A power supply service strategy optimization method based on enterprise power supply service portrait

Abstract

The present invention relates to a power supply service strategy optimization method based on an enterprise power supply service profile, comprising the following steps: collecting and pre-processing the enterprise's historical load data, historical operation data and enterprise equipment data; constructing an enterprise load forecasting model, and predicting the enterprise's future load data based on the enterprise's historical load data; calculating the enterprise's production intensity characteristics based on the enterprise's historical operation data; extracting enterprise equipment and load correlation characteristics based on the enterprise's equipment data and historical load data, and correcting the enterprise's future load data according to the correlation characteristics; identifying the enterprise's load pattern according to the corrected enterprise's future load data; constructing the enterprise power supply service profile based on the enterprise's production intensity characteristics, equipment and load correlation characteristics, and load pattern; constructing an enterprise electricity demand elasticity response model to calculate the enterprise's electricity elasticity demand curve, and optimizing the power supply service strategy according to the enterprise's electricity elasticity demand curve.

Description

Technical Field

[0001] The present invention relates to a power supply service strategy optimization method based on an enterprise power supply service portrait, and belongs to the technical field of energy management. Background Art

[0002] In the fields of power system planning and enterprise power management, load forecasting and power supply service strategy optimization have always been key to achieving efficient, safe, and economical power supply. Traditional methods mainly include statistical methods and time series models based on historical data, such as the autoregressive moving average model (ARMA), exponential smoothing, and simple regression analysis. These methods generally have certain predictive capabilities when the data volume is small. However, with the increasing complexity of enterprise production, equipment operation, and market environment, traditional technologies have many limitations:

[0003] Existing technologies often focus solely on using historical enterprise load data for load forecasting, while ignoring the role of multi-dimensional data such as enterprise production intensity, order fulfillment, and equipment operating conditions. The use of a single data source or feature limits the model's ability to capture nonlinear and multimodal changes.

[0004] Traditional load forecasting models rely primarily on simple statistical models or shallow neural networks, which struggle to capture the long-term dependencies and complex nonlinear characteristics of enterprise electricity consumption data. This is especially true when faced with time-series fluctuations in load data, volatile production rhythms, and changes in equipment status. Traditional models are prone to underfitting or large prediction errors.

[0005] Previous power supply service strategies mainly focused on static cost analysis, without fully considering the company's response flexibility to price fluctuations. There was a lack of a comprehensive model that introduced the synergistic effects of multiple factors such as the company's actual production, equipment operation, and market electricity prices into the decision-making process, making it difficult for power supply service strategies to cope with complex market environments and rapidly changing electricity demand. Summary of the Invention

[0006] In order to solve the above problems existing in the prior art, the present invention proposes a power supply service strategy optimization method based on enterprise power supply service portrait.

[0007] The technical solutions of the present invention are as follows:

[0008] In one aspect, the present invention provides a method for optimizing a power supply service strategy based on an enterprise power supply service profile, comprising the following steps:

[0009] Collect historical load data, historical operation data and enterprise equipment data, and pre-process the historical load data, historical operation data and enterprise equipment data;

[0010] Build an enterprise load forecasting model to predict the enterprise's future load data based on the enterprise's historical load data;

[0011] Calculate the production intensity characteristics of the enterprise based on its historical operating data;

[0012] Extract the correlation characteristics between enterprise equipment and load based on enterprise equipment data and historical load data, and revise the enterprise's future load data based on the correlation characteristics;

[0013] Identify the load pattern of the enterprise based on the revised future load data of the enterprise;

[0014] Construct an enterprise power supply service profile based on the enterprise's production intensity characteristics, equipment and load correlation characteristics, and load patterns;

[0015] Construct an enterprise electricity demand elastic response model, input the enterprise power supply service portrait and the corrected future load data into the enterprise electricity demand elastic response model to obtain the enterprise electricity elastic demand curve, and optimize the power supply service strategy according to the enterprise electricity elastic demand curve.

