Electricity demand forecasting methods, devices, and media adapted to the new electricity price reform

Abstract

This application discloses a method, device, and medium for forecasting electricity demand to adapt to the new electricity price reform. The method includes: determining information on changes in electricity price factors and economic factors in the target analysis area; acquiring historical electricity consumption data and factors influencing electricity demand for different electricity users in the target analysis area; generating electricity consumption curves for each electricity user and clustering them; analyzing the degree of influence of each electricity demand influencing factor based on the historical electricity consumption data of each electricity user in the electricity user class, and selecting key electricity demand influencing factors; updating the electricity users in each electricity user class based on the key electricity demand influencing factors; obtaining an electricity user class including electricity price factors and economic factors as the target electricity user class; training an electricity demand model based on the target electricity user class, and forecasting the electricity demand of each electricity user in the future forecast period.

Description

Technical Field

[0001] This application relates to the field of electricity demand forecasting technology, and in particular to an electricity demand forecasting method, device and medium adapted to the new electricity price reform. Background Technology

[0002] With socio-economic development and energy structure adjustments, the power industry is facing unprecedented changes. Particularly in terms of electricity price reform, governments worldwide have introduced new electricity pricing policies, such as tiered pricing and peak-valley pricing, to promote energy conservation, emission reduction, and rational resource allocation. These new pricing policies not only affect the operating costs and profits of power companies but also directly impact users' electricity consumption behavior and demand patterns. Therefore, accurately predicting electricity demand under the new electricity price reform framework has become a pressing issue for power companies and related research institutions.

[0003] Traditional electricity demand forecasting methods primarily rely on historical electricity data, using statistical methods or machine learning algorithms to predict future electricity demand. However, these methods often overlook the impact of factors such as electricity price reforms and economic policies on user electricity consumption behavior, leading to significant biases in the forecast results. For example, after the implementation of new electricity price policies, some electricity consumers may reduce their consumption due to price increases or increase their consumption under preferential electricity price policies, and traditional forecasting methods struggle to capture these changing trends.

[0004] Furthermore, different types of electricity consumers (such as industrial users, commercial users, and residential users) respond differently to changes in electricity prices and economic policies. Therefore, using a uniform forecasting model may not accurately reflect the actual changes in electricity demand across various consumer groups. This further increases the difficulty of electricity demand forecasting. Summary of the Invention

[0005] In view of this, embodiments of this application provide a method, apparatus and medium for predicting electricity demand in response to the new electricity price reform.

[0006] According to one aspect of this application, a method for forecasting electricity demand to adapt to the new electricity price reform is provided, the method comprising:

[0007] Based on information on the new electricity price reform situation and the impact of economic policies in the target analysis region during the future forecast period, information on changes in electricity price factors and economic factors in the target analysis region during the future forecast period is determined.

[0008] The historical electricity consumption data of different electricity users in the target analysis area within a set time period and the factors affecting electricity demand are obtained. The factors affecting electricity demand include at least electricity price factors, economic factors, climate factors, and holiday factors.

[0009] Based on the historical electricity consumption data, electricity consumption curves are generated for each electricity consumer. Based on the electricity consumption curves, each electricity consumer is clustered to obtain multiple electricity consumer classes.

[0010] For each electricity user category, the influence of each electricity demand influencing factor is analyzed based on the historical electricity consumption data of each electricity user in the category, and the key electricity demand influencing factors of each electricity user are selected based on the influence of each electricity demand influencing factor according to the preset influence degree screening conditions.

[0011] Based on the key electricity demand influencing factors of each electricity user in each electricity user category, the electricity users in each electricity user category are updated to obtain multiple updated electricity user categories.

[0012] The target electricity consumer class is identified by identifying at least one of the key factors influencing electricity demand, including electricity price factors and economic factors.

[0013] The electricity demand model is trained based on the historical electricity consumption data and factors influencing electricity demand of each electricity consumer in the target electricity consumer category. Based on the electricity price change information and the economic factor change information, the electricity demand of each electricity consumer in the future forecast period is predicted.

[0014] According to another aspect of this application, a power demand forecasting device adapted to the new electricity price reform is provided, the device comprising:

[0015] The change information determination module is used to determine the change information of electricity price factors and economic factors in the target analysis area during the future forecast period, based on the information on the new electricity price reform situation and the impact information of economic policies in the target analysis area during the future forecast period.

[0016] The historical data acquisition module is used to acquire historical electricity consumption data of different electricity users in the target analysis area within a set time period, as well as factors affecting electricity demand. The factors affecting electricity demand include at least electricity price factors, economic factors, climate factors, and holiday factors.

[0017] The clustering module is used to generate electricity consumption curves for each electricity consumer based on the historical electricity consumption data, and to cluster each electricity consumer based on the electricity consumption curves to obtain multiple electricity consumer classes.

[0018] The factor analysis module is used to analyze the degree of influence of each electricity demand influencing factor for each electricity user category based on the historical electricity consumption data of each electricity user in the category, and to filter out the key electricity demand influencing factors for each electricity user based on the degree of influence of each electricity demand influencing factor according to the preset influence degree screening conditions.

[0019] The update module is used to update the electricity users in each electricity user class based on the key electricity demand influencing factors of each electricity user in each electricity user class, so as to obtain multiple updated electricity user class classes.

[0020] The model training module is used to obtain at least one of the key electricity demand influencing factors, including electricity price factors and economic factors, as the target electricity demand subject class; to train the electricity demand model based on the historical electricity data and electricity demand influencing factors of each electricity subject in the target electricity demand subject class; and to predict the electricity demand of each electricity subject in the future forecast period based on the electricity price factor change information and the economic factor change information.

[0021] According to another aspect of this application, a storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described method for predicting electricity demand in response to the new electricity price reform.

[0022] According to another aspect of this application, a computer device is provided, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the program to implement the above-mentioned electricity demand forecasting method adapted to the new electricity price reform.

