Artificial intelligence-based distributed wind-solar-storage integrated device intelligent scheduling system

Abstract

The application discloses an intelligent scheduling system of a distributed wind-solar energy storage integrated equipment based on artificial intelligence, relates to the technical field of energy storage equipment scheduling, and is used for solving the problems of increased abnormal operation risk of high-energy-consumption components and reduced energy efficiency level, calculating load distribution characteristics and judging whether a low load mode is present by detecting total output power and external load power, collecting component current data in the low load mode to evaluate current state, detecting standby power consumption and calculating an energy consumption index, generating an energy consumption level according to energy consumption index sorting, screening high-energy-consumption components and obtaining the temperature and operation state of the high-energy-consumption components, generating an energy-saving scheduling score and determining whether to execute an energy-saving mode and outputting a prompt signal, realizing low load identification and high-energy-consumption component screening by real-time detection of power, current, temperature and operation state, and automatically triggering an energy-saving mode and a prompt signal in combination with the scheduling score, so that the energy consumption is reduced and the system scheduling efficiency and safety are improved.

Description

Technical Field

[0001] This invention relates to the field of energy storage equipment scheduling technology, and more specifically, to an intelligent scheduling system for distributed wind-solar-storage integrated equipment based on artificial intelligence. Background Technology

[0002] With the rapid development of the new energy industry, distributed wind power and photovoltaic power generation are gradually being widely used on both the grid and user sides. To address the issues of high volatility and poor stability in new energy power generation, it is typically necessary to integrate energy storage units with wind and solar power systems to form integrated distributed wind-solar-energy storage devices. These devices enable local consumption and regulation of new energy power generation, improving the reliability and flexibility of the power system.

[0003] The existing technology has the following shortcomings:

[0004] Currently, existing technologies in distributed wind-solar-storage integrated equipment rely primarily on power detection for extensive energy consumption management. They cannot accurately identify the differences in energy consumption among components under low-load conditions and lack comprehensive analysis of current status, temperature, and operating status. This leads to an increased risk of abnormal operation of high-energy-consuming components and a reduction in energy efficiency. Therefore, an intelligent scheduling system for distributed wind-solar-storage integrated equipment based on artificial intelligence is proposed.

[0005] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide an intelligent scheduling system for distributed wind-solar-storage integrated equipment based on artificial intelligence, which solves the problems mentioned in the background art by using multi-source operation data fusion analysis and energy-saving scheduling scoring algorithms.

[0007] To achieve the above objectives, the present invention provides the following technical solution: an intelligent scheduling system for distributed wind-solar-storage integrated equipment based on artificial intelligence, comprising a power detection module, a current assessment module, an energy consumption identification module, and an energy-saving scheduling module, the functions of each module being as follows:

[0008] The power detection module is used to detect the total output power of the equipment and the power of the external load branch. It calculates the load distribution characteristics based on the power of the external load branch and determines whether the equipment is in a low-load mode based on the total output power and the load distribution characteristics.

[0009] The current assessment module is used to collect current data of each component of the device and assess the current status when the device is in low load mode, detect the standby power consumption of each component of the device, and calculate the energy consumption index of each component of the device based on the current status.

[0010] The energy consumption identification module is used to sort each component according to the energy consumption index and generate an energy consumption level. Based on the energy consumption level, the module filters each component to obtain high-energy-consuming components and obtains the current temperature and operating status of the high-energy-consuming components.

[0011] The energy-saving scheduling module is used to generate an energy-saving scheduling score for high-energy-consuming components by comprehensively considering the current temperature and operating status. Based on the energy-saving scheduling score, it determines whether to execute the energy-saving mode for high-energy-consuming components and outputs an energy-saving prompt signal.

[0012] In a preferred embodiment, the power detection module has a preset acquisition period and acquires the voltage and current at the total output terminal of the device through voltage transformers and current transformers.

[0013] Multiply the voltage and current at the total output terminal of the device to obtain the instantaneous total output power of the device;

[0014] The average value of the device's instantaneous total output power within the preset acquisition period is taken as the device's total output power;

[0015] The instantaneous power of each external load branch of the device is obtained through the intelligent power detection unit;

[0016] The average value of the instantaneous power of the external load branch within the preset acquisition period is taken as the power of the external load branch;

[0017] The total power of the external load is obtained by summing the power of each external load branch.

