Decision assistance method based on correlation analysis

Abstract

The invention discloses a decision-making assistance method based on correlation analysis, relates to the technical field of big data processing, and solves the problem that more accurate decision-making assistance data cannot be provided for decision-making due to the fact that correlation analysis of decision-making influence factors and environmental data is not performed in the prior art. The method comprises the steps of firstly collecting power grid data, weather data and transaction data; then obtaining association conditions between the weather data and the power grid data and between the weather data and the transaction data, obtaining a sequence of association degrees between the weather data and the power grid data and between the weather data and the transaction data, further obtaining a comprehensive sequence, and assigning a value to each sequence; then obtaining prediction data of the power grid data and the weather data; and finally, constructing a decision-aided objective function, taking benefit maximization as an objective and considering a fluctuation coefficient in the objective function, and inputting prediction data to obtain a strategy for decision reference, thereby providing more accurate decision-aided data for decision.

Description

Technical Field

[0001] The present invention relates to the technical field of big data processing, and in particular to a decision-making assistance method based on association analysis. Background Art

[0002] With the rapid development of information technology, the digitization of power grid data has become a key trend in power system management. Through the large-scale deployment of smart meters and the application of big data technology, the distribution network has accumulated massive amounts of data in its daily operations. These data are not only used in areas such as load forecasting, optimal site selection and operation management of substations, but also significantly improve the efficiency of power grid work. The application of digital technology enables power grid data to be efficiently collected and stored, laying a solid foundation for subsequent data analysis and application. The digitalization and intelligent construction of power grids, such as the projects implemented by the State Grid Chongqing Electric Power, uses technologies such as cloud computing, big data, the Internet of Things, mobile Internet, artificial intelligence and blockchain to integrate multi-dimensional data such as power grid and equipment operation monitoring, greatly improving the level of intelligent operation and maintenance of power grids.

[0003] However, the current processing of power grid data is often based on processing one or several types of data to achieve the purpose of prediction or data feature extraction and analysis, but rarely based on the relationship between data. Among the many data in the power grid, those that affect decision-making, such as power generation, power purchase, and electricity prices, may be closely related to environmental data, such as weather data, but there is currently no correlation analysis between decision-making factors and environmental data, which cannot provide decision-makers with more accurate decision-making auxiliary data.

[0004] In view of this, a decision support method based on association analysis is needed. Summary of the invention

[0005] In view of the problem that the prior art does not analyze the correlation between decision-making factors and environmental data, and cannot provide more accurate decision-making auxiliary data for decision-makers, the present invention provides a decision-making auxiliary method based on correlation analysis, which can collect power grid data, weather data and transaction data, and obtain the correlation between weather data and power grid data and transaction data, and construct an objective function of maximizing benefits based on the correlation and electricity price, purchased electricity volume and cost, and obtain a strategy by solving the objective function for decision-making reference. The specific technical solution is as follows:

[0006] A decision support method based on association analysis comprises the following steps:

[0007] Collect power grid data, weather data, and transaction data;

[0008] Obtain the correlation between weather data, power grid data and transaction data, derive the ranking of the correlation between weather data, power grid data and transaction data, and then derive the comprehensive ranking And assign a value to each sort Among them, y j Indicates the sorting situation, l j Indicates the assignment situation, m is the total number of sorts;

[0009] Get forecast data for power grid data and weather data;

[0010] Construct the objective function of decision-making assistance, with the goal of maximizing benefits. Input the predicted data to solve the strategy for decision-making reference. The objective function is as follows:

[0011]

[0012] In the formula, H 电价 Indicates the unit electricity price, Q 购电 Indicates the amount of electricity purchased, C 成本 represents the total cost, including the cost of wind, solar, water, fire and storage. is the fluctuation coefficient, ΔU j is the rate of change of the j-th sorted weather data.

[0013] Preferably, the power grid data includes the power generation and total power generation of wind, photovoltaic, hydropower, and thermal power generating units at different sampling times, and the output power of energy storage; the weather data includes weather temperature, weather humidity, wind speed, precipitation, light intensity, and season at different sampling times; and the transaction data includes electricity prices and electricity purchase amounts at different sampling times.

