Electric power spot market safety management verification method and system

Abstract

The invention discloses an electric power spot market safety management verification method and system, and relates to the technical field of electric power market management, and the method comprises the steps: obtaining real-time transaction data and historical statistical data of an electric power spot market, and carrying out the preprocessing; based on the preprocessed data, using an LSTM network evaluation model to perform verification evaluation to obtain a preliminary evaluation result; and based on the preliminary evaluation result and in combination with a power grid topological structure, correcting the preliminary evaluation result to obtain a final safety verification result, and completing safety management verification of the electric power spot market. According to the invention, more comprehensive and accurate electric power spot market safety management verification is realized, and the trend and characteristics of market safety risks can be better captured. Through cooperative work of real-time data evaluation and historical data evaluation, accuracy and reliability of safety management verification of the electric power spot market are improved, and improvement of safety and stability of the electric power spot market is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of power market management, and in particular to a power spot market safety management verification method and system. Background Art

[0002] With the deepening of power system reform, the power spot market has been gradually established and developed in my country. As a new power trading model, the safety and stability of the power spot market are directly related to the safe operation and economic benefits of the power system. Traditional power market safety management methods mainly rely on static rules and manual supervision, which are difficult to cope with the rapidly changing trading conditions and potential safety risks in the spot market.

[0003] The existing safety management methods of the electricity spot market have the following shortcomings: First, most methods fail to fully consider the dynamics and uncertainty of the behavior of market participants, resulting in inaccurate safety risk assessment. Second, traditional safety verification methods are often based on statistical analysis of historical data, which is difficult to reflect the real-time status of the market in a timely manner. In addition, the existing methods lack effective identification and prevention mechanisms for market manipulation, which can easily lead to market imbalances and system safety hazards. Finally, when faced with emergencies or abnormal transactions, the existing methods are not responsive and adaptable enough, making it difficult to take effective safety management measures in a timely manner. Summary of the invention

[0004] In view of the problems existing in the existing power spot market security management verification method, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is how to provide a method for verifying the safety management of the electricity spot market, so as to solve the problems in the prior art of failing to fully consider the market dynamics, inaccurate safety risk assessment and insufficient identification of market manipulation behavior.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present invention provides a method for verifying the safety management of the electricity spot market, which includes obtaining real-time transaction data and historical statistical data of the electricity spot market and performing preprocessing; based on the preprocessed data, using an LSTM network evaluation model to perform verification and evaluation to obtain preliminary evaluation results; based on the preliminary evaluation results combined with the power grid topology, the preliminary evaluation results are corrected to obtain final safety verification results, thereby completing the safety management verification of the electricity spot market.

[0008] As a preferred scheme of the power spot market security management verification method described in the present invention, the real-time transaction data includes real-time electricity prices, transaction volumes, supply and demand balance, market participant behaviors, system operating status and abnormal transaction marks; the historical statistical data includes historical transaction records, market participant credit ratings, power grid topology, generator set characteristics and load characteristics.

[0009] As a preferred solution of the power spot market safety management verification method described in the present invention, the preprocessing of the real-time transaction data includes data verification, real-time outlier detection, data standardization, feature encoding, real-time feature calculation, missing data processing, data alignment and data streaming; the preprocessing of the historical statistical data includes data cleaning, missing value processing, time series analysis, data standardization / normalization, feature engineering, data encoding, data aggregation, correlation analysis, data segmentation, data enhancement, feature selection and data storage; and the real-time transaction data and the historical statistical data are integrated and preprocessed at the same time, including feature consistency check, scale alignment, time window matching, dynamic feature update and model input preparation.

[0010] As a preferred solution of the power spot market security management verification method of the present invention, wherein: a preliminary evaluation of the real-time security status of the power spot market based on the LSTM network evaluation model is performed, and the preliminary evaluation result is expressed as:

[0011]

[0012] Among them, S1 is the preliminary safety assessment value; P t is the electricity price vector at time t; V t is the trading volume vector at time t; B t is the supply and demand balance at time t; W p ,W v ,W b is the weight matrix; b is the bias term; σ is the S-type activation function.