[0016] Preferably, the enterprise load forecasting model is constructed based on a deep hybrid attention temporal network model, including a short-term feature extraction layer, a multi-head self-attention mechanism layer, and a multi-layer perceptron layer;

[0017] The load data of the enterprise at different historical moments are normalized to construct the input sample set, as shown in the following formula:

[0018] ;

[0019] in: Indicates to The input sample set at time t; express Time-normalized enterprise load data; Indicates the length of the input sample set; Represents feature dimension; represents the field of real numbers;

[0020] The short-term feature extraction layer is constructed based on a convolutional neural network. The input sample set is input into the short-term feature extraction layer to extract short-term features, as shown in the following formula:

[0021] ;

[0022] in: express The output of the short-term feature extraction layer; represents the activation function; Indicates the number of convolutional layers in the short-term feature extraction layer; Indicates the The weight matrix of the convolutional layer; Indicates the The bias of the convolutional layer;

[0023] The short-term features are concatenated and input into the multi-head self-attention mechanism layer to extract long-term features, as shown in the following formula:

[0024] ;

[0025] ;

[0026] in: Represents the long-term features extracted by the multi-head self-attention layer; 、 、 Represent the query vector, key vector, and value vector of the concatenated short-term features respectively; Represents a splicing operation; Indicates the The output of an attention head; represents the total number of attention heads; Represents the output linear projection weight matrix of multi-head attention; represents the normalization function; 、 、 Respectively represent The parameter weight matrix of each attention head corresponding to the query vector, key vector, and value vector; Represents a transpose operation; Indicates the The dimension of the attention heads;

[0027] The long-term features are then input into the multi-layer perceptron layer map to generate the load forecast results.

[0028] Preferably, the calculation formula for the production intensity characteristic of the enterprise is:

[0029] ;

[0030] in: express The production intensity characteristics of the enterprise at each moment; represents the normalization factor; express The actual production capacity of the enterprise at any moment; Indicates the enterprise's historical maximum production capacity; express The urgency of the company's order fulfillment at all times; express The amount of new orders for the company at any given moment; represents the nonlinear control parameter; 、 、 represents the characteristic weight coefficient of production intensity; Represents a natural constant.

[0031] Preferably, the correlation characteristics between enterprise equipment and load are extracted based on enterprise equipment data and historical load data as shown in the following formula:

[0032] ;

[0033] in: express Moment Enterprise Equipment Correlation characteristics with the company's historical load; Indicates from a historical interval that looks back at every moment; Indicates the maximum lookback window length; Represents enterprise equipment The set of spatial neighborhood devices; Represents enterprise equipment The first device in its spatial neighborhood The spatial weight of each device; Represents enterprise equipment The first device in the spatial neighborhood of devices; Represents the historical time weight attenuation coefficient; express Time equipment Historical load data; express The overall historical load data of the enterprise at all times; represents the correlation function;

[0034] The enterprise's future load data is corrected based on the correlation characteristics, as shown in the following formula:

[0035] ;

[0036] in: express The enterprise's future load data after constant revision; express The enterprise's future load data at all times; represents the forecast span time; Represents enterprise equipment Importance weight of express Moment Enterprise Equipment Correlation characteristics with the enterprise's historical load; express Moment Enterprise Equipment load data.

[0037] Preferably, the specific steps of identifying the load pattern of the enterprise based on the corrected future load data of the enterprise are:

[0038] Construct different types of typical load pattern time series of the same length;

[0039] The improved dynamic time warping algorithm is used to align the enterprise's future load data with any typical load pattern time series, as shown in the following formula:

[0040] ;

[0041] ;

[0042] in: Represents the output of the improved dynamic time warping algorithm, which is to transform the enterprise's future load data into Time series with typical load patterns Perform alignment; Indicates that the company's future load data Time series with typical load patterns A collection of alignments between ; express The data points; express The data points; represents the time weight function; represents the time offset penalty factor; express and the distance between them;

[0043] Based on the aligned enterprise future load data, the Gaussian mixture model is used to identify the load pattern that is closest to it, as shown in the following formula:

[0044] ;

[0045] ;

[0046] in: Indicates the aligned enterprise future load data; represents the parameter set of the Gaussian mixture model, ; Indicates the number of typical load patterns; Indicates that given a set of parameters Under the conditions, Probability density of occurrence; Indicates the The prior probability of a load pattern; Indicates that based on The determinant of the covariance matrix constructed from the typical load pattern time series corresponding to each load pattern; Indicates the The mean of the typical load pattern time series corresponding to each load pattern; express The load pattern corresponding to the enterprise's future load data at that moment; Indicates that the aligned enterprise future load data is Data points at a moment in time; express The load pattern with the highest probability density The corresponding parameter set of the Gaussian mixture model under .

