Quantitative measuring and calculating method and system for unbalanced fund scale and kilowatt-hour electricity allocation in electricity market

Abstract

The invention relates to a quantitative measurement and calculation method and system for an unbalanced fund scale and kilowatt-hour sharing of an electricity market. The method comprises the following steps: establishing a multivariate data fusion system based on a 3 sigma principle and principal component analysis (PCA), and collecting and fusing power market transaction data, load data, new energy power generation data and power grid operation data; comprehensively considering the power generation deviation electric quantity and the market price deviation to construct an unbalanced fund scale calculation model, and further obtaining an unbalanced fund scale; constructing a kilowatt-hour apportionment calculation model considering differences of different market members, determining apportionment factors by adopting an analytic hierarchy process, and calculating a kilowatt-hour apportionment amount of each power generation enterprise; and establishing a solving model based on a particle swarm optimization algorithm so as to obtain an accurate unbalanced fund scale and a fair and reasonable kilowatt-hour electricity allocation scheme.

Description

Technical Field

[0001] The present invention belongs to the field of power market operation, and in particular relates to a method and system for quantitatively calculating the scale of unbalanced funds and per-kilowatt-hour electricity sharing in the power market. Background Art

[0002] With the continuous advancement of power market reform, the scale and complexity of power market transactions are increasing. The issue of imbalance funds has become increasingly prominent in power market transactions. This not only affects the economic interests of market participants but can also adversely impact the stable operation of the power market. Imbalance funds primarily arise from factors such as the discrepancy between actual and planned power generation output, market price fluctuations, and imperfect trading rules. Currently, methods for estimating the scale of imbalance funds and their allocation per kilowatt-hour remain deficient.

[0003] For example, existing technologies use simple statistical methods to estimate the size of imbalanced funds based solely on historical transaction data. This approach ignores the numerous complex factors influencing the electricity market, such as the randomness of renewable energy generation, the dynamic changes in load, and the uncertainty of market participant behavior, resulting in poorly accurate estimates. Furthermore, when calculating per-kilowatt-hour (kWh) electricity allocation, some existing methods fail to fully account for differences in generation costs and load characteristics among market participants. Their one-size-fits-all approach to allocation fails to achieve fair and reasonable allocation, sparking disputes among market participants.

[0004] In addition, although some complex models take multiple factors into consideration, they often have problems such as overly complex model structures and excessive computational effort, making them difficult to quickly apply in actual power market operations and unable to meet the market's real-time decision-making needs.

[0005] In summary, the existing measurement methods have obvious defects in accuracy, fairness and practicality. Summary of the Invention

[0006] In order to address the deficiencies in the prior art, the present invention provides a method and system for quantitatively calculating the scale of unbalanced funds in the power market and the per-kilowatt-hour electricity allocation, so as to provide data support and decision-making basis for the stable operation and fair trading of the power market and optimize the efficiency of resource allocation in the power market.

[0007] In order to solve the above technical problems, the present invention adopts the following technical solutions.

[0008] The present invention first discloses a method for quantitatively calculating the scale of funds for imbalance in the power market and the allocation of electricity per kilowatt-hour, which includes the following steps:

[0009] Step 1: Collect multivariate data of the electricity market, pre-process the data based on the 3σ principle, and then use the principal component analysis method to fuse the data to obtain a comprehensive data set for subsequent measurement;

[0010] Step 2: Calculate the power generation deviation and market price deviation of the power market, and build an imbalance capital scale calculation model based on the comprehensive data set and the power generation deviation and market price deviation. The imbalance capital scale calculation model is used to output the imbalance capital scale of the power market;

[0011] Step 3: Calculate the allocation factor for each power generation enterprise through the hierarchical structure model. Based on the allocation factor and the size of the imbalance fund, construct a kilowatt-hour allocation calculation model that takes into account the differences among different market members. The kilowatt-hour allocation calculation model is used to calculate the kilowatt-hour allocation amount for each power generation enterprise.

[0012] Step 4: Solve the imbalance fund scale calculation model and the kilowatt-hour electricity sharing calculation model based on a genetic algorithm to obtain the optimal imbalance fund scale and kilowatt-hour electricity sharing amount.

[0013] The present invention further includes the following preferred embodiments:

[0014] The collecting of multivariate data of the electricity market further includes:

[0015] Collect electricity market transaction data, including power generation plans, actual power output, transaction volume, and transaction price data of each power generation company;

[0016] Obtain power load data in different regions and time periods, and collect load forecast data;

[0017] Integrate renewable energy power generation forecast data, actual power generation data, and location information of renewable energy power generation connected to the grid;

[0018] Obtain grid operation data, including transmission line losses, transformer losses, and voltage fluctuation data.