[0013] As a preferred solution of the power spot market safety management verification method of the present invention, the correction includes a first correction and a second correction; the first correction is obtained based on the preliminary evaluation result S1 combined with the influence of historical data, and the first corrected evaluation value is expressed as:

[0014]

[0015] Among them, S1 (t1) is the first revised evaluation value, S1 is the preliminary safety evaluation value, n is the number of features considered, x i is the historical average or reference value of the i-th feature, x tis the actual value of the i-th feature at the current moment, σ i is the historical standard deviation of the i-th feature, α i Represents the weight coefficient of the i-th feature.

[0016] As a preferred solution of the power spot market safety management verification method of the present invention, wherein: based on the first revised evaluation value combined with the influence of dynamic factors, a second revised evaluation value is obtained, and the second revised evaluation value is expressed as:

[0017]

[0018] Among them, S1 (t2) is the second corrected evaluation value, β is the adjustment coefficient of the impact of electricity price fluctuations, P t is the electricity price at the current time t, P t-1 is the electricity price at the previous moment t-1, θ is the reference value of electricity price fluctuation, γ is the adjustment coefficient affected by the change in trading volume, V t is the transaction volume at the current time t, V t-1 is the trading volume at the previous moment t-1.

[0019] As a preferred solution of the power spot market safety management verification method of the present invention, a periodic function is introduced based on the second corrected evaluation value to obtain a final safety verification result, and the safety evaluation result is expressed as:

[0020]

[0021] Among them, S t is the final security verification result, δ is the intraday volatility factor, η is the market participant behavior factor, M t is the abnormal behavior index of market participants at the current time t, M ref It is the reference value or threshold of the abnormal behavior index of market participants.

[0022] In the second aspect, an embodiment of the present invention provides a power spot market security management verification system, which includes: a collection module, used to obtain real-time transaction data of the power spot market and perform preprocessing; an evaluation module, used to perform verification and evaluation based on the preprocessed data using an LSTM network evaluation model to obtain a preliminary evaluation result; a correction module, used to correct the preliminary evaluation result based on the preliminary evaluation result in combination with the power grid topology, obtain a final safety verification result, and complete the power spot market security management verification.

[0023] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, it implements any step of the above-mentioned electricity spot market security management verification method.

[0024] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the above-mentioned electricity spot market security management verification method is implemented.

[0025] The beneficial effect of the present invention is that the present invention realizes a more comprehensive and accurate power spot market security management verification by combining the evaluation results of real-time transaction data and historical statistical data, and can better capture the trends and characteristics of market security risks. Through the collaborative work of real-time data evaluation and historical data evaluation, the accuracy and reliability of power spot market security management verification are significantly improved, providing more accurate decision-making support for power market supervision and risk prevention and control, and helping to improve the security and stability of the power spot market. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0027] Figure 1 Flow chart of the verification method for safety management of electricity spot market. DETAILED DESCRIPTION

[0028] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0029] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0030] Secondly, the term "one 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 term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0031] Example 1

[0032] Reference Figure 1 , which is the first embodiment of the present invention, and provides a method for verifying the safety management of the power spot market, comprising:

[0033] S1: Obtain real-time transaction data and historical statistical data from the electricity spot market and perform preprocessing.

[0034] Collect real-time transaction data including real-time electricity prices, transaction volumes, supply and demand balance, market participant behavior, system operation status, and abnormal transaction flags;

[0035] Historical statistics include historical transaction records, credit ratings of market participants, grid topology, generator characteristics, and load characteristics.

[0036] Preprocessing of real-time transaction data includes data validation, real-time outlier detection, data standardization, feature encoding, real-time feature calculation, missing data processing, data alignment, and data streaming;

[0037] By preprocessing real-time transaction data, outliers can be quickly identified and processed to ensure the accuracy of real-time decision-making. Data of different dimensions can be made comparable, which is convenient for model processing. Possible market manipulation or system failures can be discovered in a timely manner. The system can respond quickly to immediate changes in the market and provide real-time security assessments and early warnings.