[0047] Preferably, an enterprise electricity demand elasticity response model is constructed, and the enterprise power supply service profile is input into the enterprise electricity demand elasticity response model to obtain the enterprise electricity demand elasticity curve, which is specifically shown in the following formula:

[0048] ;

[0049] in: express The elasticity of electricity demand of enterprises at all times; Indicates the total number of time-of-use electricity price tiers; Indicates the The price elasticity coefficient of each time-of-use electricity price ladder; Indicates the The electricity price of each time-of-use electricity price ladder; Indicates the basic electricity price; represents the service profile impact function; express A portrait of the enterprise's power supply services at all times.

[0050] Preferably, the power supply service strategy is optimized according to the enterprise's electricity elasticity demand curve, as shown in the following formula:

[0051] ;

[0052] in: Indicates the company's optimized power supply service strategy; express The electricity price at the time; represents the balance coefficient; Represents the variance of the enterprise's electricity demand elasticity.

[0053] In another aspect, the present invention further provides a power supply service strategy optimization system based on enterprise power supply service portrait, comprising a data acquisition module, an enterprise load forecasting module, a production intensity feature generation module, a correlation feature production module, a load pattern recognition module, an enterprise power supply service portrait construction module, and a power supply service strategy optimization module;

[0054] The data acquisition module is used to collect the enterprise's historical load data, historical operation data and enterprise equipment data, and pre-process the historical load data, historical operation data and enterprise equipment data;

[0055] The enterprise load forecasting module is used to build an enterprise load forecasting model and predict the enterprise's future load data based on the enterprise's historical load data;

[0056] The production intensity feature generation module is used to calculate the production intensity feature of the enterprise based on the enterprise's historical operating data;

[0057] The correlation feature production module is used to extract the correlation features between enterprise equipment and load based on enterprise equipment data and historical load data, and to modify the enterprise's future load data according to the correlation features;

[0058] The load pattern identification module is used to identify the load pattern of the enterprise based on the corrected future load data of the enterprise;

[0059] The enterprise power supply service portrait construction module is used to construct the enterprise power supply service portrait based on the enterprise's production intensity characteristics, equipment and load correlation characteristics, and load mode;

[0060] The power supply service strategy optimization module is used to construct an enterprise electricity demand elastic response model, input the enterprise power supply service portrait and the corrected future load data into the enterprise electricity demand elastic response model to obtain the enterprise electricity elastic demand curve, and optimize the power supply service strategy according to the enterprise electricity elastic demand curve.

[0061] On the other hand, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method of the present invention when executing the program.

[0062] In another aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the method of the present invention when executed by a processor.

[0063] The present invention has the following beneficial effects:

[0064] 1. The present invention constructs a comprehensive enterprise power supply service portrait by collecting the enterprise's historical load data, historical operation data and enterprise equipment data. This portrait integrates the production intensity characteristics, the correlation between equipment and load, and the typical load pattern. It can fully reflect the actual situation of the enterprise from production to power supply, and improve the adaptability and accuracy of load forecasting and power consumption response.

[0065] 2. This paper proposes a load forecasting model based on a deep hybrid attention time series network. By introducing a convolutional neural network for short-term feature extraction, a multi-head self-attention mechanism to capture long-term dependencies, and a multi-layer perceptron for mapping, the model's ability to model complex time series features and nonlinear relationships is greatly improved, ensuring the robustness and accuracy of the prediction results.

[0066] 3. This invention constructs an electricity demand elasticity response model, combining enterprise power supply service profiles with forecasted load data. Taking into account the impact of electricity prices, price elasticity coefficients, and comprehensive enterprise characteristics, this model minimizes costs while ensuring stable power consumption through elastic demand curve analysis. By combining this with the power supply service strategy to optimize the objective function, this model reduces power supply costs while further balancing power load volatility, thereby improving the economic efficiency and stability of the power supply system. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 Flow chart of the method of the present invention. DETAILED DESCRIPTION

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

[0069] It should be understood that the step numbers used herein are only for convenience of description and are not intended to limit the order in which the steps are to be executed.