[0019] The preprocessing of the multivariate data of the power market based on the 3σ principle further includes:

[0020] The 3σ principle based on statistics is used to detect outliers. For a set of data x1, x2, ..., x n , n is the number of data, calculate its mean And the standard deviation σ:

[0021]

[0022] If the data point x j satisfy Then determine xj is an outlier;

[0023] For the detected outliers, the data smoothing method is used to process them, and the mean of the adjacent data is used to replace the outliers; assuming x j For outliers, use x j-1 and x j+1 The mean of x j ,Right now:

[0024]

[0025] If j = 1, then x2 replaces x1; if j = n, then x n-1 Replace x n ;

[0026] Duplicate data is identified by comparing the unique identifier of the data, which includes a combination of the transaction number, the power generation enterprise ID and the timestamp. If there are multiple data with exactly the same unique identifiers, one of them is retained and the rest of the duplicate data is deleted.

[0027] The data fusion using principal component analysis method further includes:

[0028] (1) Standardize the data after feature selection so that different features have the same scale. For each feature x i , the standardization formula is:

[0029]

[0030] in, is the standardized feature data, and σ are the mean and standard deviation of the feature respectively;

[0031] (2) The standardized data is constructed into a matrix X, and its covariance matrix C is calculated. The elements of the covariance matrix C are ij The calculation formula is:

[0032]

[0033] Where n is the number of samples, and are the normalized values ​​of the kth sample on the i-th and j-th features, respectively. and are the standardized means of the i-th and j-th features respectively;

[0034] (3) Perform eigenvalue decomposition on the covariance matrix C and obtain the eigenvalues ​​λ1≥λ2≥…≥λ p and the corresponding eigenvectors e1,e2,…,e p ; p is the number of features;

[0035] (4) Calculate the contribution rate α of each eigenvalue i and the cumulative contribution rate β k , the calculation formulas are:

[0036]

[0037] Select the cumulative contribution rate β k principal components that reach a predefined threshold;

[0038] (5) The selected principal components are used as new features and fused with the data after feature selection to finally obtain a comprehensive data set for subsequent measurement.

[0039] The calculation of the power generation deviation and the market price deviation in the power market further includes:

[0040] Calculate the power generation deviation:

[0041]

[0042] Where ΔQ i represents the power generation deviation of the i-th power generation enterprise, is the actual power generation output of the i-th power generation enterprise, is the power generation plan of the i-th power generation enterprise;

[0043] Calculate market price deviation ΔP t :

[0044] ΔP t =P t -P0

[0045] Assume that the market has n trading sessions, and the market transaction price in each session is P t , the base price is P0.

[0046] The step of constructing an unbalanced capital scale calculation model by combining the power generation deviation and the market price deviation further includes:

[0047] Calculate the size of unbalanced funds:

[0048]

[0049] Where m is the number of power generation companies, n is the number of trading periods, ΔQ i,t is the power generation deviation of the i-th power generation enterprise in the t-th period, L j Other factors that lead to imbalanced funds.

[0050] The solving the imbalance fund scale calculation model and the kilowatt-hour electricity sharing calculation model based on the genetic algorithm further includes:

[0051] A predefined number of particles are randomly generated. Each particle represents a set of decision variable values, i.e., the power generation plan and trading strategy combination of the power generation company. The position of the particle represents the initial value of the decision variable, and the particle speed determines the direction and step size of the particle's movement in the search space.

[0052] Set the maximum number of iterations T for the genetic algorithm to run;

[0053] Set crossover probability and mutation probability;

[0054] Substitute the position of each particle into the imbalanced capital scale calculation model and the per-kilowatt-hour electricity allocation calculation model, calculate the corresponding imbalanced capital scale and per-kilowatt-hour electricity allocation amount, and use them as the particle's fitness value;

[0055] The particle position and velocity are continuously updated according to the particle swarm optimization algorithm. In each iteration, the particle adjusts its movement direction and step size based on its own historical optimal position and the global optimal position of the swarm, gradually approaching the optimal solution.

[0056] Set the maximum number of iterations or the convergence accuracy of the fitness value as the termination condition. When the maximum number of iterations is reached or the change in the fitness value is less than the set convergence accuracy, the iteration is stopped and the optimal solution is output.

[0057] The present invention also discloses a system for quantitatively calculating the scale of funds and per-kilowatt-hour allocation in the power market using the aforementioned method for quantitatively calculating the scale of funds and per-kilowatt-hour allocation in the power market, comprising:

[0058] A data acquisition and fusion module is used to collect multivariate data from the power market, pre-process the multivariate data based on the 3σ principle, and then fuse the data using principal component analysis to obtain a comprehensive data set for subsequent measurement;

[0059] An unbalanced capital scale calculation model construction module is used to calculate the power generation deviation and market price deviation of the power market, and to construct an unbalanced capital scale calculation model based on the comprehensive data set and in combination with the power generation deviation and the market price deviation. The unbalanced capital scale calculation model is used to output the unbalanced capital scale of the power market;

[0060] A kilowatt-hour electricity allocation calculation model construction module is used to calculate the allocation factor of each power generation enterprise through a hierarchical structure model, and based on the allocation factor and the imbalance fund scale, construct a kilowatt-hour electricity allocation calculation model that takes into account the differences between different market members. The kilowatt-hour electricity allocation calculation model is used to calculate the kilowatt-hour electricity allocation amount of each power generation enterprise;

[0061] The model solving module is used to solve the imbalance fund scale calculation model and the kilowatt-hour electricity sharing calculation model based on a genetic algorithm to obtain the optimal imbalance fund scale and kilowatt-hour electricity sharing amount.

