Generator set operation control method and device based on carbon emission factor, terminal equipment and storage medium

Abstract

The invention discloses a generator set operation control method and device based on a carbon emission factor, terminal equipment and a storage medium, and relates to the field of carbon emission management. The method comprises the following steps of: performing iterative solution operation on a target function taking carbon emission minimization and operation cost minimization as targets, optimizing initial operation parameters in the iterative solution process, and predicting carbon emission factors of each generator set under different operation parameters through a carbon emission factor prediction model, the target operation parameters enable the carbon emission factors and the operation cost of the generator sets to be minimized, so that all the generator sets can operate under the corresponding target operation parameters. Therefore, the problem that cost minimization and carbon emission minimization are difficult to consider at the same time when the regional power system regulates and controls the generator set at present is solved.

Description

Technical Field

[0001] The present invention relates to the field of carbon emission management, and in particular to a method, device, terminal device and storage medium for controlling the operation of a generator set based on a carbon emission factor. Background Art

[0002] Coal-fired power generation is the primary source of carbon emissions in the current power industry. Therefore, reducing carbon emissions from coal-fired power plants is crucial to promoting the power industry's transition to a low-carbon economy. In regional power systems, numerous coal-fired power plants participate in power dispatch, each with varying power outputs yet interdependent. This requires the ability to adjust the operating status of each plant's generator units in a timely manner, ensuring safe operation while minimizing costs and achieving low-carbon operations.

[0003] However, the current carbon emission factor calculation method for regional power systems relies on the overall carbon emissions calculated by each coal-fired power plant, which cannot be accurately calculated for each generator unit. Therefore, the current carbon emission factor calculation method is not very accurate and has a certain lag. During the process of regulating generator units, it is impossible to accurately grasp the carbon emissions they produce, and carbon emissions often exceed the standard. In addition, these excessive carbon emissions may even incur additional environmental costs. Therefore, when regulating generator units, the current regional power system cannot simultaneously minimize costs and carbon emissions. Summary of the Invention

[0004] The embodiments of the present invention provide a generator set operation control method, apparatus, terminal device and storage medium based on carbon emission factors, which can effectively solve the problem that the current regional power system cannot simultaneously take into account cost minimization and carbon emission minimization when regulating generator sets.

[0005] An embodiment of the present invention provides a method for controlling the operation of a generator set based on a carbon emission factor, comprising:

[0006] Obtaining initial operating parameters of all operating data items of each generator set in the regional power system;

[0007] Construct an objective function with the goal of minimizing carbon emissions and operating costs;

[0008] calculating the initial output of each of the generator sets according to the initial operating parameters, and iteratively solving the objective function according to the initial operating parameters and the initial output under preset constraints for ensuring stable operation of the power system until target operating parameters of the generator sets are generated;

[0009] The iterative solution operation includes:

[0010] Obtaining the operating parameters to be evaluated and the target output of the generator set; wherein, initially, the operating parameters to be evaluated are the initial operating parameters, and the target output is the initial output;

[0011] Inputting the to-be-assessed operating parameters of the preset target operating data items as predicted operating parameters into a preset carbon emission factor prediction model, so that the carbon emission factor prediction model predicts the to-be-assessed carbon emission factor of each generating unit under the to-be-assessed operating parameters;

[0012] Calculating the estimated operating cost of each generator set based on the target output and the estimated operating parameters;

[0013] Calculating the objective function value of the operating parameter to be evaluated based on the target output, the carbon emission factor to be evaluated, and the operating cost to be evaluated by using the objective function;

[0014] Determining whether the objective function value meets a preset threshold;

[0015] If not, optimizing the operating parameters to be evaluated under the constraints to generate the operating parameters to be evaluated and the target output required for the next round of iterative solution operation;

[0016] If so, the operating parameter to be evaluated is used as the target operating parameter.

[0017] Furthermore, the selection of the target operation data item includes:

[0018] Obtain historical operating parameters and historical carbon emission factors of all operating data items of the generator set;

[0019] Determining, based on the historical operating parameters and the historical carbon emission factors, an importance score of each of the operating data items in the task of predicting the carbon emission factors;

[0020] Several operation data items whose importance scores are greater than a preset score threshold are used as the target operation data items.

