Thermal power generating unit short-term load prediction method, system and equipment based on Gaussian weighted domain generalization network and medium

Abstract

The invention discloses a thermal power generating unit short-term load prediction method, system and device based on a Gaussian weighted domain generalization network and a medium, and belongs to the technical field of thermal power generating unit operation optimization and intelligent power generation, and the method comprises the steps: collecting the historical operation data of a thermal power generating unit, and carrying out the preprocessing; fitting the probability distribution of the first operation data to obtain a probability density function, and dividing the first operation data into Q time sequence sub-domains; constructing a domain adversarial neural network framework and constructing a soft label vector; calculating a joint loss function and determining parameters of the domain adversarial neural network framework; and outputting a short-term load prediction result of the target unit according to the real-time operation data of the target unit. According to the method, the problem that the generalization performance of a traditional prediction method is suddenly reduced during cross-unit migration or long-term operation due to the fact that the heterogeneity of load data distribution and time sequence distribution offset are difficult to capture in the traditional load prediction method is solved.

Description

A method, system, equipment, and medium for short-term load forecasting of thermal power units based on Gaussian weighted domain generalization networks. Technical Field

[0001] This invention relates to the field of thermal power unit operation optimization and intelligent power generation technology, specifically to a method, system, equipment and medium for short-term load forecasting of thermal power units based on Gaussian weighted domain generalization network. Background Technology

[0002] Short-term load forecasting for thermal power units is a crucial technical aspect of grid dispatching and unit optimization. However, actual operation of thermal power units presents two types of distribution offsets: heterogeneity in load data distribution among units and temporal distribution offset within a single unit. Specifically, different units exhibit significant heterogeneity in load data distribution due to differences in installed capacity or boiler type; a single unit's load data also shows temporal distribution offsets at different times due to operating condition switching and fuel fluctuations. Traditional load forecasting methods, which rely on the assumption of independent and identically distributed loads based on training and testing data, struggle to capture these offsets. This leads to a sharp decline in the generalization performance of traditional forecasting methods during cross-unit migration or long-term operation, failing to meet the flexible peak-shaving requirements of modern power systems.

[0003] If we can analyze these data using a data-driven approach and construct an adaptive distribution offset prediction method, we can significantly improve the prediction performance of load forecasting in complex operating conditions and break through the generalization bottleneck of traditional prediction methods.

[0004] Therefore, conducting research on short-term load forecasting of thermal power units based on domain generalization and adversarial learning, and solving the model generalization problem under distribution offset, has important engineering and theoretical value for flexible grid dispatching and efficient unit operation. Summary of the Invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by this invention is that traditional load forecasting methods, which adopt the assumption of independent and identical distribution based on training and test data, are difficult to capture the heterogeneity of load data distribution and temporal distribution offset. This leads to a sharp drop in the generalization performance of traditional forecasting methods during cross-unit migration or long-term operation, and they cannot meet the needs of flexible peak shaving in new power systems.

[0007] To address the aforementioned technical problems, this invention provides the following technical solution: a short-term load forecasting method for thermal power units based on a Gaussian weighted domain generalization network, comprising the following steps: performing time-domain partitioning on first operating data to obtain several time-series sub-domains, wherein the first operating data is preprocessed historical operating data of the target thermal power unit; constructing a domain adversarial neural network framework, wherein the domain adversarial neural network framework is used to obtain soft label vectors of several time-series sub-domains; determining the parameters of the domain adversarial neural network framework, wherein the parameters of the domain adversarial neural network framework are determined according to a joint loss function, wherein the joint loss function is calculated based on the soft label vectors and the output of the domain adversarial neural network framework; and outputting the short-term load forecasting result of the target unit, wherein the short-term load forecasting result of the target unit is generated by inputting the real-time operating data of the target unit into the trained domain adversarial neural network framework.

[0008] As a preferred embodiment of the short-term load forecasting method for thermal power units based on Gaussian weighted domain generalization network described in this invention, the step of obtaining preprocessed historical operating data of the target thermal power unit includes: collecting historical operating data related to load forecasting from the operating database of the thermal power unit; removing outliers from the historical operating data and performing normalization processing to obtain normalized operating data; preprocessing the normalized operating data, calculating the correlation coefficient between each operating data and load data in the normalized operating data, and filtering the normalized operating data according to the correlation coefficient to obtain the first operating data.

[0009] As a preferred embodiment of the short-term load forecasting method for thermal power units based on a Gaussian weighted domain generalization network described in this invention, the step of performing time-domain partitioning on the first operating data includes: using a Gaussian mixture model for the probabilistic graphical model, fitting the probability distribution of each data point in the first operating data using the Gaussian mixture model to construct a probability density function; calculating the posterior probability of a data point in the first operating data belonging to the k-th Gaussian component based on the probability density function; updating the parameters of the probability density function based on the posterior probability of the k-th Gaussian component; continuously calculating the posterior probability of the k-th Gaussian component and updating the parameters of the probability density function until the parameter change is less than the parameter threshold, and determining the final parameters of the probability density function; sequentially setting the number of time-series subdomains to K, dividing the first operating data into K time-series subdomains, and calculating the Bayesian information criterion coefficient corresponding to the final parameters of the probability density function for each K value, and taking the K value with the smallest Bayesian information criterion coefficient as the number Q of time-series subdomains; dividing the first operating data into Q time-series subdomains.

[0010] The beneficial effects of this preferred technical solution are as follows: by combining the Gaussian mixture model with the Bayesian information criterion, the changes in the data distribution characteristics of the unit at different operating stages are identified, and the continuous operating data is divided into a specified number of time-series subdomains with statistical significance, providing a high-quality domain partitioning basis for domain generalization, and being able to cope with the problem of time-series distribution changes in single unit operation.

