IES load-energy price coupling prediction method and system based on mixed attention

Abstract

The invention relates to the field of integrated energy system management, and discloses an IES load-energy price coupling prediction method and system based on mixed attention, and the method comprises the steps: determining a multi-dimensional management feature through a multi-dimensional management feature extraction unit according to integrated energy management information; wherein the comprehensive energy management information comprises renewable energy output information, multi-energy load information and energy price information in a time sequence; according to the multi-dimensional management features, through a mixed attention unit, determining fusion management features of the multi-dimensional management features under the channel attention weight and the time attention weight; and according to the fusion management features, through a fusion output unit, determining a renewable energy output prediction value, a multi-energy load prediction value and an energy price prediction value. The multi-dimensional management feature extraction unit comprises a multi-column convolutional neural network unit and a long-short term memory network unit. According to the invention, the integrated energy system can be managed and dispatched to plan and operate under the optimal target.

Description

Technical Field

[0001] The present application relates to the technical field of integrated energy system management, and more specifically, to an IES load-energy price coupling prediction method and system based on hybrid attention. Background Art

[0002] In the Integrated Energy System (IES), there are three uncertain variables: renewable energy, multi-energy loads, and energy prices. The three uncertain variables have a complex coupling relationship. Among them, the coupling of renewable energy and multi-energy loads includes supply and demand matching. The output of renewable energy (such as wind energy and solar energy) is volatile and intermittent, and the demand of multi-energy loads (such as power load, heat load, and cooling load) also varies with time and season. The coupling of renewable energy and energy prices includes that the output fluctuation of renewable energy will affect the supply and demand relationship in the power market, thereby affecting energy prices. For example, when the output of renewable energy is high, the power supply increases and the electricity price may fall; conversely, the electricity price may rise. The coupling of multi-energy loads and energy prices includes that the demand of multi-energy loads is sensitive to energy prices. When energy prices rise, users may reduce load demand and choose more economical alternative energy; when prices fall, users may increase load demand.

[0003] There is also a comprehensive coupling relationship between renewable energy, multi-energy loads and energy prices. The integrated energy system needs to optimize scheduling and management to comprehensively consider factors such as renewable energy output, load demand and energy prices to achieve the optimal operation of the system. For example, through optimization algorithms, operating costs can be minimized while ensuring power supply reliability. In the operation and scheduling applications of existing integrated energy systems, due to the large uncertainty in renewable energy production and user-side energy utilization in the system, it is currently difficult to manage and schedule the integrated energy system to plan and operate under the optimal goal. Summary of the invention

[0004] The purpose of this application is to provide an IES load-energy price coupling prediction method and system based on hybrid attention, which solves the technical problem that it is difficult to manage and schedule the integrated energy system for planning and operation under the optimal goal, and achieves the technical effect of managing and scheduling the integrated energy system for planning and operation under the optimal goal.

[0005] An embodiment of the present application provides an IES load-energy price coupling prediction method based on hybrid attention, the method comprising: determining multi-dimensional management features through a multi-dimensional management feature extraction unit according to comprehensive energy management information; wherein the comprehensive energy management information includes renewable energy output information, multi-energy load information and energy price information in time series; according to the multi-dimensional management features, determining the fusion management features of the multi-dimensional management features under channel attention weights and time attention weights through a hybrid attention unit; according to the fusion management features, determining the renewable energy output prediction value, the multi-energy load prediction value and the energy price prediction value through a fusion output unit.

[0006] In one possible implementation, the multi-dimensional management feature extraction unit includes a multi-column convolutional neural network unit and a long short-term memory network unit; the multi-dimensional management features include local features, spatial dependency features, and time series dependency features corresponding to renewable energy output information, multi-energy load information, and energy price information, respectively.

[0007] In another possible implementation, the hybrid attention unit includes a channel attention unit and a time attention unit; the fusion management feature includes a fusion management feature that is fused according to the channel attention weight and the time attention weight by respectively fusing the local features, spatial dependence features and time series dependence features corresponding to the renewable energy output information, multi-energy load information and energy price information.

[0008] In another possible implementation, the method also includes: obtaining seasonal parameters and meteorological parameters within the time period to be predicted, determining the outdoor wind speed and outdoor light intensity based on the seasonal parameters and meteorological parameters, and determining the outdoor temperature and indoor temperature based on the seasonal parameters and meteorological parameters; determining the compensation value of renewable energy output information based on the outdoor wind speed and outdoor light intensity, and correcting the renewable energy output information based on the compensation value of the renewable energy output information; determining the compensation value of multi-energy load information based on the outdoor temperature and indoor temperature, and correcting the multi-energy load information based on the compensation value of the multi-energy load information within the time period to be predicted.

