Industrial equipment cluster regulation and control method and device, storage medium and electronic device

Abstract

The invention discloses an industrial equipment cluster regulation and control method and device, a storage medium and an electronic device, and relates to the technical field of power systems. The method comprises the following steps: acquiring an industrial equipment information sample and a regulation and control demand information sample; training the initial multi-dimensional identification model based on the industrial equipment information sample and the regulation and control demand information sample, and generating a target multi-dimensional identification model; evaluating a target electrical load curve of the target industrial equipment cluster based on the target multi-dimensional identification model to obtain an evaluation result; and regulating and controlling the electrical load of the target industrial equipment cluster based on a preset industrial equipment cluster regulation and control strategy and the evaluation result. According to the method, the technical problems that a relatively high-dimensional calculation problem can be generated for optimal solution of a cluster equipment regulation and control strategy and the production habit, the start-stop characteristic, the rigid-flexible characteristic and the like of industrial equipment are not considered in related technologies are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to an industrial equipment cluster control method, device, storage medium and electronic device. Background Art

[0002] In recent years, the national level has released construction and development goals related to new power systems and new load management. Against this background, power load management and control has gradually shifted from the traditional user level to the equipment level, with higher requirements for equipment-level regulation and analysis. Industrial equipment loads are characterized by large load scale and strong control operability, but the power consumption characteristics of each device are highly different, and their adaptability to actual grid regulation needs is also different. Therefore, how to accurately identify and profile the power consumption characteristics of industrial equipment is an important prerequisite for further formulating cluster industrial equipment regulation.

[0003] At present, most of the traditional industrial equipment control strategies use optimization solutions based on specific objective functions to generate strategies. On the one hand, the optimal solution to the cluster equipment control strategy will produce high-dimensional computing problems, and have high requirements for related system software and server background configuration, which is not conducive to large-scale promotion and application in practice; on the other hand, the existing cluster industrial equipment control strategy lacks consideration of the production habits, start-stop characteristics, rigidity and flexibility characteristics of industrial equipment, and therefore lacks a good critical standard for the adaptability of equipment to participate in power control. Summary of the invention

[0004] The embodiments of the present invention provide an industrial equipment cluster control method, device, storage medium and electronic device to at least solve the technical problems that the related technology will generate high-dimensional computing problems for the optimal solution of cluster equipment control strategy and lack of consideration for the production habits, start-stop characteristics, rigidity and flexibility characteristics of industrial equipment.

[0005] According to one embodiment of the present invention, a method for controlling an industrial equipment cluster is provided, the method comprising obtaining industrial equipment information samples and control demand information samples, wherein the industrial equipment information samples are used to represent the operating data of the industrial equipment cluster within a first preset time period, and the control demand information samples are used to represent the power consumption control target of the industrial equipment cluster within a second preset time period; training an initial multidimensional identification model based on the industrial equipment information samples and the control demand information samples to generate a target multidimensional identification model; evaluating a target power load curve of the target industrial equipment cluster based on the target multidimensional identification model to obtain an evaluation result, wherein the target power load curve is a graph of the time trend of power consumption within a third preset time period, and the evaluation result is used to reflect the power load priority corresponding to any industrial equipment in the target industrial equipment cluster; and controlling the power load of the target industrial equipment cluster based on the preset industrial equipment cluster control strategy and the evaluation result.

[0006] Optionally, training an initial multidimensional identification model based on industrial equipment information samples and control demand information samples to generate a target multidimensional identification model includes: determining multidimensional characteristic indicators, wherein the multidimensional characteristic indicators are used to reflect the operating properties of industrial equipment; determining feature correspondences based on the multidimensional characteristic indicators, industrial equipment information samples and control demand information samples, wherein the feature correspondences are used to represent the relationship between the operating properties of industrial equipment and multidimensional features; and training an initial multidimensional identification model based on the feature correspondences to generate a target multidimensional identification model.

[0007] Optionally, the characteristic correspondence includes: the correspondence between load peak and load peak type characteristics, the correspondence between the average duration of industrial equipment operation and load continuity characteristics, the correspondence between industrial equipment power state and load regularity characteristics, the correspondence between the average deviation of industrial equipment operating power and load periodic characteristics, and the correspondence between the average load rate of industrial equipment and load characteristics.

[0008] Optionally, the evaluation results include: a load peak characteristic identification result score, a load continuity characteristic identification result score, a load regularity characteristic identification result score, a load periodicity characteristic identification result score, and a load characteristic identification result score.

[0009] Optionally, the industrial equipment cluster control method also includes: determining a judgment matrix based on a scaling construction method, wherein the judgment matrix is ​​used for the importance of indicators; determining a preset number of weight indicators based on the judgment matrix, wherein the weight indicators correspond to the evaluation results.

[0010] Optionally, regulating the power load of the target industrial equipment cluster based on the preset industrial equipment cluster regulation strategy and evaluation results includes: weighting the evaluation results based on the preset industrial equipment cluster regulation strategy and weight indicators to obtain a target score, wherein the target score includes the score corresponding to any target industrial equipment in the target industrial equipment cluster; regulating the power load of the target industrial equipment cluster based on the score corresponding to any target industrial equipment and the overall regulation requirement of the cluster.

[0011] According to one embodiment of the present invention, there is also provided an industrial equipment cluster control device, the device comprising: an acquisition module, used to acquire industrial equipment information samples and control demand information samples, wherein the industrial equipment information samples are used to represent the operating data of the industrial equipment cluster within a first preset time period, and the control demand information samples are used to represent the power consumption control target of the industrial equipment cluster within a second preset time period; a training module, used to train an initial multidimensional identification model based on the industrial equipment information samples and the control demand information samples to generate a target multidimensional identification model; an evaluation module, used to evaluate a target power load curve of a target industrial equipment cluster based on the target multidimensional identification model to obtain an evaluation result, wherein the target power load curve is a graph of the time trend of power consumption within a third preset time period, and the evaluation result is used to reflect the power load priority corresponding to any industrial equipment in the target industrial equipment cluster; a control module, used to control the power load of the target industrial equipment cluster based on a preset industrial equipment cluster control strategy and the evaluation result.

[0012] Optionally, the training module is also used to determine multidimensional characteristic indicators, wherein the multidimensional characteristic indicators are used to reflect the operating properties of industrial equipment; determine feature correspondences based on the multidimensional characteristic indicators, industrial equipment information samples and regulation demand information samples, wherein the feature correspondences are used to represent the relationship between the operating properties of industrial equipment and multidimensional features; train an initial multidimensional identification model based on the feature correspondences to generate a target multidimensional identification model.

[0013] Optionally, the training module is also used to determine feature correspondences including: the correspondence between load peak and load peak type characteristics, the correspondence between the average duration of industrial equipment operation and load continuity characteristics, the correspondence between industrial equipment power state and load regularity characteristics, the correspondence between the average deviation of industrial equipment operating power and load periodic characteristics, and the correspondence between the average load rate of industrial equipment and load characteristics.

[0014] Optionally, the evaluation module is also used to determine the evaluation results including: load peak characteristic identification result score, load continuity characteristic identification result score, load regularity characteristic identification result score, load periodicity characteristic identification result score and load characteristic identification result score.

[0015] Optionally, the control module is also used to determine a judgment matrix based on a scaling construction method, wherein the judgment matrix is ​​used for the importance of indicators; and determine a preset number of weight indicators based on the judgment matrix, wherein the weight indicators correspond to the evaluation results.

