BP neural network model to confirm the corresponding parameter weights of the water resource module, the energy module, and the waste module.

[0037] The water resources module is used to process data associated with water resources to obtain processed data associated with water resources; the energy module is used to process data associated with energy to obtain processed data associated with energy; the waste module is used to process data associated with waste resources to obtain processed data associated with waste resources; the planning module is used to process data output by the water resources module, the energy module and the waste module.

[0038] S2: Obtain resource training data, wherein the resource training data includes water resource training data, energy training data, and waste training data for several years.

[0039] The water resources training data is obtained by using the collected hydrological and meteorological and water resources statistical data, wherein the water resources training data includes the residential water consumption data of several years, the water demand data of the energy system and the water demand data of the waste system, wherein the residential water consumption data includes the residential water supply data and the water demand data of the residential system;

[0040] The energy training data includes regional power generation system statistical data for several years, wherein the regional power generation system statistical data includes power generation capacity data and power supply security data.

[0041] The waste training data includes waste production data of several years and influencing factor data of waste treatment system, wherein the influencing factor data of waste treatment system includes waste system treatment demand data, waste minimum resource level data and waste treatment capacity data.

[0042] In this embodiment, the pipe fitting device obtains resource training data input by the user, performs analysis, and obtains water resource training data, energy training data, and waste training data for several years.

[0043] S3: Input the resource training data into the corresponding module of the neural network model, simulate the demand data of the next year corresponding to the resource training data, and obtain resource simulation training data.

[0044] The pipe matching equipment inputs the acquired resource training data into the corresponding module of the neural network model, simulates the demand data of the next year corresponding to the resource training data, and obtains resource simulation training data.

[0045] In an optional embodiment, the pipe distribution equipment inputs several years of residential water consumption data, waste treatment facility water consumption data, and sewage treatment plant treatment water consumption data into the water resource module, simulates the water resource demand data for the next year, and obtains water resource simulation training data.

[0046] In another optional embodiment, the distribution equipment inputs several years of power plant operation data and regional power generation system statistical data into the energy module, simulates the energy demand data for the next year, and obtains energy simulation data.

[0047] See also Figure 2 , Figure 2 The schematic diagram of the process of S3 in the process of the resource management method based on the neural network model provided in the first embodiment of the present application includes steps S301 to S303:

[0048] S301: Initialize the waste training data to obtain second waste training data.

[0049] In this embodiment, the pipe matching device performs initialization processing on the waste training data according to the historical years in the waste training data to obtain second waste training data, where the second waste data is initialized waste training data, wherein the initialized waste training data is:

[0050] X (1) ={x (1) (1),x (2) (2),…,x (1) (n)}

[0051] In the formula, x (1) (n) is the waste training data of the nth year.

[0052] S302: Input the second waste training data into the waste module, and obtain the waste characteristic parameters according to the second waste training data and the waste module.

[0053] The waste module includes functions f1-f2, which are as follows:

[0054]

[0055] f2=x (0) (t)+az (1) (t) = b

[0056] In the formula, x (0) (t) is the sequence of the waste training data; (1) (t) is the whitening background value of the waste module; X (1) is the sequence of the second waste training data, a is the development coefficient of the waste module, and b is the gray action amount of the waste module;

[0057] In this embodiment, the pipe matching device inputs the second waste training data into the waste module, and obtains the waste characteristic parameters a, b and z through functions f1 and f2. (1) (t), and using the least squares method, obtain the data vector of the development coefficient of the waste module Linear regression value of the grey contribution of the waste module and a parameter vector Y of the waste module, where for:

[0058]

[0059] Wherein, B is the data matrix of the waste module, and B and Y are:

[0060]

[0061] S303: According to the second waste training data, waste characteristic parameters and the fitting curve algorithm, the second waste training data is subjected to cumulative subtraction processing to obtain waste simulation data.

[0062] The curve fitting algorithm is function f3, which is as follows:

[0063]

[0064] In this embodiment, the pipe fitting device performs cumulative subtraction processing on the second waste training data according to the second waste training data, waste characteristic parameters and fitting curve algorithm to obtain waste simulation data

[0065] S4: Input the resource training data and resource simulation training data into the corresponding module, obtain resource error data, perform several training and error verification on the corresponding module according to the resource error data, and obtain the target module of the neural network model.