[0021] Furthermore, determining the importance score of each of the operating data items in the task of predicting the carbon emission factor based on the historical operating parameters and the historical carbon emission factor includes:

[0022] Randomly extracting a number of historical operating parameters and corresponding historical carbon emission factors as training samples, and using the training samples to construct a number of decision trees for predicting carbon emission factors;

[0023] Using the unextracted historical operating parameters as out-of-bag data, and inputting the out-of-bag data into the decision trees, so that each decision tree outputs a corresponding first predicted carbon emission factor;

[0024] Calculating a first out-of-bag error of each decision tree according to the first predicted carbon emission factor and the corresponding historical carbon emission factor;

[0025] Noising each of the out-of-bag data to generate noisy out-of-bag data, and inputting the noisy out-of-bag data into the decision tree so that each decision tree outputs a corresponding second predicted carbon emission factor;

[0026] Calculating a second out-of-bag error of each decision tree according to the second predicted carbon emission factor and the corresponding historical carbon emission factor;

[0027] Calculating an initial importance value of each out-of-bag data according to the first out-of-bag error and the second out-of-bag error;

[0028] The importance score of each of the operating data items is calculated according to the initial importance value of the out-of-bag data under the same operating data item.

[0029] Furthermore, the construction of the carbon emission factor prediction model includes:

[0030] Obtain target historical operating parameters and target historical carbon emission factors for a number of target operating data items, and construct training samples using the target historical operating parameters and corresponding target historical carbon emission factors;

[0031] Based on the multi-layer perceptron model structure, build the initial prediction model;

[0032] The initial prediction model is trained using the training samples, and during the training process, a preset loss function is used to calculate the loss function value based on the predicted value output by the initial prediction model and the corresponding target historical carbon emission factor. When it is determined that the loss function value is minimized, the prediction model generated by the last iteration is used as the carbon emission factor prediction model.

[0033] Another embodiment of the present invention provides a generator set operation control device based on a carbon emission factor, comprising:

[0034] An operating parameter acquisition module is used to obtain the initial operating parameters of all operating data items of each generator set in the regional power system;

[0035] An objective function construction module is used to construct an objective function with the goal of minimizing carbon emissions and operating costs;

[0036] an operating parameter optimization module, configured to calculate an initial output of each of the generator sets based on the initial operating parameters, and iteratively solve the objective function based on the initial operating parameters and the initial output under preset constraints for ensuring stable operation of the power system until target operating parameters of the generator sets are generated;

[0037] The iterative solution operation includes:

[0038] Obtaining the operating parameters to be evaluated and the target output of the generator set; wherein, initially, the operating parameters to be evaluated are the initial operating parameters, and the target output is the initial output;

[0039] Inputting the to-be-assessed operating parameters of the preset target operating data items as predicted operating parameters into a preset carbon emission factor prediction model, so that the carbon emission factor prediction model predicts the to-be-assessed carbon emission factor of each generating unit under the to-be-assessed operating parameters;

[0040] Calculating the estimated operating cost of each generator set based on the target output and the estimated operating parameters;

[0041] Calculating the objective function value of the operating parameter to be evaluated based on the target output, the carbon emission factor to be evaluated, and the operating cost to be evaluated by using the objective function;

[0042] Determining whether the objective function value meets a preset threshold;

[0043] If not, optimizing the operating parameters to be evaluated under the constraints to generate the operating parameters to be evaluated and the target output required for the next round of iterative solution operation;

[0044] If so, the operating parameter to be evaluated is used as the target operating parameter.

[0045] Furthermore, the generator set operation control device based on carbon emission factors described in the above embodiment of the invention further includes: an operation parameter optimization module;

[0046] An operating parameter optimization module is used to obtain historical operating parameters and historical carbon emission factors of all operating data items of the generator set;

[0047] Determining, based on the historical operating parameters and the historical carbon emission factors, an importance score of each of the operating data items in the task of predicting the carbon emission factors;

[0048] Several operation data items whose importance scores are greater than a preset score threshold are used as the target operation data items.