[0018] In a preferred embodiment, in the power detection module, the ratio of the power of each external load branch to the total power of the external load is taken as the power percentage of each external load branch.

[0019] The load distribution characteristics are obtained by calculating the standard deviation of the power proportion of external load branches.

[0020] The load characteristics of the equipment are calculated after standardizing the total output power and load distribution characteristics of the equipment.

[0021] If the load characteristics are less than the preset load threshold, the equipment is determined to be in low load mode;

[0022] Conversely, if the device is not in low-load mode, it is determined that the device is not in low-load mode.

[0023] In a preferred embodiment, the current assessment module collects the current consumed by each functional unit or execution component inside the device during operation in real time to obtain the current data of each component of the device, including the current value and current fluctuation amplitude of each component of the device.

[0024] The instantaneous current of each component of the device is collected using a non-contact Hall sensor;

[0025] The preset detection period is used to take the average value of the instantaneous current of each component of the equipment within the preset detection period as the current value of each component of the equipment.

[0026] The current fluctuation amplitude of each component of the equipment is obtained by subtracting the minimum value from the maximum value of the instantaneous current of each component within the preset detection period.

[0027] The current status of each component of the equipment is calculated by combining the current values ​​and current fluctuation amplitudes of each component.

[0028] In a preferred embodiment, in the current evaluation module and the power detection module, each component of the device is matched with the standby power consumption database to obtain the corresponding standby power consumption of each component of the device.

[0029] The energy consumption index of each component in the device is obtained by calculating the standby power consumption and current state of the integrated components.

[0030] In a preferred embodiment, the energy consumption identification module sorts the components of the device in ascending order according to the size of the energy consumption index and labels them with serial numbers.

[0031] The ratio of the serial number of each component of the equipment to the sum of the serial numbers of all components of the equipment is used as the energy consumption level of each component of the equipment.

[0032] If the energy consumption level of each component of the device is greater than or equal to the preset energy consumption level threshold, it is determined to be a high energy consumption component.

[0033] If the energy consumption level of each component of the device is lower than the preset energy consumption level threshold, it is determined to be a low energy consumption component.

[0034] In a preferred embodiment, in the energy consumption identification module, the current temperature of the high-energy-consuming component is obtained by a digital temperature sensor, and the current temperature of the high-energy-consuming component is integrated into a temperature dataset.

[0035] The vibration acceleration of high-energy-consuming components is obtained by using a MEMS triaxial accelerometer, and the root mean square value of the vibration acceleration of high-energy-consuming components is used as the vibration intensity of high-energy-consuming components.

[0036] The instantaneous power of high-energy-consuming components is obtained through an intelligent power detection unit;

[0037] The ratio of the instantaneous power to the rated power of a high-energy-consuming component is taken as the load rate of the high-energy-consuming component.

[0038] The operating status of high-energy-consuming components is calculated by combining the vibration intensity and load rate of the components.

[0039] The operating status of high-energy-consuming components is integrated into an operating dataset.

[0040] In a preferred embodiment, in the energy-saving scheduling module, a multilayer perceptron model is constructed by integrating the temperature dataset and the operation dataset to analyze the energy-saving scheduling score of each high-energy-consuming component;

[0041] The multilayer perceptron model consists of three layers: an input layer, a hidden layer, and an output layer. The input layer receives input features and converts them into easily manipulated data. The hidden layer processes the converted data and the output layer outputs the calculation results.

[0042] The output layer is used to output the calculation results as an energy-saving scheduling score for high-energy-consuming components.

[0043] In a preferred embodiment, the specific steps for calculating the energy-saving scheduling score in the energy-saving scheduling module are as follows:

[0044] Step 1: Calculate the loss function by comparing the output of the multilayer perceptron model with the preset actual labels;

[0045] Step 2: Calculate the gradients of the effects of the hidden layer and the input layer on the loss function;

[0046] Step 3: Set the learning rate based on the values ​​of the multilayer perceptron in parameter optimization scenarios for similar industrial equipment;

[0047] Output results: Output the output results of the output layer after the model converges, and use the output results of the output layer as the energy-saving scheduling score of high-energy-consuming components.