[0066] The pipe matching equipment inputs the acquired resource training data and resource simulation training data into the corresponding module, obtains the corresponding resource error data according to the mean square error (MSE) algorithm in the module, modifies the parameter weight of the corresponding module of the neural network according to the resource error data, inputs the resource training data and resource simulation training data into the modified corresponding module again, obtains the corresponding resource error data, continuously performs training and error verification until the value of the resource error data is less than the preset error threshold, and uses the corresponding module of the neural network model obtained after this training as the target module, wherein the mean square error (MSE) algorithm is:

[0067]

[0068] In the formula, y n Represents the value of resource simulation training data, y * n is the value of resource training data, (y n -y * n ) is the value of resource error data; N is the number of training times.

[0069] Specifically, the pipe matching equipment inputs the acquired water resource training data and water resource simulation training data into the water resource module, obtains water resource error data according to the mean square error (MSE) algorithm in the water resource module, modifies the parameter weights of the water resource module according to the water resource error data, inputs the water resource training data and water resource simulation training data into the modified water resource module again to obtain water resource error data, continuously performs training and error verification until the value of the water resource error data is less than a preset water resource error threshold, and uses the water resource module obtained after this training as the target water resource module of the neural network model.

[0070] The pipe matching equipment inputs the acquired energy training data and water resource simulation training data into the energy module, obtains energy error data according to the mean square error (MSE) algorithm in the energy module, modifies the parameter weights of the energy module according to the energy error data, inputs the energy training data and energy simulation data into the modified energy module again to obtain energy error data, continuously performs training and error verification until the value of the energy error data is less than the preset energy error threshold, and uses the energy module obtained after this training as the target energy module of the neural network model.

[0071] The pipe matching equipment inputs the acquired waste training data and waste simulation data into the waste module, obtains waste error data according to the mean square error (MSE) algorithm in the waste module, modifies the parameter weights of the waste module according to the waste error data, inputs the waste training data and waste simulation data into the modified waste module again to obtain waste error data, continuously performs training and error verification until the value of the waste error data is less than a preset waste error threshold, and uses the waste module obtained after this training as the target waste module of the neural network model.

[0072] S5: In response to the user's pipe configuration instruction, the resource data input by the user and the operating cost data of the waste treatment facility are obtained, the resource data is input into the target module corresponding to the neural network model, and the resource simulation data output by the target module is obtained.

[0073] The resource data includes water resource data, energy data and waste data.

[0074] The water resource data include data on water supply for residential use, water demand data for residential systems, water demand data for energy systems, and water demand data for waste systems.

[0075] The energy data includes power generation capacity data and power supply security data;

[0076] The waste data includes waste system processing demand data, waste minimum resource level data and waste processing capacity data.

[0077] In this embodiment, the user can input the resource data and the operating cost data of the waste treatment facility through the input device, send a pipe matching instruction to the pipe matching device, the pipe matching device obtains the pipe matching device instruction and responds to obtain the resource data and the operating cost data of the waste treatment facility, the pipe matching device inputs the resource data into the corresponding target module of the neural network model, and obtains the resource simulation data output by the target module.

[0078] Specifically, the pipe fitting equipment inputs the water resource data into the target water resource module of the neural network model, and obtains the water resource simulation data output by the target water resource module; the pipe fitting equipment inputs the energy data into the target energy module of the neural network model, and obtains the energy resource simulation data output by the target energy module; the pipe fitting equipment inputs the waste data into the target waste module of the neural network model, and obtains the waste simulation data output by the target waste module.

[0079] S6: Input the resource simulation data into the planning model, analyze the resource simulation data in combination with the constraint algorithm corresponding to the resource simulation data in the planning model and the operation cost data of the waste treatment facility, and obtain a resource allocation plan.

[0080] The planning model is a fuzzy chance constrained programming model, which is an optimization model used to solve constraint data containing random fuzziness.

[0081] In this embodiment, the pipe matching equipment inputs the resource simulation data into the planning model, selects the corresponding constraint algorithm in the planning model and the operating cost data of the waste treatment facility according to the resource simulation data, analyzes the resource simulation data, and obtains the resource pipe matching plan.

[0082] See also Figure 3 , Figure 3 The flowchart of S6 in the resource management method based on the neural network model provided in the first embodiment of the present application also includes steps S601 to S605, which are as follows:

[0083] S601: Obtain a first constraint algorithm corresponding to the residential water supply data, call the influencing data corresponding to the residential water supply data according to the first constraint algorithm, and analyze the water resource simulation data to obtain the residential water supply analysis result.