[0023] By means of the above technical solution, the present application provides a method, device and medium for predicting electricity demand in response to the new electricity price reform. Based on information about the new electricity price reform and the impact of economic policies on the target analysis region during the future prediction period, it determines the changes in electricity price factors and economic factors in the target analysis region during the future prediction period; it acquires historical electricity consumption data and electricity demand influencing factors for different electricity users in the target analysis region within a set time period, wherein the electricity demand influencing factors include at least electricity price factors, economic factors, climate factors, and holiday factors; it generates electricity consumption curves for each electricity user based on the historical electricity consumption data, and clusters each electricity user based on the electricity consumption curves to obtain multiple electricity user class groups; for each electricity user class group, it determines the electricity demand influencing factors based on the electricity consumption data of each electricity user in the class group. The historical electricity consumption data of the main body is used to analyze the degree of influence of various electricity demand factors. Based on preset influence degree screening conditions, key electricity demand influencing factors for each electricity consumption subject are selected. According to the key electricity demand influencing factors for each electricity consumption subject category, the electricity consumption subjects in each category are updated to obtain multiple updated electricity consumption subject categories. The target electricity consumption subject category is selected based on at least one of the key electricity demand influencing factors: electricity price and economic factors. An electricity demand model is trained based on the historical electricity consumption data and electricity demand influencing factors of each electricity consumption subject in the target category. The electricity demand of each electricity consumption subject in the future prediction period is predicted based on the changes in the electricity price and economic factors. This embodiment of the application, through detailed analysis of the electricity demand influencing factors of different electricity consumption subjects, especially electricity price and economic factors, and cluster analysis based on these factors, can more accurately predict future electricity demand and reduce prediction errors. This method can adapt to the new electricity price reform situation and economic policy changes, and maintains the timeliness and accuracy of the prediction model by continuously updating the electricity consumption subject categories and key electricity demand influencing factors. This will further help power system operators, energy suppliers and policymakers to better plan and allocate power resources, improve energy efficiency, reduce waste, better balance power supply and demand, reduce power shortages or surpluses, and promote the sustainable development of the power industry.

[0024] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0025] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0026] Figure 1 A flowchart illustrating a method for forecasting electricity demand in accordance with the new electricity price reform provided in an embodiment of this application is shown.

[0027] Figure 2 A flowchart illustrating another electricity demand forecasting method adapted to the new electricity price reform provided in this application embodiment is shown.

[0028] Figure 3 This paper presents a schematic diagram of the structure of a power demand forecasting device adapted to the new electricity price reform, provided in an embodiment of this application. Detailed Implementation

[0029] The present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.

[0030] This embodiment provides a method for forecasting electricity demand that adapts to the new electricity price reform, such as... Figure 1 As shown, the method includes:

[0031] Step 101: Based on the information on the new electricity price reform situation and the impact of economic policies in the target analysis region during the future forecast period, determine the information on changes in electricity price factors and economic factors in the target analysis region during the future forecast period.

[0032] Step 102: Obtain historical electricity consumption data and electricity demand influencing factors for different electricity users in the target analysis area within a set time period. The electricity demand influencing factors include at least electricity price factors, economic factors, climate factors, and holiday factors.

[0033] Step 103: Generate electricity consumption curves for each electricity user based on the historical electricity consumption data, and cluster each electricity user based on the electricity consumption curves to obtain multiple electricity user class groups.

[0034] Step 104: For each electricity user category, analyze the degree of influence of each electricity demand influencing factor based on the historical electricity consumption data of each electricity user in the category, and select the key electricity demand influencing factors of each electricity user based on the degree of influence of each electricity demand influencing factor according to the preset influence degree screening conditions.

[0035] Step 105: Update the electricity users in each electricity user class according to the key electricity demand influencing factors of each electricity user class to obtain multiple updated electricity user class categories.

[0036] Step 106: Obtain at least one of the key electricity demand influencing factors, including electricity price factors and economic factors, as the target electricity consumer class.

[0037] Step 107: Train the electricity demand model based on the historical electricity consumption data and electricity demand influencing factors of each electricity consumption entity in the target electricity consumption entity category, and predict the electricity demand of each electricity consumption entity in the future forecast period based on the electricity price factor change information and the economic factor change information.

[0038] In this embodiment, information on potential new electricity price reforms (such as changes in time-of-use pricing and tiered pricing) and the impact of economic policies (such as economic growth rates and industrial restructuring) that the target region may experience during a future forecast period is collected and analyzed. Historical electricity consumption data for different electricity-consuming entities (such as residents, industrial users, and commercial users) within the target region is collected over a set time period (such as the past few years), along with various factors influencing their electricity demand, including electricity prices, the economy, climate (such as temperature and humidity), and holidays. This data forms the basis for subsequent analysis and modeling. By generating electricity consumption curves for each electricity-consuming entity, the electricity consumption trends of different entities can be visually observed. Based on these curves, cluster analysis is performed on the electricity-consuming entities, grouping those with similar electricity consumption trends into one category to facilitate more accurate analysis of the factors influencing the electricity demand of each category. For each category of electricity-consuming entities, the degree of influence is analyzed based on its historical electricity consumption data and various factors influencing electricity demand. Specifically, statistical analysis and machine learning techniques can be used to determine which factors have a significant impact on electricity demand. Then, based on preset impact criteria (such as an impact coefficient greater than a certain threshold), key electricity demand influencing factors for each electricity consumer are selected. Based on these key electricity demand influencing factors, the electricity consumer class is updated. This step aims to further refine the electricity consumer class to more accurately reflect the electricity demand characteristics of different electricity consumers. From the updated electricity consumer class, those classes whose key electricity demand influencing factors include at least one of electricity price factors and economic factors are selected as target electricity consumer classes. These electricity consumer classes are more likely to be affected by new electricity price reforms and changes in economic policies, and therefore are the focus of prediction. The electricity demand model is trained using historical electricity consumption data and electricity demand influencing factors for each electricity consumer in the target electricity consumer class. This model should be able to capture the impact of changes in electricity prices and economic factors on electricity demand; the electricity demand model can be a time series model. After training, based on the collected information on changes in electricity price factors and economic factors, electricity demand for the future forecast period is predicted.