[0070] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0071] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0072] The term "and / or" refers to and includes any and all possible combinations of one or more of the associated listed items.

[0073] Example 1:

[0074] See also Figure 1 , a power supply service strategy optimization method based on enterprise power supply service portrait, comprising the following steps:

[0075] Collect historical load data, historical operation data, and enterprise equipment data, and pre-process the historical load data, historical operation data, and enterprise equipment data, including missing value interpolation, outlier removal, and normalization;

[0076] Build an enterprise load forecasting model to predict the enterprise's future load data based on the enterprise's historical load data;

[0077] Calculate the production intensity characteristics of the enterprise based on its historical operating data;

[0078] Extract the correlation characteristics between enterprise equipment and load based on enterprise equipment data and historical load data, and revise the enterprise's future load data based on the correlation characteristics;

[0079] Identify the load pattern of the enterprise based on the revised future load data of the enterprise;

[0080] Construct an enterprise power supply service profile based on the enterprise's production intensity characteristics, equipment and load correlation characteristics, and load patterns;

[0081] Construct an enterprise electricity demand elastic response model, input the enterprise power supply service portrait and the corrected future load data into the enterprise electricity demand elastic response model to obtain the enterprise electricity elastic demand curve, and optimize the power supply service strategy according to the enterprise electricity elastic demand curve.

[0082] As a preferred implementation of this embodiment, the enterprise load forecasting model is constructed based on a deep hybrid attention temporal network model, including a short-term feature extraction layer, a multi-head self-attention mechanism layer, and a multi-layer perceptron layer;

[0083] The load data of the enterprise at different historical moments are normalized to construct the input sample set, as shown in the following formula:

[0084] ;

[0085] in: Indicates to The input sample set at time t; express Time-normalized enterprise load data; Indicates the length of the input sample set; Represents feature dimension; represents the field of real numbers;

[0086] The short-term feature extraction layer is constructed based on a convolutional neural network. The input sample set is input into the short-term feature extraction layer to extract short-term features, as shown in the following formula:

[0087] ;

[0088] in: express The output of the short-term feature extraction layer; represents the activation function; Indicates the number of convolutional layers in the short-term feature extraction layer; Indicates the The weight matrix of the convolutional layer; Indicates the The bias of the convolutional layer;

[0089] The short-term features are concatenated and input into the multi-head self-attention mechanism layer to extract long-term features, as shown in the following formula:

[0090] ;

[0091] ;

[0092] in: Represents the long-term features extracted by the multi-head self-attention layer; 、 、 Represent the query vector, key vector, and value vector of the concatenated short-term features respectively; Represents a splicing operation; Indicates the The output of an attention head; Indicates the total number of attention heads (usually 8, 12, 16, etc.); Represents the linear projection weight matrix of the multi-head attention output, which is used to transform the concatenated head output to the desired dimension; represents the normalization function; 、 、 Respectively represent The parameter weight matrix of each attention head corresponding to the query vector, key vector, and value vector; Represents a transpose operation; Indicates the The dimension of the attention heads;

[0093] The long-term features are then input into the multi-layer perceptron layer map to generate the load forecast results.

[0094] As a preferred implementation of this embodiment, the calculation formula for the production intensity characteristic of the enterprise is:

[0095] ;

[0096] in: express The production intensity characteristics of the enterprise at each moment; represents the normalization factor; express The actual production capacity of the enterprise at any moment; Indicates the enterprise's historical maximum production capacity; express The urgency of the company's order fulfillment at all times; express The amount of new orders for the company at any given moment; represents the nonlinear control parameter; 、 、 represents the characteristic weight coefficient of production intensity; Represents a natural constant.

