A clean energy consumption capacity evaluation method and system oriented to sending and receiving end cooperation

Abstract

The application discloses a kind of clean energy consumption capacity evaluation methods and systems for sending and receiving end cooperation, it is related to the technical field of consumption capacity evaluation, including real-time acquisition sending and receiving end data, utilize acquisition data to build sending and receiving end cooperation's clean energy big data platform, and the pre-processing of acquisition data is carried out, the feature extraction of data after pre-processing is carried out, and the power generation capacity of sending end clean energy is analyzed, and the load demand of receiving end data is learned and predicted, utilize sending end clean energy power generation capacity and receiving end load prediction result, build sending and receiving end cooperation's clean energy consumption capacity evaluation model, and optimize model parameter, utilize the dynamic evaluation of sending and receiving end cooperation's clean energy consumption capacity of optimized evaluation model, according to evaluation result matches clean energy scheduling strategy.The application improves the operation efficiency and economy of power system, ensures the efficient use of clean energy, provides solid technical support for the construction of sustainable development energy system.

Description

Technical Field

[0001] This invention relates to the field of energy absorption capacity assessment technology, and specifically to a method and system for assessing the absorption capacity of clean energy in a coordinated manner between the sending and receiving ends. Background Technology

[0002] With the transformation of the global energy structure and the increasing emphasis on environmental protection, the development and utilization of clean energy has become an important part of the energy strategies of various countries. In recent years, grid-connected power generation technologies for renewable energy sources such as wind and solar power have developed rapidly, but this has also brought uncertainty and complexity to power system operation. To improve the absorption capacity of clean energy and ensure the stable operation of the power system, research in related technical fields mainly focuses on data-driven assessment of clean energy absorption capacity and optimal power system dispatch.

[0003] However, existing technologies have certain shortcomings. First, traditional clean energy absorption capacity assessment methods often rely on static models, which cannot reflect the volatility of clean energy and changes in load demand in real time, resulting in low accuracy of assessment results. Second, existing technologies fail to fully consider the diversity and complexity of data from both the sending and receiving ends during data preprocessing and feature extraction, thus affecting the accuracy of subsequent assessment models. Furthermore, current clean energy dispatch strategies lack flexibility and adaptability, making it difficult to dynamically adjust according to changes in real-time absorption capacity, which to some extent limits the efficient utilization of clean energy and the optimized operation of the power system. The clean energy absorption capacity assessment method proposed in this invention, oriented towards sending and receiving end collaboration, through real-time data acquisition, preprocessing, feature extraction, and the construction of a dynamic assessment model, is expected to achieve significant technological advancements and beneficial effects in the aforementioned aspects. Summary of the Invention

[0004] In view of the above-mentioned existing problems, the present invention provides a method and system for assessing the clean energy absorption capacity in a coordinated manner between the sending and receiving ends, in order to solve the problems of low accuracy of assessment results, low precision of assessment models, and limitations on the efficient utilization of clean energy and the optimized operation of power systems in the prior art.

[0005] To address the aforementioned technical challenges, a method for assessing clean energy consumption capacity based on sender-receiver collaboration is proposed, including:

[0006] Real-time data collection at both the sending and receiving ends is used to construct a collaborative clean energy big data platform. The collected data is then preprocessed. Feature extraction is performed on the preprocessed data, and the power generation capacity of clean energy at the sending end is analyzed. Load demand is predicted based on the receiving end data. A collaborative clean energy absorption capacity assessment model is constructed using the power generation capacity of clean energy at the sending end and the load prediction results at the receiving end, and the model parameters are optimized. The optimized assessment model is then used to dynamically evaluate the collaborative clean energy absorption capacity of the sending and receiving ends, and clean energy dispatch strategies are matched based on the assessment results.

[0007] As a preferred embodiment of the clean energy consumption capacity assessment method for collaborative transmission and receiving ends described in this invention, the construction of the clean energy big data platform for collaborative transmission and receiving ends includes real-time collection of transmission end data and receiving end data, and designing the platform's data layer, service layer and application layer, and designing the data processing flow.