[0009] In another possible implementation, the method also includes: determining the seasonal parameter change range of the seasonal parameters and the seasonal parameter change range of the meteorological parameters within the time period to be predicted, and determining the seasonal parameter change range and the maximum change range among the seasonal parameter change ranges; determining the product of the compensation value of the multi-energy load information and the maximum change range as the compensation value threshold; when the compensation value of the renewable energy output information is greater than or equal to the compensation value threshold, using the compensation value threshold as the compensation value of the renewable energy output information; when the compensation value of the renewable energy output information is less than the compensation value threshold, keeping the compensation value of the renewable energy output information unchanged.

[0010] In another possible implementation, the method further includes: obtaining supply and demand relationship information of traditional energy within the predicted time period, determining a compensation value of energy price information based on the supply and demand relationship information of traditional energy; and correcting the energy price information based on the compensation value of the energy price information.

[0011] In another possible implementation, the method also includes: obtaining supply and demand relationship information of traditional energy and regional carbon emission adjustment information within the predicted time period, determining the compensation value of energy price information based on the supply and demand relationship information of traditional energy and regional carbon emission adjustment information; and correcting the energy price information based on the compensation value of the energy price information.

[0012] In another possible implementation, the method further includes: determining a compensation value of the supply and demand relationship information of traditional energy according to seasonal parameters and meteorological parameters, and adjusting the supply and demand relationship information of traditional energy according to the compensation value of the supply and demand relationship information of traditional energy.

[0013] An embodiment of the present application also provides an IES load-energy price coupling prediction system based on hybrid attention, comprising a unit for executing any of the methods described above.

[0014] An embodiment of the present application also provides an IES load-energy price coupling prediction system based on hybrid attention, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, it implements any of the methods described above.

[0015] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the above items is implemented.

[0016] An embodiment of the present application also provides a computer program product, including a computer program, which implements the steps of any of the methods described above when executed by a processor.

[0017] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0018] The embodiment of the present application provides an IES load-energy price coupling prediction method based on hybrid attention, and the method includes: according to the comprehensive energy management information, through the multi-dimensional management feature extraction unit, determining the multi-dimensional management feature; wherein the comprehensive energy management information includes the renewable energy output information, multi-energy load information and energy price information in the time series; according to the multi-dimensional management feature, through the hybrid attention unit, determining the fusion management feature of the multi-dimensional management feature under the channel attention weight and the time attention weight; according to the fusion management feature, through the fusion output unit, determining the renewable energy output prediction value, the multi-energy load prediction value and the energy price prediction value. The method in the embodiment of the present application can obtain the renewable energy output prediction value, the multi-energy load prediction value and the energy price prediction value of the comprehensive energy system by utilizing the comprehensive coupling relationship between renewable energy, multi-energy load and energy price, thereby improving the accuracy of long-term prediction of the renewable energy output prediction value, the multi-energy load prediction value and the energy price prediction value, and improving the management effect of the comprehensive energy system. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0020] Figure 1 A flow chart of a hybrid attention-based IES load-energy price coupling prediction method provided in an embodiment of the present application;

[0021] Figure 2 A schematic diagram of the workflow of a hybrid attention-based IES load-energy price coupling prediction method provided in an embodiment of the present application;

[0022] Figure 3 A schematic diagram of a workflow of a multi-dimensional management feature extraction unit provided in an embodiment of the present application;

[0023] Figure 4 A schematic diagram of a workflow of a hybrid attention unit provided in an embodiment of the present application;

[0024] Figure 5 A flow chart of a second IES load-energy price coupling prediction method based on hybrid attention provided in an embodiment of the present application;

[0025] Figure 6 A flow chart of a third IES load-energy price coupling prediction method based on hybrid attention provided in an embodiment of the present application;

[0026] Figure 7 A schematic diagram of the logical structure of an IES load-energy price coupling prediction system based on hybrid attention provided in an embodiment of the present application;

[0027] Figure 8 A schematic diagram of the physical structure of an IES load-energy price coupling prediction system based on hybrid attention provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0029] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0030] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0031] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0032] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0033] In the operation and scheduling applications of existing integrated energy systems, there is a comprehensive coupling relationship between renewable energy, multi-energy loads and energy prices. In addition, due to the large uncertainty in renewable energy production and user-side energy utilization in the system, it is currently difficult to manage and schedule the integrated energy system to plan and operate under the optimal goal.