[0048] In a preferred embodiment, the energy-saving scheduling module compares the energy-saving scheduling score of high-energy-consuming components with a preset energy-saving threshold for determination.

[0049] If the energy-saving scheduling score of a high-energy-consuming component is greater than or equal to the preset energy-saving threshold, then the energy-saving mode is executed for the high-energy-consuming component and an energy-saving prompt signal is output.

[0050] Conversely, energy-saving mode will not be applied to high-energy-consuming components.

[0051] The technical effects and advantages of this invention are as follows:

[0052] This invention detects the total output power of the equipment and the power of the external load branches, calculates the load distribution characteristics based on the power of the external load branches, and determines whether the equipment is in a low-load mode by combining the total output power and load distribution characteristics. In the low-load mode, it collects current data of each component of the equipment to evaluate the current status, detects standby power consumption and calculates the energy consumption index, generates energy consumption levels based on the energy consumption index, filters high-energy-consuming components and obtains their current temperature and operating status, generates an energy-saving scheduling score by combining temperature and operating status, and determines whether to execute the energy-saving mode and outputs an energy-saving prompt signal based on the score. By detecting power, current, temperature and operating status in real time, it realizes the identification of low load of the equipment and the accurate screening of high-energy-consuming components. Combined with the energy-saving scheduling score, it automatically triggers the energy-saving mode and prompt signals, reduces overall energy consumption and improves the intelligent scheduling efficiency and safety of distributed wind-solar-storage integrated equipment, avoids high-energy-consuming components from continuing to operate under abnormal conditions, and extends the equipment life. Attached Figure Description

[0053] Figure 1 This is a flowchart illustrating the implementation of the intelligent scheduling system for the distributed wind-solar-storage integrated equipment based on artificial intelligence, as described in this invention.

[0054] Figure 2 This is a schematic diagram of the intelligent scheduling system for the distributed wind-solar-storage integrated equipment based on artificial intelligence, as described in this invention. Detailed Implementation

[0055] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] This invention detects the total output power of the device and the power of the external load branches, calculates the load distribution characteristics based on the power of the external load branches, and determines whether the device is in a low-load mode by combining the total output power and load distribution characteristics. In the low-load mode, it collects current data of each component of the device to evaluate the current status, detects standby power consumption and calculates the energy consumption index, generates energy consumption levels based on the energy consumption index, screens high-energy-consuming components and obtains their current temperature and operating status, generates an energy-saving scheduling score by combining temperature and operating status, and determines whether to execute the energy-saving mode and outputs an energy-saving prompt signal based on the score. By detecting power, current, temperature and operating status in real time, it realizes the identification of low load of the device and the accurate screening of high-energy-consuming components. Combined with the energy-saving scheduling score, it automatically triggers the energy-saving mode and prompt signals, reduces overall energy consumption and improves the intelligent scheduling efficiency and safety of distributed wind and solar energy storage integrated equipment.

[0057] Example 1: Intelligent scheduling system for distributed wind-solar-storage integrated equipment based on artificial intelligence, such as... Figures 1 to 2 As shown, it includes a power detection module, a current assessment module, an energy consumption identification module, and an energy-saving scheduling module. The modules interact with each other through signal connections.

[0058] The functions of each module are as follows:

[0059] The power detection module is used to detect the total output power of the equipment and the power of the external load branch. It calculates the load distribution characteristics based on the power of the external load branch and determines whether the equipment is in a low-load mode based on the total output power and the load distribution characteristics.

[0060] The current assessment module is used to collect current data of each component of the device and assess the current status when the device is in low load mode, detect the standby power consumption of each component of the device, and calculate the energy consumption index of each component of the device based on the current status.

[0061] The energy consumption identification module is used to sort each component according to the energy consumption index and generate an energy consumption level. Based on the energy consumption level, the module filters each component to obtain high-energy-consuming components and obtains the current temperature and operating status of the high-energy-consuming components.