[0062] Accordingly, the present application also discloses a terminal, including a processor and a storage medium;

[0063] The storage medium is used to store instructions;

[0064] The processor is used to operate according to the instructions to execute the steps of the quantitative calculation method based on the above-mentioned power market imbalance fund scale and kilowatt-hour electricity sharing.

[0065] Accordingly, the present application also discloses a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the aforementioned method for quantitatively calculating the scale of electricity market imbalance funds and per-kilowatt-hour electricity sharing.

[0066] The beneficial effects of the present invention are that, compared with the prior art, the present invention provides a quantitative measurement method and system for the scale of imbalance funds and per-kilowatt-hour electricity allocation in the power market. By integrating multivariate data, the present invention comprehensively considers various factors affecting the scale of imbalance funds and per-kilowatt-hour electricity allocation in the power market, and the constructed measurement model is more in line with the actual market situation. Compared with traditional methods, it can significantly improve the accuracy of the measurement results and provide reliable data support for the precise management of the power market. In the per-kilowatt-hour electricity allocation measurement model, the hierarchical analysis method is used to determine the allocation factors, fully considering the differences in power generation costs, load characteristics and grid impacts of different power generation enterprises, achieving fair and reasonable allocation of imbalance funds, effectively reducing disputes among market members, and promoting fair transactions in the power market. The particle swarm optimization algorithm is used to solve the model. The algorithm has fast convergence speed and high computational efficiency, and can obtain the optimal solution in a short time, meeting the needs of real-time decision-making in the power market. At the same time, the algorithm is easy to implement and can be conveniently applied to actual power market operation and management to improve the operational efficiency of the power market. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 This is a flow chart of the method for quantitatively calculating the scale of funds for imbalance in the power market and the kilowatt-hour allocation of electricity in the present invention. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solutions and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0069] The embodiments described in this application are only part of the embodiments of the present invention, not all of the embodiments. Based on the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without making creative work are all within the scope of protection of the present invention.

[0070] In response to the shortcomings of the existing technology, the present invention proposes a method and system for quantitatively measuring the scale of funds for imbalance in the power market and the allocation of electricity per kilowatt-hour. By integrating multivariate data, constructing a comprehensive measurement model, and applying an optimization algorithm to solve the problem, the method achieves accurate measurement of the scale of funds for imbalance in the power market and fair and reasonable allocation of electricity per kilowatt-hour, providing strong support for the scientific management and healthy development of the power market.

[0071] See also Figure 1 As shown, the method for quantitatively calculating the scale of funds for imbalance in the power market and the allocation of electricity per kilowatt-hour disclosed in the present invention includes the following steps:

[0072] Step 1: Collect multivariate data of the electricity market, pre-process the multivariate data based on the 3σ principle, and then use the principal component analysis method to fuse the data to obtain a comprehensive data set for subsequent measurement.

[0073] There are many factors that affect the scale of imbalance funds and the distribution of electricity in the power market. In order to obtain comprehensive and accurate data, it is necessary to establish a multi-data fusion system. Step 1 further includes:

[0074] Step 1.1: Collect and integrate multivariate data of the power market, including power market transaction data, power load data, renewable energy generation data, and power grid operation data.

[0075] (1) Collect electricity market transaction data, including the power generation plans, actual power output, transaction volume, transaction prices and other data of each power generation enterprise. These data reflect the transaction behavior and power generation situation of the electricity market and are the basic data for measurement.

[0076] (2) Obtain power load data for different regions and time periods, taking into account seasonal and cyclical load changes and the impact of emergencies on load. At the same time, collect load forecast data, such as the output results of load forecast models based on historical load data and meteorological data, for comprehensive analysis of load change trends.

[0077] (3) Integrate renewable energy power generation data. Given the intermittent and fluctuating nature of renewable energy generation, such as wind power and photovoltaics, data on power generation forecasts, actual power generation, and the location of renewable energy power grid connections are collected. As renewable energy generation accounts for a growing share of the electricity market, accurately understanding its power generation is crucial for measuring the scale of unbalanced funds.

[0078] (4) Obtain grid operation data, including data on transmission line losses, transformer losses, voltage fluctuations, etc. The grid operation status affects the transmission and distribution of electricity, which in turn affects the scale of imbalance funds and the allocation of electricity per kilowatt-hour. This data helps to make more accurate calculations.