[0011] As a preferred embodiment of the short-term load forecasting method for thermal power units based on Gaussian weighted domain generalization network described in this invention, the step of constructing a domain adversarial neural network framework includes: constructing a domain adversarial neural network framework containing a feature extractor, a predictor, and a domain classifier; extracting the hidden layer feature representations of each time-series subdomain from the output of the feature extractor in the domain adversarial neural network framework; calculating the correlation weights between two time-series subdomains based on the hidden layer feature representations; calculating the dynamic smoothing coefficient based on the number of time-series subdomains; and constructing a soft label vector based on the correlation weights and the dynamic smoothing coefficient.

[0012] The beneficial effects of this preferred technical solution are as follows: by setting a smoothing coefficient that decreases with the training process, the common learning between domains is emphasized in the early stage of training, while the extraction of intra-domain characteristics is emphasized in the later stage. This achieves the adjustment of the contribution of each domain to the model training, ensures the balance and stability of the learning process, and improves the prediction accuracy of the model on unknown target units.

[0013] As a preferred embodiment of the short-term load forecasting method for thermal power units based on Gaussian weighted domain generalization network described in this invention, the step of determining the parameters of the domain adversarial neural network framework includes: calculating the prediction loss function based on the output of the predictor in the domain adversarial neural network framework; calculating the domain classification loss function based on the soft label vector and the output of the domain classifier in the domain adversarial neural network framework; calculating the joint loss function based on the prediction loss function and the domain classification loss function; and updating the parameters of the feature extractor, predictor, and domain classifier in the domain adversarial neural network framework based on the joint loss function.

[0014] The beneficial effects of this preferred technical solution are as follows: by constructing a domain adversarial neural network framework and training the adversarial neural network framework with Q temporal subdomains, the feature extractor learns the domain-invariant feature representation that can confuse the domain classifier, thus overcoming the problem of domain distribution shift caused by differences in equipment parameters and operating strategies among different thermal power units; by quantifying the similarity of different temporal subdomains and constructing a correlation weight matrix through the maximum mean difference between the feature distributions of different temporal subdomains, the model focuses on different temporal subdomains with similar distributions.

[0015] As a preferred embodiment of the short-term load forecasting method for thermal power units based on Gaussian weighted domain generalization network described in this invention, the formula for constructing the probability density function in the time-domain partitioning operation of the first operating data is: ;in, For probability density, This is the first running data for the k-th time-series subdomain. The set number of time-series subdomains, The number of samples in the first run. For mixed weights, Let be the mean of the k-th time series subdomain. Let be the k-th covariance matrix; the formula for calculating the posterior probability of a data point in the first running data belonging to the k-th Gaussian component based on the probability density function is: ;in, Let be the posterior probability that the j-th data point belongs to the k-th Gaussian component, and i be the sample index.

[0016] As a preferred embodiment of the short-term load forecasting method for thermal power units based on Gaussian weighted domain generalization network described in this invention, the formula for calculating the correlation weight between two time-series subdomains based on the hidden layer feature representation is as follows: ;in, The correlation weights between the k-th and j-th time series subdomains are given. It is the function of maximum mean difference. and The hidden layer feature representations obtained after the k-th and j-th temporal subdomains are processed by the feature extractor. The number of time-series subdomains is used as the formula for calculating the dynamic smoothing coefficient based on the number of time-series subdomains. ;in, For dynamic smoothing coefficients, The number of time-series subdomains. To preset the total number of training steps, Let be the current training iteration number; the formula for constructing the soft label vector based on the relevant weights and dynamic smoothing coefficient is: ;in, To construct a soft tag vector based on the k-th temporal subdomain, assign a value to the position (i.e., the k-th position) of the soft tag vector corresponding to its own domain. As the positive class confidence level, the rest... Each position is assigned a value. ⋅ , as the weighted confidence level.

[0017] This invention provides a short-term load forecasting system for thermal power units based on a Gaussian weighted domain generalization network.

[0018] To address the aforementioned technical problems, the present invention further provides the following technical solution: a short-term load forecasting system for thermal power units based on a Gaussian weighted domain generalization network, comprising: a data acquisition module: acquiring historical operating data of thermal power units and preprocessing it to obtain first operating data; a data partitioning module: fitting the probability distribution of the first operating data using a probabilistic graphical model to obtain a probability density function, determining the number Q of time-series subdomains based on the probability density function, and dividing the first operating data into Q time-series subdomains; a framework construction module: constructing a domain adversarial neural network framework and training the adversarial neural network framework through Q time-series subdomains, determining the feature extractor parameters, predictor parameters, and domain classifier parameters in the domain adversarial neural network framework; and a data output module: inputting the real-time operating data of the target unit into the trained domain adversarial neural network framework, and outputting the short-term load forecasting result of the target unit.

[0019] The present invention provides a computer device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the described method for short-term load forecasting of thermal power units based on a Gaussian weighted domain generalization network.

[0020] The present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the aforementioned method for short-term load forecasting of thermal power units based on a Gaussian weighted domain generalization network.

[0021] The beneficial effects of this invention are as follows: This invention uses a Gaussian mixture model combined with Bayesian information criteria to identify changes in the data distribution characteristics of a power unit at different operating stages, and segments continuous operating data into a specified number of statistically significant time-series subdomains, providing a high-quality domain partitioning foundation for domain generalization and addressing the problem of time-series distribution changes in single-unit operation; by constructing a domain adversarial neural network framework and training the framework with Q time-series subdomains, the feature extractor learns domain-invariant feature representations that can confuse the domain classifier, overcoming the problem of domain distribution shift caused by differences in equipment parameters and operating strategies among different thermal power units; by quantifying the similarity of different time-series subdomains and constructing a correlation weight matrix through the maximum mean difference between the feature distributions of different time-series subdomains, the model focuses on different time-series subdomains with similar distributions; by setting a smoothing coefficient that decreases with the training process, the invention emphasizes the learning of commonalities between domains in the early stage of training and the extraction of intra-domain characteristics in the later stage, thereby adjusting the contribution of each domain to the model training, ensuring the balance and stability of the learning process, and improving the prediction accuracy of the model on unknown target units. Attached Figure Description

[0022] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 is an overall flowchart of a short-term load forecasting method for thermal power units based on a Gaussian weighted domain generalization network according to an embodiment of the present invention.