[0049] Furthermore, the operating parameter optimization module determines the importance score of each operating data item in the task of predicting the carbon emission factor based on the historical operating parameters and the historical carbon emission factor, including:

[0050] Randomly extracting a number of historical operating parameters and corresponding historical carbon emission factors as training samples, and using the training samples to construct a number of decision trees for predicting carbon emission factors;

[0051] Using the unextracted historical operating parameters as out-of-bag data, and inputting the out-of-bag data into the decision trees, so that each decision tree outputs a corresponding first predicted carbon emission factor;

[0052] Calculating a first out-of-bag error of each decision tree according to the first predicted carbon emission factor and the corresponding historical carbon emission factor;

[0053] Noising each of the out-of-bag data to generate noisy out-of-bag data, and inputting the noisy out-of-bag data into the decision tree so that each decision tree outputs a corresponding second predicted carbon emission factor;

[0054] Calculating a second out-of-bag error of each decision tree according to the second predicted carbon emission factor and the corresponding historical carbon emission factor;

[0055] Calculating an initial importance value of each out-of-bag data according to the first out-of-bag error and the second out-of-bag error;

[0056] The importance score of each of the operating data items is calculated according to the initial importance value of the out-of-bag data under the same operating data item.

[0057] Furthermore, the generator set operation control device based on carbon emission factors described in the above-mentioned embodiment of the invention further includes: a prediction model building module;

[0058] The prediction model construction module is used to obtain target historical operating parameters and target historical carbon emission factors of several target operating data items, and construct training samples with the target historical operating parameters and corresponding target historical carbon emission factors;

[0059] Based on the multi-layer perceptron model structure, build the initial prediction model;

[0060] The initial prediction model is trained using the training samples, and during the training process, a preset loss function is used to calculate the loss function value based on the predicted value output by the initial prediction model and the corresponding target historical carbon emission factor. When it is determined that the loss function value is minimized, the prediction model generated by the last iteration is used as the carbon emission factor prediction model.

[0061] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the generator set operation control method based on the carbon emission factor described in the above-mentioned embodiment of the invention.

[0062] Another embodiment of the present invention provides a storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a generator set operation control method based on a carbon emission factor as described in the above-mentioned embodiment of the invention.

[0063] The following beneficial effects are achieved by implementing the present invention:

[0064] The present invention discloses a method, apparatus, terminal equipment and storage medium for controlling the operation of a generator set based on a carbon emission factor. The method iteratively solves an objective function with the goal of minimizing carbon emissions and minimizing operating costs according to the initial operating parameters of each generator set in a regional power system. During the iterative solution process, the initial operating parameters are optimized, and the carbon emission factor of each generator set under different operating parameters is predicted by a carbon emission factor prediction model until target operating parameters are generated that can minimize the carbon emission factor and operating cost of the generator set, so that each of the generator sets can operate under the corresponding target operating parameters. Therefore, the present invention solves the problem that it is difficult for the current regional power system to simultaneously take into account cost minimization and carbon emission minimization when regulating the generator set by predicting the carbon emission factor and reacting to the optimization of the generator set operating parameters according to the predicted carbon emission factor. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a flow chart of a method for controlling the operation of a generator set based on a carbon emission factor provided by one embodiment of the present invention.

[0066] Figure 2 This is a structural diagram of a generator set operation control device based on carbon emission factors provided by one embodiment of the present invention.

[0067] Figure 3 The present invention provides a schematic diagram of the communication structure between a power dispatching center and coal-fired power plants in a regional power system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0068] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0069] To solve the problem that it is difficult to minimize both cost and carbon emissions when regulating power generation units in the current regional power system, see Figure 1 This is a flow chart of a method for controlling the operation of a generator set based on a carbon emission factor according to an embodiment of the present invention, including:

[0070] S1. Obtaining initial operating parameters of all operating data items of each generator set in the regional power system;

[0071] In a preferred embodiment of the present invention, the operating data items include the coal consumption of each generator set, boiler combustion temperature, main steam flow rate, condensate flow rate, and other operating data items closely related to factors such as energy consumption and combustion efficiency. Furthermore, to ensure data quality and thus the accuracy of subsequent calculation results, in this embodiment, the initial operating parameters are preprocessed. The specific preprocessing includes the following steps:

[0072] First, a boxplot method was used to eliminate outliers. After sorting the initial operating parameters of each operating data item in ascending order, the first quartile q1 and the third quartile q3 of the initial operating parameters of each operating data item were found. Data with values less than [q1-1.5×(q3-q1)] and greater than [q3+1.5×(q3-q1)] were eliminated. q1 is the first quartile, and a value at the 25% percentile indicates that 25% of the observations in the data are less than or equal to q1. q3 is the third quartile, and a value at the 75% percentile indicates that 75% of the observations in the data are less than or equal to q3.