[0079] Step 1.2: Clean and preprocess all types of collected data to remove outliers and duplicate data. Then, use data fusion technology (such as methods based on feature selection and principal component analysis) to fuse data from different sources to obtain a comprehensive data set for subsequent measurement.

[0080] (1) Outlier detection and processing. In the power market data, outliers may be caused by equipment failure, data transmission errors, etc., which will seriously affect the accuracy of the measurement results. The 3σ principle based on statistics is used for outlier detection. For a set of data x1, x2, ..., x n , n is the number of data, first calculate its mean And standard deviation σ, the calculation formulas are:

[0081]

[0082] If the data point x j satisfy Then determine x j is an outlier.

[0083] For the detected outliers, the data smoothing method is used to process them and the mean of the adjacent data is used to replace the outliers. Assume that x j For outliers, use x j-1 and x j+1 The mean of x j ,Right now:

[0084]

[0085] If j = 1, then x2 replaces x1; if j = n, then x n-1 Replace x n .

[0086] (2) Duplicate data processing. Duplicate data increases the computational complexity and may affect model performance. Duplicate data is identified by comparing the unique identifiers of the data (such as transaction number, power generation company ID, and timestamp combination). If there are multiple data with the same unique identifier, one of them is retained and the remaining duplicate data is deleted.

[0087] Step 1.3: Data fusion based on principal component analysis (PCA):

[0088] (1) Standardize the data after feature selection so that different features have the same scale to avoid the influence of different feature dimensions on the principal component analysis results. i , the standardization formula is:

[0089]

[0090] in, is the standardized feature data, and σ are the mean and standard deviation of the feature respectively.

[0091] (2) The standardized data is constructed into a matrix X, and its covariance matrix C is calculated. The elements of the covariance matrix C are ij The calculation formula is:

[0092]

[0093] Where n is the number of samples, and are the normalized values ​​of the kth sample on the i-th and j-th features, respectively. and are the standardized means of the i-th and j-th features respectively.

[0094] (3) Perform eigenvalue decomposition on the covariance matrix C and obtain the eigenvalues ​​λ1≥λ2≥…≥λ p (p is the number of features) and the corresponding eigenvectors e1, e2,…, e p The eigenvalue reflects the variance of the principal component. The larger the variance, the more information the principal component contains.

[0095] (4) Select the principal component. Calculate the contribution rate α of each eigenvalue i and the cumulative contribution rate β k , the calculation formulas are:

[0096]

[0097] In a specific embodiment, the cumulative contribution rate β is selected k The first k principal components that reach a predefined threshold (such as 85% or 90%, which can be adjusted according to actual conditions) retain the main information of the original data while achieving data dimensionality reduction.

[0098] (5) The selected principal components are used as new features and fused with the data after feature selection. Assuming that k principal components are selected, the comprehensive data set consists of these k principal components and key features with importance scores greater than the threshold. Through the above steps of data cleaning, feature selection, and principal component analysis, a comprehensive data set for subsequent measurement is finally obtained. This data set can not only retain the key information of the original data, but also reduce the data dimension and improve the measurement efficiency and accuracy.

[0099] Step 2: Calculate the power generation deviation and market price deviation of the power market, and build an unbalanced capital scale calculation model based on the comprehensive data set and the power generation deviation and the market price deviation. The unbalanced capital scale calculation model is used to output the unbalanced capital scale of the power market.

[0100] Based on the integrated multivariate data, a model for calculating the scale of unbalanced funds is constructed to accurately calculate the scale of unbalanced funds in the power market. Step 2 specifically includes:

[0101] Step 2.1: Calculate the power generation deviation. Power generation deviation is one of the important factors that lead to the generation of unbalanced funds. For each power generation enterprise, the power generation deviation calculation formula is:

[0102]

[0103] Where ΔQ i represents the power generation deviation of the i-th power generation enterprise, is the actual power generation output of the i-th power generation enterprise, is the power generation plan of the i-th power generation enterprise.

[0104] Step 2.2: Determine the market price deviation. Market price fluctuations will also cause changes in the imbalanced funds. The market price deviation is determined by calculating the difference between the actual market transaction price and the benchmark price. Assume that the market has n trading sessions and the market transaction price in each session is P t , the benchmark price is P0, then the market price deviation is:

[0105] ΔP t =P t -P0 (9)

[0106] Step 2.3: Considering the power generation deviation and market price deviation, a model for calculating the imbalanced capital scale is constructed:

[0107]

[0108] Among them, U represents the scale of unbalanced funds, m is the number of power generation companies, n is the number of trading periods, ΔQ i,tis the power generation deviation of the i-th power generation enterprise in the t-th period, L j Other factors that lead to imbalance funds, such as adjustments to grid operating costs, are included. This formula comprehensively considers the impact of power generation deviation and price deviation on the scale of imbalance funds, and can more accurately calculate the scale of imbalance funds.