[0062] The energy-saving scheduling module is used to generate an energy-saving scheduling score for high-energy-consuming components by comprehensively considering the current temperature and operating status. Based on the energy-saving scheduling score, it determines whether to execute the energy-saving mode for high-energy-consuming components and outputs an energy-saving prompt signal.

[0063] The specific implementation is as follows:

[0064] In the power detection module, a preset acquisition period is used to acquire the voltage and current at the total output terminal of the device through voltage transformers and current transformers;

[0065] Multiply the voltage and current at the total output terminal of the device to obtain the instantaneous total output power of the device;

[0066] The average value of the device's instantaneous total output power within the preset acquisition period is taken as the device's total output power;

[0067] It should be noted that the preset acquisition cycle is used to periodically acquire the voltage and current at the total output terminal of the device. The preset acquisition cycle is set based on the frequency of change and data fluctuation of the voltage and current at the total output terminal during the operation of the device, so as to ensure that sufficient data is acquired in each cycle. Voltage transformers and current transformers are instruments for measuring the voltage and current of high-voltage or high-current circuits and converting them into low-voltage signals that can be safely measured, which are used to acquire the voltage and current at the total output terminal of the device.

[0068] The instantaneous power of each external load branch of the device is obtained through the intelligent power detection unit;

[0069] The average value of the instantaneous power of the external load branch within the preset acquisition period is taken as the power of the external load branch;

[0070] The total power of the external load is obtained by summing the power of each external load branch.

[0071] The ratio of the power of each external load branch to the total power of the external loads is taken as the power percentage of each external load branch.

[0072] The load distribution characteristics are obtained by calculating the standard deviation of the power proportion of external load branches.

[0073] The power factor and load distribution factor are obtained by standardizing the total output power and load distribution characteristics of the equipment, respectively.

[0074] The load characteristics of the equipment are calculated using a combination of power factor and load distribution factor. The calculation formula is as follows: ,in, Power factor For load distribution factor, Load characteristics;

[0075] It should be noted that the larger the power factor and the larger the load distribution factor, the greater the actual power of the equipment, the higher the load level, and the greater the load characteristics; conversely, the smaller the load characteristics.

[0076] The load characteristics are compared with the preset load threshold for judgment.

[0077] If the load characteristics are less than the preset load threshold, the equipment is determined to be in low load mode;

[0078] If the load characteristic is greater than or equal to the preset load threshold, the device is determined not to be in low load mode.

[0079] It should be explained that the intelligent power detection unit is a unit that integrates measurement, calculation, and communication, used to monitor the power status of equipment or components in real time; the standardization processing methods include, but are not limited to, standard linear transformation based on interval scaling, Z-Score standardization method based on statistics, or normalization method based on nonlinear mapping function. The application methods of standardization processing will not be elaborated here; the preset load threshold is an important parameter for determining whether the equipment is in a low load mode. The total output power and load distribution characteristics of multiple sets of equipment under low load mode are collected, and the corresponding load characteristics are calculated. The maximum value of multiple sets of corresponding load characteristics is taken as the preset load threshold.

[0080] In the current assessment module, the current consumed by each functional unit or execution component inside the equipment during operation is collected in real time to obtain the current data of each component of the equipment. The current data includes the current value and current fluctuation amplitude of each component of the equipment.

[0081] The instantaneous current of each component of the device is collected using a non-contact Hall sensor;

[0082] The preset detection period is used to take the average value of the instantaneous current of each component of the equipment within the preset detection period as the current value of each component of the equipment.

[0083] The current fluctuation amplitude of each component of the equipment is obtained by subtracting the minimum value from the maximum value of the instantaneous current of each component within the preset detection period.

[0084] The current state of each component of the equipment is calculated by combining the current values ​​and current fluctuation amplitudes of each component. The calculation formula is as follows: ,in, For the first Current values ​​of individual device components For the first Current fluctuation amplitude of individual device components For reference current, For the first Current state of individual device components;

[0085] It should be noted that the higher the current of each component of the equipment, the greater the current fluctuation amplitude, and the more unstable the current of each component of the equipment. The greater the load, the higher the current state; conversely, the lower the current state. The reference current is the normal operating current of the equipment components under rated operating conditions, provided by the equipment manufacturer.