[0073] Secondly, the polynomial interpolation method is used to fill the missing values. By fitting the polynomial, the missing values of the initial operating parameters of each operating data item are calculated and filled;

[0074] Finally, the following formula is used to normalize the initial operating parameters of each operating data item:

[0075]

[0076] Where x * is the normalized value of the initial operating parameter x after normalization, x min is the minimum value of the initial operating parameters of each operating data item, x max It is the maximum value of the initial operating parameters of each operating data item.

[0077] S2. Construct an objective function with the goal of minimizing carbon emissions and operating costs;

[0078] In a preferred embodiment of the present invention, the objective function is as follows:

[0079] F=Minimize[F1,F2];

[0080] Among them, F is the objective function value, F1 is the total carbon emissions of the regional power system, F2 is the total operating cost of the regional power system, and Minimize[] is the minimization function.

[0081] S3. Calculating the initial output of each generator set according to the initial operating parameters, and iteratively solving the objective function according to the initial operating parameters and the initial output under preset constraints for ensuring stable operation of the power system, until target operating parameters of the generator set are generated;

[0082] In a preferred embodiment of the present invention, when there are coal-fired power plants in the regional power system, Figure 3 When the power dispatch center is located, the target operating parameters of each generator set are sent to the power dispatch center, which then controls the generator sets in a unified manner. Alternatively, the target operating parameters of each generator set are sent to the equipment control center of the corresponding coal-fired power plant, which then controls the respective generator sets.

[0083] The iterative solution operation includes:

[0084] S31, obtaining the operating parameters to be evaluated and the target output of the generator set; wherein, initially, the operating parameters to be evaluated are the initial operating parameters, and the target output is the initial output;

[0085] S32. Inputting the to-be-assessed operating parameters of the preset target operating data items as predicted operating parameters into a preset carbon emission factor prediction model, so that the carbon emission factor prediction model predicts the to-be-assessed carbon emission factor of each generating unit under the to-be-assessed operating parameters;

[0086] In a preferred embodiment of the present invention, in order to avoid overfitting of the carbon emission factor prediction model due to too many data items and to improve the computational efficiency of the carbon emission factor prediction model, this embodiment selects operating parameters of operating data items that are highly correlated with the carbon emissions of the generator set to construct the carbon emission factor prediction model.

[0087] Preferably, the selection of the target operation data item includes:

[0088] S011. Obtain historical operating parameters and historical carbon emission factors of all operating data items of the generator set;

[0089] S012. Determine, based on the historical operating parameters and the historical carbon emission factors, the importance score of each of the operating data items in the task of predicting the carbon emission factors;

[0090] S013. Taking several operation data items whose importance scores are greater than a preset score threshold as the target operation data items.

[0091] Preferably, determining the importance score of each of the operating data items in the task of predicting the carbon emission factor based on the historical operating parameters and the historical carbon emission factor includes:

[0092] S0121. Randomly select a number of historical operating parameters and corresponding historical carbon emission factors as training samples, and use the training samples to construct a number of decision trees for predicting carbon emission factors;

[0093] S0122. Use the unextracted historical operating parameters as out-of-bag data, and input the out-of-bag data into the decision tree, so that each decision tree outputs a corresponding first predicted carbon emission factor;

[0094] S0123. Calculate a first out-of-bag error of each decision tree based on the first predicted carbon emission factor and the corresponding historical carbon emission factor;

[0095] S0124. Noising each of the out-of-bag data to generate noisy out-of-bag data, and inputting the noisy out-of-bag data into the decision tree so that each decision tree outputs a corresponding second predicted carbon emission factor;

[0096] S0125. Calculate a second out-of-bag error of each decision tree based on the second predicted carbon emission factor and the corresponding historical carbon emission factor;

[0097] S0126. Calculate an initial importance value of each out-of-bag data according to the first out-of-bag error and the second out-of-bag error;

[0098] S0127. Calculate the importance score of each of the operation data items according to the initial importance value of the out-of-bag data under the same operation data item.