[0008] The sending-end data includes environmental data, power generation equipment status data, energy storage status data, and grid interaction data; the receiving-end data includes power consumption data, load characteristic data, grid operation data, user behavior data, and power quality data.

[0009] The environmental data includes wind speed, light intensity, temperature, humidity, and air pressure; the power generation equipment status data includes power generation, power generation efficiency, equipment speed, equipment temperature, and fault codes; the energy storage status data includes energy storage capacity, charge / discharge status, energy storage efficiency, and energy storage equipment temperature; and the grid interaction data includes grid connection voltage, grid connection current, frequency, and power factor.

[0010] The power consumption data includes real-time power consumption, cumulative power consumption, and peak power consumption; the load characteristic data includes load type, load curve, and load forecast; the power grid operation data includes substation load, distribution network voltage, distribution network current, and line loss; the user behavior data includes electricity consumption habits, peak and valley power consumption, and demand response; and the power quality data includes voltage fluctuation, current harmonics, and power supply reliability.

[0011] As a preferred embodiment of the clean energy consumption capacity assessment method for the collaborative transmission and receiving ends described in this invention, the preprocessing includes: data cleaning, data standardization, and data fusion of the collected transmission and receiving end data, and feature extraction of the preprocessed data.

[0012] The data cleaning includes using statistical methods to detect outliers and noise in the data, and imputing and deleting missing data; the data fusion includes using timestamp matching for time series alignment and using identifiers for data association.

[0013] As a preferred embodiment of the clean energy absorption capacity assessment method for transmission-receiving end collaboration described in this invention, the feature extraction includes extracting the time-domain and frequency-domain features of the preprocessed data and analyzing the power generation capacity of the clean energy at the transmission end.

[0014] The formula for extracting time-domain features is:

[0015]

[0016] Where σ is the variance, Y i For data points, is the average value of the data points, and m is the number of data points.

[0017] The formula for extracting frequency domain features is:

[0018]

[0019] Where X(f) is the frequency domain representation after Fourier transform, x(t) is the original time domain signal, f is the frequency, j is the imaginary unit, and t is the time.

[0020] The analysis of the power generation capacity of clean energy at the sending end includes constructing a graph neural network model, initializing the model parameters using a graph attention network, evaluating the difference between the model prediction and the actual power generation capacity using cross-entropy loss, analyzing the power generation capacity of clean energy at the sending end, and predicting load demand.

[0021] The initialization model parameters include the node feature matrix. Where N is the number of nodes, F

[0022] For the feature dimension, the weight matrix Perform node feature transformation, where F is the transformed feature dimension and the bias is...

[0023] The cross-entropy loss formula is as follows:

[0024]

[0025] Where y represents the real label. Let N be the probability distribution predicted by the model, and N be the number of nodes. This is the loss function.

[0026] As a preferred embodiment of the clean energy absorption capacity assessment method for transmission-receiving end coordination described in this invention, the construction of the clean energy absorption capacity assessment model for transmission-receiving end coordination includes: utilizing the clean energy generation capacity of the sending end and the load prediction results of the receiving end and extracting features, and selecting a time series model and setting the model structure.

[0027] The time series model combines the sending-end and receiving-end prediction models to determine the model parameters and order, uses information criteria to select the optimal model order, and performs parameter significance tests; the model structure includes a predicted generation capacity layer and a predicted load demand layer.

[0028] The formula for the optimization model parameters is:

[0029]

[0030] Where θ is the gradient and α is the learning rate. Let θ be the gradient of the loss function with respect to the parameter θ.

[0031] As a preferred embodiment of the clean energy absorption capacity assessment method for transmission-receiving end collaboration described in this invention, the dynamic assessment of the clean energy absorption capacity for transmission-receiving end collaboration includes dynamically assessing the clean energy absorption capacity for transmission-receiving end collaboration based on the output of the clean energy predicted power generation and the predicted power load demand through the clean energy absorption capacity assessment model for transmission-receiving end collaboration.