[0086] The standby power consumption of each component of the device is obtained by matching each component with the standby power consumption database.

[0087] The current state factor and standby power consumption of each component of the device are normalized to obtain the current state factor and standby power consumption factor. The calculation formula is as follows:

[0088] , ;

[0089] in, For the first Current state of individual device components For the first Standby power consumption of individual device components The number of each component in the equipment. For current state factor, This is the standby power consumption factor;

[0090] The energy consumption index of each component of the device is calculated by combining the current state factor and the standby power consumption factor. The calculation formula is as follows: ,in, For current state factor, This is the standby power consumption factor. This refers to the energy consumption index of each component of the equipment.

[0091] It should be explained that the larger the current state factor and the larger the standby power consumption factor, the higher the power consumption of each component of the device and the larger the energy consumption index; conversely, the lower the power consumption of each component of the device, the smaller the energy consumption index; non-contact Hall sensors are current detection devices based on the Hall effect, which can measure current without direct contact with wires or circuits, and are used to collect the instantaneous current of each component of the device; the standby power consumption database is a database that stores the standby power consumption of each component of the device provided by the manufacturer.

[0092] In the energy consumption identification module, the components of the device are sorted in ascending order and labeled with serial numbers according to the size of the energy consumption index.

[0093] The ratio of the serial number of each component of the equipment to the sum of the serial numbers of all components of the equipment is used as the energy consumption level of each component of the equipment.

[0094] The energy consumption level of each component is compared with the preset energy consumption level threshold for determination:

[0095] If the energy consumption level of each component of the device is greater than or equal to the preset energy consumption level threshold, it is determined to be a high energy consumption component.

[0096] If the energy consumption level of each component of the device is lower than the preset energy consumption level threshold, it is determined to be a low energy consumption component.

[0097] The current temperature of high-energy-consuming components is obtained through a digital temperature sensor;

[0098] Integrate the current temperatures of high-energy-consuming components into a temperature dataset;

[0099] Vibration acceleration of high-energy-consuming components is obtained using a MEMS triaxial accelerometer.

[0100] The root mean square value of the vibration acceleration of the high-energy-consuming component is taken as the vibration intensity of the high-energy-consuming component.

[0101] The instantaneous power of high-energy-consuming components is obtained through an intelligent power detection unit;

[0102] The ratio of the instantaneous power to the rated power of a high-energy-consuming component is taken as the load rate of the high-energy-consuming component.

[0103] It should be noted that the rated power is the maximum operating power of the equipment provided by the equipment manufacturer.

[0104] The vibration intensity and load factor of high-energy-consuming components are normalized using the Max-Min normalization method to obtain the vibration factor and load factor, respectively. The calculation formula is as follows:

[0105] , ;

[0106] in, and These represent the vibration intensity and load rate of high-energy-consuming components, respectively. and These represent the maximum and minimum vibration intensity values ​​for high-energy-consuming components. and These represent the maximum and minimum load rates of high-energy-consuming components, respectively. and These are the vibration factor and the load factor, respectively.

[0107] The operating status of high-energy-consuming components is calculated by combining vibration factor and load factor. The calculation formula is as follows: ,in, For vibration factor, As the load factor, This refers to the operating status of high-energy-consuming components;

[0108] It should be noted that the larger the vibration factor and the larger the load factor, the greater the load fluctuation of high-energy-consuming components, the higher the electrical load, and the more severe the operating conditions; conversely, the smaller the load fluctuation of high-energy-consuming components, the lower the electrical load, and the more severe the operating conditions.

[0109] The operating status of high-energy-consuming components is integrated into an operating dataset.

[0110] It should be explained that the preset energy consumption level threshold is an important parameter for determining whether each component of the equipment is a high-energy-consuming component or a low-energy-consuming component. It is set according to a percentage, and the energy consumption level of each component in the equipment corresponding to 70% of the sorted components is used as the preset energy consumption level threshold; the digital temperature sensor is a temperature detection device that can directly output a digital signal and is used to obtain the current temperature of high-energy-consuming components; the MEMS triaxial accelerometer is an inertial sensor based on microelectromechanical systems technology and is used to obtain the vibration acceleration of high-energy-consuming components.