[0016] Optionally, the control module is also used to perform weighted processing on the evaluation results based on a preset industrial equipment cluster control strategy and weight indicators to obtain a target score, wherein the target score includes the score corresponding to any target industrial equipment in the target industrial equipment cluster; and to control the power load of the target industrial equipment cluster based on the score corresponding to any target industrial equipment and the overall control requirement of the cluster.

[0017] According to one embodiment of the present invention, a computer-readable storage medium is further provided, in which a computer program is stored, wherein the computer program is configured to execute any of the above industrial equipment cluster control methods when running on a computer or a processor.

[0018] According to one embodiment of the present invention, there is also provided an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute any of the above industrial equipment cluster control methods.

[0019] According to one embodiment of the present invention, a computer program product is further provided, including a computer program, and when the computer program is executed by a processor, the industrial equipment cluster control method described in any one of the above items is implemented.

[0020] In an embodiment of the present invention, industrial equipment information samples and regulation demand information samples are obtained, wherein the industrial equipment information samples are used to represent the operating data of the industrial equipment cluster within a first preset time period, and the regulation demand information samples are used to represent the power consumption regulation target of the industrial equipment cluster within a second preset time period; an initial multidimensional identification model is trained based on the industrial equipment information samples and the regulation demand information samples to generate a target multidimensional identification model; a target power load curve of the target industrial equipment cluster is evaluated based on the target multidimensional identification model to obtain an evaluation result, wherein the target power load curve is a graph of the time trend of power consumption within a third preset time period, and the evaluation result is used to reflect the power load priority corresponding to any industrial equipment in the target industrial equipment cluster; the power load of the target industrial equipment cluster is regulated based on the preset industrial equipment cluster regulation strategy and the evaluation result to achieve The purpose is to accurately and efficiently formulate control strategies for industrial equipment under differences in equipment clusters and equipment characteristics, and to provide a powerful computing means for actual industrial equipment cluster control. Therefore, on the basis of industrial equipment information and external control demand information, a multi-dimensional identification model of equipment power consumption characteristics is constructed from load peak characteristics, load continuity characteristics, load regularity characteristics, load periodicity characteristics, and load characteristics. On the basis of the identification results, an industrial equipment cluster control strategy is established, and a list of equipment to be controlled and the control task decomposition are formed, so that the control plan can meet the equipment power consumption demand and attribute requirements as much as possible, and has a stronger technical effect in terms of calculation time and actual promotion process. The technical problem that the relevant technology will produce a higher dimensional calculation problem for the optimal solution of the cluster equipment control strategy and the technical problem of lack of consideration of the production habits, start-stop characteristics, rigidity and flexibility characteristics of industrial equipment are solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0022] Figure 1 is a flow chart of an industrial equipment cluster control method according to one embodiment of the present invention;

[0023] Figure 2 It is a structural block diagram of an industrial equipment cluster control device according to one embodiment of the present invention. DETAILED DESCRIPTION

[0024] To facilitate understanding, some descriptions of concepts related to the embodiments of the present invention are exemplarily provided for reference.

[0025] As shown below:

[0026] Cluster industrial equipment: refers to a group of interconnected and collaborative industrial equipment, usually composed of multiple devices, which can work together to complete specific production tasks. Multiple devices can communicate and coordinate through the network to achieve intelligent and automated production processes. Cluster industrial equipment usually includes production machines, sensors, control systems, computers and other equipment, which together form a production system that can improve production efficiency, reduce production costs, and enhance the flexibility and reliability of the production process.

[0027] Equipment-level power consumption characteristics: Equipment-level power consumption characteristics is a multifaceted concept that requires comprehensive consideration of factors such as equipment type, power, time period, duration, and waveform. By analyzing equipment-level power consumption characteristics, we can better understand the load of the power system and conduct targeted load management and optimization.

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In the description of this embodiment, unless otherwise specified, the meaning of "multiple" is two or more. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] According to one embodiment of the present invention, an embodiment of an industrial equipment cluster control method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] The method embodiment can be executed in an electronic device including a memory and a processor, a similar control device or a system. Taking an electronic device as an example, the electronic device may include one or more processors and a memory for storing data. Optionally, the electronic device may also include a communication device and a display device for communication functions. It can be understood by a person of ordinary skill in the art that the above structural description is only illustrative and does not limit the structure of the above electronic device. For example, the electronic device may also include more or fewer components than the above structural description, or have a configuration different from the above structural description.

[0032] The processor may include one or more processing units. For example, the processor may include a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP) chip, a microcontroller unit (MCU), a programmable logic device (field-programmable gate array, FPGA), a neural network processor (NPU), a tensor processing unit (TPU), an artificial intelligence (AI) type processor, and the like. Among them, different processing units may be independent components or integrated in one or more processors. In some instances, the electronic device may also include one or more processors.

[0033] The memory can be used to store computer programs, such as storing a computer program corresponding to the industrial equipment cluster control method in an embodiment of the present invention, and the processor implements the above-mentioned industrial equipment cluster control method by running the computer program stored in the memory. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0034] The communication device is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the communication device includes a network adapter (network interface controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the communication device can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0035] The display device may be, for example, a touch screen type liquid crystal display (LCD) and a touch display (also referred to as a "touch screen" or "touch display screen"). The liquid crystal display may enable a user to interact with a user interface of a mobile terminal. In some embodiments, the mobile terminal has a graphical user interface (GUI), and a user may interact with the GUI by finger contact and / or gestures on a touch-sensitive surface, wherein the human-computer interaction functions here may optionally include the following interactions: creating web pages, drawing, word processing, making electronic documents, games, video conferencing, instant messaging, sending and receiving emails, call interfaces, playing digital videos, playing digital music and / or web browsing, etc. The executable instructions for executing the above human-computer interaction functions are configured / stored in a computer program product or a readable storage medium executable by one or more processors.

[0036] In this embodiment, a method for controlling an industrial equipment cluster running on an electronic device is provided. Figure 1 is a flow chart of an industrial equipment cluster control method according to one embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0037] Step S10, obtaining industrial equipment information samples and control demand information samples, wherein the industrial equipment information samples are used to represent the operation data of the industrial equipment cluster within a first preset time period, and the control demand information samples are used to represent the power consumption control target of the industrial equipment cluster within a second preset time period;

[0038] In the embodiment of the present invention, the first preset time period can be exemplarily understood as the past year, which is not limited here.

[0039] Operation data can be understood as data that can show the operation status of industrial equipment within a certain period of time. For example, the operation data may include operation load data P t , sampling point time interval T0, rated power of the equipment P N , no restriction is given here.

[0040] The second preset time period can be understood as starting at the control time t 0,need The time required to start is T need , no restriction is given here.

[0041] The power consumption control target can be understood as the power consumption target that the industrial equipment cluster needs to achieve within a certain period of time. For example, the power consumption level can be controlled by adjusting parameters such as the operating status, operating hours, and operating efficiency of the equipment, which are not limited here.

[0042] Acquiring industrial equipment information samples and control demand information samples can be understood as acquiring the operating data of the industrial equipment cluster in a first preset time period and the power consumption control target of the industrial equipment cluster in a second preset time period. For example, acquiring the data of the industrial equipment cluster in the past year that can show the operating status of the industrial equipment in a certain time period, and the data starting from the control time t 0,need The time required to start is T need The power consumption target that the industrial equipment cluster needs to achieve within a certain period of time is not restricted here.