[0038] Preprocessing of historical statistical data, including data cleaning, missing value processing, time series analysis, data standardization / normalization, feature engineering, data encoding, data aggregation, correlation analysis, data segmentation, data enhancement, feature selection, and data storage;

[0039] Preprocessing of historical statistical data can construct complex historical features, such as market participant credit ratings, power grid stability indicators, etc. Through feature selection or dimensionality reduction techniques, the most relevant historical information can be extracted and high-quality training data can be provided for machine learning models. This provides historical background and long-term trend information for security assessment models, enhancing the stability and interpretability of the models.

[0040] By integrating the two and preprocessing them, real-time and historical information can be combined to reduce the deviation that may be caused by a single data source. This enables the model to respond to both short-term fluctuations and long-term trends, improving its ability to adapt to market changes. And through the integration of multi-source data, the system's ability to resist failures or anomalies of a single data source is enhanced.

[0041] S2: Based on the preprocessed data, an LSTM network evaluation model is used to perform verification evaluation to obtain preliminary evaluation results.

[0042] A preliminary evaluation of the real-time security status of the electricity spot market based on the LSTM network evaluation model is shown as follows:

[0043]

[0044] Among them, S1 is the preliminary safety assessment value; P t is the electricity price vector at time t; V t is the trading volume vector at time t; B t is the supply and demand balance at time t; W p ,W v ,W b is the weight matrix; b is the bias term; σ is the S-type activation function.

[0045] It should be noted that for W p ,W v ,W b The best choices include:

[0046] Initialize W p ,W v ,W b , using the random initialization method to assign an initial value, expressed as:

[0047]

[0048] Among them, d p ,d v , d b They are the dimensions of electricity price vector, transaction volume vector and supply and demand balance status, and random represents a random function.

[0049] Define the loss function to measure the performance of the model. For the security assessment problem, the mean square error (MSE) is used as the loss function, which is expressed as:

[0050]

[0051] Where N is the number of samples, S t is the safety assessment value predicted by the model, S act is the actual safety assessment value.

[0052] The optimization of the weight matrix uses the gradient descent algorithm or the adaptive learning rate algorithm.

[0053] Among them, the gradient descent algorithm is used to minimize the loss function and thus optimize the weight matrix. The update rule is expressed as:

[0054]

[0055] Among them, α is the learning rate, They are respectively the loss function for W p , W v , W b The partial derivative of .

[0056] The adaptive learning rate algorithm Adam optimizer is used for optimization. The update rule of the Adam algorithm is expressed as:

[0057] m t =β1·m t-1 +(1-β1)·g t

[0058]

[0059] Among them, m t and v t are the first and second moment estimates, and is the bias-corrected momentum estimate, β1 and β2 are the momentum decay rates, and g t is the gradient at the current time step, α represents the learning rate, and ε is a small constant for numerical stability.

[0060] In order to prevent overfitting, a regularization term is added to the loss function, expressed as:

[0061]

[0062] Where λ is the regularization coefficient, represents the square of the L2 norm of the weight matrix W, W p , W v , W b Represent the weight matrices related to electricity price, transaction volume and supply-demand balance respectively.

[0063] The periodic learning rate adjustment strategy using cosine annealing helps the model escape from the local optimal solution, which is expressed as:

[0064]

[0065] Among them, α t is the learning rate at time t, α min and α maxare the minimum and maximum learning rates respectively, and T is the period.

[0066] Among them, after each weight update, the input data is batch normalized to speed up the training process and improve model stability:

[0067]

[0068] y=γ·x norm +β

[0069] Among them, x norm represents the normalized input, x represents the original input, μ B represents the mean of the batch, represents the variance of the batch, y represents the output of the batch normalization layer, γ represents a learnable scaling parameter, and β represents a learnable offset parameter.

[0070] During the training process, if the performance on the validation set does not improve for several consecutive rounds, the training is stopped to prevent overfitting.

[0071] Train multiple models and integrate the results to obtain W p , W v , W b The optimal value of can be obtained, thereby improving the accuracy and reliability of the power spot market security management verification method. In practical applications, the appropriate combination of optimization strategies can be selected according to the specific situation.

[0072] S3: Based on the preliminary assessment results and the grid topology, the preliminary assessment results are corrected to obtain the final safety verification results, and the safety management verification of the electricity spot market is completed.