[0014] Preferably, the steps of obtaining the ranking of the degree of correlation between weather data and total power generation are as follows:

[0015] All features and total power generation in weather data are numerically encoded, including weather temperature, weather humidity, wind speed, light intensity, and season;

[0016] Format the data into transaction datasets, where each transaction contains a set of feature items;

[0017] Calculate the support of the item, and then use the minimum support threshold Support(X) min , select the support greater than or equal to Support(X) min The calculation formula of the support of the item is as follows:

[0018]

[0019] Where X is an item set, N(X) is the number of transactions containing item set X, and Ntotal is the total number of transactions;

[0020] For each frequent item set, a conditional pattern base and a conditional FP tree are constructed to mine deeper frequent item sets;

[0021] Use FP-tree to recursively mine frequent itemsets until no more frequent itemsets can be found;

[0022] Based on the frequent item sets, association rules are generated and the confidence of each rule is calculated. The calculation formula of the confidence is as follows:

[0023]

[0024] In the formula, X is the antecedent of the rule, Y is the consequent of the rule, Support(X∪Y) is the frequency of item sets X and Y appearing at the same time, and Support(X) is the frequency of item set X appearing;

[0025] Select a confidence level greater than or equal to the minimum confidence threshold min The rules are then sorted according to their confidence.

[0026] Preferably, the process of obtaining the comprehensive ranking Y and the ranking assignment L is as follows:

[0027] S301: Assign values ​​to the ranking of the correlation between weather data, power grid data, and transaction data, respectively, expressed as: x i =r i , where x i is the ranking, r i It is a ranking assignment, and the higher the ranking, the higher the assignment;

[0028] S302: Calculate the comprehensive ranking coefficient of each weather data, as follows:

[0029] R 综合 =λ 1 r i +λ 2 r i +λ 3 r i +λ 4 r i

[0030] In the formula, R 综合 represents the comprehensive ranking coefficient, λ 1 , 2 , 3 , 4 The weight coefficients of the four dimensions of total power generation, energy storage output power, electricity price and power purchase can be set and adjusted according to actual conditions; iIt is the sorting assignment of the currently calculated weather data in the corresponding dimension.

[0031] S303: further sorting based on the comprehensive sorting coefficient values ​​of each weather data. The higher the value, the higher the sorting. The same value corresponds to the same sorting, which is expressed as follows:

[0032]

[0033] S304: Based on the comprehensive ranking Y, assign L to each ranking. Among them, y j Indicates the sorting situation, l j Indicates the assignment situation, and m is the total number of sorts, that is, the number of weather data.

[0034] Preferably, the prediction data of the power grid data is obtained by a constructed data prediction model, and the construction process of the data prediction model is as follows:

[0035] Determine the ARIMA model parameters: Draw the autocorrelation function and partial autocorrelation function graphs to determine the parameters of the ARIMA model, namely the autoregressive term p, the difference order d, and the moving average term q; use the grid search method to traverse different combinations of p, d, and q to find the optimal model parameters;

[0036] Model building and training: Define the ARIMA model based on the determined parameters; fit the model using the training data set;

[0037] Model evaluation: Check whether the residual is white noise to evaluate the model fitting effect and calculate the prediction error;

[0038] Model prediction: Use the fitted model to predict future data.

[0039] Preferably, the forecast data of weather data is obtained through a meteorological forecast platform.

[0040] Preferably, there are also constraints on the objective function, including a budget constraint:

[0041] C 成本 ≤B;

[0042] Where B is the available budget.

[0043] Preferably, the total cost C 成本 The calculation of is as follows:

[0044] C 成本 =C 风电 +C 光电 +C 水电 +C 火电 +C 储能 ;

[0045] In the formula, C 风电 represents the cost of wind power generation, which is calculated by the following formula:

[0046]

[0047] Among them, P dynamic_cost is the dynamic investment cost of wind farm, T O&M is the operation time of the wind farm, D deprectation is the depreciation of fixed assets of the wind farm, P O&M is the operation and maintenance cost of the wind farm, R tax is the income tax rate for wind farms, R discount is the discount rate, V restdualvaiue is the residual value of fixed assets of the wind farm, E annual is the annual power generation of the wind farm, Q 风电_发电 is the power generation of the wind turbine.

[0048] C 光电 The photovoltaic power generation cost is calculated by the following formula:

[0049]

[0050] Among them, P dynamic_cost_g is the dynamic investment cost of the photovoltaic field, T O&M_g is the operation time of the photovoltaic power plant, D deprectation_g is the depreciation of the fixed assets of the photovoltaic power plant, P O&M_g is the operation and maintenance cost of the photovoltaic power plant, R tax_g is the income tax rate of the photovoltaic field, R discount is the discount rate, V restdualvaiue_g is the residual value of the fixed assets of the photovoltaic power plant, E annual_g is the annual power generation of the photovoltaic field, Q 光电_发电 The power generated by the photovoltaic generator set.