[0034] Based on the above reasons, the embodiment of the present application provides an IES load-energy price coupling prediction method based on hybrid attention, and the method includes: according to the comprehensive energy management information, through the multi-dimensional management feature extraction unit, determine the multi-dimensional management feature; wherein the comprehensive energy management information includes the renewable energy output information, multi-energy load information and energy price information in the time series; according to the multi-dimensional management feature, through the hybrid attention unit, determine the fusion management feature of the multi-dimensional management feature under the channel attention weight and the time attention weight; according to the fusion management feature, through the fusion output unit, determine the renewable energy output prediction value, the multi-energy load prediction value and the energy price prediction value. The method in the embodiment of the present application can obtain the renewable energy output prediction value, the multi-energy load prediction value and the energy price prediction value of the comprehensive energy system by utilizing the comprehensive coupling relationship between renewable energy, multi-energy load and energy price, improve the accuracy of the long-term prediction of the renewable energy output prediction value, the multi-energy load prediction value and the energy price prediction value, and improve the management effect of the comprehensive energy system.

[0035] In some scenarios, an IES load-energy price coupling prediction method based on hybrid attention in an embodiment of the present application can be applied to the integrated management and scheduling of integrated energy systems, and can perform long-term and accurate predictions of renewable energy, multi-energy loads and energy prices, thereby improving the integrated management and scheduling effects of integrated energy systems.

[0036] The following is a specific example to illustrate an IES load-energy price coupling prediction method based on hybrid attention provided in an embodiment of the present application.

[0037] Figure 1 A flow chart of a hybrid attention-based IES load-energy price coupling prediction method provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method includes S110 to S130, and S110 to S130 are described in detail below.

[0038] S110: Determine multi-dimensional management features through a multi-dimensional management feature extraction unit according to the comprehensive energy management information, wherein the comprehensive energy management information includes renewable energy output information, multi-energy load information and energy price information in time series.

[0039] Figure 2A schematic diagram of the workflow of a hybrid attention-based IES load-energy price coupling prediction method provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, in an embodiment of the present application, a multidimensional management feature can be first determined based on the comprehensive energy management information through a multidimensional management feature extraction unit. The multidimensional management feature can be a multidimensional feature including time dependency and space dependency, and then the renewable energy output information, multi-energy load information and energy price information can be more accurately predicted based on the multidimensional management feature.

[0040] Exemplarily, comprehensive energy management information may include time series renewable energy output information, multi-energy load information and energy price information, and then the time characteristics of the renewable energy output information, multi-energy load information and energy price information can be accurately extracted based on the time series information of the renewable energy output information, multi-energy load information and energy price information.

[0041] S120. According to the multi-dimensional management features, a fusion management feature of the multi-dimensional management features under the channel attention weight and the time attention weight is determined through a mixed attention unit.

[0042] like Figure 2 As shown, after obtaining the multidimensional management features, the fusion management features of the multidimensional management features under the channel attention weight and the time attention weight can be determined through the mixed attention unit according to the multidimensional management features. The fusion management features characterize the multidimensional management features that integrate the characteristics of the channel attention weight and the time attention weight, and then the renewable energy output information, multi-energy load information and energy price information can be accurately predicted according to the fusion management features.

[0043] S130. According to the fusion management characteristics, the renewable energy output forecast value, the multi-energy load forecast value and the energy price forecast value are determined through the fusion output unit.

[0044] After obtaining the fusion management characteristics, the renewable energy output forecast value, the multi-energy load forecast value and the energy price forecast value can be determined according to the fusion management characteristics through the fusion output unit to achieve the output of the renewable energy output forecast value, the multi-energy load forecast value and the energy price forecast value.

[0045] The beneficial effect of the above-mentioned implementation method is that the multidimensional management features of the time dependency and space dependency of the comprehensive energy management information are extracted through the multidimensional management feature extraction unit, and the fusion management features of the multidimensional management features under the channel attention weight and time attention weight can be determined, and finally the renewable energy output forecast value, multi-energy load forecast value and energy price forecast value are obtained, and the hybrid channel and time attention mechanism algorithm is realized to guide the fusion of multiple features, which can provide accurate reference for the operation and planning theory of the comprehensive energy system.

[0046] In some implementations, the multi-dimensional management feature extraction unit includes a multi-column convolutional neural network unit and a long short-term memory network unit.