[0043] In an embodiment of the present invention, by acquiring industrial equipment information samples and regulation demand information samples, wherein the industrial equipment information samples are used to represent the operating data of the industrial equipment cluster within a first preset time period, and the regulation demand information samples are used to represent the power consumption regulation target of the industrial equipment cluster within a second preset time period, through data collection and demand analysis, a basis is provided for subsequent power consumption regulation, and a regulation plan is formulated to achieve the goals of energy conservation, emission reduction and effective utilization of resources, thereby achieving effective management and regulation of the energy consumption of industrial equipment.

[0044] Step S11, training an initial multidimensional identification model based on industrial equipment information samples and control demand information samples to generate a target multidimensional identification model;

[0045] In the embodiment of the present invention, the initial multidimensional identification model can be understood as a multidimensional identification model that has not been trained or whose parameters have not been optimized. For example, in the scenario of identifying the power consumption characteristics of industrial equipment, the multidimensional identification model can be a multivariate analysis model used to identify and understand the power consumption characteristics of industrial equipment, such as the shape of the load curve, the start and stop mode of the equipment, the operating time, etc., which are not limited here.

[0046] The target multidimensional identification model can be understood as a model obtained after training and optimizing the initial multidimensional identification model. For example, the target multidimensional identification model can more accurately identify and predict the power consumption characteristics of industrial equipment, and can be effectively used to formulate control strategies for clustered industrial equipment to meet the needs of power grid control, which is not limited here.

[0047] An initial multidimensional identification model is trained based on industrial equipment information samples and control demand information samples to generate a target multidimensional identification model. By way of example, it can be understood that by inputting industrial equipment information samples and control demand information samples into the initial multidimensional identification model, the model adjusts internal parameters by learning patterns and rules in the data to improve the ability to identify the power consumption characteristics of the equipment and the accuracy of predicting the control demand, and finally obtains the target multidimensional identification model, which is not limited here.

[0048] In an embodiment of the present invention, by training an initial multidimensional identification model based on industrial equipment information samples and control demand information samples to generate a target multidimensional identification model, the efficiency, accuracy and intelligence level of industrial equipment cluster control can be significantly improved, providing strong technical support for achieving optimized operation and load management of the power system.

[0049] Step S12, evaluating the target power load curve of the target industrial equipment cluster based on the target multidimensional identification model to obtain an evaluation result, wherein the target power load curve is a chart showing the trend of power consumption over time in a third preset time period, and the evaluation result is used to reflect the power load priority corresponding to any industrial equipment in the target industrial equipment cluster;

[0050] In the embodiment of the present invention, the target power load curve of the target industrial equipment cluster can be understood as actual power consumption data by way of example, and is not limited here.

[0051] The third preset time period can be understood as being within a certain period of time, which is not limited here.

[0052] The power load priority can be understood as, for example, if a certain device has higher load fluctuation and lower rigidity during the target time period, then it may be assigned a higher priority, which is not limited here.

[0053] Based on the target multidimensional identification model, the target power load curve of the target industrial equipment cluster is evaluated to obtain an evaluation result, which can be understood as a quantitative evaluation of the power control capability of each industrial equipment in the cluster, thereby obtaining an evaluation result, which is not limited here.

[0054] In an embodiment of the present invention, an evaluation result is obtained by evaluating the target power load curve of the target industrial equipment cluster based on a target multidimensional identification model, wherein the target power load curve is a graph of the power consumption over time in a third preset time period, and the evaluation result is used to reflect the power load priority corresponding to any industrial equipment in the target industrial equipment cluster, which can provide a more intelligent, efficient and safe regulation method for the power system, help to achieve refined management of power load, and at the same time ensure the smooth progress of industrial production, promote the rational use of power resources and the stable operation of the power system.

[0055] Step S13: regulating the power load of the target industrial equipment cluster based on the preset industrial equipment cluster regulation strategy and the evaluation result.

[0056] In the embodiment of the present invention, the preset industrial equipment cluster control strategy can be understood as a strategy for adjusting the power load of the industrial equipment cluster under specific conditions, which is not limited here.

[0057] The control of the power load of the target industrial equipment cluster based on the preset industrial equipment cluster control strategy and evaluation results can be understood as adjusting the power load of the industrial equipment cluster based on the preset industrial equipment cluster control strategy and the power load priority corresponding to any industrial equipment in the target industrial equipment cluster, which is not restricted here.

[0058] In the embodiment of the present invention, the power load of the target industrial equipment cluster is regulated based on the preset industrial equipment cluster regulation strategy and evaluation results, so as to intelligently respond to the regulation needs of the power grid, while minimizing the impact on industrial production and achieving optimal allocation of power resources. The combination of the preset regulation strategy and the evaluation results makes the regulation of the power system more accurate, efficient and intelligent, which helps to improve the stability and reliability of the power system, and also supports the continuity and economic benefits of industrial production.

[0059] By acquiring industrial equipment information samples and control demand information samples, where the industrial equipment information samples are used to represent the operating data of the industrial equipment cluster in the first preset time period, and the control demand information samples are used to represent the power consumption control target of the industrial equipment cluster in the second preset time period, through data collection and demand analysis, a basis is provided for subsequent power consumption control, and a control plan is formulated to achieve the goals of energy conservation, emission reduction and effective utilization of resources, and to achieve effective management and control of industrial equipment energy consumption. By training the initial multidimensional identification model based on the industrial equipment information samples and the control demand information samples and generating the target multidimensional identification model, the efficiency, accuracy and intelligence level of industrial equipment cluster control can be significantly improved, providing strong technical support for the optimization of power system operation and load management. The target power load curve of the target industrial equipment cluster is evaluated based on the target multidimensional identification model to obtain the evaluation result, wherein the target power load curve is a chart showing the trend of power consumption over time in the third preset time period, and the evaluation result is used to reflect the power load priority corresponding to any industrial equipment in the target industrial equipment cluster, which can provide a more intelligent, efficient and safe control method for the power system, help to achieve the refined management of power load, and at the same time ensure the smooth progress of industrial production, promote the rational use of power resources and the stable operation of the power system. By regulating the power load of the target industrial equipment cluster based on the preset industrial equipment cluster control strategy and evaluation results, it is possible to intelligently respond to the control needs of the power grid, while minimizing the impact on industrial production and achieving the optimal allocation of power resources. The combination of the preset control strategy and the evaluation results makes the control of the power system more accurate, efficient and intelligent, which helps to improve the stability and reliability of the power system, and also supports the continuity and economic benefits of industrial production.