[0024] Figure 2 is an overall framework diagram of a short-term load forecasting method for thermal power units based on a Gaussian weighted domain generalization network provided by an embodiment of the present invention.

[0025] Figure 3 is a heat map of the time-series subdomains after time-series segmentation of a thermal power unit according to an embodiment of the present invention, which is a method for short-term load forecasting of thermal power units based on Gaussian weighted domain generalization network.

[0026] Figure 4 is a domain neural adversarial network framework diagram of a short-term load forecasting method for thermal power units based on a Gaussian weighted domain generalization network provided in an embodiment of the present invention.

[0027] Figure 5 shows the loss change before and after introducing a soft label vector into the loss function of the domain classifier in a short-term load forecasting method for thermal power units based on a Gaussian weighted domain generalization network according to an embodiment of the present invention.

[0028] Figure 6 is a comparison of the prediction results of the proposed method for short-term load forecasting of thermal power units based on Gaussian weighted domain generalization network with the prediction results of other models.

[0029] Figure 7 shows the feature distribution alignment effect before and after using a short-term load prediction method for thermal power units based on a Gaussian weighted domain generalization network, according to an embodiment of the present invention. Detailed Implementation

[0030] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0031] Example 1, referring to Figure 1, is the first embodiment of the present invention. This embodiment provides a method for short-term load forecasting of thermal power units based on a Gaussian weighted domain generalization network, including: S100: performing a time-domain partitioning operation on first operating data to obtain several time-series sub-domains, wherein the first operating data is the preprocessed historical operating data of the target thermal power unit; S200: constructing a domain adversarial neural network framework, wherein the domain adversarial neural network framework is used to obtain soft label vectors of several time-series sub-domains; S300: determining the parameters of the domain adversarial neural network framework, wherein the parameters of the domain adversarial neural network framework are determined according to a joint loss function, wherein the joint loss function is calculated based on the soft label vectors and the output of the domain adversarial neural network framework; S400: outputting the short-term load forecasting result of the target unit, wherein the short-term load forecasting result of the target unit is generated by inputting the real-time operating data of the target unit into the trained domain adversarial neural network framework.

[0032] It should be noted that, in response to the heterogeneity of load data distribution and temporal distribution offset, traditional load forecasting methods adopt the assumption of independent and identically distributed load data based on training and test data. This makes it difficult to capture the heterogeneity of load data distribution and temporal distribution offset, resulting in a sharp drop in the generalization performance of traditional forecasting methods during cross-unit migration or long-term operation. This makes it impossible to meet the flexible peak-shaving requirements of new power systems. Therefore, it is very important to construct a forecasting method that can adapt to distribution offset.

[0033] Therefore, to address the aforementioned problems in short-term load forecasting for thermal power units, this invention constructs a short-term load forecasting method for thermal power units based on a Gaussian weighted domain generalization network through steps S100~S400. This invention uses a Gaussian mixture model combined with Bayesian information criteria to identify changes in the data distribution characteristics of the unit at different operating stages, and segments continuous operating data into a specified number of statistically significant time-series subdomains, providing a high-quality domain partitioning foundation for domain generalization and addressing the problem of time-series distribution changes during single-unit operation. Furthermore, it constructs a domain adversarial neural network framework and trains the framework using Q time-series subdomains. This approach enables the feature extractor to learn domain-invariant feature representations that can obfuscate the domain classifier, overcoming the domain distribution shift problem caused by differences in equipment parameters and operating strategies among different thermal power units. By quantifying the similarity between different time-series subdomains through the maximum mean difference between feature distributions, a correlation weight matrix is ​​constructed, allowing the model to focus on different time-series subdomains with similar distributions. Furthermore, a smoothing coefficient that decreases with the training process is set, emphasizing the learning of commonalities between domains in the early stage of training and emphasizing the extraction of intra-domain characteristics in the later stage, thereby adjusting the contribution of each domain to the model training, ensuring the balance and stability of the learning process, and improving the prediction accuracy of the model on unknown target units.

[0034] Example 2, referring to Figures 1-4, is the second embodiment of the present invention, which provides a method for short-term load forecasting of thermal power units based on Gaussian weighted domain generalization network.

[0035] In this embodiment of the application, obtaining the preprocessed historical operating data of the target thermal power unit in step S100 includes the following steps A1-A3: A1: Collecting historical operating data related to load forecasting from the thermal power unit's operating database; In this embodiment of the application, historical operating data is collected from the distributed control system (DCS) of the thermal power unit. The collected historical operating data includes, but is not limited to: generator active power, boiler efficiency, main steam temperature, reheat steam temperature, flue gas oxygen content, nitrogen oxide concentration at the inlet of the selective catalytic reduction system, real-time coal flow of each coal mill, and other operating parameters, as well as corresponding load data; The time span of the collection is usually 1-2 years of historical data during the normal operation of the unit, and the sampling frequency is once every 5 minutes to ensure that the data has sufficient time length and representativeness; A2: Removing outliers from the historical operating data and performing normalization. Normalized operating data is obtained; in this embodiment, the isnan function of MATLAB is used to identify and remove null values ​​in historical operating data; then, the mean and standard deviation of each operating parameter sequence are calculated using the 3σ criterion, and data points exceeding the mean ± 3 times the standard deviation are regarded as outliers and removed; after removing outliers in historical operating data, the minimum-maximum normalization formula is used for normalization processing. For each operating parameter in historical operating data, the minimum value of the operating parameter in the entire dataset is subtracted, and then divided by the range of the operating parameter, thereby mapping the parameter to the interval [0,1] to obtain normalized operating data; A3: The normalized operating data is preprocessed, the correlation coefficient between each operating parameter and the load data in the normalized operating data is calculated, and the normalized operating data is filtered according to the correlation coefficient to obtain the first operating data.

