Transformer consumption reduction intelligent control method and system based on power generation end

Abstract

The invention discloses a transformer consumption reduction intelligent control method and system based on a power generation end, and relates to the technical field of electric power control. A transformer operation data set and a historical load data set are collected in advance, an ARIMA model is constructed based on the transformer operation data set and the historical load data set, a residual data set is generated by using the ARIMA model, and the residual data set is stored in a database; based on the residual data set and the transformer operation data set, constructing and training an LSTM model for predicting a future load demand, collecting real-time operation data in the actual use process of the transformer in real time, predicting the future load demand corresponding to the real-time operation data by using the combination of the ARIMA model and the LSTM model, and determining the real-time operation data of the transformer based on the future load demand and the real-time operation data. And a consumption reduction optimization model is constructed, and a transformer operation strategy is adjusted by using an optimization algorithm based on the consumption reduction optimization model, so that load change can be intelligently responded in real time and a regulation and control strategy can be generated.

Description

Technical Field

[0001] The present invention relates to the technical field of power control, and in particular to a transformer consumption reduction intelligent control method and system based on a power generation end. Background Art

[0002] In modern power systems, transformers at the power generation end are the key link between power generation equipment and transmission networks. Their operating efficiency directly affects the energy transmission and distribution efficiency of the entire power system. With the growth of global energy consumption and the increasing demand for sustainable energy utilization, reducing the energy consumption of transformers has become one of the important tasks of the power industry. In traditional transformer operation, fixed strategies are often used to cope with changing load demands. Although this method is simple, it is not efficient. Especially in the case of large load fluctuations, fixed strategies may lead to energy waste and excessive wear of equipment. In addition, current load forecasting often relies on simple historical averages or regular scheduling, lacking the ability to fully utilize real-time data and dynamically adjust.

[0003] Existing technologies have obvious deficiencies in dealing with complex load changes and improving transformer operating efficiency. Traditional load forecasting methods usually ignore the dynamic characteristics and multi-dimensional interactions of real-time data. In addition, the adjustment of transformer operation strategies relies on manual experience and static rules, which cannot respond quickly to load changes. This not only leads to energy waste, but also may increase the risk of equipment failure and shorten its service life.

[0004] A Chinese patent with authorization announcement number CN117691594B discloses a method and system for determining energy conservation and consumption reduction for a transformer, which collects and processes real-time operation data, historical data and cost data of the transformer; analyzes the processed data; assigns preset weights to each analysis result and scores them; calculates a comprehensive score based on the score of each analysis result and the corresponding weight; and determines whether energy conservation and consumption reduction are required based on whether the comprehensive score exceeds a preset comprehensive score threshold. However, this method fails to solve the problem of how to intelligently control consumption reduction.

[0005] To this end, the present invention proposes a transformer power consumption reduction intelligent control method and system based on the power generation end. Summary of the invention

[0006] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a transformer consumption reduction intelligent control method and system based on the power generation end, which can intelligently respond to load changes and generate regulation strategies in real time.

[0007] To achieve the above purpose, a transformer consumption reduction intelligent control method based on the power generation end is proposed, comprising the following steps:

[0008] Step 1: Collect transformer operation data set and historical load data set in advance;

[0009] Step 2: Based on the transformer operation data set and the historical load data set, an ARIMA model is constructed, and the residual data set is generated using the ARIMA model;

[0010] Step 3: Based on the residual data set and the transformer operation data set, build and train an LSTM model for predicting future load demand;

[0011] Step 4: Collect real-time operation data of the transformer during actual use, and use the combination of ARIMA model and LSTM model to predict the future load demand corresponding to the real-time operation data;

[0012] Step 5: Build a power consumption reduction optimization model based on future load demand and real-time operation data;

[0013] Step 6: Based on the consumption reduction optimization model, use the optimization algorithm to adjust the transformer operation strategy;

[0014] The method of pre-collecting the transformer operation data set and the historical load data set is:

[0015] Install a sensor network for the transformer, and monitor and record the parameter values ​​of each sensor in real time. By reading the parameter values ​​of each sensor, a transformer operation data set is formed;

[0016] Collect historical load data sets by reading the historical database and smart meters during transformer operation;