[0032] The formula for predicting clean energy power generation is as follows:

[0033] A t =f(B t B t-1 ,...,B t-P )+ε t

[0034] Among them, A t For the predicted clean energy power generation at time t, B t Let ε be the clean energy feature vector input at time t, P be the impact of clean energy data on the prediction, and ε be the value of ε. t This is the error term.

[0035] The formula for the predicted electricity load demand is:

[0036]

[0037] Among them, E t For the predicted electricity load demand at time t, H t Let be the load feature vector input at time t, and q be the impact of the load data on the forecast. This is the error term.

[0038] The formula for calculating absorption capacity is:

[0039] ΔS t =A t -E t

[0040] Among them, A tE is the predicted clean energy power generation at time t. t For the predicted electricity load demand at time t, ΔS t The clean energy absorption capacity over time t.

[0041] As a preferred embodiment of the clean energy consumption capacity assessment method for the collaborative transmission and reception ends described in this invention, the matching clean energy scheduling strategy includes setting a clean energy consumption capacity threshold and matching a clean energy scheduling strategy according to different consumption capacity ranges.

[0042] When ΔS t When the value is greater than or equal to a set threshold, it is necessary to increase clean energy generation, activate backup energy, and adjust user electricity consumption behavior by adjusting electricity prices to reduce peak-hour load; when ΔS t When the power generation is below a set threshold, reduce the amount of clean energy generated, increase the use of energy storage systems, store energy when there is a surplus of power generation, release energy when demand is at its peak, and optimize the operation of the power grid.

[0043] Another objective of this invention is to provide a clean energy absorption capacity assessment system oriented towards end-to-end collaboration. This invention optimizes the operating efficiency of the power system and improves the absorption capacity of clean energy. Through real-time data acquisition, preprocessing, feature extraction, and the construction of a dynamic evaluation model, this system promotes the optimized operation of the power system, improves the absorption capacity of clean energy, reduces energy waste, enhances the reliability and economy of the power system, and provides strong support for building a cleaner, more efficient, and intelligent power system.

[0044] As a preferred embodiment of the clean energy absorption capacity assessment system for the collaborative transmission and reception ends described in this invention, it is characterized by including a data acquisition and preprocessing module, a feature extraction and analysis module, a dynamic assessment module for absorption capacity, and a clean energy dispatch strategy matching module.

[0045] The data acquisition and preprocessing module is used to collect data from the sending and receiving ends in real time through sensors and smart meters, and to clean, standardize and fuse the collected data to lay the foundation for subsequent analysis.

[0046] The feature extraction and analysis module is used to extract time-domain and frequency-domain features from the preprocessed data. Using the extracted features, a graph neural network model is constructed to evaluate the power generation capacity of clean energy at the sending end, and the receiving end data is analyzed to predict the power load demand, providing a basis for the assessment of absorption capacity.

[0047] The dynamic assessment module for absorption capacity is used to construct an assessment model by combining the clean energy generation capacity at the sending end and the load forecast results at the receiving end. The model parameters are adjusted by the gradient descent optimization algorithm. Using the optimized assessment model, the predicted clean energy generation and the predicted power load demand are output in real time. The absorption capacity of clean energy is calculated by comparing the predicted clean energy generation and the power load demand.

[0048] The clean energy dispatch strategy matching module is used to set a threshold for clean energy absorption capacity based on the absorption capacity assessment results, and to match the corresponding clean energy dispatch strategy based on the comparison results between the absorption capacity and the threshold.

[0049] A computer device includes a memory and a processor, the memory storing a computer program, characterized in that the processor executes the computer program to implement the steps of a method for assessing the clean energy consumption capacity of a collaborative sending and receiving end.

[0050] A computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of a method for assessing clean energy consumption capacity in a collaborative manner between the sending and receiving ends.