[0084] The first constraint algorithm is:

[0085]

[0086] Where Pr{} represents chance-constrained programming; WC it is the per capita water consumption of residents in the impact data; WE jt WW is the water consumption for power generation in the impact data; kt The amount of water used for waste treatment in the impact data; AWR t is the available water volume of the system in the impact data; p is the probability level of the available water volume in the impact data; t is the time data in the impact data.

[0087] In this embodiment, the pipe distribution equipment obtains the first constraint algorithm corresponding to the residential water supply data, calls the impact data corresponding to the residential water supply data, and analyzes the water resource simulation data to obtain the residential water supply constraint data.

[0088] S602: Obtain a second constraint algorithm corresponding to the water demand data of the residential system, call the influencing data corresponding to the water demand data of the residential system according to the second constraint algorithm, and analyze the water resource simulation data to obtain the water demand constraint data of the residential system.

[0089] The second constraint algorithm is:

[0090]

[0091] In the formula, NP it is the number of residents in the impact data; The per capita water consumption of residents in the impact data; WC it is the per capita water consumption of residents in the impact data; i is the set of research communities in the impact data; t is the time data in the impact data;

[0092] In this embodiment, the pipe distribution equipment obtains a second constraint algorithm corresponding to the water demand data of the residential system, calls the influence data corresponding to the water demand data of the residential system, and analyzes the water resource simulation data to obtain the water demand data constraint data of the residential system.

[0093] S603: Obtain a third constraint algorithm corresponding to the water demand data of the energy system, call the influencing data corresponding to the water demand data of the energy system according to the third constraint algorithm, and analyze the water resource simulation data to obtain the water demand analysis result of the energy system.

[0094] The third constraint algorithm is:

[0095]

[0096] Where, Cr{} represents fuzzy credibility planning; EG jt The amount of electricity generated by the power generation method in the impact data; It is the water consumption per unit of power generation in the impact data; WE jt is the water consumption for power generation in the impact data; α is the confidence level; j is the power generation type in the impact data; t is the time data in the impact data;

[0097] In this embodiment, the pipe distribution equipment obtains the second constraint algorithm corresponding to the water demand data of the residential system, calls the influence data corresponding to the water demand data of the energy system, and analyzes the water resource simulation data to obtain the water demand data constraint data of the residential system.

[0098] S604: Obtain a fourth constraint algorithm corresponding to the water demand data of the waste system, call the impact data corresponding to the water demand data of the waste system according to the fourth constraint algorithm, and analyze the water resource simulation data to obtain the water demand analysis result of the waste system.

[0099] The fourth constraint algorithm is:

[0100]

[0101] Where Cr{} represents fuzzy credibility planning; x kt is the water consumption of waste treatment in the impact data. When k=1, it means the water consumption of waste landfill treatment in the impact data; when k=2, it means the water consumption of waste resource treatment in the impact data; WW is the unit waste treatment water consumption in the impact data; kt is the amount of water used for waste treatment in the impact data; α is the confidence level; t is the time data in the impact data;

[0102] In this embodiment, the pipe matching equipment obtains a second constraint algorithm corresponding to the water demand data of the waste system, calls the impact data corresponding to the water demand data of the waste system, and analyzes the water resource simulation data to obtain the water demand data constraint data of the waste system.

[0103] S605: Obtain a resource management plan related to the water resource simulation result based on the operating cost data of the waste treatment facility, the water supply constraint data of residents, the water demand constraint data of the waste system, and the water demand constraint data of the waste system.

[0104] In this embodiment, the pipe distribution equipment uses the fuzzy chance constraint programming model to analyze the operating cost data of the waste treatment facility, the water supply constraint data of residents, the water demand constraint data of the waste system, the water demand constraint data of the waste system, and the water demand constraint data of the waste system to obtain a resource pipe distribution plan related to the water resource simulation results.

[0105] See also Figure 4 , Figure 4 The flowchart of S6 in the resource management method based on the neural network model provided in the second embodiment of the present application also includes steps S606 to S608, which are as follows:

[0106] S606: Obtain a fifth constraint algorithm corresponding to the power generation capacity data, call the impact data corresponding to the power generation capacity data according to the fifth constraint algorithm, and analyze the energy simulation data to obtain power generation capacity constraint data.