[0017] The method of constructing an ARIMA model based on the historical load data set and using the ARIMA model to generate a residual data set is as follows:

[0018] For each load parameter in the historical load data set, generating the residual data set includes the following steps:

[0019] Step 21: Arrange the parameter values ​​of the load parameter in chronological order and organize them into a time series format to obtain a load parameter time series of the corresponding load parameter;

[0020] Step 22: Analyze whether each load parameter time series has a stable mean and variance by using a statistical method. If it does not have a stable mean and variance, apply a difference method to make the load parameter time series stable. The difference method eliminates trends or seasonality by calculating the difference between adjacent data points.

[0021] Step 23: Draw autocorrelation function graphs and partial autocorrelation function graphs for the load parameter time series to identify the intrinsic patterns of the time series data;

[0022] Step 24: According to the autocorrelation function graph and the partial autocorrelation function graph, select the parameter combination (p, d, q) of the ARIMA model; where p is the order of the autoregressive part, which refers to the number of lags in the model, d is the number of differences, which indicates the order of differences required for stabilization, and q is the order of the moving average part, which indicates the number of lagged forecast error terms;

[0023] Step 25: Use the selected (p, d, q) parameters to construct an ARIMA model and perform fitting; verify the accuracy of the model by testing the residuals of the model, and use statistical test methods to confirm the randomness of the residuals;

[0024] Step 26: During the ARIMA model fitting process, there is a predicted value for each parameter value per unit time in the load parameter time series; the residual is the actual parameter value minus the predicted value given by the ARIMA model;

[0025] Step 27: Collect the residuals of each unit time to form a residual data set;

[0026] The construction process of the LSTM model includes:

[0027] Standardize all parameters in all transformer operation data sets and residual data sets to ensure that all parameters are on the same scale;

[0028] A fixed time window is preset to predict the load demand at the next time step;

[0029] The LSTM model uses a parameter time series composed of parameters of various transformer operation data and a residual time series composed of residual values ​​of various load parameters within a fixed time window as an input sample;

[0030] The LSTM model uses the load demand within the next preset time step of each input sample as output, and uses the actual load demand within the next preset time step in the historical load data set as the prediction target;

[0031] The structure of the LSTM model includes an input layer, an LSTM layer, a fully connected layer and an output layer;

[0032] The input layer is used to receive multidimensional time series data, namely residuals and transformer operation data;

[0033] The LSTM layer includes one or more LSTM layers that can be stacked to capture long-term dependencies in the time series; the fully connected layer connects the output of the LSTM layer to the final output node to generate a prediction value, and the output layer: outputs a single prediction value, that is, the load demand for the next time step;

[0034] The training process of the LSTM model includes:

[0035] Split all input samples into training and test sets;

[0036] The mean square error is used as the loss function of the LSTM model to measure the difference between the predicted value and the actual value;

[0037] Use the Adam optimizer as the optimizer for the LSTM model to improve the efficiency and effectiveness of training;

[0038] Train the LSTM model on the training set and adjust the network weights to minimize the loss function;

[0039] At the end of each iteration, the performance of the LSTM model is evaluated on the validation set and the model hyperparameters are adjusted to prevent overfitting.

[0040] The method of using the ARIMA model and the LSTM model to combine and predict the future load demand corresponding to the real-time operation data is as follows:

[0041] By using the ARIMA model to predict each load parameter per unit time, the corresponding load parameter prediction value is obtained;

[0042] Calculate the difference between the predicted value of the load parameter per unit time and the actual parameter value to form a residual set;

[0043] The residual set and the parameter values ​​of various real-time operating parameters are used to form a new input sample, which is input into the LSTM model to obtain the predicted value of the load demand output by the LSTM model;

[0044] The method of constructing the energy saving optimization model based on future load demand and real-time operation data is as follows:

[0045] The predicted value of the load demand is marked as Pr, the voltage of the transformer is marked as V, the power factor of the transformer is marked as pf, and the equivalent resistance of the core is marked as Rc;

[0046] Mark the transformer winding resistance as R;

[0047] Based on the predicted value of load demand, voltage, and power factor, a power reduction objective function F is constructed;

[0048] According to the preset safe voltage range and safe current range of the transformer, a consumption reduction optimization condition set U is constructed;

[0049] Taking minimizing the energy saving objective function F as the optimization goal and the energy saving optimization condition set U as the constraint condition set, a convex optimization model is constructed as the energy saving optimization model.