[0047] Figure 3 A schematic diagram of a workflow of a multi-dimensional management feature extraction unit provided in an embodiment of the present application, such as Figure 3 As shown, in an embodiment of the present application, the multi-dimensional management feature extraction unit includes a multi-column convolutional neural network unit and a long short-term memory network unit. The multi-column convolutional neural network (CNN) unit can effectively extract local features and spatial dependency features, while the long short-term memory network (LSTM) unit is good at capturing time series dependency features. Through the combination of these two network units, the multi-dimensional management features of renewable energy output information, multi-energy load information and energy price information can be comprehensively extracted, thereby providing basic data support for the optimized management of the integrated energy system.

[0048] When performing feature extraction, multi-column convolutional neural network units can extract the local features and spatial dependence features of renewable energy output information, multi-energy load information and energy price information respectively by performing convolution operations on the input data. These features can reflect the spatial variation patterns of renewable energy output information, multi-energy load information and energy price information.

[0049] When extracting features, the long short-term memory network unit can capture the time series dependency characteristics of renewable energy output information, multi-energy load information and energy price information through its special memory unit structure, thereby reflecting the temporal change patterns of this information.

[0050] In some implementations, the multi-dimensional management features include local features, spatial dependency features, and time series dependency features corresponding to renewable energy output information, multi-energy load information, and energy price information, respectively.

[0051] like Figure 3As shown, through the multi-dimensional management feature extraction unit, the local features, spatial dependence features and time series dependence features corresponding to the renewable energy output information, multi-energy load information and energy price information can be obtained, and then the subsequent feature fusion can be performed based on the local features, spatial dependence features and time series dependence features corresponding to the renewable energy output information, multi-energy load information and energy price information.

[0052] The beneficial effect of the above-mentioned implementation method is that the combination of multi-column convolutional neural network units and long short-term memory network units can realize the comprehensive extraction of multi-dimensional management characteristics in the integrated energy system by extracting and fusing different dimensional features of renewable energy output information, multi-energy load information and energy price information respectively.

[0053] In some implementations, the hybrid attention unit includes a channel attention unit and a temporal attention unit.

[0054] Figure 4 A schematic diagram of a workflow of a hybrid attention unit provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, the hybrid attention unit includes a channel attention unit and a time attention unit, and different types of attention weights can be processed respectively through these two attention units. The fusion management feature is obtained by fusing the local features, spatial dependence features and time series dependence features of renewable energy output information, multi-energy load information and energy price information according to the channel attention weight and time attention weight. This method weightedly fuses the management features through the attention mechanism of different dimensions, thereby improving the processing capability of multi-dimensional management features in the integrated energy system, and solving the problem of how to effectively integrate the management features and mutual coupling of renewable energy output information, multi-energy load information and energy price information in the integrated energy system.

[0055] Exemplarily, the hybrid attention unit can be implemented in the following manner: the channel attention unit is used to process the relative importance of different types of input data, and the time attention unit is used to process the dependency of the input data on the time series. Specifically, the channel attention unit can be implemented by a convolutional neural network (CNN), and the time attention unit can be implemented by a long short-term memory network (LSTM). The fusion management feature can be implemented by applying the channel attention weight and the time attention weight to the local features, the spatial dependency features, and the time series dependency features, respectively, and then fusing these weighted features.

[0056] Exemplarily, the fusion process may be implemented by weighted summation or other linear combination methods.

[0057] In some implementations, the fusion management features include fusion management features that are fused according to channel attention weights and time attention weights by respectively fusing local features, spatial dependency features, and time series dependency features corresponding to renewable energy output information, multi-energy load information, and energy price information.

[0058] like Figure 4 As shown, the fusion management features include fusion management features that are fused according to channel attention weights and time attention weights by respectively fusing local features, spatial dependency features, and time series dependency features corresponding to renewable energy output information, multi-energy load information, and energy price information, and then the final prediction value can be obtained based on the fusion management features.

[0059] The beneficial effect of the above implementation method is that the introduction of a hybrid attention unit can process different types of attention weights separately, thereby more accurately evaluating and integrating the management characteristics of renewable energy output information, multi-energy load information and energy price information, so that the integrated energy system can more effectively cope with the complex coupling relationship of multi-dimensional information and improve the prediction accuracy and management efficiency of the system. The method of the present application has higher flexibility and adaptability when processing multi-dimensional management characteristics, and can better support the optimal scheduling and operation of the integrated energy system.