[0039] By applying the technical solution of this embodiment, and through detailed analysis of the factors influencing the electricity demand of different electricity consumers, particularly electricity prices and economic factors, and through cluster analysis based on these factors, future electricity demand can be predicted more accurately, reducing prediction errors. This method can adapt to changes in new electricity price reforms and economic policies, maintaining the timeliness and accuracy of the prediction model by continuously updating the categories of electricity consumers and key factors influencing electricity demand. Furthermore, it helps power system operators, energy suppliers, and policymakers to better plan and allocate electricity resources, improve energy efficiency, reduce waste, better balance electricity supply and demand, reduce electricity shortages or surpluses, and promote the sustainable development of the power industry.

[0040] Optionally, in this embodiment of the application, step 105 includes:

[0041] Step 105-1: For each electricity user category, based on the key electricity demand influencing factors and their degree of influence for each electricity user in the category, determine the category key electricity demand influencing factors and their degree of influence for the corresponding electricity user category. Based on the key electricity demand influencing factors and their degree of influence for each electricity user and the category key electricity demand influencing factors and their degree of influence for the electricity user category, determine the electricity users whose key electricity demand influencing factors differ from the category key electricity demand influencing factors, and the electricity users whose deviation between the degree of influence of their key electricity demand influencing factors and the degree of influence of the category key electricity demand influencing factors is greater than a preset first deviation. These are collectively identified as electricity users to be classified.

[0042] Step 105-2: For each electricity user to be classified, identify candidate electricity user classes in each electricity user class whose category key electricity demand influencing factors are the same as those of the electricity user to be classified. Calculate the influence degree deviation between the electricity user to be classified and each candidate electricity user class based on the influence degree of the key electricity demand influencing factors of the electricity user to be classified and the influence degree of the category key electricity demand influencing factors of each candidate electricity user class. Based on the influence degree deviation, classify the electricity user to be classified into an electricity user class.

[0043] In this embodiment, for each electricity user category, the key electricity demand influencing factors and their influence levels for the entire category are first determined based on the key electricity demand influencing factors and their influence levels of each individual electricity user within that category. This is an aggregation process aimed at extracting the common characteristics of this category of electricity users. Next, the differences between the key electricity demand influencing factors and their influence levels of each electricity user and the category key electricity demand influencing factors and their influence levels are compared. Specifically, electricity users whose key electricity demand influencing factors differ from the category key electricity demand influencing factors, or whose deviation between the influence levels of their key electricity demand influencing factors and the category key electricity demand influencing factors is greater than a preset first deviation, are identified. These electricity users are considered to be unclassified due to their uniqueness, and they may need to be reclassified into a more suitable electricity user category. Further, for each unclassified electricity user, candidate electricity user categories are searched among all electricity user categories for those whose category key electricity demand influencing factors are the same as those of the unclassified electricity user. This is a matching process aimed at finding the electricity user category that is closest to the unclassified electricity user in terms of key electricity demand influencing factors. Then, the deviation between the influence degree of the key electricity demand influencing factors of the electricity user to be classified and the influence degree of the category key electricity demand influencing factors of each candidate electricity user class is calculated, i.e., the influence degree deviation. This deviation value reflects the degree of similarity between the electricity user to be classified and the candidate electricity user class. Finally, the electricity user to be classified is classified based on the influence degree deviation. Specifically, the electricity user to be classified can be classified into the candidate electricity user class with the smallest influence degree deviation. In this way, the electricity user class is updated, so that each electricity user class more accurately reflects the electricity demand characteristics of the electricity users within it. By comparing the differences between the key electricity demand influencing factors and their influence degree of each electricity user and the category key electricity demand influencing factors and their influence degree of each category, the embodiments of this application can identify those electricity users that do not match the category characteristics and reclassify them, which helps to more accurately classify electricity user classes and improve the accuracy of subsequent electricity demand prediction. By continuously updating and optimizing the types of electricity users, we can ensure that the electricity demand forecasting model can handle more diverse electricity user characteristics, thereby enhancing the model's generalization ability and enabling it to better adapt to electricity demand forecasting tasks in different scenarios.

[0044] In this embodiment of the application, optionally, the classification of the electricity user subject to be classified based on the influence degree deviation in step 105-2 includes: if the minimum deviation in the influence degree deviation is less than a preset second deviation, then the electricity user subject to be classified is assigned to the candidate electricity user subject class corresponding to the minimum deviation; wherein, the preset second deviation is less than the preset first deviation; if the minimum deviation in the influence degree deviation is greater than or equal to the preset second deviation, then the electricity user subject to be classified is returned to the original electricity user subject class in which the electricity user subject to be classified originally belonged.

[0045] In this embodiment, a preset second deviation is established, which is less than a preset first deviation. The preset second deviation is set to provide a more stringent classification standard, ensuring that the similarity between the electricity user to be classified and the candidate electricity user class reaches a certain level. In the classification decision, the minimum deviation in the influence degree deviation is first checked to see if it is less than the preset second deviation. If the minimum deviation is less than the preset second deviation, it indicates that the similarity between the electricity user to be classified and the candidate electricity user class corresponding to the minimum deviation is very high, and therefore the electricity user to be classified can be assigned to this candidate electricity user class. However, if the minimum deviation is greater than or equal to the preset second deviation, it indicates that the similarity between the electricity user to be classified and all candidate electricity user classes is insufficient to meet the classification standard. In this case, to avoid classification errors, the electricity user to be classified is reverted to its original electricity user class. This maintains the stability and consistency of the electricity user classes while reducing electricity demand prediction errors caused by inaccurate classification. This application embodiment, by setting a preset second deviation as a classification standard, can more strictly control the similarity between the electricity user to be classified and the candidate electricity user class, which helps improve the accuracy of classification and ensures that the electricity user to be classified is correctly classified into the most appropriate electricity user class. When the similarity between the electricity user to be classified and all candidate electricity user classes is insufficient to meet the classification standard, it is selected to be reverted to the original class. This strategy can reduce the electricity demand prediction error caused by classification errors, maintain the stability and consistency of electricity user classes, and help the training and prediction of the electricity demand prediction model in subsequent steps, thereby improving the model's generalization ability and prediction accuracy.