[0036] In this embodiment, the Pearson correlation coefficient is used to calculate the correlation coefficient between each operating parameter in the normalized operating data and the corresponding load data. The formula for calculating the correlation coefficient between each operating parameter in the normalized operating data and the corresponding load data is as follows: ;in, The correlation coefficient is... Let i be the i-th sample value of the running parameter in the normalized running data. For the i-th sample value of the load data corresponding to the operating parameters in the normalized operating data, This is the average value of the operating parameters in the normalized operating data. Let n be the average load data corresponding to the operating parameters in the normalized operating data, and i be the sample index. The correlation coefficient between each operating parameter and its corresponding load data in the normalized operating data is calculated, with a threshold of 0.5. The absolute values ​​of the calculated correlation coefficients are compared with the threshold. Only operating parameters and their corresponding load data with an absolute correlation coefficient greater than the threshold are retained as the first set of operating data. Operating parameters with an absolute correlation coefficient less than or equal to the threshold are considered weakly correlated and are not retained. It should be noted that by calculating the correlation coefficient and selecting highly correlated operating parameters for subsequent calculations while eliminating weakly correlated parameters, the feature dimensions of the operating parameters are reduced. This not only improves training efficiency and shortens training time but also reduces the resource requirements for subsequent calculations. It allows for a greater focus on learning key operating parameters strongly correlated with the load data, contributing to improved final prediction accuracy and generalization ability.

[0037] In one alternative implementation, dimensionality reduction of normalized operational data can also be achieved through principal component analysis. This involves standardizing historical operational data containing multiple operational parameters, calculating the covariance matrix and corresponding eigenvalues ​​and eigenvectors, sorting the eigenvalues ​​from largest to smallest, and selecting the top k eigenvectors as principal components. Finally, the original data is projected onto a new coordinate system composed of these principal components, thus achieving dimensionality reduction. Cross-validation can be used to determine the optimal number of principal components, avoiding information loss or overfitting.

[0038] In another alternative implementation, dimensionality reduction of normalized running data can also be achieved through recursive feature elimination. A base learner is trained using all normalized running parameters, such as linear regression, support vector regression, or random forest. Based on the importance of the output features of the base learner, the features are sorted and the features with the lowest importance are removed, for example, one feature at a time. Then, the model is retrained using the remaining features, and this process is repeated until a preset number of features is reached, thereby achieving dimensionality reduction of the data.

[0039] In this embodiment, the time-domain partitioning operation of the first running data in step S100 includes the following steps B1-B5: B1: The probabilistic graphical model adopts a Gaussian mixture model, and the probability density function is constructed by fitting the probability distribution of each data point in the first running data using the Gaussian mixture model; in this embodiment, the formula for constructing the probability density function is: ;in, For probability density, The first running data for the k-th Gaussian component. The set number of time-series subdomains, each corresponding to a Gaussian component. The number of samples in the first run. The mixing weights for the k-th Gaussian component. Let be the mean of the k-th Gaussian component. Let K be the covariance matrix of the k-th Gaussian component. It should be noted that the K Gaussian distribution components in the probability density function represent dividing the first running data into K temporal subdomains. This allows for the identification and quantification of multiple different temporal subdomains implicit in historical data in an unsupervised manner, providing a precise temporal domain division basis based on data distribution characteristics for subsequent domain adversarial training. B2: Calculate the posterior probability that a data point in the first running data belongs to the k-th Gaussian component based on the probability density function. In this embodiment, the formula for calculating the posterior probability that a data point in the first running data belongs to the k-th Gaussian component is: ;in, Let i be the posterior probability that the j-th data point belongs to the k-th Gaussian component, and i be the sample index. It should be noted that in the formula for calculating the posterior probability, the numerator represents the probability density of the k-th Gaussian component, and the denominator is the overall probability density. Dividing the two yields the posterior probability that the j-th data point belongs to the k-th Gaussian component. This allocation method quantifies the confidence level of each data point belonging to each Gaussian component, i.e., the time-series subdomain, rather than making a rigid, either-or division, thus providing data for subsequent parameter updates. B3: Update the parameters of the probability density function based on the posterior probability of the k-th Gaussian component. In this embodiment, the parameters of the probability density function include the mixture weights, mean, and covariance matrix. The formula for updating the mixture weights of the k-th Gaussian component is: The formula for updating the mean of the k-th Gaussian component is: The formula for updating the covariance matrix of the k-th Gaussian component is: It should be noted that, based on the current posterior probability, the mixture weights, mean, and covariance matrix of the probability density function are updated. The mixture weights are updated to the average of the posterior probabilities of all data points with respect to the k-th Gaussian component, reflecting the proportion of this component in the overall data. Using the posterior probability of the k-th Gaussian component as the weight, the mean is updated to the weighted average of all data points, repositioning the center of this component in the feature space. Using the posterior probability of the k-th Gaussian component as the weight, the covariance matrix is ​​updated to the weighted sample covariance around the updated mean, characterizing the dispersion shape and correlation of the data within this component. By iteratively updating the parameters of the probability density function, the mixture distribution of the real data is gradually approximated, so that each Gaussian component can more accurately represent a statistically consistent time series subdomain, providing a data foundation for time series subdomain partitioning; B4: Continuously calculate the posterior probability of the k-th Gaussian component and update the parameters of the probability density function until the parameter change is less than the parameter threshold, and determine the final parameters of the probability density function; In this embodiment, step B2 of calculating the posterior probability and step B3 of updating the parameters are repeated until the parameters of the probability density function converge; Specifically, the parameter threshold is set to 10. -5 Calculate the change in the parameters of the probability density function between the current iteration and the previous iteration. If the change in the parameters of the probability density function is greater than the parameter threshold, continue to the next iteration. If the change in the parameters of the probability density function is less than or equal to the parameter threshold, stop the iteration and take the parameters of the probability density function after the last update as the final parameters. It should be noted that when judging the magnitude between the change in the parameters of the probability density function and the parameter threshold, it is necessary to ensure that the changes in the mixing weights, mean, and covariance matrix of the parameters of the probability density function are all less than or equal to the parameter threshold. Only then can it be considered that the change in the parameters of the probability density function is less than or equal to the parameter threshold, and the iteration can be stopped. B5: Sequentially set the number of time series subdomains to K, divide the first running data into K time series subdomains, and calculate the Bayesian information criterion coefficient corresponding to the final parameters of the probability density function for each K value. Take the K value with the smallest Bayesian information criterion coefficient as the number Q of time series subdomains, and divide the first running data into Q time series subdomains in the time domain.