[0060] Figure 5 A flow chart of a second IES load-energy price coupling prediction method based on hybrid attention provided in an embodiment of the present application is shown in FIG. Figure 5 As shown, the above method further includes S210 to S220, and S210 to S220 are described in detail below.

[0061] S210, obtaining seasonal parameters and meteorological parameters within the time period to be predicted, determining outdoor wind speed and outdoor light intensity according to the seasonal parameters and meteorological parameters, and determining outdoor temperature and indoor temperature according to the seasonal parameters and meteorological parameters.

[0062] In an embodiment of the present application, seasonal parameters and meteorological parameters can be obtained, and the outdoor wind speed, light intensity, outdoor temperature and indoor temperature can be determined based on the seasonal parameters and meteorological parameters. The outdoor wind speed and light intensity are used to calculate compensation values ​​for renewable energy output information and multi-energy load information. These compensation values ​​are used to correct the original renewable energy output information and multi-energy load information to improve the accuracy of the prediction.

[0063] Exemplarily, seasonal parameters and meteorological parameters can be obtained through existing meteorological data collection systems and seasonal data analysis systems. Specifically, real-time meteorological data, including temperature, wind speed, light intensity, etc., can be obtained through meteorological sensors installed at different locations, and seasonal analysis can be performed in combination with historical data to determine seasonal parameters.

[0064] Similarly, outdoor temperature and indoor temperature data can be determined by seasonal parameters and meteorological parameters, and the outdoor temperature and indoor temperature data can be used to calculate the compensation value of multi-energy load information. For example, outdoor temperature changes can affect the air-conditioning demand in the power load, and indoor temperature changes can affect the load demand of the heating system. The multi-energy load information can then be further corrected according to the compensation value of the multi-energy load information.

[0065] S220, determining the compensation value of renewable energy output information according to the outdoor wind speed and the outdoor light intensity, and correcting the renewable energy output information according to the compensation value of the renewable energy output information. Determining the compensation value of multi-energy load information according to the outdoor temperature and the indoor temperature, and correcting the multi-energy load information according to the compensation value of the multi-energy load information in the predicted time period.

[0066] After obtaining the outdoor wind speed and light intensity data, the outdoor wind speed and light intensity data can be converted into compensation values ​​of renewable energy output information through a calculation model, and then the renewable energy output information can be corrected according to the compensation values ​​of the renewable energy output information. For example, wind speed data can be used for prediction and correction of wind power generation, and light intensity data can be used for prediction and correction of solar power generation.

[0067] Exemplarily, the calculation model for converting outdoor wind speed and light intensity data into compensation values ​​of renewable energy output information may be a deep learning model, which may be trained by collecting outdoor wind speed, light intensity data and renewable energy output information.

[0068] Exemplarily, when the renewable energy output information is corrected according to the compensation value of the renewable energy output information, the compensation value of the renewable energy output information may be superimposed on the renewable energy output information to achieve correction of the renewable energy output information.

[0069] Similarly, the compensation value of the multi-energy load information can be determined according to the outdoor temperature and the indoor temperature, and the multi-energy load information can be corrected according to the compensation value of the multi-energy load information in the time period to be predicted.

[0070] Exemplarily, when the multi-energy load information is corrected according to the compensation value of the multi-energy load information in the time period to be predicted, the compensation value of the multi-energy load information in the time period to be predicted can be superimposed on the multi-energy load information to achieve correction of the multi-energy load information.

[0071] The beneficial effect of the above-mentioned implementation method is that by obtaining seasonal parameters and meteorological parameters, and correcting renewable energy output information and multi-energy load information according to seasonal parameters and meteorological parameters, the uncertainty of this information caused by seasonal factors and meteorological factors can be effectively reduced, thereby improving the management and scheduling efficiency of the integrated energy system, and in actual applications it can significantly reduce the fluctuations in energy supply and demand caused by meteorological changes, and improve the stability and economy of the system.

[0072] Figure 6 A flow chart of a third IES load-energy price coupling prediction method based on hybrid attention provided in an embodiment of the present application is shown in FIG. Figure 6 As shown, the above method also includes S310 to S320, and S310 to S320 are described in detail below.

[0073] S310: Determine the seasonal parameter variation range of the seasonal parameters and the seasonal parameter variation range of the meteorological parameters within the time period to be predicted, and determine the maximum variation range of the seasonal parameter variation range and the seasonal parameter variation range. Determine the product of the compensation value of the multi-energy load information and the maximum variation range as the compensation value threshold.