[0060] Through the above steps, by obtaining industrial equipment information samples and control demand information samples, wherein the industrial equipment information samples are used to represent the operating data of the industrial equipment cluster within the first preset time period, and the control demand information samples are used to represent the power consumption control target of the industrial equipment cluster within the second preset time period; based on the industrial equipment information samples and the control demand information samples, an initial multidimensional identification model is trained to generate a target multidimensional identification model; based on the target multidimensional identification model, the target power load curve of the target industrial equipment cluster is evaluated to obtain an evaluation result, wherein the target power load curve is a chart of the power consumption change trend over time in the third preset time period, and the evaluation result is used to reflect the power load priority corresponding to any industrial equipment in the target industrial equipment cluster; based on the preset industrial equipment cluster control strategy and the evaluation result, the power load of the target industrial equipment cluster is regulated to achieve The purpose is to accurately and efficiently formulate control strategies for industrial equipment under differences in equipment clusters and equipment characteristics, and to provide a powerful computing means for actual industrial equipment cluster control. Therefore, on the basis of industrial equipment information and external control demand information, a multi-dimensional identification model of equipment power consumption characteristics is constructed from load peak characteristics, load continuity characteristics, load regularity characteristics, load periodicity characteristics, and load characteristics. On the basis of the identification results, an industrial equipment cluster control strategy is established, and a list of equipment to be controlled and the control task decomposition are formed, so that the control plan can meet the equipment power consumption demand and attribute requirements as much as possible, and has a stronger technical effect in terms of calculation time and actual promotion process. The technical problem that the relevant technology will produce a higher dimensional calculation problem for the optimal solution of the cluster equipment control strategy and the technical problem of lack of consideration of the production habits, start-stop characteristics, rigidity and flexibility characteristics of industrial equipment are solved.

[0061] Optionally, in step S11, training an initial multidimensional identification model based on the industrial equipment information samples and the regulation demand information samples to generate a target multidimensional identification model may include the following execution steps:

[0062] Step S111, determining a multidimensional characteristic index, wherein the multidimensional characteristic index is used to reflect the operation properties of the industrial equipment;

[0063] Step S112, determining a feature correspondence relationship based on the multidimensional characteristic index, the industrial equipment information sample, and the control demand information sample, wherein the feature correspondence relationship is used to represent the relationship between the operating attributes of the industrial equipment and the multidimensional characteristics;

[0064] Step S113: training an initial multi-dimensional recognition model based on the feature correspondence relationship to generate a target multi-dimensional recognition model.

[0065] In an embodiment of the present invention, the multidimensional characteristic index can be understood as a variety of indicators reflecting the characteristics of electricity consumption. By way of example, the multidimensional characteristic index can include the number of daily starts and stops, the average daily operating time, the equipment operating load rate, the equipment operating fluctuation rate, etc., which are not limited here.

[0066] The feature correspondence can be understood as the correlation or causal relationship between different features, and the mapping relationship between these features and the target variable. Exemplarily, the feature correspondence may include the correspondence between the load peak and the load peak type characteristics, the correspondence between the average duration of industrial equipment operation and the load continuity characteristics, the correspondence between the power state of industrial equipment and the load regularity characteristics, the correspondence between the average deviation of the operating power of industrial equipment and the load periodicity characteristics, and the correspondence between the average load rate of industrial equipment and the load characteristics, which are not limited here.

[0067] Determining the multidimensional characteristic index can be understood as calculating the multidimensional characteristic index used to reflect the operating attributes of industrial equipment. For example, the number of daily starts and stops can be calculated by combining formula (1) and formula (2), which is not limited here:

[0068]

[0069] In formula (1), N t∈T is the number of times the equipment starts and stops within the time period T, N T is the time data within a day, β t is the start / stop state of the device at time t. t When it is 1, it means the device is started at that moment. t When it is 0, the device has no startup status change.

[0070] The daily average running time can be calculated by combining formula (3) and formula (4), which is not limited here:

[0071]

[0072] In formula (3), T work is the duration of startup operation within the cycle, α t is the equipment operation status at time t, when α t When it is 1, it means the device is in operation. t When it is 0, it means the device is not running. T0 is the time interval between adjacent sampling points. N T The time is the time data within a day.

[0073] The average duration of equipment operation can be calculated using formula (5), which is not limited here:

[0074]

[0075] The equipment operation load rate can be calculated by combining formula (6) and formula (7). The equipment operation load rate refers to the ratio of the measured active power of the equipment to the rated power of the equipment. This indicator can include the instantaneous load rate at a certain moment and the average load rate within a cycle. When considering the characteristic indicators within the cycle, the statistics are mainly based on the equipment operation status, which is not limited here:

[0076]

[0077] In formula (6) and formula (7), η t is the load rate of the equipment at time t, P N is the rated power of the equipment, are the average load rate of the equipment under operation status during the period, T work is the set of operating time periods within the equipment cycle, N T,work is the number of times the time period set is run within the device cycle.

[0078] The equipment operation fluctuation rate can be calculated by combining formula (8) and formula (9). The equipment operation fluctuation rate refers to the fluctuation of active power at adjacent moments of equipment operation. This indicator can include the instantaneous equipment operation fluctuation rate at a certain moment and the average equipment operation fluctuation rate within a cycle. When considering the characteristic indicators within the cycle, the equipment operation fluctuation rate is mainly counted, which is not limited here:

[0079]

[0080] In formula (8) and formula (9), ξ t is the equipment operation fluctuation rate at time t, They are the average equipment operation fluctuation rates under the equipment operation status within the period.

[0081] Determining the feature correspondence based on multidimensional feature indicators, industrial equipment information samples, and control demand information samples can be understood as determining the correlation or causal relationship between different features, as well as the mapping relationship between these features and the target variable based on the multidimensional feature indicators, industrial equipment information samples, and control demand information samples. Exemplarily, determining the feature correspondence based on multidimensional feature indicators, industrial equipment information samples, and control demand information samples may include the following steps, which are not limited here:

[0082] (1) Identify the load peak characteristics as follows:

[0083] If the peak value of the equipment load and the point of [-2%, 0] peak deviation in a typical day both appear between 0:00 and 6:00, it is identified as a night peak type;

[0084] If the peak value of equipment load and the peak deviation of [-2%, 0] in a typical day both appear between 6:00 and 12:00, it is identified as a daily peak type (morning);

[0085] If the peak value of equipment load and the point of [-2%, 0] peak deviation in a typical day both appear between 12:00 and 18:00, it is identified as a daily peak type (afternoon);

[0086] If the peak value of equipment load and the point of [-2%, 0] peak deviation in a typical day both appear between 18:00 and 24:00, it is identified as a late peak type;

[0087] If the peak value of equipment load and the peak deviation of [-2%, 0] in a typical day appear in multiple time periods, it is identified as a multi-peak type.

[0088] (2) Identify the load continuity characteristics, as follows:

[0089] If the average number of equipment operations in a typical day lasts for more than 12 hours, it is identified as Class I random type;

[0090] If the average number of equipment operations in a typical day lasts 4-12 hours, it is identified as a Class II random type;

[0091] If the average number of equipment operations in a typical day lasts 2-4 hours, it is identified as a Class III random type;

[0092] If the equipment runs for less than 2 hours on a typical day, it is identified as a Class IV random type.

[0093] (3) Identify the load regularity characteristics, as follows:

[0094] Constant power type: The equipment maintains the same or similar active power at multiple consecutive moments during a typical day, and the average power deviation does not exceed ±5%;

[0095] Step power type: The equipment operating period in a typical day presents multiple different steps of active power levels, and the average deviation of each step of active power does not exceed ±5%;

[0096] Continuous fluctuation type: The active power of the equipment during a typical day shows continuous fluctuations, and the average power deviation exceeds ±5%.

[0097] (4) Identify the load periodicity characteristics, as follows:

[0098] Similarity of periodic power consumption: within the control demand period, the average deviation of equipment operating power at the same time on multiple sample days shall not exceed ±10%;

[0099] Periodic power consumption difference type: within the control demand period, the average deviation of equipment operating power at the same time on multiple sample days exceeds ±10%.