[0097] As a preferred implementation of this embodiment, the correlation characteristics between enterprise equipment and load are extracted based on enterprise equipment data and historical load data, as shown in the following formula:

[0098] ;

[0099] in: express Moment Enterprise Equipment Correlation characteristics with the enterprise's historical load; Indicates from a historical interval that looks back at every moment; Indicates the maximum lookback window length; Represents enterprise equipment The set of spatial neighborhood devices; Represents enterprise equipment The first device in its spatial neighborhood The spatial weight of each device is usually calculated based on the physical distance between devices or the similarity of device functions, reflecting the strength of spatial association; Represents enterprise equipment The first device in the spatial neighborhood of devices; Represents the historical time weight attenuation coefficient; express Time equipment Historical load data; express The overall historical load data of the enterprise at all times; represents the correlation function;

[0100] The correlation function is specifically shown in the following formula:

[0101] ;

[0102] ;

[0103] in: Indicates the maximum length of the short-term dynamic window, which controls the depth of tracing the dynamic change characteristics of the load; Indicates the length is The time decay weight function of the short-term dynamic window, , represents the time weight decay rate; Represents enterprise equipment exist Historical load data at each moment; Indicates The overall historical load data of the enterprise at the moment; represents the nonlinear coupling correlation function, where , ; Indicates the length is Enterprise equipment within the short-term dynamic window The average value of historical load data; Indicates the length is The average of the overall historical load data of the enterprise within the short-term dynamic window; Indicates the length is Enterprise equipment within the short-term dynamic window Standard deviation of historical load data; Indicates the length is The standard deviation of the overall historical load data of the enterprise within the short-term dynamic window; represents a constant;

[0104] The enterprise's future load data is corrected based on the correlation characteristics, as shown in the following formula:

[0105] ;

[0106] in: express The enterprise's future load data after constant revision; express The enterprise's future load data at all times; represents the forecast span time; Represents enterprise equipment Importance weight of express Moment Enterprise Equipment Correlation characteristics with the enterprise's historical load; express Moment Enterprise Equipment load data.

[0107] As a preferred implementation of this embodiment, the specific steps of identifying the load pattern of the enterprise based on the corrected future load data of the enterprise are as follows:

[0108] Construct different types of typical load pattern time series of the same length;

[0109] The improved dynamic time warping algorithm is used to align the enterprise's future load data with any typical load pattern time series, as shown in the following formula:

[0110] ;

[0111] ;

[0112] in: Represents the output of the improved dynamic time warping algorithm, which is to transform the enterprise's future load data into Time series with typical load patterns Perform alignment; Indicates that the company's future load data Time series with typical load patterns The set of alignments between two time series data, that is, all alignments between two time series data that satisfy certain constraints (boundary conditions, continuity and monotonicity);

[0113] The boundary conditions indicate that the path must start from the starting point of both sequences and eventually reach the end point of both sequences;

[0114] Continuity means that the index changes between adjacent points in the path are limited. Usually the allowed changes are: moving forward one grid or moving diagonally;

[0115] Monotonicity means that the indexes in the path must be strictly monotonically increasing, that is, there can be no rollback, ensuring that the time sequence of the time series is not disrupted;

[0116] express The data points; express The data points; represents the time weight function; represents the time offset penalty factor; express and the distance between them;

[0117] Based on the aligned enterprise future load data, the Gaussian mixture model is used to identify the load pattern that is closest to it, as shown in the following formula:

[0118] ;

[0119] ;

[0120] in: Indicates the aligned enterprise future load data; represents the parameter set of the Gaussian mixture model, ; Indicates the number of typical load patterns; Indicates that given a set of parameters Under the conditions, Probability density of occurrence; Indicates the The prior probability of the load pattern reflects the The proportion of each load mode in the total data; Indicates that based on The determinant of the covariance matrix constructed from the typical load pattern time series corresponding to each load pattern; Indicates the The mean of the typical load pattern time series corresponding to each load pattern; express The load pattern corresponding to the enterprise's future load data at that moment; Indicates that the aligned enterprise future load data is Data points at a moment in time; express The load pattern with the highest probability density The corresponding parameter set of the Gaussian mixture model under; Represents a portion of the normalizing constant in the normal distribution density function;

[0121] The load mode specifically includes:

[0122] 1. Stable load mode

[0123] Its characteristics are relatively stable changes in electricity consumption, small fluctuations, and the overall load level remains basically stable.

[0124] 2. Peak-trough alternating pattern

[0125] Its characteristic is that electricity demand has obvious periodic fluctuations, which is usually manifested as a sharp increase in load during certain periods (such as daytime and production peak periods), and a significant decrease in load at night or during rest periods.