[0099] In a preferred embodiment of the present invention, a random forest algorithm is used to evaluate the importance of each operating data item in the generator set in the task of predicting the carbon emission factor, and a specific importance score is obtained. Specifically, several decision trees are first constructed, and then the out-of-bag data of each decision tree are selected, and the first out-of-bag error (erroob1) is calculated; for each out-of-bag data, noise interference is randomly added, and the second out-of-bag error (erroob2) after adding noise is calculated. The difference between erroob1 and erroob2 is the initial importance value of the out-of-bag data. It can be understood that a large difference indicates that the operating data item has a large impact on the prediction result of the model, that is, the operating data item is more important; conversely, if the difference is small, it means that the operating data item is relatively unimportant. Finally, based on the initial importance value under the same operating data item, the importance score of each operating data item is calculated.

[0100] Preferably, the construction of the carbon emission factor prediction model includes:

[0101] S021. Obtain target historical operating parameters and target historical carbon emission factors for several target operating data items, and construct training samples using the target historical operating parameters and corresponding target historical carbon emission factors;

[0102] S022. Build an initial prediction model based on the multi-layer perceptron model structure;

[0103] S023. Use the training samples to train the initial prediction model, and during the training process, use a preset loss function to calculate the loss function value based on the predicted value output by the initial prediction model and the corresponding target historical carbon emission factor. When it is determined that the loss function value is minimized, the prediction model generated by the last iteration is used as the carbon emission factor prediction model.

[0104] In a preferred embodiment of the present invention, the target historical operating parameters and target historical carbon emission factors of several target operating data items are used to construct training samples, and the target historical operating parameters and the corresponding target historical carbon emission factors are divided into a training set and a validation set, wherein the training set accounts for 70% and the validation set accounts for 30%; the K-fold method is used for cross-validation during the training process to prevent the model from overfitting; fixed biases and weights are set initially to seek the optimal combination of the number of hidden layers and the number of neurons; the training data is input into the initial prediction model, and the prediction model is continuously optimized by adjusting the model parameters, etc. until the loss function is minimized. Furthermore, the carbon emission factor prediction model selects the tanh function as the activation function, and the specific formula is as follows:

[0105]

[0106] Where e is a natural constant and x is an input value.

[0107] Furthermore, the mean absolute error is selected as the loss function, and the formula is as follows:

[0108]

[0109] Among them, MAE is the loss function value, n is the number of training samples in the validation set, is the predicted value of the carbon emission factor prediction model during training based on the target historical operating parameters of the kth training sample, y k is the target historical carbon emission factor of the kth training sample.

[0110] S33. Calculating the estimated operating cost of each generator set based on the target output and the estimated operating parameters;

[0111] S34. Calculate the objective function value of the operating parameter to be evaluated based on the target output, the carbon emission factor to be evaluated, and the operating cost to be evaluated using the objective function;

[0112] In a preferred embodiment of the present invention, the total carbon emissions F1 of the regional power system is calculated using the following formula:

[0113]

[0114] Among them, CE i (P i ) is the carbon emission factor to be assessed for the i-th generator set, P i is the output of the i-th generator set under the operating parameters to be evaluated.

[0115] The total operating cost F2 of the regional power system is calculated according to the following formula:

[0116]

[0117] Among them, a i 、b i and c i are the operating cost coefficients of the i-th generator set respectively.

[0118] Finally, the objective function shown in step S2 is used to determine the objective function value of the operating parameter to be evaluated.

[0119] S35, determining whether the objective function value meets a preset threshold;

[0120] S36: If not, optimizing the operating parameters to be evaluated under the constraints to generate the operating parameters to be evaluated and the target output required for the next round of iterative solution operation;

[0121] In a preferred embodiment of the present invention, the constraints include: a load demand balance constraint and a unit output upper and lower limit constraint. Specifically, the load demand balance constraint is used to constrain the total output of all coal-fired power generation units in the regional power grid to meet the power load demand D:

[0122]

[0123] Among them, P i is the output of the i-th generator set, and N is the total number of generator sets.

[0124] The upper and lower limits of unit output are used to constrain the output of each generator unit to be within its rated power range:

[0125]

[0126] Among them, P min,i and P max,i are the minimum and maximum allowable outputs of the i-th generator set respectively.

[0127] Finally, according to the objective function value corresponding to the evaluated operating parameters, the optimization direction of each target operating data item is determined, and according to the optimization direction, the operating parameters that meet the constraints are randomly generated, and the corresponding target output is calculated.

[0128] S37: If yes, use the operating parameter to be evaluated as the target operating parameter.