[0040] In this embodiment, the number of time series subdomains is sequentially set to K, K=2, 3, ..., 10; the first running data is divided into K time series subdomains, and steps B1 to B4 are executed respectively. After determining the final parameters, the log-likelihood value of the probability density function under the final parameters is determined. Combining the sample size of the first running data and the total number of parameters of all probability density functions, the Bayesian information criterion coefficient is calculated; the formula for calculating the Bayesian information criterion coefficient is: ;in, These are the coefficients of the Bayesian information criterion. The log-likelihood value is... The total number of parameters for all probability density functions. Let Q be the number of samples in the first running data. Calculate the Bayesian information criterion coefficients corresponding to the number K of each time series subdomain. Select the K with the smallest Bayesian information criterion coefficient as the final number Q of time series subdomains. Divide the first running data into Q time series subdomains. In an optional implementation, the number of time series subdomains to be divided into the first running data can also be determined by evaluating the clustering quality of silhouette coefficient pairs. Set multiple K values ​​sequentially for the first running data, perform K-means clustering algorithm on each K value and calculate the silhouette coefficient of each sample, then calculate the average silhouette coefficient of all samples, and select the K value that maximizes the average silhouette coefficient as the optimal number of time series subdomains.

[0041] In another alternative implementation, the number of time-series subdomains to be divided into the first running data can also be determined by gap statistics. Multiple K values ​​are set sequentially, and the clustering error under different K values ​​is calculated for the first running data. A set number of reference datasets are generated, and the clustering error under different K values ​​is calculated for each reference dataset. The gap statistics are calculated, and the K value that maximizes the gap statistics is selected as the optimal number of time-series subdomains.

[0042] By using the Bayesian information criterion to automatically balance model fit and complexity, the number of time-series subdomains that best represent the inherent distribution structure of the data can be objectively and quantifiably identified. This avoids overfitting or underfitting problems that may result from subjectively setting the number of time-series subdomains. The number of time-series subdomains for each unit's 14-day operating data is shown in Table 2: Table 2 Number of Time-Series Subdomains for Each Unit's 14-Day Operating Data

[0043] To demonstrate that there is a distribution shift in each temporal subdomain after temporal segmentation, the MMD heatmap measuring the distribution shift of each subdomain is shown in Figure 3. It can be seen that after temporal subdomain segmentation, there is a certain degree of temporal distribution shift in each subdomain.

[0044] In this embodiment, the construction of the domain adversarial neural network framework in step S200 includes the following steps C1-C4: C1: Constructing a domain adversarial neural network framework containing a feature extractor, a predictor, and a domain classifier; In this embodiment, a domain adversarial neural network framework containing a feature extractor, a predictor, and a domain classifier is constructed, and the network architecture diagram of the domain adversarial neural network framework is shown in Figure 4; wherein, the feature extractor adopts a three-layer fully connected network, the input dimension is the feature dimension of the first running data, and the output hidden layer feature dimension is 128; the predictor is a single-layer fully connected network with an output dimension of 1, used for regression prediction; the domain classifier is a two-layer fully connected network with an output dimension of the temporal subdomain. The number Q is used for the domain classification task, including a feature extractor, a predictor, and a domain classifier connected through a gradient inversion layer; C2: Extract the hidden layer feature representations output by the feature extractor in the domain adversarial neural network framework for each temporal subdomain; In this embodiment, the first running data is divided into Q temporal subdomains according to the number determined in step S200, and the Q temporal subdomains are respectively input into the feature extractor in the domain adversarial neural network framework to extract the hidden layer feature representations corresponding to each temporal subdomain; C3: Calculate the correlation weights between two temporal subdomains based on the hidden layer feature representations; In this embodiment, the formula for calculating the correlation weights between two temporal subdomains based on the hidden layer feature representations is: ;in, The correlation weights between the k-th and j-th time series subdomains are given. It is the function of maximum mean difference. and This represents the hidden layer feature representations obtained after the feature extractor passes through the k-th and j-th time-series subdomains. It should be noted that in the formula for calculating the correlation weights between two time-series subdomains, the numerator is the reciprocal of the maximum mean difference between the k-th and j-th time-series subdomains, reflecting the similarity of feature distributions between the two subdomains. The smaller the maximum mean difference and the larger the reciprocal, the higher the similarity. The denominator is the sum of the reciprocals of the maximum mean differences between the k-th and all other m+1 time-series subdomains, ensuring that the sum of all correlation weights is 1. C4: Calculate the dynamic smoothing coefficient based on the number of time-series subdomains, and construct a soft label vector based on the correlation weights and the dynamic smoothing coefficient.

[0045] In this embodiment, the dynamic smoothing coefficient decreases with the number of training steps. The formula for calculating the dynamic smoothing coefficient based on the number of training steps and the number of temporal subdomains is as follows: ;in, For dynamic smoothing coefficients, The number of time-series subdomains. To preset the total number of training steps, Let be the current training iteration number; the formula for constructing the soft label vector based on the relevant weights and dynamic smoothing coefficient is: ;in, To construct a soft tag vector based on the k-th temporal subdomain, assign a value to the position (i.e., the k-th position) of the soft tag vector corresponding to its own domain. As the positive class confidence level, the rest... Each position is assigned a value. ⋅ As a weighted confidence level, it should be noted that the formula for constructing the soft label vector consists of a dynamic smoothing coefficient and relevant weights. By replacing the traditional hard label with a dynamic soft label vector, the gradient conflict and pattern collapse problems in domain adversarial training are alleviated, thereby making more balanced use of multi-source domain information and improving the stability of the final load prediction.