[0126] 3. Stepped load mode

[0127] Its characteristic is that the load changes in stages with the different stages of the production process or equipment status, and may cause obvious jumps due to equipment start-up and shutdown, process conversion, etc.

[0128] 4. Burst load mode

[0129] Its characteristic is that under specific events or abnormal circumstances (such as equipment failure, emergency dispatch), the load will rise or fall sharply in a short period of time, manifesting as sudden fluctuations.

[0130] 5. Increasing or decreasing trend pattern

[0131] Its characteristic is that during the period of expansion or reduction of production, the overall load of the enterprise shows a trend of gradual increase or decrease.

[0132] 6. Seasonal or cyclical change patterns

[0133] Its characteristic is that the load is affected by seasons, climate or market demand cycles, and shows a long-term fluctuation trend.

[0134] As a preferred implementation of this embodiment, an enterprise electricity demand elasticity response model is constructed, and the enterprise power supply service profile is input into the enterprise electricity demand elasticity response model to obtain the enterprise electricity demand elasticity curve, which is specifically shown in the following formula:

[0135] ;

[0136] in: express The elasticity of electricity demand of enterprises at all times; Indicates the total number of time-of-use electricity price tiers; Indicates the The price elasticity coefficient of each time-of-use electricity price ladder; Indicates the The electricity price of each time-of-use electricity price ladder; Indicates the basic electricity price; represents the service profile impact function; express A portrait of the enterprise's power supply services at all times;

[0137] The service profile impact function is specifically shown in the following formula:

[0138] ;

[0139] in: Indicates the The weight vector of the time-of-use electricity price ladder; Indicates the The bias of the time-of-use electricity price ladder; represents the Sigmoid activation function;

[0140] The enterprise power supply service portrait is specifically shown as follows:

[0141] ;

[0142] As a preferred implementation of this embodiment, the power supply service strategy is optimized according to the enterprise electricity elasticity demand curve, as shown in the following formula:

[0143] ;

[0144] in: Indicates the company's optimized power supply service strategy; express The electricity price at the time; Represents the balance coefficient, which is used to balance the trade-off between cost minimization and load stability. When it is larger, the optimization will pay more attention to the stability of the load (reducing fluctuations). When it is smaller, the main focus is on reducing the cost of power supply; represents the variance of the enterprise's electricity demand elasticity;

[0145] By minimizing To find the optimal power supply strategy, so as to achieve the goal of lowest cost or optimal load stability on the basis of meeting electricity demand. The actual optimization variables in the overall decision-making include: the company's active load management strategy (such as load peak shaving and peak shifting measures), the start-stop and charging and discharging strategies of energy storage equipment, and the reasonable adjustment of load timing in the production process.

[0146] Example 2:

[0147] A power supply service strategy optimization system based on enterprise power supply service portraits, including a data acquisition module, an enterprise load forecasting module, a production intensity feature generation module, a correlation feature generation module, a load pattern recognition module, an enterprise power supply service portrait construction module, and a power supply service strategy optimization module;

[0148] The data acquisition module is used to collect the enterprise's historical load data, historical operation data and enterprise equipment data, and pre-process the historical load data, historical operation data and enterprise equipment data;

[0149] The enterprise load forecasting module is used to build an enterprise load forecasting model and predict the enterprise's future load data based on the enterprise's historical load data;

[0150] The production intensity feature generation module is used to calculate the production intensity feature of the enterprise based on the enterprise's historical operating data;

[0151] The correlation feature production module is used to extract the correlation features between enterprise equipment and load based on enterprise equipment data and historical load data, and to modify the enterprise's future load data according to the correlation features;

[0152] The load pattern identification module is used to identify the load pattern of the enterprise based on the corrected future load data of the enterprise;

[0153] The enterprise power supply service portrait construction module is used to construct the enterprise power supply service portrait based on the enterprise's production intensity characteristics, equipment and load correlation characteristics, and load mode;

[0154] The power supply service strategy optimization module is used to construct an enterprise electricity demand elastic response model, input the enterprise power supply service portrait and the corrected future load data into the enterprise electricity demand elastic response model to obtain the enterprise electricity elastic demand curve, and optimize the power supply service strategy according to the enterprise electricity elastic demand curve.

[0155] This system is used to implement the method in Example 1 and will not be described in detail here.