[0051] C 水电 represents the cost of hydroelectric power generation, calculated by the following formula:

[0052]

[0053] In the formula, C 建设 is the construction cost of the hydropower station, C 运营维护 is the operation and maintenance cost of the hydropower station, C 折旧 is the depreciation cost of the hydropower station, C 财务 is the financial cost of the hydropower station, E 年 is the annual power generation of the hydropower station, N is the operating life of the hydropower station, Q 水电_发电 The power generation of the hydroelectric generator.

[0054] C 火电 represents the cost of thermal power generation, which is calculated by the following formula:

[0055]

[0056] In the formula, C n represents the cost expenditure in the nth year, Q n represents the electricity generated in the nth year, r represents the internal rate of return, or the discount rate, Q 火电_发电 is the power generation of the wind turbine.

[0057] C 储能 represents the energy storage cost, which is calculated by the following formula:

[0058]

[0059] Where η is the efficiency of the energy storage system, P c is the rated power of the energy storage system, T is the life cycle of the project, n c (t) is the number of cycles in year t, r is the discount rate, O&M(t) is the operation and maintenance cost in year t, C E is the energy storage cost of the energy storage system, C P is the power storage cost of the energy storage system, d is the service life of the energy storage system, P 输出 is the output power of energy storage, t h is the unit of time used to synchronize energy storage costs and other costs.

[0060] A computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the decision-making assistance method based on association analysis as described above.

[0061] A processor is used to run a program, wherein the program executes the decision-making assistance method based on association analysis as described above when running.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] 1. The present invention first collects power grid data, weather data and transaction data; then obtains the correlation between weather data and power grid data and transaction data, obtains the ranking of the correlation degree between weather data and power grid data and transaction data, and then obtains a comprehensive ranking, and assigns a value to each ranking; then obtains the predicted data of power grid data and weather data; finally, constructs a decision-making auxiliary objective function, with the goal of maximizing benefits, and inputs the predicted data to solve the strategy for decision-making reference, providing decision-makers with more accurate decision-making auxiliary data.

[0064] 2. The present invention considers the coefficient of fluctuation in the objective function, that is, the influence of weather conditions on stability, so that decision makers can choose the decision with the lowest cost and the best benefit on the basis of being as unaffected by the environment as possible. The correlation between weather conditions and the amount of electricity purchased, power generation and electricity prices is also reflected in the objective function through the coefficient of fluctuation, so that the dimensions of the strategy considered by the objective function are more comprehensive, and the decision-making reference is better. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0066] Figure 1 is a flow chart of the overall method of the present invention;

[0067] Figure 2 A schematic diagram of a process for obtaining association conditions of the present invention;

[0068] Figure 3 It is a schematic diagram of the process of obtaining the comprehensive ranking Y and the ranking assignment L of the present invention;

[0069] Figure 4 A schematic diagram of the construction process of the data prediction model of the present invention;

[0070] Figure 5 Schematic diagram of the specific steps of the gradient ascent method. DETAILED DESCRIPTION

[0071] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0072] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0073] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0074] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0075] In one embodiment of the present invention, a decision support method based on association analysis is provided, such as Figure 1 As shown, the following steps are included:

[0076] Step 1: Collect power grid data, weather data and transaction data. The power grid data includes the power generation and total power generation of wind, photovoltaic, hydropower and thermal power generating units at different sampling times, and the output power of energy storage. The weather data includes weather temperature, weather humidity, wind speed, precipitation, light intensity and season at different sampling times. The transaction data includes electricity prices and electricity purchase amounts at different sampling times.

[0077] Step 2: Obtain the correlation between weather data, power grid data and transaction data, and rank the correlation between weather data, power grid data and transaction data.

[0078] This step calculates the correlation degree of weather data in the four dimensions of total power generation, energy storage output power, electricity price and power purchase. For example, in the dimension of total power generation, the ranking of the degree of influence of weather data on it is obtained, which further reflects which factor in the weather data has the highest influence on total power generation (such as wind speed), which factor has the second highest influence on total power generation (such as sunlight), and so on.

[0079] Since the analysis of the four dimensions is the same, the following takes the dimension of total power generation as an example to obtain the associated situation. Figure 2 As shown, the details are as follows:

[0080] S201: Numerically encode all features in the weather data (such as weather temperature, weather humidity, wind speed, light intensity, season) and total power generation so that the algorithm can process them;

[0081] S202: Format the data into a transaction data set, where each transaction contains a set of feature items. For example, a transaction can be “weather temperature is high, weather humidity is normal, wind speed is high, light intensity is high, season: winter, time: 14:00”, and add a “total power generation” label at the end of the transaction.