[0107] The fifth constraint algorithm is:

[0108]

[0109] Where NEU it It refers to the residential electricity consumption in the impact data; WEU kt The water consumption per unit of power generation in the impact data; is the proportion of residential electricity and waste treatment electricity in the total power generation in the impact data; η t is the power generation loss rate in the impact data; EG jt is the amount of electricity generated by the power generation method in the impact data; i is the research community set in the impact data; j is the power generation type in the impact data; t is the time data in the impact data;

[0110] In this embodiment, the pipe matching equipment obtains the fifth constraint algorithm corresponding to the power generation capacity data, calls the influence data corresponding to the power generation capacity data, and analyzes the energy simulation data to obtain the power generation capacity constraint data.

[0111] S607: Obtain a sixth constraint algorithm corresponding to the power supply security data, call the impact data corresponding to the power supply security data according to the sixth constraint algorithm, and analyze the energy simulation data to obtain the power supply security constraint data.

[0112] The sixth constraint algorithm is:

[0113]

[0114] In the formula, EG jt The amount of electricity generated by the power generation method in the impact data; is the transmission loss rate in the impact data; is the maximum electricity consumption of residents in the impact data; j is the power generation type in the impact data; t is the time data in the impact data;

[0115] In this embodiment, the pipe distribution equipment obtains the sixth constraint algorithm corresponding to the power supply security data, calls the impact data corresponding to the power supply security data, and analyzes the energy simulation data to obtain the power supply security constraint data.

[0116] S608: Obtain a resource allocation plan related to the energy resource simulation result based on the operation cost data, power generation capacity constraint data, and power supply security constraint data of the waste treatment facility.

[0117] In this embodiment, the management and allocation equipment uses the fuzzy chance constraint programming model to analyze the operating cost data, power generation capacity constraint data and power supply security constraint data of the waste treatment facility to obtain a resource management and allocation plan related to the energy simulation results.

[0118] See also Figure 5 , Figure 5 The flowchart of S6 in the resource management method based on the neural network model provided in the third embodiment of the present application also includes steps S609 to S612, which are as follows:

[0119] S609: Obtain a seventh constraint algorithm corresponding to the waste system processing demand data, call the impact data corresponding to the waste system processing demand data according to the seventh constraint algorithm, and analyze the simulation results to obtain the waste system processing demand constraint data.

[0120] The waste system treatment demand constraint algorithm is:

[0121]

[0122] In the formula, x ikt is the processing volume of the food waste treatment method in the impact data. When k=1, it represents the processing volume of the waste landfill treatment in the impact data; when k=2, it represents the processing volume of the waste resource treatment in the impact data; NP it is the number of residents in the impact data; NPW it is the per capita food waste generation of residents in the impact data; i is the set of research communities in the impact data; j is the type of power generation in the impact data; t is the time data in the impact data;

[0123] In this embodiment, the pipe matching equipment obtains the seventh constraint algorithm corresponding to the waste system processing demand data, calls the impact data corresponding to the waste system processing demand data, and analyzes the waste simulation data to obtain the waste system processing demand constraint data.

[0124] S610: Obtain an eighth constraint algorithm corresponding to the waste minimum resource utilization level data, call the impact data corresponding to the waste minimum resource utilization level data according to the eighth constraint algorithm, and analyze the waste simulation data to obtain the waste minimum resource utilization level constraint data.

[0125] The minimum waste resource utilization level constraint algorithm is:

[0126]

[0127] In the formula, ε ± CLF is the residual rate of food waste after resource processing in the impact data; t is the waste landfill treatment capacity in the impact data; i is the research community set in the impact data; t is the time data in the impact data;

[0128] In this embodiment, the pipe matching equipment obtains the eighth constraint algorithm corresponding to the waste minimum resource utilization level data, calls the impact data corresponding to the waste minimum resource utilization level data, and analyzes the waste simulation data to obtain the waste minimum resource utilization level constraint data.

[0129] S611: Obtain a ninth constraint algorithm corresponding to the waste treatment capacity constraint data, call the impact data corresponding to the waste treatment capacity constraint data according to the ninth constraint algorithm, and analyze the waste simulation data to obtain the waste treatment capacity constraint data.

[0130] The waste treatment capacity constraint algorithm is:

[0131]

[0132] In the formula, θ ± is the safety factor in the impact data; CRT t is the capacity of waste resource treatment in the impact data; i is the research community set in the impact data; t is the time data in the impact data;

[0133] In this embodiment, the pipe matching equipment obtains a ninth constraint algorithm corresponding to the waste treatment capacity constraint data, calls the impact data corresponding to the waste treatment capacity constraint data, and analyzes the waste simulation data to obtain the waste treatment capacity constraint data.