[0073] Amendments include the first amendment and the second amendment;

[0074] The first correction is obtained based on the preliminary evaluation result S1 combined with the influence of historical data, and the first correction evaluation value is expressed as:

[0075]

[0076] Among them, S1 (t1) is the first revised evaluation value, S1 is the preliminary safety evaluation value, n is the number of features considered, x i is the historical average or reference value of the i-th feature, x t is the actual value of the i-th feature at the current moment, σ i is the historical standard deviation of the i-th feature, α i Represents the weight coefficient of the i-th feature.

[0077] Among them, n is the number of features considered, the features include:

[0078] Features related to real-time transaction data: real-time electricity prices, transaction volumes, supply and demand balance, market participant behavior, system operation status, and abnormal transaction marks;

[0079] Historical statistical data related features: historical transaction records, credit ratings of market participants, grid topology, generator characteristics, load characteristics;

[0080] Features generated after preprocessing: new features that may be generated through preprocessing steps such as data cleaning and feature engineering, trends, seasonality and other features obtained from time series analysis, and highly correlated features screened out after correlation analysis;

[0081] Features of the LSTM network evaluation model output: Features included in the preliminary evaluation results;

[0082] Dynamic market factors: electricity price fluctuations, changes in trading volume;

[0083] Cyclical factors: impact of intraday fluctuations;

[0084] Characteristics related to the behavior of market participants: Market participant behavior abnormality index.

[0085] Based on the first revised evaluation value combined with the influence of dynamic factors, a second revised evaluation value is obtained, and the second revised evaluation value is expressed as:

[0086]

[0087] Among them, S1 (t2) is the second corrected evaluation value, β is the adjustment coefficient of the impact of electricity price fluctuations, P t is the electricity price at the current time t, P t-1 is the electricity price at the previous moment t-1, θ is the reference value of electricity price fluctuation, γ is the adjustment coefficient affected by the change in trading volume, V t is the transaction volume at the current time t, V t-1 is the trading volume at the previous moment t-1.

[0088] Among them, dynamic factors include fluctuations in electricity prices and changes in transaction volume.

[0089] The electricity price fluctuation is measured by comparing the electricity price at the current time t with the electricity price at the previous time t-1, and the adjustment coefficient α of the impact of electricity price fluctuation is used to adjust the evaluation value;

[0090] The change in trading volume is measured by comparing the trading volume at the current moment t with the trading volume at the previous moment t-1, and the adjustment coefficient β of the impact of the change in trading volume is used to adjust the evaluation value.

[0091] The second corrected evaluation value is introduced into the periodic function to obtain the final safety verification result. The safety evaluation result is expressed as:

[0092]

[0093] Among them, S t is the final security verification result, δ is the intraday volatility factor, η is the market participant behavior factor, M t is the abnormal behavior index of market participants at the current time t, M ref is the threshold of the abnormal behavior index of market participants.

[0094] The threshold of the market participant behavior abnormality index is set as follows:

[0095] If a market participant's quotation frequency within 24 hours exceeds 200% of its average level in the past 30 days, and the quoted price fluctuation range exceeds ±30% of the market average price, the abnormal behavior index threshold of the participant is set at 0.6.

[0096] If within the 4 hours with the highest daily load, the actual output of a power generation enterprise continues to be lower than 85% of its bid commitment, and the system reserve capacity drops below 5% of the rated capacity, the abnormal behavior index threshold of the power generation enterprise is set to 0.5.

[0097] If the price change rate in the market for three consecutive trading sessions exceeds 300% of the same period of the previous day, and the quotations of at least three large market participants (market share > 10%) are concentrated in this price range, the behavioral anomaly index threshold of the overall market will be adjusted to 0.4.

[0098] If a participant's quotations in the spot market and the ancillary services market show a significant negative correlation (correlation coefficient <-0.8), and this pattern lasts for more than 7 days, and the resulting market settlement price deviation exceeds 25% of the historical average price, the abnormal behavior index threshold of the participant is set at 0.3.

[0099] If the intraday trading volume suddenly drops to less than 60% of the average level of the previous 30 days, and the bid-ask spread widens to more than 3 times the normal level, and this state lasts for more than 4 hours, the overall market behavior abnormality index threshold will be adjusted to 0.55.