[0109] Step 3: Calculate the allocation factor of each power generation enterprise through the hierarchical model. Based on the allocation factor and the scale of the imbalance fund, construct a kilowatt-hour allocation calculation model that takes into account the differences between different market members. The kilowatt-hour allocation calculation model is used for the kilowatt-hour allocation amount of each power generation enterprise.

[0110] In order to achieve fair and reasonable allocation of electricity, a electricity allocation calculation model is constructed to fully consider the differences between different market members. Step 3 further includes:

[0111] Step 3.1: Establish a hierarchical model consisting of a target layer, a criterion layer, and a plan layer. The target layer is set as the allocation of unbalanced funds per kWh; the criterion layer includes factors such as power generation costs, load stability, and grid impact; and the plan layer is for each power generation company. The relative importance of each factor is determined through expert scoring, etc., and a judgment matrix is ​​constructed. The weight of each factor is calculated to obtain the allocation factor for each power generation company.

[0112] The allocation factor is a key parameter in the per-kilowatt-hour allocation calculation, reflecting each market member's share of the unbalanced funds. Considering factors such as the power generation cost, load characteristics, and the impact on grid stability of the power generation company, the present invention uses the Analytic Hierarchy Process (AHP) to determine the allocation factor. Specifically:

[0113] (1) Construct a hierarchical model. In the problem of allocating unbalanced funds per kWh in the power market, the constructed hierarchical model includes the target layer, the criterion layer, and the scheme layer. The target layer is the allocation of unbalanced funds per kWh; the criterion layer includes three main factors: power generation cost, load stability, and grid impact. Power generation cost reflects the inherent cost differences of different power generation companies in producing electricity and is an important factor affecting the fairness of allocation; load stability reflects the fluctuation of the load borne by each power generation company. Companies with small load fluctuations contribute relatively more to market stability and should be reflected in the allocation; grid impact takes into account factors such as the location of the power generation company's access to the grid and the degree of impact on grid loss and stability. The scheme layer refers to each power generation company.

[0114] (2) The expert scoring method is used to determine the relative importance of each factor and then construct a judgment matrix.

[0115] For any two factors A in the criterion layer i and A j(i, j = 1, 2, 3, corresponding to power generation cost, load stability, and grid impact, respectively), and compared them pairwise using a 1-9 scale based on the experience and relevant data of experts. 1 means that the two factors are equally important, 3 means that A i than A j More important, 5 means A i than A j Obviously important, 7 means A i than A j Strongly important, 9 means A i than A j Extremely important, 2, 4, 6, and 8 are the intermediate values ​​of the above judgment.

[0116] Assume that the judgment matrix constructed for power generation cost (A1), load stability (A2), and grid impact (A3) is A:

[0117]

[0118] Among them, represents A i With A j The importance scale value of the comparison, and a ji =1 / a ij .

[0119] (3) Use the eigenvalue method to calculate the maximum eigenvalue λ of the judgment matrix max and the corresponding eigenvector W.

[0120] First, calculate the characteristic polynomial det(A-λI) of the judgment matrix A, where λ is the eigenvalue and I is the unit matrix. For each obtained eigenvalue, the corresponding eigenvector W can be found, and then the maximum eigenvalue λ is calculated. max

[0121]

[0122] Where n is the order of the judgment matrix (n=3 in this embodiment), (AW) i is the i-th element of vector AW, W i is the i-th element of the eigenvector W.

[0123] Normalize the calculated eigenvector W to obtain the weight of each factor, that is, the allocation factor ω i (i=1,2,3). The normalization formula is:

[0124]

[0125] Step 3.2: Calculate the per-kilowatt-hour electricity allocation for each power generation enterprise based on the allocation factor and the scale of the imbalance fund.

[0126] (1) When calculating the per-kilowatt-hour apportionment amount, it is necessary to consider the actual power generation output of each power generation enterprise. The scale of unbalanced funds is known to be U, and the actual power generation output of the i-th power generation enterprise is The total actual power generation output of all power generation enterprises is m is the number of power generation enterprises.

[0127] (2) According to the allocation factor ω i and the scale of unbalanced funds U, calculate the electricity sharing amount A for each power generation enterprise i :

[0128]

[0129] Among them, ω i is the allocation factor determined by the i-th power generation enterprise based on factors such as power generation cost, load stability, and grid impact, reflecting the relative responsibility of the power generation enterprise in the imbalance fund allocation; U is the scale of imbalance funds in the power market; represents the total actual power generation of all power generation companies. This formula allocates the imbalance fund size according to each power generation company's allocation factor, and then calculates the amount to be shared per kilowatt-hour based on each company's actual power generation. This calculation method fully considers the individual differences of power generation companies and their actual power generation contributions, ensuring fair allocation of imbalance funds at the kilowatt-hour level.