[0100] (5) Carry out load characteristic identification, as follows:

[0101] Light load type: the average load rate of the equipment during operation is ≤80%;

[0102] Heavy-load type: The average load rate of the equipment during operation is greater than 80% and less than 99%;

[0103] Full load type: The average load rate of the equipment during operation is ≥99%.

[0104] In an embodiment of the present invention, a multidimensional characteristic index is first determined, wherein the multidimensional characteristic index is used to reflect the operating properties of industrial equipment. Then, a feature correspondence is determined based on the multidimensional characteristic index, industrial equipment information samples, and control demand information samples, wherein the feature correspondence is used to represent the relationship between the operating properties of industrial equipment and the multidimensional characteristics. Finally, an initial multidimensional identification model is trained based on the feature correspondence to generate a target multidimensional identification model, which is of great significance for improving the intelligence level of the power system, optimizing the synergistic relationship between industrial production and power control, and ensuring the stability and reliability of power grid operation.

[0105] Optionally, in step S112, the feature correspondence relationship includes:

[0106] The correspondence between load peak and load peak characteristics, the correspondence between the average duration of industrial equipment operation and the load continuity characteristics, the correspondence between industrial equipment power state and load regularity characteristics, the correspondence between the average deviation of industrial equipment operating power and load periodic characteristics, and the correspondence between the average load rate of industrial equipment and load characteristics.

[0107] In an embodiment of the present invention, the correspondence between the load peak and the load peak type characteristics can be identified illustratively according to the following conditions: if the equipment load peak and the [-2%, 0] peak deviation points in a typical day both appear between 0:00 and 6:00, it is identified as a night peak type; if the equipment load peak and the [-2%, 0] peak deviation points in a typical day both appear between 6:00 and 12:00, it is identified as a day peak type (morning); if the equipment load peak and the [-2%, 0] peak deviation points in a typical day both appear between 12:00 and 18:00, it is identified as a day peak type (afternoon); if the equipment load peak and the [-2%, 0] peak deviation points in a typical day both appear between 18:00 and 24:00, it is identified as a night peak type; if the equipment load peak and the [-2%, 0] peak deviation points in a typical day both appear in multiple time periods, it is identified as a multi-peak type, which is not limited here.

[0108] The correspondence between the average duration of industrial equipment operation and the load continuity characteristics can be identified illustratively according to the following conditions: if the average duration of equipment operation in a typical day exceeds 12 hours, it is identified as a Class I random type; if the average duration of equipment operation in a typical day is 4-12 hours, it is identified as a Class II random type; if the average duration of equipment operation in a typical day is 2-4 hours, it is identified as a Class III random type; if the average duration of equipment operation in a typical day is less than 2 hours, it is identified as a Class IV random type, which is not restricted here.

[0109] The correspondence between the power state of industrial equipment and the regularity characteristics of the load can be identified exemplarily according to the following conditions: constant power type: the equipment maintains the same or similar active power at multiple consecutive moments during a typical day, and the average power deviation does not exceed ±5%; step power type: the equipment presents multiple different steps of active power levels during operation periods during a typical day, and the average deviation of each step of active power does not exceed ±5%; continuous fluctuation type: the active power of the equipment during a typical day shows continuous fluctuations, and the average power deviation exceeds ±5%, which is not restricted here.

[0110] The correspondence between the average deviation of the operating power of industrial equipment and the periodic characteristics of the load can be identified exemplarily according to the following conditions: periodic power consumption similarity type: within the regulation demand period, the average deviation of the equipment operating power at the same time on multiple sample days does not exceed ±10%; periodic power consumption difference type: within the regulation demand period, the average deviation of the equipment operating power at the same time on multiple sample days exceeds ±10%, which is not restricted here.

[0111] The correspondence between the average load rate of industrial equipment and the load characteristics can be identified exemplarily according to the following conditions: light load: the average load rate of equipment during operation is ≤80%; heavy load: the average load rate of equipment during operation is >80% and <99%; full load: the average load rate of equipment during operation is ≥99%, which is not limited here.

[0112] In the embodiments of the present invention, by determining the correspondence between load peak and load peak characteristics, the correspondence between the average duration of industrial equipment operation and load continuity characteristics, the correspondence between industrial equipment power state and load regularity characteristics, the correspondence between the average deviation of industrial equipment operating power and load periodic characteristics, and the correspondence between the average load rate of industrial equipment and load characteristics, a deep understanding of the power consumption characteristics of industrial equipment can be achieved, providing key information for formulating efficient, intelligent and personalized power control strategies, which helps to improve the stability and economy of the power system while reducing the impact on industrial production.

[0113] Optionally, in step S12, the evaluation result includes:

[0114] Load peak characteristic identification result scoring, load continuity characteristic identification result scoring, load regularity characteristic identification result scoring, load periodicity characteristic identification result scoring and load characteristic identification result scoring.

[0115] In the embodiment of the present invention, the load peak characteristic identification result score can be evaluated by formula (10) for example, which is not limited here:

[0116]

[0117] The load continuity characteristic identification result score can be evaluated by formula (11) for example, which is not limited here:

[0118]

[0119] The load regularity feature identification result score can be evaluated by formula (12) for example, which is not limited here:

[0120]

[0121] The load periodicity characteristic identification result score can be evaluated by formula (13) for example, which is not limited here:

[0122]

[0123] The load characteristic identification result score can be evaluated by using formula (14) for example, which is not limited here:

[0124]

[0125] In the embodiment of the present invention, by evaluating the load peak characteristic identification result score, the load continuity characteristic identification result score, the load regularity characteristic identification result score, the load periodic characteristic identification result score and the load characteristic identification result score, not only can the power consumption characteristics of the equipment be identified, but also a more reasonable and effective power control strategy can be formulated based on these characteristics.

[0126] Optionally, the industrial equipment cluster control method may further include the following execution steps:

[0127] Step S131, determining a judgment matrix based on a scaling construction method, wherein the judgment matrix is ​​used for the importance between indicators;

[0128] Step S132, determining a preset number of weight indicators based on the judgment matrix, wherein the weight indicators correspond to the evaluation results.

[0129] In the embodiment of the present invention, the judgment matrix is ​​obtained based on the transitivity of the importance between indicators. For example, the judgment matrix B can be expressed by formula (15):* , there is no restriction here:

[0130]

[0131] The preset number can be understood as the number of pre-set weight indicators. Exemplarily, the preset number can be 5, which is not limited here.

[0132] The weight indicators can be understood to include, by way of example, y1, y2, y3, y4, and y5, which are not limited here.

[0133] The judgment matrix determined based on the scale construction method can be understood as sorting the n weight indicators to be determined in a non-decreasing manner, comparing the importance of two adjacent indicators and recording them as a scale. The judgment matrices obtained in this way all meet the consistency and do not need to be tested. The improved analytic hierarchy process (AHP) is used to determine the matrix scale as follows: Compared with two elements, they have the same importance, and the scale m i is 1.0; compared with the two elements, the former is slightly more important than the latter, and the scale is m i is 1.2; compared with the two elements, the former is obviously more important than the latter, and the scale m i is 1.4; compared with the two elements, the former is extremely important than the latter, and the scale m i is 1.6; compared with the two elements, the former is more important than the latter, and the scale is m i Suppose there are five weighted indicators y1, y2, y3, y, 4y that need to be determined. The indicators are subjectively sorted according to the principle of non-decreasing importance. The result is y1≥y2≥y3≥y4≥y5. Determine the scale value according to the above steps, and record the corresponding scale as m i Finally, we get the scale values ​​m1, m2, m3, and m4 between all adjacent indicators. According to the transitivity of importance, we get other elements in the judgment matrix. Then the final judgment matrix B * As shown in formula (15), there is no restriction here.