[0074] In the embodiment of the present application, by determining the variation range of seasonal parameters and meteorological parameters, the impact of environmental factors on renewable energy output can be more accurately predicted, and then the compensation value of renewable energy output can be adjusted according to the variation range of seasonal parameters and meteorological parameters.

[0075] During processing, the seasonal parameter change range and the meteorological parameter change range within the time period to be predicted can be determined, and the maximum change range can be determined. Specifically, based on the seasonal and meteorological data of the past few years, the seasonal parameter change range and the meteorological parameter change range within the time period to be predicted can be determined through statistical analysis methods, and the maximum value can be selected as the maximum change range.

[0076] After obtaining the maximum variation range, the product of the compensation value of the multi-energy load information and the maximum variation range can be used as the compensation value threshold, thereby ensuring that the compensation value of the output information will not be too large or too small when the environment changes drastically, thereby improving the accuracy of the prediction and the stability of the system.

[0077] S320: When the compensation value of the renewable energy output information is greater than or equal to the compensation value threshold, the compensation value threshold is used as the compensation value of the renewable energy output information. When the compensation value of the renewable energy output information is less than the compensation value threshold, the compensation value of the renewable energy output information is kept unchanged.

[0078] After determining the compensation value of the multi-energy load information through S210 to S220, the product of the compensation value of the multi-energy load information and the maximum change amplitude can be used as the compensation value threshold through a combination of real-time monitoring and historical load data. When the compensation value of the renewable energy output information is greater than or equal to the compensation value threshold, it means that the current compensation value of the renewable energy output information is too large, and the compensation value threshold can be used as the compensation value of the renewable energy output information; when the compensation value of the renewable energy output information is less than the compensation value threshold, it means that the current compensation value of the renewable energy output information is relatively appropriate, and the compensation value of the renewable energy output information can be kept unchanged.

[0079] Exemplarily, when the compensation value of the renewable energy output information is compared with the compensation value threshold, corresponding logic processing can be implemented through conditional judgment.

[0080] The beneficial effect of the above-mentioned implementation method is that by introducing the variation range of seasonal parameters and meteorological parameters and combining the compensation value of multi-energy load information, a method for dynamically adjusting the compensation value of renewable energy output information is proposed, which can effectively cope with the impact of environmental changes on the system, improve the accuracy of prediction, ensure the stable operation of the system under different environmental conditions, and avoid excessive errors in the system.

[0081] The beneficial effect of the above implementation method is that it solves the problem of how to effectively correct the compensation value of renewable energy output information in the integrated energy system, and can ensure the stable operation and accurate prediction of the system under different environmental conditions.

[0082] In some implementations, the above method further includes S410 to S420, and S410 to S420 are described in detail below.

[0083] S410: Obtain supply and demand relationship information of traditional energy in a time period to be predicted, and determine a compensation value of energy price information according to the supply and demand relationship information of traditional energy.

[0084] In the embodiment of the present application, the compensation value of energy price information can be determined by obtaining the supply and demand relationship information of traditional energy in the time period to be predicted, and the energy price information can be corrected to reflect the impact of the supply and demand relationship of traditional energy on the energy price information. Obtaining the supply and demand relationship information of traditional energy can provide an accurate grasp of the energy market situation, and determining the compensation value helps to adjust the energy price information so that it more accurately reflects the real market situation.

[0085] For example, the traditional energy may be coal, natural gas or other traditional energy, and the compensation value of the energy price information in the integrated energy management system can be predicted horizontally through the supply and demand relationship information of the traditional energy.

[0086] Exemplarily, the supply and demand relationship information of traditional energy can be obtained in a variety of ways, such as through market transaction data, energy production and consumption data, etc., and then the compensation value of energy price information can be determined based on the supply and demand relationship information of traditional energy. The compensation value of energy price information can be calculated based on historical data and prediction models.

[0087] Exemplarily, the calculation method of the compensation value of the energy price information may include statistical analysis, machine learning algorithms, etc. to ensure the accuracy and reliability of the compensation value.

[0088] S420: Correct the energy price information according to the compensation value of the energy price information.

[0089] During processing, the energy price information can be corrected according to the compensation value of the energy price information. The corrected energy price information can further optimize the operation and scheduling of the integrated energy system through S110 to S130, thereby improving the economic benefits and stability of the system.

[0090] The beneficial effect of the above implementation method is that it can effectively solve the problem of the impact of traditional energy supply and demand relationships on energy price information, thereby improving the management and scheduling efficiency of the integrated energy system.