[0100] If a participant's quote deviates from the real-time market average price by more than 50% over five consecutive trading days, and such deviation occurs for more than four hours on each trading day, the abnormal behavior index threshold of the participant will be set at 0.45.

[0101] If the system detects more than 10 sudden cancellations of large orders (single transaction volume exceeds 5% of the daily average transaction volume) within 24 hours, and these cancellations cause market price fluctuations to exceed 10%, the overall market behavior anomaly index threshold will be adjusted to 0.5.

[0102] If a power generation enterprise has a deviation of more than 20% between its actual power generation curve and the submitted power generation plan curve for more than 3 days within 7 days, and this deviation lasts for more than 6 hours per day, the abnormal behavior index threshold of the power generation enterprise is set to 0.4.

[0103] If the difference between the highest and lowest intraday prices in the market exceeds 200% of the average price for three consecutive days, and such large fluctuations cannot be explained by normal supply and demand relations, the threshold of the overall market's abnormal behavior index will be adjusted to 0.35.

[0104] In summary, the present invention combines deep learning technology with traditional statistical analysis, which can capture the complex nonlinear characteristics and time-varying characteristics of the market and effectively deal with the high uncertainty of the electricity market. By considering physical constraints such as the topology of the power grid and the characteristics of the generator set, the reliability and practicality of the evaluation are improved. In addition, the dynamic weight factor is used to achieve a balanced grasp of the instantaneous changes and long-term trends in the market. It provides more accurate decision-making support for market participants and helps maintain the fairness, stability and efficiency of the market. It not only improves the safety management level of the electricity spot market, but also provides new ideas and methods for risk assessment of other types of financial markets, and has broad application prospects and important practical value.

[0105] Example 2

[0106] Reference Figure 1 Based on the first embodiment, this embodiment further provides a power spot market security management verification system, including:

[0107] The collection module is used to obtain real-time transaction data of the power spot market and perform preprocessing;

[0108] An evaluation module, used to perform verification evaluation based on the preprocessed data using an LSTM network evaluation model to obtain a preliminary evaluation result;

[0109] The correction module is used to correct the preliminary evaluation results according to the preliminary evaluation results in combination with the power grid topology, obtain the final safety verification results, and complete the safety management verification of the power spot market.

[0110] This embodiment also provides a computer device, which is applicable to the case of the electricity spot market security management verification method, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the electricity spot market security management verification method proposed in the above embodiment.

[0111] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0112] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for realizing the safety management verification method of the electricity spot market as proposed in the above embodiment is implemented.

[0113] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0114] Example 3

[0115] On the basis of the previous two embodiments, this embodiment provides a method for verifying safety management of a power spot market. In order to verify the beneficial effects of the present invention, a scientific demonstration is carried out through simulation experiments.

[0116] The electricity spot market data of a certain region from January 1, 2022 to December 31, 2023 is used, including real-time transaction data at the 5-minute level and related historical statistics.

[0117] The comparison methods include:

[0118] Method A: Traditional statistical analysis method (threshold-based anomaly detection);

[0119] Method B: Single LSTM neural network method;

[0120] Method C: The method of the present invention.

[0121] The comparison results are shown in Table 1:

[0122] Table 1 Comparative Experimental Table of Safety Management Verification Analysis in Electricity Spot Market

[0123]

[0124]

[0125] It can be found from Table 1 that by comparing eight key indicators such as accuracy, F1 score, warning time, extreme event recognition rate, computational efficiency, false alarm rate, adaptability and interpretability, the method of the present invention performs well in all aspects. Not only is it significantly ahead of traditional statistical analysis and single LSTM methods in terms of accuracy and efficiency, it also demonstrates strong capabilities in handling extreme events and adapting to new market models. It is particularly noteworthy that while maintaining high accuracy, it also maintains a low false alarm rate and high interpretability, which is crucial for actual market supervision and risk management.

[0126] Although the computational time is slightly higher than the simplest statistical method, this slight computational overhead is completely acceptable considering the huge performance improvement it brings. In addition, the significant advantage in the early warning time provides market participants and regulators with more sufficient reaction time. In general, it highlights the huge potential in practical applications and is expected to bring revolutionary improvements to the safety management of the electricity spot market.