[0051] The beneficial effects of this invention are as follows: This invention forms a closed-loop clean energy absorption capacity assessment and scheduling system through real-time data acquisition, feature extraction, dynamic evaluation model construction and optimization, and intelligent scheduling strategy matching. This effectively improves the operating efficiency and economy of the power system, ensures the efficient utilization of clean energy and the stable operation of the power system, and provides solid technical support for building a sustainable energy system. Attached Figure Description

[0052] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, wherein:

[0053] Figure 1 The above is a flowchart of an overall method for assessing the clean energy absorption capacity of the sending and receiving ends in accordance with an embodiment of the present invention.

[0054] Figure 2 The present invention provides a system scheme flowchart for a clean energy consumption capacity assessment system oriented towards sending and receiving end collaboration, as an embodiment of the present invention. Detailed Implementation

[0055] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0056] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0057] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is mutually exclusive, either alone or selectively, with other embodiments.

[0058] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0059] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used solely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0060] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0061] Example 1, referring to Figure 1 This is the first embodiment of the present invention, which provides a method for assessing the clean energy consumption capacity oriented towards transmission-receiving end coordination, including:

[0062] S1: Collect data from the sending and receiving ends in real time, use the collected data to build a clean energy big data platform that coordinates the sending and receiving ends, and preprocess the collected data.

[0063] The construction of a clean energy big data platform that coordinates the sending and receiving ends includes real-time collection of sending and receiving end data, designing the platform's data layer, service layer, and application layer, and designing the data processing flow.

[0064] The sending-end data includes environmental data, power generation equipment status data, energy storage status data, and grid interaction data; the receiving-end data includes power consumption data, load characteristic data, grid operation data, user behavior data, and power quality data.

[0065] The environmental data includes wind speed, light intensity, temperature, humidity, and air pressure; the power generation equipment status data includes power generation, power generation efficiency, equipment speed, equipment temperature, and fault codes; the energy storage status data includes energy storage capacity, charge / discharge status, energy storage efficiency, and energy storage equipment temperature; and the grid interaction data includes grid connection voltage, grid connection current, frequency, and power factor.

[0066] The power consumption data includes real-time power consumption, cumulative power consumption, and peak power consumption; the load characteristic data includes load type, load curve, and load forecast; the power grid operation data includes substation load, distribution network voltage, distribution network current, and line loss; the user behavior data includes electricity consumption habits, peak and valley power consumption, and demand response; and the power quality data includes voltage fluctuation, current harmonics, and power supply reliability.

[0067] It should be noted that the preprocessing includes data cleaning, data standardization, and data fusion of the collected data from the sending and receiving ends, and feature extraction of the preprocessed data.

[0068] The data cleaning includes using statistical methods to detect outliers and noise in the data, and imputing and deleting missing data; the data fusion includes using timestamp matching for time series alignment and using identifiers for data association.

[0069] It should also be noted that the formula for the statistical method is as follows:

[0070]

[0071] Where X is the original value, μ is the mean, τ is the standard deviation, and Z is the Z-score.

[0072] The interpolation formula is:

[0073]

[0074] in, X is the imputed value for the missing value. i represents the number of non-missing observations, n represents the number of non-missing observations, and i represents the variable index.

[0075] The standardized formula is:

[0076]

[0077] Among them, X norm The value is the standardized value, and X is the original value. min For the minimum value, X max This is the maximum value.

[0078] S2: Extract features from the preprocessed data, analyze the power generation capacity of clean energy at the sending end, and learn from the receiving end data to predict load demand.

[0079] Furthermore, the feature extraction includes extracting the time-domain and frequency-domain features of the preprocessed data to analyze the power generation capacity of the clean energy at the sending end.

[0080] The formula for extracting time-domain features is:

[0081]

[0082] Where σ is the variance, Y i For data points, is the average value of the data points, and m is the number of data points.

[0083] The formula for extracting frequency domain features is:

[0084]

[0085] Where X(f) is the frequency domain representation after Fourier transform, x(t) is the original time domain signal, f is the frequency, j is the imaginary unit, and t is the time.