[0091] The beneficial effects of the above-mentioned implementation method are that it can effectively solve the problem of the horizontal impact of traditional energy supply and demand relationships on energy price information, can provide a more accurate and efficient method for correcting energy price information, can better reflect the real market situation, improve the management and scheduling efficiency of the integrated energy system, and enable this application to have significant advantages in improving the economic benefits and stability of the energy system.

[0092] In some implementations, the above method further includes S510 to S520, and S510 to S520 are described in detail below.

[0093] S510: Obtain supply and demand relationship information of traditional energy and regional carbon emission adjustment information within a time period to be predicted, and determine a compensation value of energy price information according to the supply and demand relationship information of traditional energy and the regional carbon emission adjustment information.

[0094] In an embodiment of the present application, it is also possible to obtain information on the supply and demand relationship of traditional energy and regional carbon emission adjustment information. The regional carbon emission adjustment information can affect the energy structure of the region, and then the compensation value of the energy price information can be determined through the information on the supply and demand relationship of traditional energy and the regional carbon emission adjustment information, which is used to further correct the energy price information.

[0095] Exemplarily, to obtain information on the supply and demand relationship of traditional energy within a time period to be predicted, the supply and demand data within the time period may be obtained through a data collection system of the traditional energy market, including but not limited to market transaction data, production data, and consumption data.

[0096] For example, regional carbon emission adjustment information can be determined by analyzing regional carbon emission management regulations, including but not limited to indicator data such as carbon emissions and carbon emission intensity.

[0097] Exemplarily, the compensation value of energy price information can be determined by regression analysis, time series analysis or a prediction model based on a neural network. Specifically, a long short-term memory network (LSTM) model can be used to train historical data to predict future energy price compensation values.

[0098] S520: Correct the energy price information according to the compensation value of the energy price information.

[0099] After obtaining the compensation value of the energy price information, the energy price information can be corrected according to the compensation value of the energy price information. By compensating and correcting the energy price information, the market supply and demand relationship and the impact of carbon emission policies can be more accurately reflected.

[0100] The beneficial effect of the above-mentioned implementation method is that by considering the changes in the supply and demand relationship of traditional energy and the regional carbon emission adjustment information, a more accurate energy price compensation value is provided, thereby making more precise corrections to the energy price information, which can effectively solve the problem of accurate correction of energy price information and improve the management and scheduling efficiency of the integrated energy system.

[0101] The beneficial effect of the above-mentioned implementation method is that it can better reflect market dynamics and changes in carbon emission policies, improve the accuracy of energy price information, thereby helping to optimize the management and scheduling of integrated energy systems and improve the economy and reliability of system operations.

[0102] In some implementations, the above method further includes: determining a compensation value for the supply and demand relationship information of traditional energy based on seasonal parameters and meteorological parameters, and adjusting the supply and demand relationship information of traditional energy based on the compensation value for the supply and demand relationship information of traditional energy.

[0103] During processing, the compensation value of the supply and demand relationship information of traditional energy can be determined by seasonal parameters and meteorological parameters, and the supply and demand relationship information of traditional energy can be adjusted using the compensation value, which can improve the accuracy of the supply and demand relationship information of traditional energy and facilitate better management of the integrated energy system.

[0104] For example, seasonal parameters may include specific parameters of different seasons such as spring, summer, autumn and winter, and meteorological parameters may include temperature, humidity, wind speed, precipitation, etc. The compensation value of the traditional energy supply and demand relationship information is determined by comprehensive analysis and calculation of these parameters. For example, in high temperature weather in summer, the demand for traditional energy may increase. By analyzing the meteorological parameters, the corresponding compensation value can be determined to adjust the supply and demand relationship information and ensure the stable operation of the system.

[0105] For example, historical data and real-time monitoring data may be combined to dynamically adjust and optimize seasonal parameters and meteorological parameters, thereby further improving the accuracy of supply and demand relationship information.

[0106] The beneficial effect of the above-mentioned implementation method is that by introducing seasonal parameters and meteorological parameters to dynamically adjust the supply and demand relationship information of traditional energy, the problem of deviations that may occur in the supply and demand relationship information of traditional energy under different seasons and meteorological conditions is solved, so that the integrated energy system can accurately reflect the supply and demand relationship under various environmental conditions, thereby achieving more efficient and optimized energy management.

[0107] An embodiment of the present application also provides an IES load-energy price coupling prediction system based on hybrid attention, comprising a unit for executing any of the methods described above.