[0134] S612: Obtain a resource allocation plan related to the energy resource simulation result based on the operation cost data of the waste treatment facility, the waste system treatment demand constraint data, the waste minimum resource utilization level constraint data, and the waste treatment capacity constraint data.

[0135] In this embodiment, the management and allocation equipment uses the fuzzy chance constraint programming model to analyze the operating cost data of the waste treatment facility, the waste system treatment demand constraint data, the waste minimum resource utilization level constraint data and the waste treatment capacity constraint data to obtain a resource management and allocation plan related to the energy resource simulation results.

[0136] See also Figure 6 , Figure 6 The flowchart of S6 in the resource management method based on the neural network model provided in the fourth embodiment of the present application further includes step S613:

[0137] S613: Process the impact data according to a preset tenth constraint algorithm to obtain the processed impact data.

[0138] The tenth constraint algorithm is:

[0139] WC it , WE jt , WW kt EG jt 、x ikt ≥0

[0140] In this embodiment, the pipe fitting device inputs the influence data into the tenth constraint algorithm to obtain the influence data processed by the tenth constraint algorithm.

[0141] Please refer to Figure 7 , Figure 7This is a schematic diagram of the structure of a resource management device based on a neural network model provided in the fifth embodiment of the present application. The device can implement all or part of the resource management device based on a neural network model through software, hardware, or a combination of both. The device 7 includes:

[0142] A construction module 71 is used to construct a neural network model, wherein the neural network model includes a water resource module, an energy module, a waste module and a planning module;

[0143] An acquisition module 72, for acquiring resource training data, wherein the resource training data includes water resource training data, energy training data and waste training data of several years;

[0144] A simulation module 73, used to input the resource training data into a module corresponding to the neural network model, simulate the demand data for the next year corresponding to the resource training data, and obtain resource simulation data;

[0145] The training module 74 is used to input the resource training data and resource simulation data into the corresponding module, obtain resource error data, perform several training and error verification on the corresponding module according to the resource error data, and obtain the target module of the neural network model;

[0146] A response module 75 is used to respond to the user's pipe configuration instruction, obtain resource data and constraint data, input the resource data into the target module corresponding to the neural network model, and obtain the simulation result output by the target module;

[0147] The processing module 76 is used to input the simulation results and constraint data into the planning model, analyze the simulation results in combination with the constraint algorithm corresponding to the constraint data in the planning model, and obtain a resource allocation plan.

[0148] In an embodiment of the present application, a neural network model is constructed by a construction module, wherein the neural network model includes a water resource module, an energy module, a waste module and a planning module; resource training data is obtained by an acquisition module, wherein the resource training data includes water resource training data, energy training data and waste training data of several years; the resource training data is input into a corresponding module of the neural network model by a simulation module, and the demand data of the next year corresponding to the resource training data is simulated to obtain resource simulation data; the resource training data and resource simulation data are input into a corresponding module by a training module to obtain resource error data, and the corresponding module is trained and error verified several times according to the resource error data to obtain a target module of the neural network model; the resource data and constraint data are obtained by a response module in response to a user's pipe allocation instruction, and the resource data is input into a target module corresponding to the neural network model to obtain a simulation result output by the target module; the simulation result and constraint data are input into the planning model by a processing module, and the simulation result is analyzed in combination with the constraint algorithm corresponding to the constraint data in the planning model to obtain a resource pipe allocation plan. By integrating multiple constraint algorithms, resources can be configured from multiple aspects, achieving reasonable resource allocation, improving the efficiency of resource allocation, preventing resource waste, and enhancing the benefits obtained from resource allocation.

[0149] Please refer to Figure 8 , Figure 8 The structural diagram of the device provided for the sixth embodiment of the present application, the device 8 includes: a processor 81, a memory 82, and a computer program 83 stored in the memory 82 and executable on the processor 81; the computer device can store multiple instructions, and the instructions are suitable for being loaded by the processor 81 and executing the method steps of the above-mentioned embodiments one to four. The specific execution process can be found in the specific description of embodiments one to four, which will not be repeated here.