[0086] Furthermore, the analysis of the power generation capacity of clean energy at the sending end includes constructing a graph neural network model, initializing the model parameters using a graph attention network, evaluating the difference between the model prediction and the actual power generation capacity using cross-entropy loss, analyzing the power generation capacity of clean energy at the sending end, and predicting load demand.

[0087] The initialization model parameters include the node feature matrix. Where N is the number of nodes, F

[0088] For the feature dimension, the weight matrix Perform node feature transformation, where F is the transformed feature dimension and the bias is...

[0089] The cross-entropy loss formula is as follows:

[0090]

[0091] Where y represents the real label. Let N be the probability distribution predicted by the model, and N be the number of nodes. This is the loss function.

[0092] S3: Using the clean energy generation capacity at the sending end and the load forecast results at the receiving end, construct an assessment model for the clean energy absorption capacity of the sending and receiving ends in coordination, and optimize the model parameters.

[0093] Furthermore, the construction of the clean energy consumption capacity assessment model for the sending and receiving ends in collaboration includes utilizing the clean energy power generation capacity at the sending end and the load forecast results at the receiving end, extracting features, selecting a time series model, and setting the model structure.

[0094] The time series model combines the sending-end and receiving-end prediction models to determine the model parameters and order, uses information criteria to select the optimal model order, and performs parameter significance tests; the model structure includes a predicted generation capacity layer and a predicted load demand layer.

[0095] Furthermore, the formula for the optimized model parameters is:

[0096]

[0097] Where θ is the gradient and α is the learning rate. Let θ be the gradient of the loss function with respect to the parameter θ.

[0098] S4: Utilize the optimized evaluation model to dynamically assess the clean energy consumption capacity of the sending and receiving ends in coordination, and match clean energy dispatch strategies based on the evaluation results.

[0099] It should be noted that the dynamic assessment of the clean energy absorption capacity of the sending and receiving ends includes dynamically assessing the clean energy absorption capacity of the sending and receiving ends through the clean energy absorption capacity assessment model output by the predicted clean energy power generation and the predicted power load demand.

[0100] The formula for predicting clean energy power generation is as follows:

[0101] A t =f(B t B t-1 ,...,B t-P )+ε t

[0102] Among them, A t For the predicted clean energy power generation at time t, B tLet ε be the clean energy feature vector input at time t, P be the impact of clean energy data on the prediction, and ε be the value of ε. t This is the error term.

[0103] The formula for the predicted electricity load demand is:

[0104]

[0105] Among them, E t For the predicted electricity load demand at time t, H t Let be the load feature vector input at time t, and q be the impact of the load data on the forecast. This is the error term.

[0106] The formula for calculating absorption capacity is:

[0107] ΔS t =A t -E t

[0108] Among them, A t E is the predicted clean energy power generation at time t. t For the predicted electricity load demand at time t, ΔS t The clean energy absorption capacity over time t.

[0109] It should be further noted that the matching clean energy dispatch strategy includes setting a clean energy absorption capacity threshold and matching a clean energy dispatch strategy according to different absorption capacity ranges.

[0110] When ΔS t When the value is greater than or equal to a set threshold, it is necessary to increase clean energy generation, activate backup energy, and adjust user electricity consumption behavior by adjusting electricity prices to reduce peak-hour load; when ΔS t When the power generation is below a set threshold, reduce the amount of clean energy generated, increase the use of energy storage systems, store energy when there is a surplus of power generation, release energy when demand is at its peak, and optimize the operation of the power grid.

[0111] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

[0112] Example 2, refer to Figure 2The second embodiment of the present invention provides a clean energy consumption capacity assessment system for collaborative transmission and reception, including a data acquisition and preprocessing module M100, a feature extraction and analysis module M200, a dynamic assessment module for consumption capacity M300, and a clean energy dispatch strategy matching module M400.

[0113] The data acquisition and preprocessing module M100 is used to collect data from the sending and receiving ends in real time through sensors and smart meters, and to clean, standardize and fuse the collected data to lay the foundation for subsequent analysis.