[0108] Figure 7 A logical structure diagram of an IES load-energy price coupling prediction system based on hybrid attention provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, the system 1 of this embodiment includes a processing unit 11, a storage unit 12 and a transceiver unit 13. The processing unit 11 is used to process data, the storage unit 12 is used to store data, and the transceiver unit 13 is used to send and receive data. The processing unit 11, the storage unit 12 and the transceiver unit 13 cooperate with each other to implement the above method. The beneficial effects of the embodiment of the present application have been described in the above method and will not be repeated here.

[0109] An embodiment of the present application also provides an IES load-energy price coupling prediction system based on hybrid attention, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, it implements any of the methods described above.

[0110] Figure 8 A schematic diagram of the physical structure of an IES load-energy price coupling prediction system based on hybrid attention provided in an embodiment of the present application is shown in FIG. Figure 8 As shown, the system 2 of this embodiment includes: at least one processor 20 ( Figure 8Only one processor 20 is shown in the figure), a memory 21, and a computer program 22 stored in the memory 21 and executable on the at least one processor 20. When the processor 20 executes the computer program 22, the steps in any of the above-mentioned method embodiments are implemented. The beneficial effects of the embodiments of the present application have been described in the above-mentioned methods and will not be repeated here.

[0111] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0112] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0113] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0114] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0115] If the integrated unit is implemented in the form of 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 present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0116] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0117] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0118] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0119] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0120] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An IES load-energy price coupling prediction method based on hybrid attention, characterized in that: The method comprises: According to the comprehensive energy management information, a multi-dimensional management feature is determined by a multi-dimensional management feature extraction unit; wherein the comprehensive energy management information includes renewable energy output information, multi-energy load information and energy price information in time series; According to the multi-dimensional management features, the fusion management features of the multi-dimensional management features under the channel attention weight and the time attention weight are determined through the mixed attention unit; According to the fusion management characteristics, the renewable energy output forecast value, multi-energy load forecast value and energy price forecast value are determined through the fusion output unit.

2. The method according to claim 1, characterized in that The multi-dimensional management feature extraction unit includes a multi-column convolutional neural network unit and a long short-term memory network unit; The multi-dimensional management features include local features, spatial dependence features and time series dependence features corresponding to renewable energy output information, multi-energy load information and energy price information respectively.

3. The method according to claim 2, characterized in that The hybrid attention unit includes channel attention unit and temporal attention unit; The fusion management features include the fusion management features that are fused according to the channel attention weight and time attention weight respectively by the local features, spatial dependence features and time series dependence features corresponding to the renewable energy output information, multi-energy load information and energy price information.

4. The method according to claim 3, characterized in that The method further comprises: Obtain seasonal parameters and meteorological parameters within the time period to be predicted, determine outdoor wind speed and outdoor light intensity according to the seasonal parameters and meteorological parameters, and determine outdoor temperature and indoor temperature according to the seasonal parameters and meteorological parameters; The compensation value of the renewable energy output information is determined according to the outdoor wind speed and the outdoor light intensity, and the renewable energy output information is corrected according to the compensation value of the renewable energy output information; the compensation value of the multi-energy load information is determined according to the outdoor temperature and the indoor temperature, and the multi-energy load information is corrected according to the compensation value of the multi-energy load information in the predicted time period.

5. The method according to claim 4, characterized in that The method further comprises: Determine the seasonal parameter variation range of the seasonal parameters and the seasonal parameter variation range of the meteorological parameters within the time period to be predicted, and determine the seasonal parameter variation range and the maximum variation range among the seasonal parameter variation ranges; determine the product of the compensation value of the multi-energy load information and the maximum variation range as the compensation value threshold; When the compensation value of the renewable energy output information is greater than or equal to the compensation value threshold, the compensation value threshold is used as the compensation value of the renewable energy output information; when the compensation value of the renewable energy output information is less than the compensation value threshold, the compensation value of the renewable energy output information is kept unchanged.

6. The method according to claim 5, characterized in that The method further comprises: Obtaining information on the supply and demand relationship of traditional energy within the forecast period, and determining the compensation value of energy price information based on the information on the supply and demand relationship of traditional energy; The energy price information is corrected according to the compensation value of the energy price information.

7. An IES load-energy price coupling prediction system based on hybrid attention, characterized in that: Comprising means for performing the method according to any one of claims 1 to 6.

8. An IES load-energy price coupling prediction system based on hybrid attention, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images