[0046] In the embodiments of this application, optionally, as shown... Figure 2 As shown, step 107, which involves training the electricity demand model based on historical electricity consumption data and factors influencing electricity demand for the target electricity-consuming entity, includes:

[0047] Step 107-1: Obtain the electricity user class other than the target electricity user class from the electricity user class as the reference electricity user class;

[0048] Step 107-2: Construct an initial power demand model based on the factors affecting power demand, and based on the total number of the target power user class and the reference power user class, copy the initial power demand model to obtain multiple initial power demand models that match the total number, and determine the initial power demand model that matches each target power user class and each reference power user class respectively.

[0049] Step 107-3: Based on the historical electricity consumption data and electricity demand influencing factors of each electricity consumption subject in each target electricity consumption subject class, train the initial electricity demand model corresponding to each target electricity consumption subject class respectively; and based on the historical electricity consumption data and electricity demand influencing factors of each electricity consumption subject in each reference electricity consumption subject class, train the initial electricity demand model corresponding to each reference electricity consumption subject class respectively.

[0050] Step 107-4: Optimize the model parameters of the initial power demand model corresponding to the target power demand model based on the model parameters of the initial power demand model corresponding to the reference power demand model to obtain the power demand model corresponding to each target power demand model.

[0051] This embodiment proposes an innovative method for training electricity demand models. This method combines data from target and reference electricity demand classes. By replicating, training, and optimizing initial electricity demand models, it ultimately obtains accurate electricity demand models for each target electricity demand class. First, electricity demand classes other than the target classes are selected from all electricity demand classes as reference classes. These reference classes provide different electricity demand characteristics and influencing factors than the target classes, helping to introduce more diversity and generalization ability during model training. Next, initial electricity demand models are constructed based on electricity demand influencing factors (such as electricity price, economy, climate, holidays, etc.). To handle data from multiple electricity demand classes, the initial electricity demand models are replicated according to the total number of target and reference classes, resulting in multiple initial electricity demand models matching the total number. Each electricity demand class (whether target or reference) is assigned a matching initial electricity demand model. Then, historical electricity data and electricity demand influencing factors from each electricity demand class are used to train the corresponding initial electricity demand model. This step aims to enable the model to learn the specific electricity demand characteristics and influencing factors of each electricity user class and their relationship with electricity demand. Finally, based on the model parameters of the initial electricity demand model corresponding to the reference electricity user class, the model parameters of the initial electricity demand model corresponding to the target electricity user class are optimized. This step utilizes the idea of ​​transfer learning, improving the model of the target electricity user class by learning knowledge from the reference electricity user class. The optimized model can better capture the electricity demand characteristics of the target electricity user class and improve prediction accuracy. By introducing a reference electricity user class, this embodiment of the application can introduce more diversity and generalization ability during model training, which helps the model to perform better when processing unseen data. By replicating, training, and optimizing multiple initial electricity demand models, we can obtain an accurate electricity demand model for each electricity user class (including the target electricity user class). These models can better capture the specific electricity demand characteristics and influencing factors of each electricity user class, thereby improving prediction accuracy.

[0052] Optionally, in this embodiment, step 107-3 includes: when training the initial power demand model corresponding to each target power user class, determining the non-critical power demand influencing factors corresponding to the target power user class based on the power demand influencing factors and the key power demand influencing factors corresponding to the target power user class, freezing the model parameters corresponding to the non-critical power demand influencing factors, and training the initial power demand model based on the historical power data and power demand influencing factors of each power user in the target power user class to optimize the model parameters corresponding to the key power demand influencing factors; when training the initial power demand model corresponding to each reference power user class, not freezing any model parameters, and training the initial power demand model based on the historical power data and power demand influencing factors of each power user in the reference power user class to optimize all model parameters of the initial power demand model, thereby obtaining the power demand model corresponding to the reference power user class.

[0053] In this embodiment, a detailed explanation of the implementation of step 107-3 and a derivation of its beneficial effects are provided.

[0054] Step 107-3 Detailed Implementation: First, based on the factors influencing electricity demand and the key factors influencing electricity demand corresponding to the target electricity user class, determine the non-key factors influencing electricity demand for the target electricity user class. These non-key factors may have a small or unstable impact on electricity demand, so they do not need to be focused on during model training. When training the initial electricity demand model for the target electricity user class, freeze the model parameters corresponding to the non-key factors influencing electricity demand. This means that these parameters will not be updated during training, thereby reducing the complexity and computational cost of model training. Then, train the initial electricity demand model based on the historical electricity data and factors influencing electricity demand (especially key factors influencing electricity demand) for each electricity user in the target electricity user class. During training, only the model parameters corresponding to the key factors influencing electricity demand are optimized to improve the model's prediction accuracy for the electricity demand of the target electricity user class. For the initial electricity demand model for the reference electricity user class, a more comprehensive training method is adopted. Specifically, when training the initial electricity demand model for the reference electricity user class, no model parameters are frozen, and all parameters are updated during training to fully utilize the diversity and generalization ability provided by the reference electricity user class. Then, based on the historical electricity consumption data and electricity demand influencing factors of each electricity consumer in the reference electricity consumer class, the initial electricity demand model is trained. During training, all model parameters are optimized to obtain a more accurate electricity demand model. This embodiment of the application reduces the complexity and computational load of model training by freezing the model parameters of non-critical electricity demand influencing factors corresponding to the target electricity consumer class, thereby improving model training efficiency. By focusing on optimizing the model parameters corresponding to key electricity demand influencing factors, the electricity demand characteristics of the target electricity consumer class can be captured more accurately, thereby improving the model's prediction accuracy. By comprehensively training the initial electricity demand model corresponding to the reference electricity consumer class, the diversity and generalization ability provided by the reference electricity consumer class are fully utilized, enhancing the model's generalization ability.