[0130] Step 4: Solve the imbalance fund scale calculation model and the kilowatt-hour electricity sharing calculation model based on a genetic algorithm to obtain the optimal imbalance fund scale and kilowatt-hour electricity sharing amount.

[0131] Because the calculation model for imbalance fund size and per-kilowatt-hour electricity allocation involves multiple variables and complex calculations, an optimization algorithm is employed to improve solution efficiency and accuracy. Particle swarm optimization, a swarm intelligence-based optimization algorithm, boasts rapid convergence and ease of implementation. In this method, imbalance fund size and per-kilowatt-hour electricity allocation are used as optimization objectives, while power generation company generation plan adjustments and trading strategies are used as decision variables.

[0132] Step 4.1: Initialize the particle swarm. A predefined number of particles are randomly generated, each representing a set of decision variable values, namely, a combination of a power generation company's power generation plan and trading strategy. The particle's position and velocity are randomly initialized within a certain range. The position represents the initial value of the decision variable, while the velocity determines the particle's movement direction and step size in the search space.

[0133] Step 4.2: Set the maximum number of iterations, T, for the genetic algorithm to terminate. This parameter determines the algorithm's search time and depth. For example, setting T = 200 iterations ensures the algorithm has enough time to find a good solution.

[0134] Step 4.3: Set the learning rate. In genetic algorithms, crossover probability and mutation probability affect the convergence speed and search ability of the algorithm. Crossover probability P c Control the frequency of individual crossover operations, mutation probability P m Controls the probability of individual mutation operation. In a preferred embodiment, P c The value is between 0.6-0.95, P m The value range is 0.001-0.01. For example, set P c =0.8, P m =0.005.

[0135] Step 4.4: Substitute the position of each particle into the imbalanced capital scale calculation model and the per-kWh electricity allocation calculation model to calculate the corresponding imbalanced capital scale and per-kWh electricity allocation amount. This is used as the particle's fitness value. The fitness value reflects the quality of the decision variable combination represented by the particle.

[0136] Step 4.5: Continuously update the particle position and velocity according to the iterative formula of the particle swarm optimization algorithm. In each iteration, the particle adjusts its movement direction and step size based on its own historical optimal position and the global optimal position of the swarm, gradually approaching the optimal solution.

[0137] Step 4.6: Set the maximum number of iterations or the convergence accuracy of the fitness value as the termination condition. When the algorithm reaches the maximum number of iterations or the change in the fitness value is less than the set convergence accuracy, the algorithm stops iterating and outputs the optimal solution, which is the accurate imbalance fund scale and fair and reasonable power allocation plan.

[0138] The beneficial effects of the present invention are that, compared with the prior art, the present invention provides a quantitative measurement method and system for the scale of imbalance funds and per-kilowatt-hour electricity allocation in the power market. By integrating multivariate data, the present invention comprehensively considers various factors affecting the scale of imbalance funds and per-kilowatt-hour electricity allocation in the power market, and the constructed measurement model is more in line with the actual market situation. Compared with traditional methods, it can significantly improve the accuracy of the measurement results and provide reliable data support for the precise management of the power market. In the per-kilowatt-hour electricity allocation measurement model, the hierarchical analysis method is used to determine the allocation factors, fully considering the differences in power generation costs, load characteristics and grid impacts of different power generation enterprises, achieving fair and reasonable allocation of imbalance funds, effectively reducing disputes among market members, and promoting fair transactions in the power market. The particle swarm optimization algorithm is used to solve the model. The algorithm has fast convergence speed and high computational efficiency, and can obtain the optimal solution in a short time, meeting the needs of real-time decision-making in the power market. At the same time, the algorithm is easy to implement and can be conveniently applied to actual power market operation and management to improve the operational efficiency of the power market.

[0139] The present invention may be a system, method, and / or computer program product. The present invention also discloses a system for quantitatively calculating the scale of funds for imbalance in the power market and the per-kilowatt-hour allocation of electricity, based on the aforementioned method for quantitatively calculating the scale of funds for imbalance in the power market and the per-kilowatt-hour allocation of electricity, comprising:

[0140] A data acquisition and fusion module is used to collect multivariate data from the power market, pre-process the multivariate data based on the 3σ principle, and then fuse the data using principal component analysis to obtain a comprehensive data set for subsequent measurement;

[0141] An unbalanced capital scale calculation model construction module is used to calculate the power generation deviation and market price deviation of the power market, and to construct an unbalanced capital scale calculation model based on the comprehensive data set and in combination with the power generation deviation and the market price deviation. The unbalanced capital scale calculation model is used to output the unbalanced capital scale of the power market;

[0142] A kilowatt-hour electricity allocation calculation model construction module is used to calculate the allocation factor of each power generation enterprise through a hierarchical structure model, and based on the allocation factor and the imbalance fund scale, construct a kilowatt-hour electricity allocation calculation model that takes into account the differences between different market members. The kilowatt-hour electricity allocation calculation model is used to calculate the kilowatt-hour electricity allocation amount of each power generation enterprise;

[0143] The model solving module is used to solve the imbalance fund scale calculation model and the kilowatt-hour electricity sharing calculation model based on a genetic algorithm to obtain the optimal imbalance fund scale and kilowatt-hour electricity sharing amount.