[0111] In the energy-saving scheduling module, a multilayer perceptron model is constructed by integrating the temperature dataset and the operation dataset to analyze the energy-saving scheduling scores of each high-energy-consuming component. The multilayer perceptron model consists of three layers: an input layer, a hidden layer, and an output layer. The input layer receives input features and transforms them into easily manipulated data. The hidden layer processes the transformed data, and the output layer outputs the calculation results. The specific steps are as follows:

[0112] Input data: The temperature dataset and the running dataset are passed as input features to the input layer. The input layer normalizes the data in the temperature dataset and the running dataset before passing them to the hidden layer.

[0113] Initialization parameters: In a multilayer perceptron model, the initial weights and bias parameters from the input layer to the hidden layer are set;

[0114] Setting the hidden layer processing algorithm: The temperature dataset and the running dataset are processed by setting the hidden layer activation function. Taking a relatively simple weighted function as an example, the activation function can be constructed as follows: ,in The output of the hidden layer, This represents the normalized values ​​for high-energy-consuming components corresponding to the temperature dataset. To run the dataset, the normalized values ​​for the high-energy-consuming components are used. and These are two initial weights set between the input layer and the hidden layer. These are the bias parameters set between the output layer and the hidden layer.

[0115] Set the output layer processing algorithm: Set the activation function of the output layer: ,in The output layer outputs the results. The initial energy-saving scheduling threshold can be set to the hidden layer output result calculated from the average value of the temperature dataset and the running dataset.

[0116] Propagation: The multilayer perceptron passes the input features sequentially through the input layer, hidden layer and output layer, and finally the output layer calculates the output result as the energy-saving scheduling score of high-energy-consuming components;

[0117] The specific steps for calculating the energy-saving dispatch score are as follows:

[0118] Step 1: Calculate the loss function by comparing the output of the multilayer perceptron model with the preset actual labels. The mean squared error of the output results of all output layers can be calculated using the loss function. ,in Let n be the mean squared error, and n be the number of data points in the temperature dataset or the running dataset. The first one randomly selected from the temperature dataset The output layer outputs the results obtained by passing the temperature normalization result and the corresponding normalized result of the operating status of high-energy-consuming components in the running dataset. For the preset first One actual label;

[0119] Step 2: Calculate the gradients of the hidden layer and input layer's influence on the loss function. Use the partial derivatives of the hidden layer's weights and bias parameters with respect to the loss function as the gradients. The formulas for calculating the gradients of the weights and bias parameters are as follows: , ,in and These are the gradients of the weights and the gradients of the bias parameters in the activation function of the hidden layer, respectively.

[0120] Step 3: Set the learning rate. The learning rate can be set with reference to the values ​​used in parameter optimization scenarios for multilayer perceptrons in similar industrial equipment. Adjust the weights and bias parameters using the weight gradient, bias parameter gradient, and learning rate. For example, update the weights and bias parameters using the product of the learning rate and the corresponding weight gradient or bias parameter gradient: , ,in, For learning rate, For the adjusted weights or , To adjust the bias parameters; repeat the above steps until the model converges, use the final output of the hidden layer as the energy-saving scheduling threshold, and replace the initial energy-saving scheduling threshold with the calculated energy-saving scheduling threshold;

[0121] Output results: Output the output results of the output layer after the model converges, and use the output results of the output layer as the energy-saving scheduling score of high-energy-consuming components;

[0122] It should be noted that the higher the current temperature of a high-energy-consuming component, the greater the load on the component or the less heat dissipation, the higher the energy-saving scheduling score output by the model; the higher the operating state of a high-energy-consuming component, the greater its power consumption and the higher its energy consumption; the weights and bias parameters in the activation function of the hidden layer are randomly assigned and initialized. The convergence weights and bias parameters are continuously adjusted using actual labels to obtain the optimal weights and bias parameters for calculating the energy-saving scheduling threshold, thereby improving the accuracy of the multilayer perceptron output results. The actual labels are set by professionals in this field and will not be elaborated here.