[0134] Determining a preset number of weight indicators based on the judgment matrix can be understood as, for example, using formula (16) to calculate the subjective weights of various power consumption characteristics identifications, which is not limited here:

[0135]

[0136] In formula (16), g ij is the judgment matrix B * The element at row i and column j in .

[0137] In an embodiment of the present invention, a judgment matrix is ​​first determined based on a scaling construction method, wherein the judgment matrix is ​​used to determine the importance of indicators, and then a preset number of weight indicators are determined based on the judgment matrix, wherein the weight indicators correspond to the evaluation results, which helps to reduce the subjectivity and arbitrariness in the decision-making process and improve the scientificity and accuracy of the decision.

[0138] Optionally, regulating the power load of the target industrial equipment cluster based on the preset industrial equipment cluster regulation strategy and the evaluation result may include the following execution steps:

[0139] The evaluation results are weighted based on the preset industrial equipment cluster control strategy and weight indicators to obtain a target score, wherein the target score includes the score corresponding to any target industrial equipment in the target industrial equipment cluster;

[0140] The power load of the target industrial equipment cluster is regulated based on the score corresponding to any target industrial equipment and the overall control requirement of the cluster.

[0141] In the embodiment of the present invention, weighted processing of the evaluation results based on the preset industrial equipment cluster control strategy and weight index can be exemplarily understood as weighted processing of the evaluation results based on the preset industrial equipment cluster control strategy and weight index using formula (17), which is not limited here:

[0142]

[0143] In formula (17), G m The comprehensive score for the priority ranking of device m, D m,i is the score of the i-th power consumption characteristic dimension of equipment m, β i is the scoring weight of the i-th electricity consumption characteristic dimension.

[0144] The power load of the target industrial equipment cluster is regulated based on the score corresponding to any target industrial equipment and the overall control amount required by the cluster. It can be understood that the power load of the target industrial equipment cluster is regulated according to the preset industrial equipment cluster control strategy based on the score corresponding to any target industrial equipment and the overall control amount required by the cluster.

[0145] In an embodiment of the present invention, the evaluation results are first weighted based on a preset industrial equipment cluster control strategy and weight indicators to obtain a target score, wherein the target score includes a score corresponding to any target industrial equipment in the target industrial equipment cluster, and then the power load of the target industrial equipment cluster is controlled based on the score corresponding to any target industrial equipment and the overall control requirement of the cluster. By finely managing the power load of industrial equipment, overload or underload of the power system can be effectively avoided, thereby improving the stability and reliability of the power grid.

[0146] The present invention aims to improve the current cluster industrial equipment control strategy, a cluster industrial equipment control strategy based on multi-dimensional identification of equipment power consumption characteristics, characterized in that it includes the following steps:

[0147] Step 1: Collect industrial equipment information and external regulation demand information;

[0148] Step 2: Establish a multi-dimensional identification model of equipment power consumption characteristics;

[0149] Step 3: Develop a cluster industrial equipment control strategy that takes into account the multi-dimensional identification results of power consumption characteristics.

[0150] 1. In step 1, collect industrial equipment information and external control demand information. The industrial equipment information includes the operating load data P of the industrial equipment in the past year. t , sampling point time interval T0, rated power of the equipment P N ; External control demand information includes the overall control quantity P required by the cluster need , the required adjustment time T need , starting control time t 0,need .

[0151] 2. In step 2, a multi-dimensional identification model of equipment power consumption characteristics is established, as follows:

[0152] Step 2-1 calculates the multi-dimensional characteristic process index, as shown in formula (1) and formula (2):

[0153] (1) Daily start and stop times:

[0154]

[0155] In formula (1), N t∈T is the number of times the equipment starts and stops within the time period T, N T is the time data within a day, β t is the start / stop state of the device at time t. t When it is 1, it means the device is started at that moment. t When it is 0, the device has no startup status change.

[0156] (2) Daily average operating time, as shown in formula (3) and formula (4):

[0157]

[0158] In formula (3), T work is the duration of startup operation within the cycle, α t is the equipment operation status at time t, when α t When it is 1, it means the device is in operation. tWhen it is 0, it means the device is not running. T0 is the time interval between adjacent sampling points. N T The time is the time data within a day.

[0159] The average duration of equipment operation is shown in formula (5):

[0160]

[0161] (3) Equipment operating load rate: refers to the ratio of the measured active power of the equipment to the rated power of the equipment. This indicator can include the instantaneous load rate at a certain moment and the average load rate within a cycle. When considering the characteristic indicators within a cycle, the statistics are mainly based on the equipment operating status, as shown in formulas (6) and (7).

[0162]

[0163] In formula (6) and formula (7), η t is the load rate of the equipment at time t, P N is the rated power of the equipment, are the average load rate of the equipment under operation status during the period, T work is the set of operating time periods within the equipment cycle, N T,work is the number of times the time period set is run within the device cycle.

[0164] (4) Equipment operation fluctuation rate: refers to the fluctuation of active power at adjacent moments of equipment operation. This indicator can include the instantaneous equipment operation fluctuation rate at a certain moment and the average equipment operation fluctuation rate within a cycle. When considering the characteristic indicators within the cycle, the equipment operation fluctuation rate is mainly statistically analyzed, as shown in formulas (8) and (9).

[0165]

[0166]

[0167] In formula (8) and formula (9), ξ t is the equipment operation fluctuation rate at time t, They are the average equipment operation fluctuation rates under the equipment operation status within the period.

[0168] Step 2-2: Identify the load peak characteristics, as follows:

[0169] If the peak value of the equipment load and the point of [-2%, 0] peak deviation in a typical day both appear between 0:00 and 6:00, it is identified as a night peak type;

[0170] If the peak value of equipment load and the peak deviation of [-2%, 0] in a typical day both appear between 6:00 and 12:00, it is identified as a daily peak type (morning);

[0171] If the peak value of equipment load and the point of [-2%, 0] peak deviation in a typical day both appear between 12:00 and 18:00, it is identified as a daily peak type (afternoon);

[0172] If the peak value of equipment load and the point of [-2%, 0] peak deviation in a typical day both appear between 18:00 and 24:00, it is identified as a late peak type;

[0173] If the peak value of equipment load and the peak deviation of [-2%, 0] in a typical day appear in multiple time periods, it is identified as a multi-peak type.

[0174] Step 2-3: Identify the load continuity characteristics, as follows:

[0175] If the average number of equipment operations in a typical day lasts for more than 12 hours, it is identified as Class I random type;

[0176] If the average number of equipment operations in a typical day lasts 4-12 hours, it is identified as a Class II random type;

[0177] If the average number of equipment operations in a typical day lasts 2-4 hours, it is identified as a Class III random type;

[0178] If the equipment runs for less than 2 hours on a typical day, it is identified as a Class IV random type.

[0179] Step 2-4: Identify the load regularity characteristics, as follows:

[0180] Constant power type: The equipment maintains the same or similar active power at multiple consecutive moments during a typical day, and the average power deviation does not exceed ±5%;

[0181] Step power type: The equipment operating period in a typical day presents multiple different steps of active power levels, and the average deviation of each step of active power does not exceed ±5%;

[0182] Continuous fluctuation type: The active power of the equipment during a typical day shows continuous fluctuations, and the average power deviation exceeds ±5%.