[0144] Based on the spirit of the present invention, those skilled in the art can easily conceive of a computer program product based on the aforementioned method for quantitatively calculating the scale of electricity market imbalance funds and per-kilowatt-hour electricity allocation. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure. That is, the present application also includes a terminal comprising a processor and a storage medium; the storage medium is configured to store instructions; and the processor is configured to operate according to the instructions to execute the steps of the aforementioned method for quantitatively calculating the scale of electricity market imbalance funds and per-kilowatt-hour electricity allocation.

[0145] Computer-readable storage medium can be the tangible device that can keep and store the instruction used by instruction execution device.Computer-readable storage medium can be, for example, but not limited to, electric storage device, magnetic storage device, optical storage device, electromagnetic storage device, semiconductor storage device or above-mentioned any suitable combination.The more specific example (non-exhaustive list) of computer-readable storage medium comprises: portable computer disk, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical coding device, for example, punch card or the convex structure in the groove that stores instruction thereon and above-mentioned any suitable combination.Computer-readable storage medium used here is not interpreted as instantaneous signal itself, such as radio wave or other free propagating electromagnetic wave, electromagnetic wave (for example, by the light pulse of fiber optic cable) that waveguide or other transmission medium propagates or the electric signal that is transmitted by wire.

[0146] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0147] The computer program instructions for performing the operation of the present disclosure can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, and conventional procedural programming languages ​​such as "C" language or similar programming languages. Computer-readable program instructions can be executed entirely on a user's computer, partially on a user's computer, executed as an independent software package, partially on a user's computer and partially on a remote computer, or executed entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer via any type of network including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., utilizing an Internet service provider to connect via the Internet). In some embodiments, by utilizing the state information of computer-readable program instructions to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0148] Finally, 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 above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for quantitatively calculating the scale of funds for imbalance in the power market and the per-kilowatt-hour electricity allocation, characterized in that: The following steps are involved: Collecting multivariate data from the electricity market, preprocessing the data based on the 3σ principle, and then fusing the data using principal component analysis to obtain a comprehensive data set for subsequent measurement; Calculating the power generation deviation and market price deviation in the power market, and constructing an imbalance capital scale calculation model based on the comprehensive data set and in combination with the power generation deviation and the market price deviation, wherein the imbalance capital scale calculation model is used to output the imbalance capital scale in the power market; Calculate the allocation factor of each power generation enterprise through the hierarchical structure model, and build a kilowatt-hour allocation calculation model that takes into account the differences between different market members based on the allocation factor and the imbalance fund scale. The kilowatt-hour allocation calculation model is used to calculate the kilowatt-hour allocation amount of each power generation enterprise; The imbalance fund scale calculation model and the kilowatt-hour electricity sharing calculation model are solved based on a genetic algorithm to obtain the optimal imbalance fund scale and kilowatt-hour electricity sharing amount.

2. The method for quantitatively calculating the scale of funds for imbalance in the power market and the per-kilowatt-hour electricity allocation according to claim 1, characterized in that: The collecting of multivariate data of the electricity market further includes: Collect electricity market transaction data, including power generation plans, actual power output, transaction volume, and transaction price data of each power generation company; Obtain power load data in different regions and time periods, and collect load forecast data; Integrate renewable energy power generation forecast data, actual power generation data, and location information of renewable energy power generation connected to the grid; Obtain grid operation data, including transmission line losses, transformer losses, and voltage fluctuation data.

3. The method for quantitatively calculating the scale of power market imbalance funds and per-kilowatt-hour electricity allocation according to claim 2, characterized in that: The preprocessing of the multivariate data of the power market based on the 3σ principle further includes: The 3σ principle based on statistics is used to detect outliers. For a set of data x1, x2, ..., x n , n is the number of data, calculate its mean And the standard deviation σ: If the data point x j satisfy Then determine x j is an outlier; For the detected outliers, the data smoothing method is used to process them, and the mean of the adjacent data is used to replace the outliers; assuming x j For outliers, use x j-1 and x j+1 The mean of x j ,Right now: If j = 1, then x2 replaces x1; if j = n, then x n-1 Replace x n ; Duplicate data is identified by comparing the unique identifier of the data, which includes a combination of the transaction number, the power generation enterprise ID and the timestamp. If there are multiple data with exactly the same unique identifiers, one of them is retained and the rest of the duplicate data is deleted.