[0123] The energy-saving scheduling score of high-energy-consuming components is compared with the preset energy-saving threshold for judgment:

[0124] If the energy-saving scheduling score of a high-energy-consuming component is greater than or equal to the preset energy-saving threshold, then the energy-saving mode is executed for the high-energy-consuming component and an energy-saving prompt signal is output.

[0125] If the energy-saving scheduling score of a high-energy-consuming component is less than the preset energy-saving threshold, then the energy-saving mode will not be executed on the high-energy-consuming component.

[0126] It should be explained that the preset energy-saving threshold is an important parameter for determining whether to implement energy-saving mode and output energy-saving prompt signals for high-energy-consuming components. It is calculated by taking the average value and standard deviation of the energy-saving scheduling score from historical data, and the difference between the average value and standard deviation is used as the preset energy-saving threshold. The energy-saving mode refers to a series of control strategies adopted for high-energy-consuming components to reduce energy consumption, extend equipment life, and optimize the overall system operating efficiency. The energy-saving prompt signal is feedback information on whether high-energy-consuming components need to enter energy-saving mode. It can be used for automatic control execution and can also be provided to operators as a reference for decision-making.

[0127] Finally, it should be noted that in this paper, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0128] Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0129] In this document, the singular forms “a,” “an,” and “the” may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that terms such as “comprising / including” or “having” specify the presence of the stated features, integrals, steps, operations, components, parts, or combinations thereof, but do not preclude the possibility of the presence or addition of one or more other features, integrals, steps, operations, components, parts, or combinations thereof. Meanwhile, the term “and / or” as used in this specification includes any and all combinations of the associated listed items.

[0130] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referred to each other.

[0131] The above description of the disclosed embodiments will enable those skilled in the art to make or use various modifications to these embodiments. It will be readily apparent to those skilled in the art that the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An artificial intelligence-based distributed wind-solar-storage integrated device intelligent scheduling system, characterized in that: The power detection module, the current evaluation module, the energy consumption identification module, and the energy-saving scheduling module are included, and the functions of the modules are as follows: The power detection module is used to detect the total output power of the device and the external load branch power, calculate the load distribution characteristics according to the external load branch power, and determine whether the device is in a low load mode according to the total output power and the load distribution characteristics; In the power detection module, the ratio of each external load branch power to the total external load power is taken as the external load branch power ratio; The load distribution characteristics are calculated by standard deviation of the external load branch power ratio; The load characteristics of the device are calculated after the total output power of the device and the load distribution characteristics are standardized; If the load characteristics are less than the preset load threshold, it is determined that the device is in a low load mode; Otherwise, it is determined that the device is not in a low load mode; The current evaluation module is used to collect the current data of each component of the device and evaluate the current state when the device is in a low load mode, detect the standby power consumption of each component of the device, and calculate the energy consumption index of each component of the device in combination with the current state; In the current evaluation module, the current data of each component of the device is collected in real time by collecting the current consumed by each functional unit or execution component of the device during operation, including the current value and current fluctuation amplitude of each component of the device; The instantaneous current of each component of the device is collected by a non-contact Hall sensor; The average value of the instantaneous current of each component of the device in the preset detection period is taken as the current value of each component of the device; The maximum value of the instantaneous current of each component of the device in the preset detection period is subtracted from the minimum value to obtain the current fluctuation amplitude of each component of the device; The current state of each component of the device is calculated by integrating the current value and current fluctuation amplitude of each component of the device; The energy consumption identification module is used to sort each component according to the energy consumption index and generate an energy consumption level, filter each component based on the energy consumption level to obtain a high energy consumption component, and obtain the current temperature and operating state of the high energy consumption component; The energy-saving scheduling module is used to generate an energy-saving scheduling score of the high energy consumption component by integrating the current temperature and operating state, determine whether to execute an energy-saving mode for the high energy consumption component according to the energy-saving scheduling score, and output an energy-saving prompt signal.