[0046] In an alternative implementation, the soft label vector can also be constructed by adversarial sample perturbation. For each training sample, the gradient of the loss function corresponding to the hard label of the training sample is first calculated, and adversarial perturbation is generated based on the gradient of the loss function to generate perturbed samples. Then, the predicted probability distribution is obtained based on the perturbed samples, and the hard label of the original sample and the predicted distribution of the adversarial sample are weighted and fused to obtain the soft label vector.

[0047] In another alternative implementation, the soft label vector can also be constructed using a teacher-student soft label model. A teacher model is trained, and for training samples, the teacher model generates a soft prediction distribution. The student model fits the true labels during training, and also needs to fit the soft labels of the teacher model. In the domain adversarial training scenario, the teacher prediction of the domain classifier can be used as the soft label. For the sample of the k-th temporal subdomain, the domain classification output of the teacher model is used as the soft label target for the current training, and the soft label vector is constructed through the soft label target.

[0048] In this embodiment, determining the parameters of the domain adversarial neural network framework in step S300 includes the following steps D1-D4: D1: Calculate the prediction loss function based on the output of the predictor in the domain adversarial neural network framework; In this embodiment, the mean squared error is used as the prediction loss function, and the formula for calculating the prediction loss function based on the output of the predictor in the domain adversarial neural network framework is as follows: ;in, For the prediction loss function, For the i-th sample of the running parameters in the first running data, To input the i-th sample of the running parameters in the first running data into the output of the predictor in the domain adversarial neural network framework, where N is the total number of samples in the first running data; it should be noted that the standard loss function of regression task, mean squared error, is used as the prediction loss function. The mathematical property of continuous differentiability of mean squared error facilitates the updating of parameters by the gradient optimization algorithm; at the same time, the squared term imposes a higher penalty on larger prediction errors, thereby prioritizing the correction of significantly deviated prediction results and providing a stable and reliable prediction accuracy supervision signal for the joint loss function; D2: Calculate the domain classification loss function based on the soft label vector and the output of the domain classifier in the domain adversarial neural network framework; in this embodiment, the formula for calculating the domain classification loss function is: ;in, For the domain classification loss function, The number of time-series subdomains. This represents the soft domain label of the j-th sample in the i-th time-series subdomain. Let k be the total number of samples in the k-th time-series subdomain, where k is a fixed index specifically referring to the subdomain currently being computed. The output of the feature extractor for the j-th sample in the i-th subdomain. This represents the predicted probability distribution of features by the domain classifier. The core of this loss function lies in comparing the distribution differences between the current sample's domain k and all other source domains, rather than calculating the loss of each domain in isolation. Cross-entropy loss measures the difference between the domain classifier's predicted probability and the true soft label. By averaging across all source domains and their samples, the feature extractor is guided to generate domain-invariant features, ultimately achieving the goal of cross-domain feature alignment.

[0049] D3: Calculate the joint loss function based on the prediction loss function and the domain classification loss function; in this embodiment, the formula for calculating the joint loss function is: in, For the joint loss function, For the prediction loss function, For the domain classification loss function, These are the parameters of the feature extractor. For the parameters of the predictor, For the parameters of the domain classifier, The loss tradeoff coefficient is used to adjust the relative weights of the prediction loss function and the domain classification loss function in the joint loss function. The value of the loss tradeoff coefficient needs to be adjusted experimentally to balance prediction performance and domain generalization ability. By combining the prediction loss function and the domain classification loss function as parameters of the feature extractor, predictor, and domain classifier, a clear and mutually restraining optimization objective is set. The predictor's objective is to minimize the prediction loss to improve load prediction accuracy. The domain classifier's objective is to minimize the domain classification loss to accurately identify the data source. The feature extractor needs to extract features that are effective for load prediction to minimize the prediction loss, and it also needs to generate hidden feature representations for the obfuscated domain classifier to cooperate in minimizing the domain classification loss. In an optional implementation, the joint loss function can also be calculated by regularizing the loss based on domain-invariant feature constraints. A regularization term that measures the cross-domain difference of feature distribution, such as maximum mean difference or correlation alignment, is introduced into the loss function. The regularization term is multiplied by a regularization coefficient and then added to the domain classification loss to obtain the joint loss function.

[0050] In another alternative implementation, the joint loss function can also be calculated through task importance awareness. Task importance metrics are evaluated using the performance improvement rate, loss descent rate, or gradient norm ratio on the validation set. Dynamic weights are calculated based on the importance metrics, and the joint loss function is obtained by weighted summing of the predictor's loss and the domain classifier's loss.

[0051] D4: Update the parameters of the feature extractor, predictor, and domain classifier based on the joint loss function.

[0052] In this embodiment of the application, the optimization objective expression for the parameters of the feature extractor and the predictor is: ;in, The optimization objective for the parameters of the feature extractor is... The optimization objective for the predictor's parameters; For and Let be the parameters that minimize the joint loss function; the optimization objective expression for the parameters of the domain classifier is: ;in, The optimization objective is to optimize the parameters of the domain classifier; For the sake of peace The parameters that determine when the joint loss function reaches its maximum value are defined as variables; the gradient is calculated using the backpropagation algorithm based on the joint loss function, and the parameters of the feature extractor, predictor, and domain classifier are updated using the Adam optimizer; a convergence threshold of 10 is set for one parameter. -5If the change in the joint loss function over five consecutive training epochs is less than the parameter convergence threshold, the training is considered to have converged. At this point, the parameters of the feature extractor, predictor, and domain classifier are the final parameters. It should be noted that this adversarial training is achieved through a gradient reversal layer (GRL). Specifically, during backpropagation, the domain classification loss gradient passed to the feature extractor is multiplied by a negative coefficient −λ, thereby achieving gradient reversal. This causes the parameter update direction of the feature extractor to be opposite to the target of the domain classifier, forcing the feature extractor to generate hidden feature representations that the domain classifier cannot distinguish.