[0156] Example 3:

[0157] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method described in any embodiment of the present invention is implemented.

[0158] Example 4:

[0159] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method described in any embodiment of the present invention is implemented.

[0160] In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can represent: a, b, c, a and b, a and c, b and c or a and b and c, where a, b, c can be single or multiple.

[0161] Those skilled in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented using a combination of electronic hardware, 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. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0162] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0163] In the several embodiments provided in this application, if any function 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 technical solution of this application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of this application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), magnetic disk or optical disk, and other media that can store program code.

[0164] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention's description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A power supply service strategy optimization method based on enterprise power supply service portrait, characterized in that: The following steps are involved: Collect historical load data, historical operation data and enterprise equipment data, and pre-process the historical load data, historical operation data and enterprise equipment data; Build an enterprise load forecasting model to predict the enterprise's future load data based on the enterprise's historical load data; The production intensity characteristics of an enterprise are calculated based on the enterprise's historical operating data. The calculation formula for the production intensity characteristics of the enterprise is: ； in: express The production intensity characteristics of the enterprise at each moment; represents the normalization factor; express The actual production capacity of the enterprise at any moment; Indicates the historical maximum production capacity of the enterprise; express The urgency of the company's order fulfillment at all times; express The amount of new orders for the company at any given moment; represents the nonlinear control parameter; 、 、 represents the characteristic weight coefficient of production intensity; represents a natural constant; The correlation characteristics between enterprise equipment and load are extracted based on enterprise equipment data and historical load data, as shown in the following formula: ； in: express Moment Enterprise Equipment Correlation characteristics with the enterprise's historical load; Indicates from a historical interval that looks back at every moment; Indicates the maximum lookback window length; Represents enterprise equipment The set of spatial neighborhood devices; Represents enterprise equipment The first device in its spatial neighborhood The spatial weight of each device; Represents enterprise equipment The first device in the spatial neighborhood of devices; Represents the historical time weight attenuation coefficient; express Time equipment Historical load data; express The overall historical load data of the enterprise at all times; represents the correlation function; The enterprise's future load data is corrected based on the correlation characteristics, as shown in the following formula: ； in: express The enterprise's future load data after constant revision; express The enterprise's future load data at all times; represents the forecast span time; Represents enterprise equipment Importance weight of express Moment Enterprise Equipment Correlation characteristics with the company's historical load; express Moment Enterprise Equipment Load data; Identify the load pattern of the enterprise based on the revised future load data of the enterprise; Construct an enterprise power supply service profile based on the enterprise's production intensity characteristics, equipment and load correlation characteristics, and load patterns; Construct an enterprise electricity demand elastic response model, input the enterprise power supply service portrait and the corrected future load data into the enterprise electricity demand elastic response model to obtain the enterprise electricity elastic demand curve, and optimize the power supply service strategy according to the enterprise electricity elastic demand curve.

2. The power supply service strategy optimization method based on enterprise power supply service portrait according to claim 1 is characterized in that: The enterprise load forecasting model is built based on a deep hybrid attention temporal network model, including a short-term feature extraction layer, a multi-head self-attention mechanism layer, and a multi-layer perceptron layer; The load data of the enterprise at different historical moments are normalized to construct the input sample set, as shown in the following formula: ； in: Indicates to The input sample set at time t; express Time-normalized enterprise load data; Indicates the length of the input sample set; Represents feature dimension; represents the field of real numbers; The short-term feature extraction layer is constructed based on a convolutional neural network. The input sample set is input into the short-term feature extraction layer to extract short-term features, as shown in the following formula: ； in: express The output of the short-term feature extraction layer; represents the activation function; Indicates the number of convolutional layers in the short-term feature extraction layer; Indicates the The weight matrix of the convolutional layer; Indicates the The bias of the convolutional layer; The short-term features are concatenated and input into the multi-head self-attention mechanism layer to extract long-term features, as shown in the following formula: ； ； in: Represents the long-term features extracted by the multi-head self-attention layer; 、 、 Represent the query vector, key vector, and value vector of the concatenated short-term features respectively; Represents a splicing operation; Indicates the The output of an attention head; represents the total number of attention heads; Represents the output linear projection weight matrix of multi-head attention; represents the normalization function; 、 、 Respectively represent The parameter weight matrix of each attention head corresponding to the query vector, key vector, and value vector; Represents a transpose operation; Indicates the The dimension of the attention head; The long-term features are then input into the multi-layer perceptron layer map to generate the load forecast results.