[0050] The method of adjusting the transformer operation strategy using the optimization algorithm based on the consumption reduction optimization model is as follows:

[0051] The consumption reduction optimization model is solved using a nonlinear programming solution algorithm or a heuristic algorithm to obtain a solved voltage value, and the transformer operation strategy is to adjust the transformer voltage to the solved voltage value.

[0052] A transformer consumption reduction intelligent control system based on the power generation end is proposed, which includes a sample data collection module, a residual data generation module, an LSTM model training module, a load prediction module and a strategy adjustment module; wherein each module is electrically connected;

[0053] The sample data collection module collects the transformer operation data set and the historical load data set in advance, sends the historical load data set to the residual data generation module, and sends the transformer operation data set to the LSTM model training module;

[0054] The residual data generation module builds an ARIMA model based on the transformer operation data set and the historical load data set, and uses the ARIMA model to generate a residual data set, and sends the residual data set to the LSTM model training module, and sends the trained ARIMA model to the load prediction module;

[0055] The LSTM model training module builds and trains an LSTM model for predicting future load demand based on the residual data set and the transformer operation data set, and sends the trained LSTM model to the load prediction module;

[0056] The load prediction module collects real-time operation data of the transformer during actual use, uses the ARIMA model and LSTM model to predict the future load demand corresponding to the real-time operation data, and sends the future load demand to the strategy adjustment module;

[0057] The strategy adjustment module builds a consumption reduction optimization model based on future load demand and real-time operation data, and uses an optimization algorithm to adjust the transformer operation strategy based on the consumption reduction optimization model.

[0058] An electronic device is proposed, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0059] The processor executes the above-mentioned intelligent control method for transformer consumption reduction based on the power generation end by calling the computer program stored in the memory.

[0060] A computer-readable storage medium is provided, on which a rewritable computer program is stored;

[0061] When the computer program is executed on a computer device, the computer device is enabled to execute the above-mentioned intelligent control method for transformer consumption reduction based on the power generation end.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] The present invention collects transformer operation data sets and historical load data sets in advance, builds an ARIMA model based on the transformer operation data sets and historical load data sets, and uses the ARIMA model to generate a residual data set, builds and trains an LSTM model for predicting future load demand based on the residual data set and the transformer operation data set, collects real-time operation data in the actual use process of the transformer in real time, uses the ARIMA model and the LSTM model to combine and predict the future load demand corresponding to the real-time operation data, builds a consumption reduction optimization model based on the future load demand and the real-time operation data, and uses an optimization algorithm to adjust the transformer operation strategy based on the consumption reduction optimization model; first, by collecting the operation data and historical load data of the transformer, a refined load demand prediction model is established. The advanced ARIMA and LSTM combined model can effectively decompose and predict the linear and nonlinear parts of the load. Based on the prediction results, the tap switch position and cooling system settings of the transformer are dynamically adjusted to optimize the voltage level and reduce energy loss, and can respond to load changes and generate regulation strategies in real time and intelligently. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 This is a flow chart of a transformer power consumption reduction intelligent control method based on a power generation end in Embodiment 1 of the present invention;

[0065] Figure 2 This is a module connection diagram of an intelligent control system for reducing power consumption of a transformer based on a power generation end in Example 2 of the present invention. DETAILED DESCRIPTION

[0066] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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 are within the scope of protection of the present invention.