[0055] Optionally, in this embodiment, optimizing the model parameters of the initial power demand model corresponding to the target power demand class based on the model parameters of the initial power demand model corresponding to the reference power demand class to obtain the power demand model corresponding to each target power demand class includes: for each target power demand class, extracting model parameters corresponding to the non-critical power demand influencing factors from the power demand model corresponding to each reference power demand class, and determining the fusion weight of the model parameters corresponding to each non-critical power demand influencing factor based on the degree of influence of the non-critical power demand influencing factors in the target power demand class and the degree of influence of each non-critical power demand influencing factor in the reference power demand class; fusing the model parameters of each non-critical power demand influencing factor based on the fusion weight to obtain the model parameters corresponding to each non-critical power demand influencing factor; setting the model parameters corresponding to each non-critical power demand influencing factor in the initial power demand model corresponding to the target power demand class; and performing a second round of training on the set initial power demand model based on the historical power data and power demand influencing factors corresponding to each power demand class in the target power demand class to obtain the power demand model corresponding to the target power demand class.

[0056] In this embodiment, for each target electricity consumption class, model parameters corresponding to non-critical electricity demand influencing factors are first extracted from the electricity demand model corresponding to each reference electricity consumption class. These parameters reflect the impact of non-critical factors on electricity demand in the reference electricity consumption class. Next, based on the degree of influence of the non-critical electricity demand influencing factors in the target electricity consumption class and the degree of influence of these factors in the reference electricity consumption class, the fusion weights of the model parameters corresponding to each non-critical electricity demand influencing factor are determined. This step aims to ensure that non-critical factors with a greater impact on the target electricity consumption class receive greater weights during the fusion process. Based on the determined fusion weights, the model parameters of each non-critical electricity demand influencing factor are fused to obtain the optimized model parameters corresponding to each non-critical electricity demand influencing factor in the target electricity consumption class. Then, the fused model parameters corresponding to the non-critical electricity demand influencing factors are set in the initial electricity demand model corresponding to the target electricity consumption class. Finally, based on the historical electricity consumption data and electricity demand influencing factors corresponding to each electricity consumer in the target electricity consumer class, the initial electricity demand model is trained twice, iterating all the model parameters to further optimize the model parameters and improve the model's prediction accuracy for the electricity demand of the target electricity consumer class. This embodiment of the application, by fusing model parameters of non-critical electricity demand influencing factors in the reference electricity consumer class and determining the fusion weights based on the degree of influence, can provide more accurate model parameters for the target electricity consumer class, thereby improving the model's prediction accuracy. Using data from the reference electricity consumer class to optimize the model parameters of the target electricity consumer class helps to introduce more diversity and generalization ability, enabling the model to exhibit better performance when processing unseen data. Guiding the optimization process of model parameters through fusion weights allows for faster finding of the optimal combination of model parameters, thus accelerating the model optimization process.

[0057] In this embodiment of the application, optionally, the step 107 of predicting the electricity demand of each electricity user in the future forecast period based on the electricity price factor change information and the economic factor change information includes: determining the electricity demand model corresponding to each electricity user; obtaining the prediction information of each electricity demand influencing factor in the target analysis area in the future forecast period, wherein the electricity price factor change information is used as the electricity price factor prediction information, and the economic factor change information is used as the economic factor prediction information; and predicting the electricity demand of each electricity user in the future forecast period based on the historical electricity data of each electricity user and the prediction information of each electricity demand influencing factor through the corresponding electricity demand model.

[0058] In this embodiment, the electricity demand model corresponding to each electricity consumer is determined, and the predicted information of various electricity demand influencing factors in the target analysis area during the future forecast period is obtained. This predicted information can be obtained through methods such as time series analysis, regression analysis, and expert prediction. The predicted information for electricity price factors uses the electricity price factor change information mentioned above, and the predicted information for economic factors uses the economic factor change information mentioned above. Finally, based on the historical electricity data of each electricity consumer and the predicted information of various electricity demand influencing factors, the electricity demand of each electricity consumer during the future forecast period is predicted through the corresponding electricity demand model. The predicted information is input into the electricity demand model, and the model is run to obtain the prediction results. Electricity price and economic factors are important factors affecting electricity demand, and their changes often directly reflect electricity demand. This embodiment of the application, by combining the predicted information of electricity price factors and economic factors, can more comprehensively consider various factors affecting electricity demand, thereby improving the accuracy of prediction.

[0059] By applying the technical solution of this embodiment, through the refined construction and training of the electricity demand model, combined with the prediction of changes in electricity price factors and economic factors, and the differentiated processing of the target electricity user class and the reference electricity user class, including the distinction between key and non-key electricity demand influencing factors, the freezing and optimization of model parameters, and the parameter fusion strategy based on fusion weights, this technical solution significantly improves the accuracy of electricity demand forecasting, enhances the generalization ability and adaptability of the model, provides more accurate decision support for power system operators, promotes the optimal allocation and efficient utilization of power resources, and at the same time promotes sustainable energy development, reduces energy waste, and improves energy utilization efficiency.

[0060] Furthermore, as Figure 1 In terms of specific implementation, this application provides an electricity demand forecasting device adapted to the new electricity price reform, such as... Figure 3 As shown, the device includes:

[0061] The change information determination module is used to determine the change information of electricity price factors and economic factors in the target analysis area during the future forecast period, based on the information on the new electricity price reform situation and the impact information of economic policies in the target analysis area during the future forecast period.

[0062] The historical data acquisition module is used to acquire historical electricity consumption data of different electricity users in the target analysis area within a set time period, as well as factors affecting electricity demand. The factors affecting electricity demand include at least electricity price factors, economic factors, climate factors, and holiday factors.