[0114] The feature extraction and analysis module M200 is used to extract time-domain and frequency-domain features from the preprocessed data. Using the extracted features, a graph neural network model is constructed to evaluate the power generation capacity of clean energy at the sending end, and the receiving end data is analyzed to predict the power load demand, providing a basis for the assessment of absorption capacity.

[0115] The dynamic evaluation module M300 for absorption capacity is used to construct an evaluation model by combining the clean energy generation capacity at the sending end and the load forecast results at the receiving end. The model parameters are adjusted by the gradient descent optimization algorithm. Using the optimized evaluation model, the predicted clean energy generation and the predicted power load demand are output in real time. The absorption capacity of clean energy is calculated by comparing the predicted clean energy generation and the power load demand.

[0116] The clean energy dispatch strategy matching module M400 is used to set a threshold for clean energy absorption capacity based on the absorption capacity assessment results, and to match the corresponding clean energy dispatch strategy based on the comparison results between the absorption capacity and the threshold.

[0117] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

[0118] Example 3, the third embodiment of the present invention, differs from the previous two embodiments in that:

[0119] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0120] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0121] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0122] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

Claims

1. A method for assessing the clean energy consumption capacity oriented towards transmission-receiving end collaboration, characterized in that: include, Real-time data collection at the sending and receiving ends; use the collected data to build a clean energy big data platform for collaboration between the sending and receiving ends; and preprocess the collected data. Feature extraction is performed on the preprocessed data, and the power generation capacity of clean energy at the sending end is analyzed. The receiving end data is then used to learn and predict load demand. Using the clean energy generation capacity at the sending end and the load forecast results at the receiving end, a clean energy absorption capacity assessment model that coordinates sending and receiving ends is constructed, and the model parameters are optimized. The optimized evaluation model is used to dynamically evaluate the clean energy consumption capacity of the sending and receiving ends, and clean energy dispatch strategies are matched according to the evaluation results. The construction of a clean energy big data platform that coordinates the sending and receiving ends includes real-time collection of sending and receiving end data, designing the platform's data layer, service layer, and application layer, and designing the data processing flow. The sending-end data includes environmental data, power generation equipment status data, energy storage status data, and grid interaction data; the receiving-end data includes power consumption data, load characteristic data, grid operation data, user behavior data, and power quality data. The environmental data includes wind speed, light intensity, temperature, humidity, and air pressure; the power generation equipment status data includes power generation, power generation efficiency, equipment speed, equipment temperature, and fault codes; the energy storage status data includes energy storage capacity, charge / discharge status, energy storage efficiency, and energy storage equipment temperature; the grid interaction data includes grid connection voltage, grid connection current, frequency, and power factor. The power consumption data includes real-time power consumption, cumulative power consumption, and peak power consumption; the load characteristic data includes load type, load curve, and load forecast; the power grid operation data includes substation load, distribution network voltage, distribution network current, and line loss; and the user behavior data includes electricity consumption habits, peak and off-peak electricity consumption, and demand response. The power quality data includes voltage fluctuations, current harmonics, and power supply reliability. The preprocessing includes data cleaning, data standardization, and data fusion of the collected data from the sending and receiving ends, and feature extraction of the preprocessed data. The data cleaning includes using statistical methods to detect outliers and noise in the data, and imputing and deleting missing data; the data fusion includes using timestamp matching for time series alignment and using identifiers for data association. The feature extraction This includes extracting the time-domain and frequency-domain features of the preprocessed data to analyze the power generation capacity of clean energy at the sending end; The formula for extracting time-domain features is: Where σ is the variance. For data points, is the average value of the data points, and m is the number of data points; The formula for extracting frequency domain features is: in, For the frequency domain representation after Fourier transform, x The original time-domain signal is given by f, where f is the frequency, j is the imaginary unit, and t is the time. The analysis of the power generation capacity of clean energy at the sending end includes constructing a graph neural network model, initializing the model parameters using a graph attention network, evaluating the difference between the model prediction and the actual power generation capacity using cross-entropy loss, analyzing the power generation capacity of clean energy at the sending end, and predicting load demand. The initialization model parameters include the node feature matrix. Where N is the number of nodes, F is the feature dimension, and the weight matrix is... Perform node feature transformation. For the transformed feature dimensions, the bias is... ; The cross-entropy loss formula is as follows: Where y represents the real label. Let N be the probability distribution predicted by the model, and N be the number of nodes. The loss function; The construction of the clean energy consumption capacity assessment model for the sending and receiving ends includes utilizing the clean energy power generation capacity at the sending end and the load prediction results at the receiving end, extracting features, selecting a time series model, and setting the model structure. The time series model combines the sending-end and receiving-end prediction models to determine the model parameters and order, uses information criteria to select the optimal model order, and performs parameter significance testing; the model structure includes a predicted generation capacity layer and a predicted load demand layer. The formula for the optimization model parameters is: in, For gradient, For learning rate, The gradient of the loss function with respect to the parameter θ; The dynamic assessment of the clean energy absorption capacity of the sending and receiving ends includes dynamically assessing the clean energy absorption capacity of the sending and receiving ends through the clean energy absorption capacity assessment model of the sending and receiving ends, based on the output of the predicted clean energy power generation and the predicted power load demand. The formula for predicting clean energy power generation is as follows: in, For the predicted clean energy power generation at time t, Let be the clean energy feature vector input at time t, and P be the impact of clean energy data on the prediction. This is the error term; The formula for the predicted electricity load demand is: in, Forecast electricity load demand at time t, The load feature vector is input at time t. This represents the impact of load data on the forecast. This is the error term; The formula for calculating absorption capacity is: in, For the predicted clean energy power generation at time t, Forecast electricity load demand at time t, The clean energy absorption capacity over time t.