[0067] Example 1

[0068] like Figure 1 As shown, a transformer consumption reduction intelligent control method based on the power generation end includes the following steps:

[0069] Step 1: Collect transformer operation data set and historical load data set in advance;

[0070] Step 2: Based on the transformer operation data set and the historical load data set, an ARIMA model is constructed, and the residual data set is generated using the ARIMA model;

[0071] Step 3: Based on the residual data set and the transformer operation data set, build and train an LSTM model for predicting future load demand;

[0072] Step 4: Collect real-time operation data of the transformer during actual use, and use the combination of ARIMA model and LSTM model to predict the future load demand corresponding to the real-time operation data;

[0073] Step 5: Build a power consumption reduction optimization model based on future load demand and real-time operation data;

[0074] Step 6: Based on the consumption reduction optimization model, use the optimization algorithm to adjust the transformer operation strategy;

[0075] The method of pre-collecting the transformer operation data set and the historical load data set is as follows:

[0076] Install a sensor network for the transformer, and monitor and record the parameter values ​​of each sensor in real time. By reading the parameter values ​​of each sensor, a transformer operation data set is formed;

[0077] Collect historical load data sets by reading the historical database and smart meters during transformer operation;

[0078] Specifically, the sensor network is used to collect real-time operating parameters of the transformer in real time, and the real-time operating parameters include but are not limited to voltage, current, temperature, power factor and switch state, etc. Each sensor in the sensor network corresponds to a real-time operating parameter. For example, the voltage sensor collects the real-time voltage, and then uses a data acquisition device such as a data recorder or a programmable logic controller to connect the sensor network to realize real-time collection and storage of operating data; further, the parameter data collected by the sensor can also be transmitted to a centralized database or cloud storage platform through a wired or wireless network, so as to be stored using a SCADA system;

[0079] The historical database is an existing database of the power company or power station, which records the past transformer operation and load data;

[0080] The historical load data set includes various load parameters of the transformer per unit time;

[0081] Specifically, the load parameters include, but are not limited to, load demand, power consumption, seasonality, and diurnal variation;

[0082] The load demand can be read by using the load data stored in the smart meter and the historical record database, the power consumption can be recorded by the meter or extracted from the historical power bill, and the seasonality and daily variation refer to the seasonality and daily variation patterns of the load demand, which can be formed by long-term data accumulation, usually recorded by the power company; it should be noted that the collection frequency of each load parameter in the historical load data set should be consistent, for example, once every hour;

[0083] Furthermore, the method of constructing an ARIMA model based on the historical load data set and using the ARIMA model to generate a residual data set is as follows:

[0084] For each load parameter in the historical load data set, generating the residual data set includes the following steps:

[0085] Step 21: Arrange the parameter values ​​of the load parameter in chronological order and organize them into a time series format to obtain a load parameter time series of the corresponding load parameter;

[0086] Step 22: Analyze whether each load parameter time series has a stable mean and variance by using a statistical method. If it does not have a stable mean and variance, apply a difference method to make the load parameter time series stable. The difference method eliminates trends or seasonality by calculating the difference between adjacent data points. Specifically, the determination of the stability can be determined using an ADF test method.

[0087] Step 23: Draw autocorrelation function graphs and partial autocorrelation function graphs for the load parameter time series to identify the intrinsic patterns of the time series data;

[0088] Step 24: According to the autocorrelation function graph and the partial autocorrelation function graph, select the parameter combination (p, d, q) of the ARIMA model; where p is the order of the autoregressive part, which refers to the number of lags in the model, d is the number of differences, which indicates the order of differences required for stabilization, and q is the order of the moving average part, which indicates the number of lagged forecast error terms;

[0089] It should be noted that the autocorrelation function diagram is the ACF diagram, which shows the correlation between the time series and its lagged value, and is used to identify the order qq of the moving average (MA) component; in the ACF diagram, a significant cutoff at the lag (i.e., a point significantly different from zero) indicates the order of the MA;

[0090] The partial autocorrelation function diagram is a PACF diagram, which shows the correlation between the time series and its lagged values ​​while controlling other lagged effects, so as to identify the order pp of the autoregressive (AR) component; in the PACF diagram, a significant truncation at the lag indicates the order of the AR;

[0091] Therefore, the number of differences d can generally be set to 1, and p and q can be selected manually by observing the ACF and PACF graphs according to the truncation and tailing patterns, or the automatic function of the statistical software can be used to select the optimal parameters;

[0092] For example, when the following characteristics are observed:

[0093] ACF chart: significant cutoff at lag 2, indicating possible MA(2);

[0094] PACF plot: significant truncation at lag 1, indicating possible AR(1);

[0095] Set the parameter combination (p, d, q) to (1, 2, 1);