[0150] Among them, the processor 81 may include one or more processing cores. The processor 81 uses various interfaces and lines to connect various parts in the server, and executes various functions and processes data of the resource management device 7 based on the neural network model by running or executing instructions, programs, code sets or instruction sets stored in the memory 82, and calling the data in the memory 82. Optionally, the processor 81 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programble Logic Array, PLA). The processor 81 can integrate one or a combination of a central processing unit 81 (Central Processing Unit, CPU), a graphics processor 81 (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the touch display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 81, and it can be implemented separately through a chip.

[0151] Among them, the memory 82 may include a random access memory 82 (Random Access Memory, RAM), and may also include a read-only memory 82 (Read-Only Memory). Optionally, the memory 82 includes a non-transitory computer-readable storage medium. The memory 82 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 82 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch instructions, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 82 may also be optionally at least one storage device located away from the aforementioned processor 81.

[0152] An embodiment of the present application also provides a storage medium, which can store multiple instructions. The instructions are suitable for being loaded by a processor and executing the method steps of the above-mentioned embodiments one to four. The specific execution process can be found in the specific descriptions of embodiments one to four, which will not be repeated here.

[0153] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0154] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0155] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraint algorithm of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0156] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0157] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0158] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0159] If the integrated module / unit 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 present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc.

[0160] The present invention is not limited to the above-mentioned embodiments. If various changes or modifications to the present invention do not depart from the spirit and scope of the present invention, and if these changes and modifications fall within the scope of the claims and equivalent technologies of the present invention, the present invention is also intended to include these changes and modifications.

Claims

1. A resource management method based on a neural network model, characterized in that: The following steps are involved: Constructing a neural network model, wherein the neural network model includes a water resource module, an energy module, a waste module and a planning module; Obtaining resource training data, wherein the resource training data includes water resource training data, energy training data, and waste training data of several years; Input the resource training data into the corresponding module of the neural network model, simulate the demand data of the next year corresponding to the resource training data, and obtain resource simulation training data; Input the resource training data and resource simulation training data into corresponding modules, obtain resource error data, perform several training and error verification on corresponding modules according to the resource error data, and obtain the target module of the neural network model, wherein the target module includes a target water resource module, a target energy module and a target waste module; In response to the user's pipe matching instruction, the resource data input by the user and the operation cost data of the waste treatment facility are obtained, the resource data are input into the corresponding target module of the neural network model, and the resource simulation data output by the target module is obtained, wherein the resource data includes water resource data, energy data and waste data, the water resource data includes the water supply data of residents, the water demand data of the residents' system, the water demand data of the energy system and the water demand data of the waste system; the energy data includes the power generation capacity data and the power supply security data; the waste data includes the waste system treatment demand data, the waste minimum resource level data and the waste treatment capacity data; the resource simulation data includes the water resource simulation data, the energy resource simulation data and the waste simulation data; Input the water resource data into the target water resource module of the neural network model to obtain the water resource simulation data output by the target water resource module; input the energy data into the target energy module of the neural network model to obtain the energy resource simulation data output by the target energy module; input the waste data into the target waste module of the neural network model to obtain the waste simulation data output by the target waste module; The resource simulation data is input into the planning model, and combined with the constraint algorithm corresponding to the resource simulation data in the planning model, water resource constraint data, energy constraint data and waste constraint data are obtained, wherein the water resource constraint data includes the water supply constraint data of residents, the water demand constraint data of the residents system, the water demand constraint data of the energy system and the water demand constraint data of the waste system; the energy constraint data includes the power generation capacity constraint data and the power supply security constraint data; the waste constraint data includes the waste system treatment demand constraint data, the waste minimum resource level constraint data and the waste treatment capacity constraint data, wherein the planning model is a fuzzy chance constraint planning model, which is an optimization model for solving constraint data containing random fuzziness; Utilizing the fuzzy chance constrained programming model, the operating cost data of the waste treatment facility, the water supply constraint data of residents, the water demand constraint data of the waste system, the water demand constraint data of the waste system, and the water demand constraint data of the waste system are analyzed to obtain a resource management and allocation plan related to the water resource simulation results; Utilizing the fuzzy chance constrained programming model, the operating cost data, power generation capacity constraint data, and power supply security constraint data of the waste treatment facility are analyzed to obtain a resource management and allocation plan related to the energy resource simulation results; The fuzzy chance constrained programming model is used to analyze the operating cost data of the waste treatment facility, the waste system treatment demand constraint data, the waste minimum resource utilization level constraint data and the waste treatment capacity constraint data to obtain a resource management solution related to the waste resource simulation results.