[0053] The feature extractor processes input data from different temporal subdomains to generate high-level feature representations and reduces inter-domain bias by optimizing the parameters of the feature extractor. The predictor makes predictions based on the features extracted by the feature extractor and is trained under the supervision of the temporal subdomains. Accurate predictions are achieved by optimizing the parameters of the predictor. The domain classifier is used to determine the temporal subdomain to which the features extracted by the feature extractor belong. By updating the parameters of the domain classifier, the feature extractor is driven to generate hidden feature representations.

[0054] The parameters learned after training convergence will be the saddle points of the joint loss function in the minimax optimization.

[0055] In this embodiment of the application, the output of the short-term load forecast result of the target unit in step S500 includes: setting Unit 3 of a certain power plant as the target unit, and taking the operating parameters of the target unit at the current moment, such as the total coal quantity, plant power consumption rate, power generation coal consumption, heat consumption, main steam temperature, real-time coal quantity of the coal mill, weather temperature, wind speed, precipitation and reheat steam temperature, as inputs into the trained domain adversarial neural network framework. The feature extractor of the domain adversarial neural network framework extracts the features of the input data, and the predictor performs load forecast based on the extracted features, and outputs the short-term load forecast value of the target unit for the next hour.

[0056] Example 3, referring to Figures 1-4, is the third embodiment of the present invention. This embodiment provides a short-term load forecasting system for thermal power units based on a Gaussian weighted domain generalization network, including: a data acquisition module: acquiring historical operating data of thermal power units and preprocessing it to obtain first operating data; a data partitioning module: fitting the probability distribution of the first operating data using a probabilistic graphical model to obtain a probability density function, determining the number Q of time-series subdomains based on the probability density function, and dividing the first operating data into Q time-series subdomains; a framework construction module: constructing a domain adversarial neural network framework and training the adversarial neural network framework through Q time-series subdomains, determining the feature extractor parameters, predictor parameters, and domain classifier parameters in the domain adversarial neural network framework; and a data output module: inputting the real-time operating data of the target unit into the trained domain adversarial neural network framework, and outputting the short-term load forecasting result of the target unit.

[0057] Example 4, the fourth embodiment of the present invention, differs from the previous three embodiments in that: if the function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0058] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0059] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0060] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0061] Example 5, referring to Figures 5-7, is the fifth embodiment of the present invention, which provides a short-term load forecasting method for thermal power units based on a Gaussian weighted domain generalization network. To verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0062] Figure 5 shows the change in loss before and after introducing soft label vectors into the loss function of the domain classifier. As the number of training rounds increases, the loss value of the short-term load forecasting method for thermal power units proposed in this application shows a more stable trend, with a significantly reduced fluctuation amplitude compared to the short-term load forecasting method using normal domain labels. This phenomenon indicates that the weighted smoothing label strategy adopted in the short-term load forecasting method for thermal power units proposed in this application can effectively alleviate the oscillation problem commonly encountered in adversarial training, thereby making the model parameter updates more stable and reliable.

[0063] Figure 6 shows a comparison of the prediction results using the proposed method with those of other models. The short-term load prediction method for thermal power units proposed in this application shows the highest degree of agreement between the prediction curve and the actual load curve, effectively tracking actual load fluctuations, especially during rapid load changes at peak and trough stages. Models like domain adversarial neural networks exhibit systemic fluctuations at certain cycle points, particularly showing overfitting to source domain units during stable operation. The No DG (no-domain generalization) baseline shows significant deviations from actual values ​​across the entire prediction range, even exhibiting directional errors at load inflection points. Its MAPE (mean absolute percentage error) ranges from 7.52% to 10.21%, MAE (mean absolute error) ranges from 26.27 to 36.45, and the minimum R² value (coefficient of determination) is only 0.573. This reflects the fundamental shortcomings of traditional methods when facing variations in load distribution. Table 2 shows a comparison of the prediction accuracy of the proposed method with other models, further validating the superiority of the proposed short-term load forecasting method for thermal power units: its MAPE consistently ranges from 1.74% to 2.09%, MAE consistently ranges from 6.29 to 8.84, and R² consistently remains above 0.97. Compared with various benchmark models, the proposed method for short-term load forecasting of thermal power units achieves an average MAPE reduction of 18.9% compared to Gaussian domain generalization networks using normal domain labels, confirming the effectiveness of the weighted smoothing label strategy. Compared with domain adversarial neural networks, generative adversarial networks, and multi-domain learning generative adversarial networks, the accuracy is improved by 29.1% to 43.1%, 44.7% to 50.3%, and 30.7% to 45.3%, respectively. This fully demonstrates that its dual mechanism of Gaussian mixture model temporal distribution segmentation and weighted adversarial training can effectively solve the problems of inter-unit variation and temporal distribution shift.

[0064] Table 2 Comparison of prediction accuracy metrics with other models

[0065] As shown in Figure 7, the t-SNE dimensionality reduction algorithm is used to conduct an in-depth analysis of the feature distribution alignment effect of the proposed short-term load forecasting method for thermal power units. The processed feature distribution of the proposed method exhibits an ideal continuous manifold structure, with samples from different domains fully fused, domain boundaries largely eliminated, and a highly consistent feature distribution formed. This feature alignment effect confirms that the proposed method for short-term load forecasting of thermal power units, through a dual mechanism of temporal distribution segmentation and weighted adversarial training, extracts more accurate domain-invariant features and eliminates domain-specific features related to the unit and time period.