[0129] In summary, the embodiment of the present invention provides a method for controlling the operation of a generator set based on a carbon emission factor. The method iteratively solves the objective function with the goal of minimizing carbon emissions and minimizing operating costs according to the initial operating parameters of each generator set in the regional power system. During the iterative solution process, the initial operating parameters are optimized, and the carbon emission factor of each generator set under different operating parameters is predicted by the carbon emission factor prediction model, until the target operating parameters that can minimize the carbon emission factor and operating cost of the generator set are generated, so that each of the generator sets can operate under the corresponding target operating parameters. Therefore, the present invention solves the problem that it is difficult for the current regional power system to simultaneously take into account cost minimization and carbon emission minimization when regulating the generator set.

[0130] See also Figure 2 , is a structural diagram of a generator set operation control device based on a carbon emission factor according to an embodiment of the present invention, comprising:

[0131] An operating parameter acquisition module is used to obtain the initial operating parameters of all operating data items of each generator set in the regional power system;

[0132] An objective function construction module is used to construct an objective function with the goal of minimizing carbon emissions and operating costs;

[0133] an operating parameter optimization module, configured to calculate an initial output of each of the generator sets based on the initial operating parameters, and iteratively solve the objective function based on the initial operating parameters and the initial output under preset constraints for ensuring stable operation of the power system until target operating parameters of the generator sets are generated;

[0134] The iterative solution operation includes:

[0135] Obtaining the operating parameters to be evaluated and the target output of the generator set; wherein, initially, the operating parameters to be evaluated are the initial operating parameters, and the target output is the initial output;

[0136] Inputting the to-be-assessed operating parameters of the preset target operating data items as predicted operating parameters into a preset carbon emission factor prediction model, so that the carbon emission factor prediction model predicts the to-be-assessed carbon emission factor of each generating unit under the to-be-assessed operating parameters;

[0137] Calculating the estimated operating cost of each generator set based on the estimated operating parameters;

[0138] Calculating the objective function value of the operating parameter to be evaluated based on the carbon emission factor to be evaluated and the operating cost to be evaluated by using the objective function;

[0139] Determining whether the objective function value meets a preset threshold;

[0140] If not, optimizing the operating parameters to be evaluated under the constraints to generate the operating parameters to be evaluated and the target output required for the next round of iterative solution operation;

[0141] If so, the operating parameter to be evaluated is used as the target operating parameter.

[0142] Furthermore, the generator set operation control device based on carbon emission factors described in the above embodiment of the invention further includes: an operation parameter optimization module;

[0143] An operating parameter optimization module is used to obtain historical operating parameters and historical carbon emission factors of all operating data items of the generator set;

[0144] Determining, based on the historical operating parameters and the historical carbon emission factors, an importance score of each of the operating data items in the task of predicting the carbon emission factors;

[0145] Several operation data items whose importance scores are greater than a preset score threshold are used as the target operation data items.

[0146] Furthermore, the operating parameter optimization module determines the importance score of each operating data item in the task of predicting the carbon emission factor based on the historical operating parameters and the historical carbon emission factor, including:

[0147] Randomly extracting a number of historical operating parameters and corresponding historical carbon emission factors as training samples, and using the training samples to construct a number of decision trees for predicting carbon emission factors;

[0148] Using the unextracted historical operating parameters as out-of-bag data, and inputting the out-of-bag data into the decision trees, so that each decision tree outputs a corresponding first predicted carbon emission factor;

[0149] Calculating a first out-of-bag error of each decision tree according to the first predicted carbon emission factor and the corresponding historical carbon emission factor;

[0150] Noising each of the out-of-bag data to generate noisy out-of-bag data, and inputting the noisy out-of-bag data into the decision tree so that each decision tree outputs a corresponding second predicted carbon emission factor;

[0151] Calculating a second out-of-bag error of each decision tree according to the second predicted carbon emission factor and the corresponding historical carbon emission factor;

[0152] Calculating an initial importance value of each out-of-bag data according to the first out-of-bag error and the second out-of-bag error;

[0153] The importance score of each of the operating data items is calculated according to the initial importance value of the out-of-bag data under the same operating data item.