2. The resource management method based on the neural network model according to claim 1, characterized in that: The step of inputting the resource training data into a module corresponding to the neural network model, simulating the demand data for the next year corresponding to the resource training data, and obtaining resource simulation training data comprises the following steps: Initializing the waste training data to obtain second waste training data; The second waste training data is input into the waste module, and the waste characteristic parameters are obtained according to the second waste training data and the waste module, wherein the waste module includes functions f1-f2, which are specifically as follows: f2=x (0) (t)+the (1) (t)=b In the formula, x (0) (t) is the sequence of the waste training data; (1) (t) is the whitening background value of the waste module; X (1) is the sequence of the second waste training data, a is the development coefficient of the waste module, and b is the gray action amount of the waste module; According to the second waste training data, waste characteristic parameters and fitting curve algorithm, the second waste training data is subjected to cumulative subtraction processing to obtain waste simulation data, wherein the fitting curve algorithm is function f3, which is specifically as follows: In the formula, is the data vector of the development coefficients of the waste module, is the linear regression value of the gray contribution of the waste module.

3. The resource management method based on a neural network model according to claim 1, characterized in that: The step of inputting the resource simulation data into a planning model and combining the constraint algorithm corresponding to the resource simulation data in the planning model to obtain water resource constraint data, energy constraint data and waste constraint data comprises the following steps: A first constraint algorithm corresponding to the residential water supply data is obtained. According to the first constraint algorithm, the impact data corresponding to the residential water supply data is called, and the water resource simulation data is analyzed to obtain the residential water supply constraint data, wherein the first constraint algorithm is: Where Pr{} represents chance constrained programming; WC it is the per capita water consumption of residents in the impact data; WE jt WW is the water consumption for power generation in the impact data; kt The amount of water used for waste treatment in the impact data; AWR t is the available water volume of the system in the impact data; p is the probability level of the available water volume in the impact data; t is the time data in the impact data; A second constraint algorithm corresponding to the water demand data of the residential system is obtained. According to the second constraint algorithm, the influence data corresponding to the water demand data of the residential system is called, and the water resource simulation data is analyzed to obtain the water demand constraint data of the residential system, wherein the second constraint algorithm is: In the formula, NP it is the number of residents in the impact data; The per capita water consumption of residents in the impact data; WC it is the per capita water consumption of residents in the impact data; i is the set of research communities in the impact data; t is the time data in the impact data; A third constraint algorithm corresponding to the water demand data of the energy system is obtained. According to the third constraint algorithm, the influence data corresponding to the water demand data of the energy system is called, and the water resource simulation data is analyzed to obtain the water demand constraint data of the energy system, wherein the third constraint algorithm is: Where, Cr{} represents fuzzy credibility planning; EG jt The amount of electricity generated by the power generation method in the impact data; It is the water consumption per unit of power generation in the impact data; WE jt is the water consumption for power generation in the impact data; α is the confidence level; j is the power generation type in the impact data; t is the time data in the impact data; A fourth constraint algorithm corresponding to the water demand data of the waste system is obtained. According to the fourth constraint algorithm, the influence data corresponding to the water demand data of the waste system is called, and the water resource simulation data is analyzed to obtain the water demand constraint data of the waste system, wherein the fourth constraint algorithm is: Where Cr{} represents fuzzy credibility planning; x kt is the water consumption of waste treatment in the impact data. When k=1, it means the water consumption of waste landfill treatment in the impact data; when k=2, it means the water consumption of waste resource treatment in the impact data; WW is the unit waste treatment water consumption in the impact data; kt is the amount of water used for waste treatment in the impact data; α is the confidence level; t is the time data in the impact data.

4. The resource management method based on a neural network model according to claim 1, characterized in that: The step of inputting the resource simulation data into a planning model and combining the constraint algorithm corresponding to the resource simulation data in the planning model to obtain water resource constraint data, energy constraint data and waste constraint data comprises the following steps: A fifth constraint algorithm corresponding to the power generation capacity data is obtained, and according to the fifth constraint algorithm, the influence data corresponding to the power generation capacity data is called, and the energy simulation data is analyzed to obtain the power generation capacity constraint data, wherein the fifth constraint algorithm is: Where NEU it It refers to the residential electricity consumption in the impact data; WEU kt The water consumption per unit of power generation in the impact data; is the proportion of residential electricity and waste treatment electricity in the total power generation in the impact data; η t is the power generation loss rate in the impact data; EG jt is the amount of electricity generated by the power generation method in the impact data; i is the research community set in the impact data; j is the power generation type in the impact data; t is the time data in the impact data; A sixth constraint algorithm corresponding to the power supply security data is obtained, and according to the sixth constraint algorithm, the impact data corresponding to the power supply security data is called, and the energy simulation data is analyzed to obtain the power supply security constraint data, wherein the sixth constraint algorithm is: In the formula, EG jt The amount of electricity generated by the power generation method in the impact data; is the transmission loss rate in the impact data; is the maximum electricity consumption of residents in the influencing data; j is the power generation type in the influencing data; t is the time data in the influencing data.