[0183] Step 2-5: Identify the load periodicity characteristics, as follows:

[0184] Similarity of periodic power consumption: within the control demand period, the average deviation of equipment operating power at the same time on multiple sample days shall not exceed ±10%;

[0185] Periodic power consumption difference type: within the control demand period, the average deviation of equipment operating power at the same time on multiple sample days exceeds ±10%.

[0186] Step 2-6: Perform load feature identification, as follows:

[0187] Light load type: the average load rate of the equipment during operation is ≤80%;

[0188] Heavy-load type: The average load rate of the equipment during operation is greater than 80% and less than 99%;

[0189] Full load type: The average load rate of the equipment during operation is ≥99%.

[0190] 3. In step 3, formulate a cluster industrial equipment control strategy that takes into account the multi-dimensional identification results of power consumption characteristics, as follows:

[0191] Step 3-1: Use the scale construction method to determine the judgment matrix, sort the n weight indicators that need to be determined in a non-decreasing manner, compare the importance of two adjacent indicators and record them as a scale. The judgment matrices obtained in this way all meet the consistency and do not need to be tested. The improved AHP judgment matrix scale is as follows:

[0192] Compared with two elements, they have the same importance, scale m i is 1.0;

[0193] Compared with the two elements, the former is slightly more important than the latter, with a scale of m i is 1.2;

[0194] Compared with the two elements, the former is obviously more important than the latter, and the scale is m i is 1.4;

[0195] Compared with the two elements, the former is extremely important than the latter, with a scale of m i is 1.6;

[0196] Compared with two elements, the former is more important than the latter, with scale m i is 1.8.

[0197] Suppose there are five weighted indicators y1, y2, y3, y4, and y5 that need to be determined. The indicators are subjectively sorted according to the principle of non-decreasing importance. The result is y1≥y2≥y3≥y4≥y5. Determine the scale value according to the above steps, and record the corresponding scale as m i Finally, we get the scale values ​​m1, m2, m3, and m4 between all adjacent indicators. According to the transitivity of importance, we get other elements in the judgment matrix. Then the final judgment matrix B * As shown in formula (15):

[0198]

[0199] The judgment matrix obtained in this way satisfies consistency and can be directly used for weight calculation without verification. The subjective weights of various power consumption characteristics can be calculated by formula (16):

[0200]

[0201] In formula (16), g ij is the judgment matrix B * The element at row i and column j in .

[0202] Step 3-2: Perform fuzzy evaluation on the identification results of the power consumption characteristics of each device:

[0203] (1) Score the load peak characteristic identification results according to formula (10):

[0204]

[0205] The load continuity feature identification results are scored according to formula (11):

[0206]

[0207] According to formula (12), the load regularity feature identification results are scored:

[0208]

[0209] Scoring of load periodicity characteristics identification results:

[0210]

[0211] The load characteristic identification results are scored according to formula (14):

[0212]

[0213] Step 3-3: According to formula (17), each device is regulated and ranked according to the priority and comprehensive score:

[0214]

[0215] In formula (17), G m The comprehensive score for the priority ranking of device m, D m,i is the score of the i-th power consumption characteristic dimension of equipment m, β i is the scoring weight of the i-th electricity consumption characteristic dimension.

[0216] Step 3-4: Sort the equipment control priorities from high to low according to their comprehensive scores, and perform load reduction control in sequence until the total reduction amount reaches the overall control amount required by the cluster.

[0217] Based on industrial equipment information and external control demand information, the present invention first constructs a multidimensional identification model of equipment power consumption characteristics from load peak characteristics, load continuity characteristics, load regularity characteristics, load periodicity characteristics, and load characteristics. Based on the identification results, an industrial equipment cluster control strategy is established to form a list of equipment to be regulated and a decomposition of control tasks. The advantage of the present invention is that a cluster control strategy is formulated based on the identification results of the multidimensional power consumption characteristics of the equipment, so that the control plan can meet the power consumption demand and attribute requirements of the equipment as much as possible. Secondly, the strategy formulation of the present invention does not adopt an optimization algorithm, and has greater convenience in calculation time and actual promotion.

[0218] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of various embodiments of the present invention.

[0219] In this embodiment, an industrial equipment cluster control device is also provided, which is used to implement the above embodiments and preferred implementations, and will not be repeated here. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0220] Figure 2 is a structural block diagram of an industrial equipment cluster control device according to one embodiment of the present invention, such as Figure 2As shown, an industrial equipment cluster control device 200 is used as an example, and the device includes: an acquisition module 201, which is used to acquire industrial equipment information samples and control demand information samples, wherein the industrial equipment information samples are used to represent the operating data of the industrial equipment cluster within a first preset time period, and the control demand information samples are used to represent the power consumption control target of the industrial equipment cluster within a second preset time period; a training module 202, which is used to train an initial multidimensional identification model based on the industrial equipment information samples and the control demand information samples to generate a target multidimensional identification model; an evaluation module 203, which is used to evaluate the target power load curve of the target industrial equipment cluster based on the target multidimensional identification model to obtain an evaluation result, wherein the target power load curve is a graph of the trend of power consumption over time within a third preset time period, and the evaluation result is used to reflect the power load priority corresponding to any industrial equipment in the target industrial equipment cluster; a control module 204, which is used to control the power load of the target industrial equipment cluster based on the preset industrial equipment cluster control strategy and the evaluation result.

[0221] Optionally, the training module 202 is also used to determine multidimensional characteristic indicators, wherein the multidimensional characteristic indicators are used to reflect the operating properties of industrial equipment; determine feature correspondences based on the multidimensional characteristic indicators, industrial equipment information samples and regulation demand information samples, wherein the feature correspondences are used to represent the relationship between the operating properties of industrial equipment and multidimensional features; train an initial multidimensional identification model based on the feature correspondences to generate a target multidimensional identification model.

[0222] Optionally, the training module 202 is also used to determine feature correspondences including: the correspondence between load peak and load peak type characteristics, the correspondence between the average duration of industrial equipment operation and load continuity characteristics, the correspondence between industrial equipment power state and load regularity characteristics, the correspondence between the average deviation of industrial equipment operating power and load periodic characteristics, and the correspondence between the average load rate of industrial equipment and load characteristics.

[0223] Optionally, the evaluation module 203 is further used to determine the evaluation results including: a load peak characteristic identification result score, a load continuity characteristic identification result score, a load regularity characteristic identification result score, a load periodicity characteristic identification result score and a load characteristic identification result score.

[0224] Optionally, the control module 204 is further used to determine a judgment matrix based on a scaling construction method, wherein the judgment matrix is ​​used for the importance of indicators; and determine a preset number of weight indicators based on the judgment matrix, wherein the weight indicators correspond to the evaluation results.

[0225] Optionally, the control module 204 is also used to perform weighted processing on the evaluation results based on a preset industrial equipment cluster control strategy and weight indicators to obtain a target score, wherein the target score includes the score corresponding to any target industrial equipment in the target industrial equipment cluster; and to control the power load of the target industrial equipment cluster based on the score corresponding to any target industrial equipment and the overall control requirement of the cluster.

[0226] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0227] An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored. The computer program is configured to execute the steps of any of the above method embodiments when running on a computer or a processor.