[0154] Furthermore, the generator set operation control device based on carbon emission factors described in the above-mentioned embodiment of the invention further includes: a prediction model building module;

[0155] The prediction model construction module is used to obtain target historical operating parameters and target historical carbon emission factors of several target operating data items, and construct training samples with the target historical operating parameters and corresponding target historical carbon emission factors;

[0156] Based on the multi-layer perceptron model structure, build the initial prediction model;

[0157] The initial prediction model is trained using the training samples, and during the training process, a preset loss function is used to calculate the loss function value based on the predicted value output by the initial prediction model and the corresponding target historical carbon emission factor. When it is determined that the loss function value is minimized, the prediction model generated by the last iteration is used as the carbon emission factor prediction model.

[0158] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement the present invention without inventive effort.

[0159] Those skilled in the art will clearly understand that for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0160] The terminal device may be a computing device such as a desktop computer, a notebook computer, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0161] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, connecting various parts of the entire terminal device using various interfaces and lines.

[0162] The memory can be used to store the computer program, and the processor realizes various functions of the terminal device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created based on the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0163] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. The computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium.

[0164] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for controlling the operation of a generator set based on a carbon emission factor, characterized in that: include: Obtaining initial operating parameters of all operating data items of each generator set in the regional power system; Construct an objective function with the goal of minimizing carbon emissions and operating costs; calculating an initial output of each of the generator sets according to the initial operating parameters, and iteratively solving the objective function according to the initial operating parameters and the initial output under preset constraints for ensuring stable operation of the power system until target operating parameters of the generator sets are generated; The iterative solution operation includes: Obtaining the operating parameters to be evaluated and the target output of the generator set; wherein, initially, the operating parameters to be evaluated are the initial operating parameters, and the target output is the initial output; Inputting the to-be-assessed operating parameters of the preset target operating data items as predicted operating parameters into a preset carbon emission factor prediction model, so that the carbon emission factor prediction model predicts the to-be-assessed carbon emission factor of each generating unit under the to-be-assessed operating parameters; Calculating the estimated operating cost of each generator set based on the target output and the estimated operating parameters; Calculating the objective function value of the operating parameter to be evaluated based on the target output, the carbon emission factor to be evaluated, and the operating cost to be evaluated by using the objective function; Determining whether the objective function value meets a preset threshold; If not, optimizing the operating parameters to be evaluated under the constraints to generate the operating parameters to be evaluated and the target output required for the next round of iterative solution operation; If so, the operating parameter to be evaluated is used as the target operating parameter.

2. A method for controlling the operation of a generator set based on a carbon emission factor according to claim 1, characterized in that: The selection of the target operation data item includes: Obtain historical operating parameters and historical carbon emission factors of all operating data items of the generator set; Determining, based on the historical operating parameters and the historical carbon emission factors, an importance score of each of the operating data items in the task of predicting the carbon emission factors; Several operation data items whose importance scores are greater than a preset score threshold are used as the target operation data items.

3. A method for controlling the operation of a generator set based on a carbon emission factor according to claim 2, characterized in that: Determining the importance score of each of the operating data items in the task of predicting the carbon emission factor based on the historical operating parameters and the historical carbon emission factor includes: Randomly extracting a number of historical operating parameters and corresponding historical carbon emission factors as training samples, and using the training samples to construct a number of decision trees for predicting carbon emission factors; Using the unextracted historical operating parameters as out-of-bag data, and inputting the out-of-bag data into the decision trees, so that each decision tree outputs a corresponding first predicted carbon emission factor; Calculating a first out-of-bag error of each decision tree according to the first predicted carbon emission factor and the corresponding historical carbon emission factor; Noising each of the out-of-bag data to generate noisy out-of-bag data, and inputting the noisy out-of-bag data into the decision tree so that each decision tree outputs a corresponding second predicted carbon emission factor; Calculating a second out-of-bag error of each decision tree according to the second predicted carbon emission factor and the corresponding historical carbon emission factor; Calculating an initial importance value of each out-of-bag data according to the first out-of-bag error and the second out-of-bag error; The importance score of each of the operating data items is calculated according to the initial importance value of the out-of-bag data under the same operating data item.

4. A method for controlling the operation of a generator set based on a carbon emission factor according to claim 3, characterized in that: The construction of the carbon emission factor prediction model includes: Obtain target historical operating parameters and target historical carbon emission factors for a number of target operating data items, and construct training samples using the target historical operating parameters and corresponding target historical carbon emission factors; Based on the multi-layer perceptron model structure, build the initial prediction model; The initial prediction model is trained using the training samples, and during the training process, a preset loss function is used to calculate the loss function value based on the predicted value output by the initial prediction model and the corresponding target historical carbon emission factor. When it is determined that the loss function value is minimized, the prediction model generated by the last iteration is used as the carbon emission factor prediction model.