[0127] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for verifying the safety management of the electricity spot market, characterized in that: include, Obtain real-time transaction data and historical statistics from the electricity spot market and perform preprocessing; Based on the preprocessed data, a LSTM network evaluation model is used to perform verification evaluation to obtain a preliminary evaluation result; Based on the preliminary assessment results and combined with the power grid topology, the preliminary assessment results are corrected to obtain the final safety verification results, thereby completing the safety management verification of the electricity spot market.

2. The power spot market safety management verification method according to claim 1, characterized in that: The real-time transaction data includes real-time electricity prices, transaction volumes, supply and demand balance, market participant behavior, system operation status, and abnormal transaction marks; The historical statistical data includes historical transaction records, credit ratings of market participants, power grid topology, generator set characteristics, and load characteristics.

3. The power spot market safety management verification method according to claim 2, characterized in that: Preprocessing of the real-time transaction data, including data verification, real-time outlier detection, data standardization, feature encoding, real-time feature calculation, missing data processing, data alignment, and data streaming; Preprocessing of the historical statistical data, including data cleaning, missing value processing, time series analysis, data standardization / normalization, feature engineering, data encoding, data aggregation, correlation analysis, data segmentation, data enhancement, feature selection, and data storage; At the same time, the real-time transaction data and the historical statistical data are integrated and pre-processed, It includes feature consistency checking, scale alignment, time window matching, dynamic feature updating, and model input preparation.

4. The power spot market safety management verification method according to claim 3, characterized in that: Based on the LSTM network evaluation model, a preliminary evaluation of the real-time security status of the power spot market is performed. The preliminary evaluation result is expressed as follows: Among them, S1 is the preliminary safety assessment value; P t is the electricity price vector at time t; V t is the trading volume vector at time t; B t is the supply and demand balance at time t; W p ,W v ,W b is the weight matrix; b is the bias term; σ is the S-type activation function.

5. The power spot market safety management verification method according to claim 4, characterized in that: The amendment includes a first amendment and a second amendment; The first correction is obtained based on the preliminary evaluation result S1 combined with historical statistical data, and is expressed as: Among them, S1 (t1) is the first revised evaluation value, S1 is the preliminary safety evaluation value, n is the number of features considered, x i is the historical average or reference value of the i-th feature, x t is the actual value of the i-th feature at the current moment, σ i is the historical standard deviation of the i-th feature, α i Represents the weight coefficient of the i-th feature.

6. The power spot market safety management verification method according to claim 5, characterized in that: Based on the first modified evaluation value combined with the influence of dynamic factors, a second modified evaluation value is obtained, and the second modified evaluation value is expressed as: Among them, S1 (t2) is the second corrected evaluation value, β is the adjustment coefficient of the impact of electricity price fluctuations, P t is the electricity price at the current time t, P t-1 is the electricity price at the previous moment t-1, θ is the reference value of electricity price fluctuation, γ is the adjustment coefficient affected by the change in trading volume, V t is the transaction volume at the current time t, V t-1 is the trading volume at the previous moment t-1.

7. The power spot market safety management verification method according to claim 6, characterized in that: A periodic function is introduced based on the second corrected evaluation value to obtain a final safety verification result, which is expressed as: Among them, S t is the final security verification result, δ is the intraday volatility factor, η is the market participant behavior factor, M t is the abnormal behavior index of market participants at the current time t, M ref is the threshold of the abnormal behavior index of market participants.

8. A power spot market security management verification system, based on the power spot market security management verification method according to any one of claims 1 to 7, characterized in that: include, The collection module is used to obtain real-time transaction data of the power spot market and perform preprocessing; An evaluation module, used to perform verification evaluation based on the preprocessed data using an LSTM network evaluation model to obtain a preliminary evaluation result; The correction module is used to correct the preliminary evaluation results according to the preliminary evaluation results in combination with the power grid topology, obtain the final safety verification results, and complete the safety management verification of the power spot market.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the power spot market security management verification method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the power spot market security management verification method according to any one of claims 1 to 7 are implemented.

Images