[0096] Step 25: Use the selected (p, d, q) parameters to construct an ARIMA model and perform fitting; verify the accuracy of the model by testing the residuals of the model, and use statistical test methods such as the Ljung-Box test to confirm the randomness of the residuals;

[0097] Step 26: During the ARIMA model fitting process, there is a predicted value for each parameter value per unit time in the load parameter time series; the residual is the actual parameter value minus the predicted value given by the ARIMA model;

[0098] Step 27: Collect the residuals of each unit time to form a residual data set;

[0099] It is understandable that the ARIMA model is usually built based on univariate time series data, that is, it mainly relies on the historical values ​​of the load data itself for prediction. Therefore, it is good at processing linear trends and seasonal components, but it may not perform well when facing complex nonlinear relationships. The residual of each unit time represents the linear part of the load data, and further analysis is needed on the nonlinear operation data of the transformer and the nonlinear changes of the load data.

[0100] Furthermore, the construction process of the LSTM model includes:

[0101] Standardize all parameters in all transformer operation data sets and residual data sets to ensure that all parameters are on the same scale;

[0102] A fixed time window is preset to predict the load demand of the next time step; specifically, the size of the time window can be set to the past 5 hours;

[0103] The LSTM model uses a parameter time series composed of parameters of various transformer operation data and a residual time series composed of residual values ​​of various load parameters within a fixed time window as an input sample;

[0104] The LSTM model uses the load demand within the next preset time step of each input sample as output, and uses the actual load demand within the next preset time step in the historical load data set as the prediction target;

[0105] The structure of the LSTM model includes an input layer, an LSTM layer, a fully connected layer and an output layer;

[0106] The input layer is used to receive multi-dimensional time series data, namely, residuals and transformer operation data. The LSTM layer includes one or more LSTM layers that can be stacked to capture long-term dependencies in the time series. The number of units in the LSTM layer is usually between 50 and 200, depending on the complexity of the data and training resources. The fully connected layer connects the output of the LSTM layer to the final output node to generate a predicted value. The output layer outputs a single predicted value, namely, the load demand for the next time step.

[0107] Furthermore, the training process of the LSTM model includes:

[0108] All input samples are divided into a training set and a test set; generally, the ratio of the training set to the test set is 70% training set and 30% test set;

[0109] The mean square error is used as the loss function of the LSTM model to measure the difference between the predicted value and the actual value;

[0110] Use the Adam optimizer as the optimizer for the LSTM model to improve the efficiency and effectiveness of training;

[0111] Train the LSTM model on the training set and adjust the network weights to minimize the loss function;

[0112] At the end of each iteration, the performance of the LSTM model is evaluated on the validation set and the model hyperparameters are adjusted to prevent overfitting.

[0113] It is understandable that the LSTM model is able to capture the complex nonlinear dynamics in the time series. Therefore, by first processing the linear part of the data with ARIMA and then processing the residual part (i.e., the nonlinear component) with LSTM, the time series can be modeled more comprehensively, thereby improving the prediction accuracy. Combining the advantages of the two models, the changes in power load can be better predicted, thereby optimizing the load management strategy of the transformer and ultimately achieving the goal of reducing consumption.

[0114] Furthermore, the method of collecting real-time operation data of the transformer during actual use is as follows:

[0115] Before the transformer is actually used, a sensor network is installed for the transformer, and the parameter values ​​of various real-time operating parameters and the parameter values ​​of the actual load parameters of the transformer per unit time are collected through the sensor network to form real-time operating data;

[0116] Furthermore, the method of using the ARIMA model and the LSTM model to combine and predict the future load demand corresponding to the real-time operation data is as follows:

[0117] By using the ARIMA model to predict each load parameter per unit time, the corresponding load parameter prediction value is obtained;

[0118] Calculate the difference between the predicted value of the load parameter per unit time and the actual parameter value to form a residual set;

[0119] The residual set and the parameter values ​​of various real-time operating parameters are used to form a new input sample, which is input into the LSTM model to obtain the predicted value of the load demand output by the LSTM model;

[0120] Furthermore, the method of constructing the energy saving optimization model based on future load demand and real-time operation data is as follows:

[0121] The predicted value of the load demand is marked as Pr, the voltage of the transformer is marked as V, the power factor of the transformer is marked as pf, and the equivalent resistance of the core is marked as Rc; it can be understood that for the transformer, the voltage value is a variable parameter, that is, the voltage is a controllable variable, and the power factor is a constant ranging between (0, 1), which represents the proportion of active power in apparent power;

[0122] Mark the transformer winding resistance as R;

[0123] Based on the predicted value of load demand, voltage, and power factor, a power reduction objective function F is constructed;

[0124] According to the preset safe voltage range and safe current range of the transformer, a consumption reduction optimization condition set U is constructed;

[0125] Taking minimizing the energy saving objective function F as the optimization goal and the energy saving optimization condition set U as the constraint condition set, a convex optimization model is constructed as the energy saving optimization model.

[0126] Since the energy consumption of the transformer under different load and operating conditions is mainly reflected in copper loss and iron loss;

[0127] Therefore, preferably, the formula form of the energy saving objective function F can be:

[0128]

[0129] Where I is the current of the transformer, and I is calculated by dividing power by voltage, that is, the calculation formula of I is: I 2 ×R is copper loss;

[0130] in, It represents the iron loss;

[0131] Furthermore, the method of constructing the energy-saving optimization condition set U is:

[0132] Construct voltage constraints: Vmin≤V≤Vmax, where Vmin and Vmax are the preset minimum voltage and maximum voltage respectively;

[0133] Construct current constraint: Imin≤I≤Imax, where Imin and Imax are the preset minimum current and maximum current respectively;

[0134] The voltage constraint and the current constraint together constitute the energy saving optimization condition set U;

[0135] Furthermore, the method of adjusting the transformer operation strategy using the optimization algorithm based on the consumption reduction optimization model is as follows:

[0136] The consumption reduction optimization model is solved using a nonlinear programming solution algorithm or a heuristic algorithm to obtain a solved voltage value, and the transformer operation strategy is to adjust the transformer voltage to the solved voltage value.

[0137] Example 2

[0138] like Figure 2 As shown, a transformer consumption reduction intelligent control system based on the power generation end includes a sample data collection module, a residual data generation module, an LSTM model training module, a load prediction module and a strategy adjustment module; wherein each module is electrically connected;

[0139] The sample data collection module collects the transformer operation data set and the historical load data set in advance, sends the historical load data set to the residual data generation module, and sends the transformer operation data set to the LSTM model training module;

[0140] The residual data generation module builds an ARIMA model based on the transformer operation data set and the historical load data set, and uses the ARIMA model to generate a residual data set, and sends the residual data set to the LSTM model training module, and sends the trained ARIMA model to the load prediction module;

[0141] The LSTM model training module builds and trains an LSTM model for predicting future load demand based on the residual data set and the transformer operation data set, and sends the trained LSTM model to the load prediction module;

[0142] The load prediction module collects real-time operation data of the transformer during actual use, uses the ARIMA model and LSTM model to predict the future load demand corresponding to the real-time operation data, and sends the future load demand to the strategy adjustment module;

[0143] The strategy adjustment module builds a consumption reduction optimization model based on future load demand and real-time operation data, and uses an optimization algorithm to adjust the transformer operation strategy based on the consumption reduction optimization model.

[0144] Example 3

[0145] According to another aspect of the present application, an electronic device is provided. The electronic device may include one or more processors and one or more memories. The memories store computer-readable codes, and when the computer-readable codes are executed by one or more processors, the transformer consumption reduction intelligent control method based on the power generation end as described above may be executed.

[0146] The electronic device may include a bus, one or more CPUs, ROM, RAM, a communication port connected to a network, an input / output component, a hard disk, etc. A storage device in the electronic device, such as a ROM or a hard disk, may store a transformer power generation end-based intelligent control method for reducing power consumption provided in the present application.

[0147] Furthermore, the electronic device may also include a user interface. Of course, this architecture is only exemplary, and when implementing different devices, one or more components in the electronic device may be omitted according to actual needs.