5. A generator set operation control device based on carbon emission factor, characterized in that: include: An operating parameter acquisition module is used to obtain the initial operating parameters of all operating data items of each generator set in the regional power system; An objective function construction module is used to construct an objective function with the goal of minimizing carbon emissions and operating costs; an operating parameter optimization module, configured to calculate an initial output of each of the generator sets based on the initial operating parameters, and iteratively solve the objective function based on the initial operating parameters and the initial output under preset constraints for ensuring stable operation of the power system until target operating parameters of the generator sets are generated; The iterative solution operation includes: Obtaining the operating parameters to be evaluated and the target output of the generator set; wherein, initially, the operating parameters to be evaluated are the initial operating parameters, and the target output is the initial output; Inputting the to-be-assessed operating parameters of the preset target operating data items as predicted operating parameters into a preset carbon emission factor prediction model, so that the carbon emission factor prediction model predicts the to-be-assessed carbon emission factor of each generating unit under the to-be-assessed operating parameters; Calculating the estimated operating cost of each generator set based on the target output and the estimated operating parameters; Calculating the objective function value of the operating parameter to be evaluated based on the target output, the carbon emission factor to be evaluated, and the operating cost to be evaluated by using the objective function; Determining whether the objective function value meets a preset threshold; If not, optimizing the operating parameters to be evaluated under the constraints to generate the operating parameters to be evaluated and the target output required for the next round of iterative solution operation; If so, the operating parameter to be evaluated is used as the target operating parameter.

6. The generator set operation control device based on carbon emission factor according to claim 5, characterized in that: It also includes: operating parameter optimization module; An operating parameter optimization module is used to obtain historical operating parameters and historical carbon emission factors of all operating data items of the generator set; Determining, based on the historical operating parameters and the historical carbon emission factors, an importance score of each of the operating data items in the task of predicting the carbon emission factors; Several operation data items whose importance scores are greater than a preset score threshold are used as the target operation data items.

7. The generator set operation control device based on carbon emission factor according to claim 6, characterized in that: The operating parameter optimization module determines the importance score of each of the operating data items in the task of predicting the carbon emission factor based on the historical operating parameters and the historical carbon emission factor, including: Randomly extracting a number of historical operating parameters and corresponding historical carbon emission factors as training samples, and using the training samples to construct a number of decision trees for predicting carbon emission factors; Using the unextracted historical operating parameters as out-of-bag data, and inputting the out-of-bag data into the decision trees, so that each decision tree outputs a corresponding first predicted carbon emission factor; Calculating a first out-of-bag error of each decision tree according to the first predicted carbon emission factor and the corresponding historical carbon emission factor; Noising each of the out-of-bag data to generate noisy out-of-bag data, and inputting the noisy out-of-bag data into the decision tree so that each decision tree outputs a corresponding second predicted carbon emission factor; Calculating a second out-of-bag error of each decision tree according to the second predicted carbon emission factor and the corresponding historical carbon emission factor; Calculating an initial importance value of each out-of-bag data according to the first out-of-bag error and the second out-of-bag error; The importance score of each of the operating data items is calculated according to the initial importance value of the out-of-bag data under the same operating data item.

8. The generator set operation control device based on carbon emission factor according to claim 7, characterized in that: Also includes: Predictive model building module; The prediction model construction module is used to obtain target historical operating parameters and target historical carbon emission factors of several target operating data items, and construct training samples with the target historical operating parameters and corresponding target historical carbon emission factors; Based on the multi-layer perceptron model structure, build the initial prediction model; The initial prediction model is trained using the training samples, and during the training process, a preset loss function is used to calculate the loss function value based on the predicted value output by the initial prediction model and the corresponding target historical carbon emission factor. When it is determined that the loss function value is minimized, the prediction model generated by the last iteration is used as the carbon emission factor prediction model.

9. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, a method for controlling the operation of a generator set based on a carbon emission factor as claimed in any one of claims 1 to 4 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute a generator set operation control method based on a carbon emission factor as described in any one of claims 1 to 4.

Images