4. The method for quantitatively calculating the scale of funds for power market imbalance and per-kilowatt-hour electricity allocation according to claim 3 is characterized in that: The data fusion using principal component analysis method further includes: (1) Standardize the data after feature selection so that different features have the same scale. For each feature x i , the standardization formula is: in, is the standardized feature data, and σ are the mean and standard deviation of the feature respectively; (2) The standardized data is constructed into a matrix X, and its covariance matrix C is calculated. The elements of the covariance matrix C are ij The calculation formula is: Where n is the number of samples, and are the normalized values ​​of the kth sample on the i-th and j-th features, respectively. and are the standardized means of the i-th and j-th features respectively; (3) Perform eigenvalue decomposition on the covariance matrix C and obtain the eigenvalues ​​λ1≥λ2≥…≥λ p and the corresponding eigenvectors e1,e2,…,e p ; p is the number of features; (4) Calculate the contribution rate α of each eigenvalue i and the cumulative contribution rate β k , the calculation formulas are: Select the cumulative contribution rate β k principal components that reach a predefined threshold; (5) The selected principal components are used as new features and fused with the data after feature selection to finally obtain a comprehensive data set for subsequent measurement.

5. The method for quantitatively calculating the scale of funds for imbalance in the power market and the per-kilowatt-hour electricity allocation according to claim 4 is characterized in that: The calculation of the power generation deviation and the market price deviation in the power market further includes: Calculate the power generation deviation: Where ΔQ i represents the power generation deviation of the i-th power generation enterprise, is the actual power generation output of the i-th power generation enterprise, is the power generation plan of the i-th power generation enterprise; Calculate market price deviation ΔP t : ΔP t =P t -P0 Assume that the market has n trading sessions, and the market transaction price in each session is P t , the base price is P0.

6. The method for quantitatively calculating the scale of funds for imbalance in the power market and the per-kilowatt-hour electricity allocation according to claim 5, characterized in that: The step of constructing an unbalanced capital scale calculation model by combining the power generation deviation and the market price deviation further includes: Calculate the size of unbalanced funds: Where m is the number of power generation companies, n is the number of trading periods, ΔQ i,t is the power generation deviation of the i-th power generation enterprise in the t-th period, L j Other factors that lead to imbalanced funds.

7. The method for quantitatively calculating the scale of funds for imbalance in the power market and the per-kilowatt-hour electricity allocation according to claim 6, characterized in that: The solving the imbalance fund scale calculation model and the kilowatt-hour electricity sharing calculation model based on the genetic algorithm further includes: A predefined number of particles are randomly generated. Each particle represents a set of decision variable values, i.e., the power generation plan and trading strategy combination of the power generation company. The position of the particle represents the initial value of the decision variable, and the particle speed determines the direction and step size of the particle's movement in the search space. Set the maximum number of iterations T for the genetic algorithm to run; Set crossover probability and mutation probability; Substitute the position of each particle into the imbalanced capital scale calculation model and the per-kilowatt-hour electricity allocation calculation model, calculate the corresponding imbalanced capital scale and per-kilowatt-hour electricity allocation amount, and use them as the particle's fitness value; The particle position and velocity are continuously updated according to the particle swarm optimization algorithm. In each iteration, the particle adjusts its movement direction and step size based on its own historical optimal position and the global optimal position of the swarm, gradually approaching the optimal solution. Set the maximum number of iterations or the convergence accuracy of the fitness value as the termination condition. When the maximum number of iterations is reached or the change in the fitness value is less than the set convergence accuracy, the iteration is stopped and the optimal solution is output.

8. A quantitative calculation system for the scale of funds and per-kilowatt-hour electricity allocation in the power market, characterized in that: include: A data acquisition and fusion module is used to collect multivariate data from the power market, pre-process the multivariate data based on the 3σ principle, and then fuse the data using principal component analysis to obtain a comprehensive data set for subsequent measurement; An unbalanced capital scale calculation model construction module is used to calculate the power generation deviation and market price deviation of the power market, and to construct an unbalanced capital scale calculation model based on the comprehensive data set and in combination with the power generation deviation and the market price deviation. The unbalanced capital scale calculation model is used to output the unbalanced capital scale of the power market; A kilowatt-hour electricity allocation calculation model construction module is used to calculate the allocation factor of each power generation enterprise through a hierarchical structure model, and based on the allocation factor and the imbalance fund scale, construct a kilowatt-hour electricity allocation calculation model that takes into account the differences between different market members. The kilowatt-hour electricity allocation calculation model is used to calculate the kilowatt-hour electricity allocation amount of each power generation enterprise; The model solving module is used to solve the imbalance fund scale calculation model and the kilowatt-hour electricity sharing calculation model based on a genetic algorithm to obtain the optimal imbalance fund scale and kilowatt-hour electricity sharing amount.

9. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of the method for quantitatively calculating the scale of electricity market imbalance funds and kilowatt-hour electricity sharing according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method for quantitatively calculating the scale of electricity market imbalance funds and kilowatt-hour electricity sharing as described in any one of claims 1 to 7 are implemented.

Images