[0063] The clustering module is used to generate electricity consumption curves for each electricity consumer based on the historical electricity consumption data, and to cluster each electricity consumer based on the electricity consumption curves to obtain multiple electricity consumer classes.

[0064] The factor analysis module is used to analyze the degree of influence of each electricity demand influencing factor for each electricity user category based on the historical electricity consumption data of each electricity user in the category, and to filter out the key electricity demand influencing factors for each electricity user based on the degree of influence of each electricity demand influencing factor according to the preset influence degree screening conditions.

[0065] The update module is used to update the electricity users in each electricity user class based on the key electricity demand influencing factors of each electricity user in each electricity user class, so as to obtain multiple updated electricity user class classes.

[0066] The model training module is used to obtain at least one of the key electricity demand influencing factors, including electricity price factors and economic factors, as the target electricity demand subject class; to train the electricity demand model based on the historical electricity data and electricity demand influencing factors of each electricity subject in the target electricity demand subject class; and to predict the electricity demand of each electricity subject in the future forecast period based on the electricity price factor change information and the economic factor change information.

[0067] Optionally, in this embodiment of the application, the update module is further configured to:

[0068] For each electricity user category, based on the key electricity demand influencing factors and their degree of influence for each electricity user in the category, the category key electricity demand influencing factors and their degree of influence for the corresponding electricity user category are determined. Based on the key electricity demand influencing factors and their degree of influence for each electricity user and the category key electricity demand influencing factors and their degree of influence for the electricity user category, electricity users whose key electricity demand influencing factors differ from the category key electricity demand influencing factors are identified, as well as electricity users whose deviation between the degree of influence of their key electricity demand influencing factors and the degree of influence of the category key electricity demand influencing factors is greater than a preset first deviation, are collectively identified as electricity users to be classified.

[0069] For each electricity user to be classified, candidate electricity user classes are identified within each electricity user class whose category-specific key electricity demand influencing factors are the same as those of the electricity user to be classified. Based on the degree of influence of the key electricity demand influencing factors of the electricity user to be classified and the degree of influence of the category-specific key electricity demand influencing factors of each candidate electricity user class, the degree of influence deviation between the electricity user to be classified and each candidate electricity user class is calculated. Based on the degree of influence deviation, the electricity user to be classified is classified into an electricity user class.

[0070] Optionally, in this embodiment of the application, the update module is further configured to:

[0071] If the minimum deviation in the degree of influence is less than the preset second deviation, then the electricity user to be classified is assigned to the candidate electricity user class corresponding to the minimum deviation; wherein, the preset second deviation is less than the preset first deviation;

[0072] If the minimum deviation in the degree of influence is greater than or equal to the preset second deviation, then the electricity user to be classified will be reverted to the original electricity user category to which the electricity user to be classified belonged.

[0073] Optionally, in this embodiment of the application, the model training module is further configured to:

[0074] Obtain the electricity user class other than the target electricity user class from the electricity user class as the reference electricity user class;

[0075] An initial electricity demand model is constructed based on the factors affecting electricity demand. Based on the total number of the target electricity user class and the reference electricity user class, the initial electricity demand model is replicated to obtain multiple initial electricity demand models that match the total number. The initial electricity demand model that matches each target electricity user class and each reference electricity user class is determined respectively.

[0076] Based on the historical electricity consumption data and electricity demand influencing factors of each electricity consumption subject in each target electricity consumption subject class, the initial electricity demand model corresponding to each target electricity consumption subject class is trained respectively; and based on the historical electricity consumption data and electricity demand influencing factors of each electricity consumption subject in each reference electricity consumption subject class, the initial electricity demand model corresponding to each reference electricity consumption subject class is trained respectively.

[0077] Based on the model parameters of the initial electricity demand model corresponding to the reference electricity user class, the model parameters of the initial electricity demand model corresponding to the target electricity user class are optimized to obtain the electricity demand model corresponding to each target electricity user class.

[0078] Optionally, in this embodiment of the application, the model training module is further configured to:

[0079] When training the initial power demand model for each target power user class, the non-critical power demand influencing factors for the target power user class are determined based on the power demand influencing factors and the key power demand influencing factors for the target power user class. The model parameters corresponding to the non-critical power demand influencing factors are frozen. The initial power demand model is trained based on the historical power data and power demand influencing factors of each power user in the target power user class to optimize the model parameters corresponding to the key power demand influencing factors.

[0080] When training the initial electricity demand model corresponding to each reference electricity user class, no model parameters are frozen. Based on the historical electricity data and electricity demand influencing factors of each electricity user in the reference electricity user class, the initial electricity demand model is trained to optimize all model parameters of the initial electricity demand model, thereby obtaining the electricity demand model corresponding to the reference electricity user class.

[0081] Optionally, in this embodiment of the application, the model training module is further configured to:

[0082] For each target electricity consumption subject class, model parameters corresponding to the non-critical electricity demand influencing factors are extracted from the electricity demand model corresponding to each reference electricity consumption subject class. Based on the influence degree of the non-critical electricity demand influencing factors in the target electricity consumption subject class and the influence degree of each non-critical electricity demand influencing factor in the reference electricity consumption subject class, the fusion weight of the model parameters corresponding to each non-critical electricity demand influencing factor is determined. The model parameters of each non-critical electricity demand influencing factor are fused based on the fusion weight to obtain the model parameters corresponding to each non-critical electricity demand influencing factor. The model parameters corresponding to each non-critical electricity demand influencing factor are set in the initial electricity demand model corresponding to the target electricity consumption subject class.

[0083] Based on the historical electricity consumption data and electricity demand influencing factors corresponding to each electricity consumption subject in the target electricity consumption subject class, the initial electricity demand model is trained twice to obtain the electricity demand model corresponding to the target electricity consumption subject class.

[0084] Optionally, in this embodiment of the application, the model training module is further configured to:

[0085] Determine the electricity demand model corresponding to each electricity consumer, and obtain the prediction information of each electricity demand influencing factor in the target analysis area during the future prediction period. Among them, the electricity price factor change information is used as the electricity price factor prediction information, and the economic factor change information is used as the economic factor prediction information.