2. The method for assessing clean energy consumption capacity based on transmission and receiving end collaboration as described in claim 1, characterized in that: The matching clean energy dispatch strategy includes setting a clean energy absorption capacity threshold and matching a clean energy dispatch strategy according to different absorption capacity ranges. when When the threshold is greater than or equal to the set threshold, it is necessary to increase clean energy generation, activate backup energy, and adjust user electricity consumption behavior by adjusting electricity prices to reduce peak-hour load; when When the power generation is below a set threshold, reduce the amount of clean energy generated, increase the use of energy storage systems, store energy when there is a surplus of power generation, release energy when demand is at its peak, and optimize the operation of the power grid.

3. A system employing a clean energy consumption capacity assessment method oriented towards end-to-end coordination as described in any one of claims 1 to 2, characterized in that: It includes a data acquisition and preprocessing module, a feature extraction and analysis module, a dynamic assessment module for absorption capacity, and a clean energy dispatch strategy matching module; The data acquisition and preprocessing module is used to collect data from the sending and receiving ends in real time through sensors and smart meters, and to clean, standardize and fuse the collected data to lay the foundation for subsequent analysis. The feature extraction and analysis module is used to extract time-domain and frequency-domain features from the preprocessed data. Using the extracted features, a graph neural network model is constructed to evaluate the power generation capacity of clean energy at the sending end, and the receiving end data is analyzed to predict the power load demand, providing a basis for the assessment of absorption capacity. The dynamic evaluation module for absorption capacity is used to construct an evaluation model by combining the clean energy power generation capacity at the sending end and the load prediction results at the receiving end. The model parameters are adjusted by the gradient descent optimization algorithm. The optimized evaluation model is used to output the predicted power generation of clean energy and the predicted demand of power load in real time. The absorption capacity of clean energy is calculated by comparing the predicted power generation of clean energy and the demand of power load. The clean energy dispatch strategy matching module is used to set a threshold for clean energy absorption capacity based on the absorption capacity assessment results, and to match the corresponding clean energy dispatch strategy based on the comparison results between the absorption capacity and the threshold.

4. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the clean energy consumption capacity assessment method for collaborative transmission and reception as described in any one of claims 1 to 2.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the clean energy consumption capacity assessment method for collaborative transmission and reception as described in any one of claims 1 to 2.

Images