[0228] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0229] Step S10, obtaining industrial equipment information samples and control demand information samples, wherein the industrial equipment information samples are used to represent the operation data of the industrial equipment cluster within a first preset time period, and the control demand information samples are used to represent the power consumption control target of the industrial equipment cluster within a second preset time period;

[0230] Step S11, training an initial multidimensional identification model based on industrial equipment information samples and control demand information samples to generate a target multidimensional identification model;

[0231] Step S12, evaluating the target power load curve of the target industrial equipment cluster based on the target multidimensional identification model to obtain an evaluation result, wherein the target power load curve is a chart showing the trend of power consumption over time in a third preset time period, and the evaluation result is used to reflect the power load priority corresponding to any industrial equipment in the target industrial equipment cluster;

[0232] Step S13: regulating the power load of the target industrial equipment cluster based on the preset industrial equipment cluster regulation strategy and the evaluation result.

[0233] Optionally, in this embodiment, the above-mentioned computer-readable storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0234] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0235] Optionally, in this embodiment, the processor in the electronic device may be configured to run a computer program to perform the following steps:

[0236] Step S10, obtaining industrial equipment information samples and control demand information samples, wherein the industrial equipment information samples are used to represent the operation data of the industrial equipment cluster within a first preset time period, and the control demand information samples are used to represent the power consumption control target of the industrial equipment cluster within a second preset time period;

[0237] Step S11, training an initial multidimensional identification model based on industrial equipment information samples and control demand information samples to generate a target multidimensional identification model;

[0238] Step S12, evaluating the target power load curve of the target industrial equipment cluster based on the target multidimensional identification model to obtain an evaluation result, wherein the target power load curve is a chart showing the trend of power consumption over time in a third preset time period, and the evaluation result is used to reflect the power load priority corresponding to any industrial equipment in the target industrial equipment cluster;

[0239] Step S13: regulating the power load of the target industrial equipment cluster based on the preset industrial equipment cluster regulation strategy and the evaluation result.

[0240] An embodiment of the present invention further provides a computer program product, including a computer program, which implements the steps in any of the above method embodiments when executed by a processor.

[0241] Optionally, in this embodiment, the computer program in the above computer program product may be configured to perform the following steps when executed by a processor:

[0242] Step S10, obtaining industrial equipment information samples and control demand information samples, wherein the industrial equipment information samples are used to represent the operation data of the industrial equipment cluster within a first preset time period, and the control demand information samples are used to represent the power consumption control target of the industrial equipment cluster within a second preset time period;

[0243] Step S11, training an initial multidimensional identification model based on industrial equipment information samples and control demand information samples to generate a target multidimensional identification model;

[0244] Step S12, evaluating the target power load curve of the target industrial equipment cluster based on the target multidimensional identification model to obtain an evaluation result, wherein the target power load curve is a chart showing the trend of power consumption over time in a third preset time period, and the evaluation result is used to reflect the power load priority corresponding to any industrial equipment in the target industrial equipment cluster;

[0245] Step S13: regulating the power load of the target industrial equipment cluster based on the preset industrial equipment cluster regulation strategy and the evaluation result.

[0246] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0247] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0248] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0249] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, 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 units or modules, which can be electrical or other forms.

[0250] 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 units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0251] 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.

[0252] If the integrated 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 technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk, etc., various media that can store program codes.

[0253] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for controlling an industrial equipment cluster, characterized in that: The method comprises: Acquire industrial equipment information samples and regulation demand information samples, wherein the industrial equipment information samples are used to represent the operation data of the industrial equipment cluster within a first preset time period, and the regulation demand information samples are used to represent the power consumption regulation target of the industrial equipment cluster within a second preset time period; Training an initial multidimensional identification model based on the industrial equipment information sample and the regulation demand information sample to generate a target multidimensional identification model; Based on the target multidimensional identification model, the target power load curve of the target industrial equipment cluster is evaluated to obtain an evaluation result, wherein the target power load curve is a chart showing the trend of power consumption over time in a third preset time period, and the evaluation result is used to reflect the power load priority corresponding to any industrial equipment in the target industrial equipment cluster; The power load of the target industrial equipment cluster is regulated based on the preset industrial equipment cluster regulation strategy and the evaluation result.

2. The method according to claim 1, characterized in that The training of the initial multidimensional identification model based on the industrial equipment information sample and the regulation demand information sample to generate the target multidimensional identification model includes: Determining a multidimensional characteristic index, wherein the multidimensional characteristic index is used to reflect the operating properties of the industrial equipment; Determining a feature correspondence relationship based on the multidimensional characteristic index, the industrial equipment information sample and the regulation demand information sample, wherein the feature correspondence relationship is used to represent the relationship between the operating attributes of the industrial equipment and the multidimensional characteristics; The initial multi-dimensional recognition model is trained based on the feature correspondence to generate the target multi-dimensional recognition model.

3. The method according to claim 2, characterized in that The characteristic correspondence includes: the correspondence between load peak and load peak type characteristics, the correspondence between the average duration of industrial equipment operation and load continuity characteristics, the correspondence between industrial equipment power state and load regularity characteristics, the correspondence between the average deviation of industrial equipment operating power and load periodic characteristics, and the correspondence between the average load rate of industrial equipment and load characteristics.

4. The method according to claim 1, characterized in that: The evaluation results include: a load peak characteristic identification result score, a load continuity characteristic identification result score, a load regularity characteristic identification result score, a load periodicity characteristic identification result score, and a load characteristic identification result score.

5. The method according to claim 1, characterized in that The method further comprises: Determine a judgment matrix based on a scale construction method, wherein the judgment matrix is ​​used for the importance between indicators; A preset number of weight indicators are determined based on the judgment matrix, wherein the weight indicators correspond to the evaluation results.

6. The method according to claim 5, characterized in that The regulating the power load of the target industrial equipment cluster based on the preset industrial equipment cluster regulation strategy and the evaluation result includes: The evaluation result is weighted based on the preset industrial equipment cluster control strategy and the weight index to obtain a target score, wherein the target score includes a score corresponding to any target industrial equipment in the target industrial equipment cluster; The power load of the target industrial equipment cluster is regulated based on the score corresponding to any target industrial equipment and the overall regulation amount required by the cluster.

7. An industrial equipment cluster control device, characterized in that: The device comprises: An acquisition module, used to acquire industrial equipment information samples and control demand information samples, wherein the industrial equipment information samples are used to represent the operation data of the industrial equipment cluster within a first preset time period, and the control demand information samples are used to represent the power consumption control target of the industrial equipment cluster within a second preset time period; A training module, used to train an initial multidimensional identification model based on the industrial equipment information sample and the regulation demand information sample to generate a target multidimensional identification model; An evaluation module, used to evaluate the target power load curve of the target industrial equipment cluster based on the target multidimensional identification model to obtain an evaluation result, wherein the target power load curve is a chart showing the trend of power consumption over time in a third preset time period, and the evaluation result is used to reflect the power load priority corresponding to any industrial equipment in the target industrial equipment cluster; A control module is used to control the power load of the target industrial equipment cluster based on a preset industrial equipment cluster control strategy and the evaluation result.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the industrial equipment cluster control method described in any one of claims 1 to 6 when running on a computer or a processor.

9. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the industrial equipment cluster control method described in any one of claims 1 to 6.

10. An electronic device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to run the computer program to execute the industrial equipment cluster control method described in any one of claims 1 to 6 above.

Images