[0086] Based on historical electricity consumption data of each electricity consumer and forecast information on factors influencing electricity demand, the electricity demand of each electricity consumer in the future forecast period is predicted through corresponding electricity demand models.

[0087] It should be noted that other corresponding descriptions of the functional units involved in the electricity demand forecasting device adapted to the new electricity price reform provided in this application embodiment can be found in the following references. Figures 1 to 2 The corresponding descriptions in the method will not be repeated here.

[0088] This application also provides a computer device, specifically a personal computer, server, network device, etc. The computer device includes a bus, processor, memory, and communication interface, and may also include input / output interfaces and a display device. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device stores location information. The network interface of the computer device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements the steps in the various method embodiments.

[0089] Those skilled in the art will understand that the structure of the computer device described above is only a partial structure related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. A specific computer device may include more or fewer components, or combine certain components, or have different component arrangements.

[0090] In one embodiment, a computer-readable storage medium is provided, which may be non-volatile or volatile, having stored thereon a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0091] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0092] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0093] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0094] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0095] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for forecasting electricity demand to adapt to the new electricity price reform, characterized in that, The method includes: Based on information on the new electricity price reform situation and the impact of economic policies in the target analysis region during the future forecast period, information on changes in electricity price factors and economic factors in the target analysis region during the future forecast period is determined. The historical electricity consumption data of different electricity users in the target analysis area within a set time period and the factors affecting electricity demand are obtained. The factors affecting electricity demand include at least electricity price factors, economic factors, climate factors, and holiday factors. Based on the historical electricity consumption data, electricity consumption curves are generated for each electricity consumer. Based on the electricity consumption curves, each electricity consumer is clustered to obtain multiple electricity consumer classes. For each electricity user category, the influence of each electricity demand influencing factor is analyzed based on the historical electricity consumption data of each electricity user in the category, and the key electricity demand influencing factors of each electricity user are selected based on the influence of each electricity demand influencing factor according to the preset influence degree screening conditions. Based on the key electricity demand influencing factors of each electricity consumer in each electricity consumer category, the electricity consumers in each electricity consumer category are updated to obtain multiple updated electricity consumer categories; the electricity consumer category whose key electricity demand influencing factors include at least one of electricity price factors and economic factors is selected as the target electricity consumer category. The electricity demand model is trained based on the historical electricity consumption data and factors affecting electricity demand of each electricity consumer in the target electricity consumer category, and the electricity demand of each electricity consumer in the future forecast period is predicted based on the electricity price factor change information and the economic factor change information. The process involves updating the electricity users in each electricity user category based on the key electricity demand influencing factors, resulting in multiple updated electricity user categories, including: For each electricity user category, based on the key electricity demand influencing factors and their degree of influence for each electricity user in the category, the category key electricity demand influencing factors and their degree of influence for the corresponding electricity user category are determined. Based on the key electricity demand influencing factors and their degree of influence for each electricity user and the category key electricity demand influencing factors and their degree of influence for the electricity user category, electricity users whose key electricity demand influencing factors differ from the category key electricity demand influencing factors are identified, as well as electricity users whose deviation between the degree of influence of their key electricity demand influencing factors and the degree of influence of the category key electricity demand influencing factors is greater than a preset first deviation, are collectively identified as electricity users to be classified. For each electricity user to be classified, candidate electricity user classes are identified in each electricity user class whose category key electricity demand influencing factors are the same as those of the electricity user to be classified. Based on the influence degree of the key electricity demand influencing factors of the electricity user to be classified and the influence degree of the category key electricity demand influencing factors of each candidate electricity user class, the influence degree deviation between the electricity user to be classified and each candidate electricity user class is calculated. Based on the influence degree deviation, the electricity user to be classified is classified into an electricity user class. The step of training the electricity demand model based on historical electricity consumption data and factors influencing electricity demand of the target electricity consumer group includes: Obtain the electricity user class other than the target electricity user class from the electricity user class as the reference electricity user class; An initial electricity demand model is constructed based on the factors affecting electricity demand. Based on the total number of the target electricity user class and the reference electricity user class, the initial electricity demand model is replicated to obtain multiple initial electricity demand models that match the total number. The initial electricity demand model that matches each target electricity user class and each reference electricity user class is determined respectively. Based on the historical electricity consumption data and electricity demand influencing factors of each electricity consumption subject in each target electricity consumption subject class, the initial electricity demand model corresponding to each target electricity consumption subject class is trained respectively; and based on the historical electricity consumption data and electricity demand influencing factors of each electricity consumption subject in each reference electricity consumption subject class, the initial electricity demand model corresponding to each reference electricity consumption subject class is trained respectively. Based on the model parameters of the initial electricity demand model corresponding to the reference electricity user class, the model parameters of the initial electricity demand model corresponding to the target electricity user class are optimized to obtain the electricity demand model corresponding to each target electricity user class.

2. The method according to claim 1, characterized in that, The classification of the electricity users to be classified based on the degree of influence deviation includes: If the minimum deviation in the degree of influence is less than the preset second deviation, then the electricity user to be classified is assigned to the candidate electricity user class corresponding to the minimum deviation; wherein, the preset second deviation is less than the preset first deviation; If the minimum deviation in the degree of influence is greater than or equal to the preset second deviation, then the electricity user to be classified will be reverted to the original electricity user category to which the electricity user to be classified belonged.

3. The method according to claim 1, characterized in that, The process of training an initial electricity demand model for each target electricity user class based on historical electricity consumption data and electricity demand influencing factors, and training an initial electricity demand model for each reference electricity user class based on historical electricity consumption data and electricity demand influencing factors, includes: When training the initial power demand model for each target power user class, the non-critical power demand influencing factors for the target power user class are determined based on the power demand influencing factors and the key power demand influencing factors for the target power user class. The model parameters corresponding to the non-critical power demand influencing factors are frozen. The initial power demand model is trained based on the historical power data and power demand influencing factors of each power user in the target power user class to optimize the model parameters corresponding to the key power demand influencing factors. When training the initial electricity demand model corresponding to each reference electricity user class, no model parameters are frozen. Based on the historical electricity data and electricity demand influencing factors of each electricity user in the reference electricity user class, the initial electricity demand model is trained to optimize all model parameters of the initial electricity demand model, thereby obtaining the electricity demand model corresponding to the reference electricity user class.