5. The resource management method based on a neural network model according to claim 1, characterized in that: The step of inputting the resource simulation data into a planning model and combining the constraint algorithm corresponding to the resource simulation data in the planning model to obtain water resource constraint data, energy constraint data and waste constraint data comprises the following steps: A seventh constraint algorithm corresponding to the waste system processing demand data is obtained, and according to the seventh constraint algorithm, the impact data corresponding to the waste system processing demand data is called, and the simulation result is analyzed to obtain the waste system processing demand constraint data, wherein the seventh constraint algorithm is: In the formula, x ikt is the processing volume of the food waste treatment method in the impact data. When k=1, it represents the processing volume of the waste landfill treatment in the impact data; when k=2, it represents the processing volume of the waste resource treatment in the impact data; NP it is the number of residents in the impact data; NPW it is the per capita food waste generation of residents in the impact data; i is the set of research communities in the impact data; j is the type of power generation in the impact data; t is the time data in the impact data; An eighth constraint algorithm corresponding to the waste minimum resource recovery level data is obtained. According to the eighth constraint algorithm, the impact data corresponding to the waste minimum resource recovery level data is called, and the waste simulation data is analyzed to obtain the waste minimum resource recovery level constraint data, wherein the eighth constraint algorithm is: In the formula, ε ± CLF is the residual rate of food waste after resource processing in the impact data; t is the waste landfill treatment capacity in the impact data; i is the research community set in the impact data; t is the time data in the impact data; A ninth constraint algorithm corresponding to the waste treatment capacity constraint data is obtained, and according to the ninth constraint algorithm, the impact data corresponding to the waste treatment capacity constraint data is called, and the waste simulation data is analyzed to obtain the waste treatment capacity constraint data, wherein the ninth constraint algorithm is: In the formula, θ ± is the safety factor in the impact data; CRT t is the capacity of waste resource treatment in the impact data; i is the research community set in the impact data; t is the time data in the impact data.

6. The resource management method based on a neural network model according to any one of claims 3 to 5, characterized in that: The step of inputting the resource simulation data into the planning model and combining the constraint algorithm corresponding to the resource simulation data in the planning model to obtain water resource constraint data, energy constraint data and waste constraint data comprises the following steps: According to a preset tenth constraint algorithm, the impact data is processed to obtain the processed impact data, wherein the tenth constraint algorithm is: WC it 、WE jt 、WW kt 、EG jt 、x ikt ≥0。 7. A device applied to the resource management method based on a neural network model as claimed in claim 1, characterized in that: include: A construction module, used to construct a neural network model, wherein the neural network model includes a water resource module, an energy module, a waste module and a planning module; An acquisition module, used to obtain resource training data, wherein the resource training data includes water resource training data, energy training data and waste training data of several years; A simulation module, used for inputting the resource training data into a module corresponding to the neural network model, simulating the demand data of the next year corresponding to the resource training data, and obtaining resource simulation training data; A training module, used to input the resource training data and resource simulation training data into a corresponding module, obtain resource error data, perform several training and error verification on the corresponding module according to the resource error data, and obtain a target module of the neural network model; A response module, for responding to a user's pipe arrangement instruction, obtaining resource data input by the user and operation cost data of the waste treatment facility, inputting the resource data into a target module corresponding to the neural network model, and obtaining resource simulation data output by the target module; A processing module is used to input the resource simulation data into a planning model, analyze the resource simulation data in combination with a constraint algorithm corresponding to the resource simulation data in the planning model and operating cost data of a waste treatment facility, and obtain a resource management solution.

8. A device, characterized in that include: A processor, a memory, and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, the steps of the resource management method based on the neural network model as described in any one of claims 1 to 6 are implemented.

9. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the resource management method based on a neural network model as described in any one of claims 1 to 6 are implemented.

Images