[0148] Example 4

[0149] A computer-readable storage medium according to an embodiment of the present application. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by the processor, a transformer consumption reduction intelligent control method based on the power generation end according to an embodiment of the present application described with reference to the above figures can be executed. The computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0150] In addition, according to the implementation of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, the non-transitory machine-readable storage medium stores machine-readable instructions, the machine-readable instructions can be run by a processor to execute instructions corresponding to the method steps provided by the present application, and when the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0151] The methods, apparatuses, and devices of the present application may be implemented in many ways. For example, the methods, apparatuses, and devices of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present application may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers recording media storing programs for executing the method according to the present application.

[0152] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0153] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0154] The above preset parameters or preset thresholds are all set by technicians in this field according to actual conditions or obtained through large-scale data simulation.

[0155] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A transformer consumption reduction intelligent control method based on the power generation end, characterized in that: The following steps are involved: Step 1: Collect transformer operation data set and historical load data set in advance; Step 2: Based on the transformer operation data set and the historical load data set, an ARIMA model is constructed, and the residual data set is generated using the ARIMA model; Step 3: Based on the residual data set and the transformer operation data set, build and train an LSTM model for predicting future load demand; Step 4: Collect real-time operation data of the transformer during actual use, and use the combination of ARIMA model and LSTM model to predict the future load demand corresponding to the real-time operation data; Step 5: Build a power consumption reduction optimization model based on future load demand and real-time operation data; Step 6: Based on the consumption reduction optimization model, use the optimization algorithm to adjust the transformer operation strategy.

2. The transformer consumption reduction intelligent control method based on the power generation end according to claim 1 is characterized in that: The method of pre-collecting the transformer operation data set and the historical load data set is: Install a sensor network for the transformer, and monitor and record the parameter values ​​of each sensor in real time. By reading the parameter values ​​of each sensor, a transformer operation data set is formed; By reading the historical database during transformer operation and the smart meter, a historical load data set is collected.

3. The transformer consumption reduction intelligent control method based on the power generation end according to claim 2 is characterized in that: The method of constructing an ARIMA model based on the historical load data set and using the ARIMA model to generate a residual data set is as follows: For each load parameter in the historical load data set, generating the residual data set includes the following steps: Step 21: Arrange the parameter values ​​of the load parameter in chronological order and organize them into a time series format to obtain a load parameter time series of the corresponding load parameter; Step 22: Analyze whether each load parameter time series has a stable mean and variance by using a statistical method. If it does not have a stable mean and variance, apply a difference method to make the load parameter time series stable. The difference method eliminates trends or seasonality by calculating the difference between adjacent data points. Step 23: Draw autocorrelation function graphs and partial autocorrelation function graphs for the load parameter time series to identify the intrinsic patterns of the time series data; Step 24: According to the autocorrelation function graph and the partial autocorrelation function graph, select the parameter combination (p, d, q) of the ARIMA model; where p is the order of the autoregressive part, which refers to the number of lags in the model, d is the number of differences, which indicates the order of differences required for stabilization, and q is the order of the moving average part, which indicates the number of lagged forecast error terms; Step 25: Use the selected (p, d, q) parameters to construct an ARIMA model and perform fitting; verify the accuracy of the model by testing the residuals of the model, and use statistical test methods to confirm the randomness of the residuals; Step 26: During the ARIMA model fitting process, there is a predicted value for each parameter value per unit time in the load parameter time series; the residual is the actual parameter value minus the predicted value given by the ARIMA model; Step 27: Collect the residuals for each unit time to form a residual data set.

4. The transformer consumption reduction intelligent control method based on the power generation end according to claim 3 is characterized in that: The construction process of the LSTM model includes: Standardize all parameters in all transformer operation data sets and residual data sets to ensure that all parameters are on the same scale; A fixed time window is preset to predict the load demand at the next time step; The LSTM model uses a parameter time series composed of parameters of various transformer operation data and a residual time series composed of residual values ​​of various load parameters within a fixed time window as an input sample; The LSTM model uses the load demand within the next preset time step of each input sample as output, and uses the actual load demand within the next preset time step in the historical load data set as the prediction target; The structure of the LSTM model includes an input layer, an LSTM layer, a fully connected layer and an output layer; The input layer is used to receive multidimensional time series data, namely residuals and transformer operation data; The LSTM layer includes one or more LSTM layer stacks to capture long-term dependencies in the time series; the fully connected layer connects the LSTM layer output to the final output node to generate a prediction value; the output layer: outputs a single prediction value, i.e., the load demand for the next time step; The training process of the LSTM model includes: Split all input samples into training and test sets; The mean square error is used as the loss function of the LSTM model to measure the difference between the predicted value and the actual value; Use Adam optimizer as the optimizer for the LSTM model; Train the LSTM model on the training set and adjust the network weights to minimize the loss function; At the end of each iteration, the performance of the LSTM model is evaluated on the validation set and the model hyperparameters are adjusted to prevent overfitting.