3. The power supply service strategy optimization method based on enterprise power supply service portrait according to claim 1 is characterized in that: The specific steps for identifying the enterprise's load pattern based on the revised enterprise's future load data are as follows: Construct different types of typical load pattern time series of the same length; The improved dynamic time warping algorithm is used to align the enterprise's future load data with any typical load pattern time series, as shown in the following formula: ； ； in: Represents the output of the improved dynamic time warping algorithm, which is to transform the enterprise's future load data into Time series with typical load patterns Perform alignment; Indicates that the company's future load data Time series with typical load patterns A collection of alignments between ; express The data points; express The data points; represents the time weight function; represents the time offset penalty factor; express and the distance between them; Based on the aligned enterprise future load data, the Gaussian mixture model is used to identify the load pattern that is closest to it, as shown in the following formula: ； ； in: Indicates the aligned enterprise future load data; represents the parameter set of the Gaussian mixture model, ; Indicates the number of typical load patterns; Indicates that given a set of parameters Under the conditions, Probability density of occurrence; Indicates the The prior probability of each load pattern; Indicates that based on The determinant of the covariance matrix constructed from the typical load pattern time series corresponding to each load pattern; Indicates the The mean of the typical load pattern time series corresponding to each load pattern; express The load pattern corresponding to the enterprise's future load data at that moment; Indicates that the aligned enterprise future load data is Data points at a moment in time; express The load pattern with the highest probability density The corresponding parameter set of the Gaussian mixture model under .

4. The power supply service strategy optimization method based on enterprise power supply service portrait according to claim 3 is characterized in that: Construct an enterprise electricity demand elasticity response model, input the enterprise power supply service profile into the enterprise electricity demand elasticity response model to obtain the enterprise electricity demand elasticity response curve, as shown in the following formula: ； in: express The elasticity of electricity demand of enterprises at all times; Indicates the total number of time-of-use electricity price tiers; Indicates the The price elasticity coefficient of each time-of-use electricity price ladder; Indicates the The electricity price of each time-of-use electricity price ladder; Indicates the basic electricity price; represents the service profile impact function; express A portrait of the enterprise's power supply services at all times.

5. The power supply service strategy optimization method based on enterprise power supply service portrait according to claim 4 is characterized in that: The power supply service strategy is optimized according to the enterprise's electricity elastic demand curve, as shown in the following formula: ； in: Indicates the company's optimized power supply service strategy; express The electricity price at the time; represents the balance coefficient; Represents the variance of the enterprise's electricity demand elasticity.

6. A power supply service strategy optimization system based on enterprise power supply service portrait, used in the method according to any one of claims 1 to 5, characterized in that: It includes data acquisition module, enterprise load forecasting module, production intensity feature generation module, correlation feature generation module, load pattern recognition module, enterprise power supply service portrait construction module and power supply service strategy optimization module; The data acquisition module is used to collect the enterprise's historical load data, historical operation data and enterprise equipment data, and pre-process the historical load data, historical operation data and enterprise equipment data; The enterprise load forecasting module is used to build an enterprise load forecasting model and predict the enterprise's future load data based on the enterprise's historical load data; The production intensity characteristic generation module is used to calculate the production intensity characteristics of the enterprise based on the enterprise's historical operating data; The correlation feature production module is used to extract the correlation features between enterprise equipment and load based on enterprise equipment data and historical load data, and to modify the enterprise's future load data according to the correlation features; The load pattern identification module is used to identify the load pattern of the enterprise based on the corrected future load data of the enterprise; The enterprise power supply service portrait construction module is used to construct the enterprise power supply service portrait based on the enterprise's production intensity characteristics, equipment and load correlation characteristics, and load mode; The power supply service strategy optimization module is used to construct an enterprise electricity demand elastic response model, input the enterprise power supply service portrait and the corrected future load data into the enterprise electricity demand elastic response model to obtain the enterprise electricity elastic demand curve, and optimize the power supply service strategy according to the enterprise electricity elastic demand curve.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images