4. The method according to claim 3, characterized in that, The optimization of the model parameters of the initial electricity demand model corresponding to the target electricity demand class based on the model parameters of the initial electricity demand model corresponding to the reference electricity demand class yields the electricity demand model corresponding to each target electricity demand class, including: For each target electricity consumption subject class, model parameters corresponding to the non-critical electricity demand influencing factors are extracted from the electricity demand model corresponding to each reference electricity consumption subject class. Based on the influence degree of the non-critical electricity demand influencing factors in the target electricity consumption subject class and the influence degree of each non-critical electricity demand influencing factor in the reference electricity consumption subject class, the fusion weight of the model parameters corresponding to each non-critical electricity demand influencing factor is determined. The model parameters of each non-critical electricity demand influencing factor are fused based on the fusion weight to obtain the model parameters corresponding to each non-critical electricity demand influencing factor. The model parameters corresponding to each non-critical electricity demand influencing factor are set in the initial electricity demand model corresponding to the target electricity consumption subject class. Based on the historical electricity consumption data and electricity demand influencing factors corresponding to each electricity consumption subject in the target electricity consumption subject class, the initial electricity demand model is trained twice to obtain the electricity demand model corresponding to the target electricity consumption subject class.

5. The method according to any one of claims 1 to 4, characterized in that, The prediction of electricity demand for each electricity user in the future forecast period based on the electricity price change information and the economic factor change information includes: Determine the electricity demand model corresponding to each electricity consumer, and obtain the prediction information of each electricity demand influencing factor in the target analysis area during the future prediction period. Among them, the electricity price factor change information is used as the electricity price factor prediction information, and the economic factor change information is used as the economic factor prediction information. Based on historical electricity consumption data of each electricity consumer and forecast information on factors influencing electricity demand, the electricity demand of each electricity consumer in the future forecast period is predicted through corresponding electricity demand models.

6. A power demand forecasting device adapted to the new electricity price reform, characterized in that, The device includes: The change information determination module is used to determine the change information of electricity price factors and economic factors in the target analysis area during the future forecast period, based on the information on the new electricity price reform situation and the impact information of economic policies in the target analysis area during the future forecast period. The historical data acquisition module is used to acquire historical electricity consumption data of different electricity users in the target analysis area within a set time period, as well as factors affecting electricity demand. The factors affecting electricity demand include at least electricity price factors, economic factors, climate factors, and holiday factors. The clustering module is used to generate electricity consumption curves for each electricity consumer based on the historical electricity consumption data, and to cluster each electricity consumer based on the electricity consumption curves to obtain multiple electricity consumer classes. The factor analysis module is used to analyze the degree of influence of each electricity demand influencing factor for each electricity user category based on the historical electricity consumption data of each electricity user in the category, and to filter out the key electricity demand influencing factors for each electricity user based on the degree of influence of each electricity demand influencing factor according to the preset influence degree screening conditions. The update module is used to update the electricity users in each electricity user class based on the key electricity demand influencing factors of each electricity user in each electricity user class, so as to obtain multiple updated electricity user class classes. The model training module is used to obtain at least one of the key electricity demand influencing factors, including electricity price factors and economic factors, as the target electricity demand subject class; to train the electricity demand model based on the historical electricity data and electricity demand influencing factors of each electricity subject in the target electricity demand subject class; and to predict the electricity demand of each electricity subject in the future prediction period based on the electricity price factor change information and the economic factor change information. The updating module is further configured to: for each electricity user category, determine the category-specific key electricity demand influencing factors and their degree of influence based on the key electricity demand influencing factors and their degree of influence for each electricity user in the category; and, based on the key electricity demand influencing factors and their degree of influence for each electricity user and the category-specific key electricity demand influencing factors and their degree of influence for the electricity user category, determine the electricity users whose key electricity demand influencing factors differ from the category-specific key electricity demand influencing factors, and the degree of influence of the key electricity demand influencing factors differs from the degree of influence of the category-specific key electricity demand influencing factors. Electricity users whose deviations from the target category are greater than a preset first deviation are collectively identified as electricity users to be classified. For each electricity user to be classified, candidate electricity user categories are identified in each electricity user category whose category key electricity demand influencing factors are the same as those of the electricity user to be classified. Based on the influence degree of the key electricity demand influencing factors of the electricity user to be classified and the influence degree of the category key electricity demand influencing factors of each candidate electricity user category, the influence degree deviation between the electricity user to be classified and each candidate electricity user category is calculated. Based on the influence degree deviation, the electricity user to be classified is classified into electricity user categories. The model training module is further configured to: acquire electricity user classes other than the target electricity user class from the electricity user class as reference electricity user classes; construct an initial electricity demand model based on the factors influencing electricity demand, and copy the initial electricity demand model based on the total number of the target electricity user class and the reference electricity user class to obtain multiple initial electricity demand models matching the total number, and determine the initial electricity demand model matching each target electricity user class and each reference electricity user class respectively; train the initial electricity demand model corresponding to each target electricity user class based on the historical electricity data and factors influencing electricity demand of each electricity user in each target electricity user class, and train the initial electricity demand model corresponding to each reference electricity user class based on the historical electricity data and factors influencing electricity demand of each electricity user in each reference electricity user class; optimize the model parameters of the initial electricity demand model corresponding to the target electricity user class based on the model parameters of the initial electricity demand model corresponding to the reference electricity user class to obtain the electricity demand model corresponding to each target electricity user class.

7. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 5.

8. A computer device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 5.

Images