2. The intelligent scheduling system of the distributed wind-solar energy storage integrated device based on artificial intelligence according to claim 1, wherein: In the power detection module, a preset collection period is set, and the voltage and current of the device total output end are collected by a voltage transformer and a current transformer; The voltage and current of the device total output end are multiplied to obtain the instantaneous total output power of the device; The average value of the instantaneous total output power of the device in the preset collection period is taken as the total output power of the device; The instantaneous power of each external load branch of the device is obtained by an intelligent power detection unit; The average value of the instantaneous power of the external load branch in the preset collection period is taken as the external load branch power; The external load total power is obtained by accumulating each external load branch power.

3. The intelligent scheduling system of the distributed wind-solar energy storage integrated device based on artificial intelligence according to claim 1, wherein: In the current evaluation module, the standby power consumption of each component of the device is matched with a standby consumption power database to obtain the corresponding standby power consumption of each component of the device; The standby power consumption and current state of the integrated assembly are calculated to obtain the energy consumption index of each component of the device.

4. The artificial intelligence-based distributed wind-solar energy storage integrated device intelligent scheduling system according to claim 1, characterized in that: In the energy consumption identification module, the components of the device are sorted in ascending order according to the size of the energy consumption index and labeled with serial numbers; The ratio of the serial number of each component of the device to the total number of serial numbers of the components of the device is taken as the energy consumption level of each component of the device; If the energy consumption level of each component of the device is greater than or equal to the preset energy consumption level threshold, it is determined to be a high energy consumption component; If the energy consumption level of each component of the device is less than the preset energy consumption level threshold, it is determined to be a low energy consumption component.

5. The artificial intelligence-based distributed wind-solar energy storage integrated device intelligent scheduling system according to claim 4, characterized in that: In the energy consumption identification module, the current temperature of the high energy consumption component is obtained through a digital temperature sensor, and the current temperature of the high energy consumption component is integrated into a temperature data set; The vibration acceleration of the high energy consumption component is obtained through a MEMS three-axis acceleration sensor, and the root mean square value of the vibration acceleration of the high energy consumption component is taken as the vibration intensity of the high energy consumption component; The instantaneous power of the high energy consumption component is obtained through an intelligent power detection unit; The ratio of the instantaneous power of the high energy consumption component to the rated power is taken as the load rate of the high energy consumption component; The running state of the high energy consumption component is calculated by integrating the vibration intensity and load rate of the high energy consumption component; The running state of the high energy consumption component is integrated into a running data set.

6. The artificial intelligence-based distributed wind-solar energy storage integrated device intelligent scheduling system according to claim 5, characterized in that: In the energy-saving scheduling module, the temperature data set and the running data set are integrated to construct a multi-layer perception machine model to analyze the energy-saving scheduling score of each high energy consumption component; The multi-layer perception machine model is composed of three layers: input layer, hidden layer and output layer, the input layer is used to receive input features and convert them into easy-to-operate data, the hidden layer is used to calculate and process the converted data, and the output layer is used to output the calculation results; The output layer is used to output the calculation results as the energy-saving scheduling score of the high energy consumption component.

7. The artificial intelligence-based distributed wind-solar energy storage integrated device intelligent scheduling system according to claim 6, characterized in that: In the energy-saving scheduling module, the specific steps for calculating the energy-saving scheduling score are as follows: Step 1: Calculate the loss function by comparing the output results of the multi-layer perception machine model with the preset actual labels; Step 2: Calculate the influence gradient of the hidden layer and the input layer on the loss function; Step 3: Set the learning rate according to the numerical value of the multi-layer perception machine in the same type of industrial equipment parameter optimization scene; Output result: output the output layer output result after the model converges, and take the output layer output result as the energy-saving scheduling score of the high energy consumption component.

8. The artificial intelligence-based distributed wind-solar energy storage integrated device intelligent scheduling system according to claim 7, characterized in that: In the energy-saving scheduling module, the energy-saving scheduling score of the high energy consumption component is compared with the preset energy-saving threshold to determine: If the energy-saving scheduling score of the high-energy-consumption component is greater than or equal to the preset energy-saving threshold, the energy-saving mode is performed on the high-energy-consumption component, and an energy-saving prompt signal is output. Otherwise, the energy-saving mode is not performed on the high-energy-consumption component.

Images