[0066] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for short-term load forecasting of thermal power units based on Gaussian weighted domain generalization networks, characterized in that, The process includes: performing a time-domain partitioning operation on the first operating data to obtain several time-series sub-domains, wherein the first operating data is the preprocessed historical operating data of the target thermal power unit; constructing a domain adversarial neural network framework, wherein the domain adversarial neural network framework is used to obtain soft label vectors of several time-series sub-domains; determining the parameters of the domain adversarial neural network framework, wherein the parameters of the domain adversarial neural network framework are determined according to a joint loss function, wherein the joint loss function is calculated based on the soft label vectors and the output of the domain adversarial neural network framework; and outputting the short-term load forecast result of the target unit, wherein the short-term load forecast result of the target unit is generated by inputting the real-time operating data of the target unit into the trained domain adversarial neural network framework.

2. The method for short-term load forecasting of thermal power units based on Gaussian weighted domain generalization network as described in claim 1, characterized in that, The steps for performing time-domain partitioning on the first running data include: using a Gaussian mixture model for the probabilistic graphical model, fitting the probability distribution of each data point in the first running data using the Gaussian mixture model to construct a probability density function; calculating the posterior probability of a data point in the first running data belonging to the k-th Gaussian component based on the probability density function; updating the parameters of the probability density function based on the posterior probability of the k-th Gaussian component; continuously calculating the posterior probability of the k-th Gaussian component and updating the parameters of the probability density function until the parameter change is less than the parameter threshold, thus determining the final parameters of the probability density function; sequentially setting the number of time-series subdomains to K, dividing the first running data into K time-series subdomains, and calculating the Bayesian information criterion coefficient corresponding to the final parameters of the probability density function for each K value, taking the K value with the smallest Bayesian information criterion coefficient as the number Q of time-series subdomains; and dividing the first running data into Q time-series subdomains.

3. The method for short-term load forecasting of thermal power units based on Gaussian weighted domain generalization network as described in claim 2, characterized in that, The steps for constructing a domain adversarial neural network framework include: constructing a domain adversarial neural network framework containing a feature extractor, a predictor, and a domain classifier; extracting the hidden layer feature representations of each temporal subdomain from the output of the feature extractor in the domain adversarial neural network framework; calculating the correlation weights between two temporal subdomains based on the hidden layer feature representations; calculating the dynamic smoothing coefficient based on the number of temporal subdomains; and constructing soft label vectors based on the correlation weights and the dynamic smoothing coefficient.

4. The method for short-term load forecasting of thermal power units based on Gaussian weighted domain generalization network as described in claim 3, characterized in that, The steps for determining the parameters of a domain adversarial neural network framework include: calculating the prediction loss function based on the output of the predictor in the domain adversarial neural network framework; calculating the domain classification loss function based on the soft label vector and the output of the domain classifier in the domain adversarial neural network framework; calculating the joint loss function based on the prediction loss function and the domain classification loss function; and updating the parameters of the feature extractor, predictor, and domain classifier in the domain adversarial neural network framework based on the joint loss function.

5. The method for short-term load forecasting of thermal power units based on Gaussian weighted domain generalization network as described in claim 4, characterized in that, The steps to obtain the preprocessed historical operating data of the target thermal power unit include: collecting historical operating data related to load forecasting from the thermal power unit's operating database; removing outliers from the historical operating data and normalizing it to obtain normalized operating data; preprocessing the normalized operating data, calculating the correlation coefficient between each operating data and load data in the normalized operating data, and filtering the normalized operating data according to the correlation coefficient to obtain the first operating data.

6. The method for short-term load forecasting of thermal power units based on Gaussian weighted domain generalization network as described in claim 2, characterized in that, The formula for constructing the probability density function during the time-domain partitioning operation of the first running data is as follows: ;in, For probability density, This is the first running data for the k-th time-series subdomain. The set number of time-series subdomains, The number of samples in the first run. For mixed weights, Let be the mean of the k-th time series subdomain. Let be the k-th covariance matrix; the formula for calculating the posterior probability of a data point in the first running data belonging to the k-th Gaussian component based on the probability density function is: ;in, Let be the posterior probability that the j-th data point belongs to the k-th Gaussian component, and i be the sample index.

7. The method for short-term load forecasting of thermal power units based on Gaussian weighted domain generalization network as described in claim 3, characterized in that, The formula for calculating the correlation weight between two temporal subdomains based on the hidden layer feature representation is as follows: ;in, The correlation weights between the k-th and j-th time series subdomains are given. It is the function of maximum mean difference. and The hidden layer feature representations obtained after the k-th and j-th temporal subdomains are processed by the feature extractor. The number of time-series subdomains: The formula for calculating the dynamic smoothing coefficient based on the number of time-series subdomains is: ;in, For dynamic smoothing coefficients, The number of time-series subdomains. To preset the total number of training steps, Let be the current training iteration number; the formula for constructing the soft label vector based on the relevant weights and dynamic smoothing coefficient is: ;in, To construct a soft tag vector based on the k-th temporal subdomain, assign a value to the position (i.e., the k-th position) of the soft tag vector corresponding to its own domain. As the positive class confidence level, the rest... Each position is assigned a value. ⋅ , as the weighted confidence level.

8. A short-term load forecasting system for thermal power units based on a Gaussian weighted domain generalization network, employing the short-term load forecasting method for thermal power units based on a Gaussian weighted domain generalization network as described in any one of claims 1 to 7, characterized in that, include: Data Acquisition Module: Collects historical operating data of thermal power units and preprocesses it to obtain the first operating data; Data Partitioning Module: Fits the probability distribution of the first operating data using a probabilistic graphical model to obtain the probability density function, determines the number Q of time-series subdomains based on the probability density function, and divides the first operating data into Q time-series subdomains; Framework Construction Module: Constructs a domain adversarial neural network framework and trains the adversarial neural network framework through Q time-series subdomains to determine the parameters of the feature extractor, predictor, and domain classifier in the domain adversarial neural network framework; Data Output Module: Inputs the real-time operating data of the target unit into the trained domain adversarial neural network framework and outputs the short-term load forecast results of the target unit.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method for short-term load forecasting of thermal power units based on Gaussian weighted domain generalization network as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for short-term load forecasting of thermal power units based on Gaussian weighted domain generalization network as described in any one of claims 1 to 7.

Images