5. The transformer consumption reduction intelligent control method based on the power generation end according to claim 4 is characterized in that: The method of using the ARIMA model and the LSTM model to combine and predict the future load demand corresponding to the real-time operation data is as follows: By using the ARIMA model to predict each load parameter per unit time, the corresponding load parameter prediction value is obtained; Calculate the difference between the predicted value of the load parameter per unit time and the actual parameter value to form a residual set; The residual set and the parameter values ​​of various real-time operating parameters constitute a new input sample, which is input into the LSTM model to obtain the predicted value of the load demand output by the LSTM model.

6. The transformer consumption reduction intelligent control method based on the power generation end according to claim 5 is characterized in that: The method of constructing the energy saving optimization model based on future load demand and real-time operation data is as follows: The predicted value of the load demand is marked as Pr, the voltage of the transformer is marked as V, the power factor of the transformer is marked as pf, and the equivalent resistance of the core is marked as Rc; Mark the transformer winding resistance as R; Based on the predicted value of load demand, voltage, and power factor, a power reduction objective function F is constructed; According to the preset safe voltage range and safe current range of the transformer, a consumption reduction optimization condition set U is constructed; Taking minimizing the energy saving objective function F as the optimization goal and the energy saving optimization condition set U as the constraint condition set, a convex optimization model is constructed as the energy saving optimization model.

7. The transformer consumption reduction intelligent control method based on the power generation end according to claim 6 is characterized in that: The method of adjusting the transformer operation strategy using the optimization algorithm based on the consumption reduction optimization model is as follows: The consumption reduction optimization model is solved using a nonlinear programming solution algorithm or a heuristic algorithm to obtain a solved voltage value, and the transformer operation strategy is to adjust the transformer voltage to the solved voltage value.

8. A transformer consumption reduction intelligent control system based on a power generation end, which is used to implement the transformer consumption reduction intelligent control method based on a power generation end as described in any one of claims 1 to 7, characterized in that: It includes a sample data collection module, a residual data generation module, an LSTM model training module, a load prediction module and a strategy adjustment module; wherein each module is electrically connected; The sample data collection module collects the transformer operation data set and the historical load data set in advance, sends the historical load data set to the residual data generation module, and sends the transformer operation data set to the LSTM model training module; The residual data generation module builds an ARIMA model based on the transformer operation data set and the historical load data set, and uses the ARIMA model to generate a residual data set, and sends the residual data set to the LSTM model training module, and sends the trained ARIMA model to the load prediction module; The LSTM model training module builds and trains an LSTM model for predicting future load demand based on the residual data set and the transformer operation data set, and sends the trained LSTM model to the load prediction module; The load prediction module collects real-time operation data of the transformer during actual use, uses the ARIMA model and LSTM model to predict the future load demand corresponding to the real-time operation data, and sends the future load demand to the strategy adjustment module; The strategy adjustment module builds a consumption reduction optimization model based on future load demand and real-time operation data, and uses an optimization algorithm to adjust the transformer operation strategy based on the consumption reduction optimization model.

9. An electronic device, characterized in that: include: A processor and a memory, wherein: The memory stores a computer program that can be called by the processor; The processor executes the transformer consumption reduction intelligent control method based on the power generation end as described in any one of claims 1 to 7 in the background by calling the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: A rewritable computer program is stored thereon; When the computer program is executed on a computer device, the computer device executes the transformer consumption reduction intelligent control method based on the power generation end as described in any one of claims 1 to 7 in the background.

Images