[0082] S203: Construct an FP-tree. The FP-tree is a compressed data structure for storing frequent item sets. The construction steps are: calculate the support of the item, and then according to the minimum support threshold Support(X) min , select the support greater than or equal to Support(X) min The calculation formula of the support of the item is as follows:

[0083]

[0084] Where X is an item set, N(X) is the number of transactions containing item set X, and N total is the total number of transactions;

[0085] S204: For each frequent item set, a conditional pattern base (CM) and a conditional FP (CFPT) tree are constructed to mine deeper frequent item sets.

[0086] S205: recursively mine frequent item sets using the FP-tree until no more frequent item sets can be found;

[0087] S206: Generate association rules based on frequent item sets and calculate the confidence of each rule. The calculation formula of the confidence is as follows:

[0088]

[0089] In the formula, X is the antecedent of the rule, Y is the consequent of the rule, Support(X∪Y) is the frequency of item sets X and Y appearing at the same time, and Support(X) is the frequency of item set X appearing.

[0090] S207: Select a confidence level greater than or equal to the minimum confidence threshold Confidence min Then the rules are sorted according to their confidence.

[0091] After the above steps, we can determine the several data items that affect the total power generation, and the order of these data items based on the degree of influence. In other words, we can determine which weather data has the greatest impact on the total power generation, which data has the second greatest impact on the total power generation, and so on. So far, the analysis of the impact of weather data on the total power generation has been completed.

[0092] After that, the correlation between weather data and the remaining three dimensions is obtained, and then the correlation degree ranking of the four dimensions of total power generation, energy storage output power, electricity price and power purchase amount is obtained.

[0093] Step 3: Based on the correlation degree ranking of the four dimensions of total power generation, energy storage output power, electricity price and power purchase amount, the comprehensive ranking coefficient of the weather data correlation degree is obtained, and the weather data correlation degree is further comprehensively ranked based on the comprehensive ranking coefficient.

[0094] like Figure 3 As shown, the steps are as follows:

[0095] S301: Assign a value to the sorting condition, expressed as: x i =r i , where x i is the ranking, r i It is a ranking assignment, and the higher the ranking, the higher the assignment;

[0096] S302: Calculate the comprehensive ranking coefficient of each weather data, as follows:

[0097] R 综合 =λ 1 r i +λ 2 r i +λ 3 r i +λ 4 r i

[0098] In the formula, R 综合 represents the comprehensive ranking coefficient, λ 1 , 2 , 3 , 4 The weight coefficients of the four dimensions of total power generation, energy storage output power, electricity price and power purchase can be set and adjusted according to actual conditions; i It is an assignment. When multiplied by the weight coefficient of a dimension, the assignment is the sorting assignment corresponding to the currently calculated weather data under that weight.

[0099] S303: further sorting based on the comprehensive sorting coefficient values ​​of each weather data. The higher the value, the higher the sorting. The same value corresponds to the same sorting, which is expressed as follows:

[0100]

[0101] S304: Based on the comprehensive ranking Y, assign L to each ranking. Among them, y j Indicates the sorting situation, l jIndicates the assignment status. The higher the ranking, the greater the assignment value. m is the total number of rankings, that is, the number of weather data.

[0102] Step 4: Build a data prediction model to predict the total power generation, energy storage output power, electricity price and power purchase at future times based on the current and historical wind, photovoltaic, hydropower and thermal power generation units, energy storage output power, electricity price and power purchase. Then obtain weather data forecast data through weather forecast platforms (such as AIRWISE, NVIDIAEarth-2, Mirror Earth Weather Query, etc.).

[0103] The construction process of the data prediction model is as follows:

[0104] like Figure 4 As shown, this embodiment uses the ARIMA model to build a data prediction model. The following are the specific steps:

[0105] S01: Determine the ARIMA model parameters: Draw the autocorrelation function (ACF) and partial autocorrelation function (PACF) graphs to determine the parameters p (autoregressive term), d (difference order), and q (moving average term) of the ARIMA model; use the grid search method to traverse different combinations of p, d, and q to find the optimal model parameters.

[0106] S02: Model building and training: Define the ARIMA model based on the determined parameters; fit the model using the training data set.

[0107] S03: Model evaluation: Check whether the residual is white noise to evaluate the fitting effect of the model, and calculate the prediction error, such as mean square error (MSE), to evaluate the prediction performance of the model.

[0108] S04: Model prediction: Use the fitted model to predict future data.

[0109] In short, the ARIMA model uses historical data (power generation of wind, photovoltaic, hydropower, thermal power generation units, output power of energy storage, electricity prices and electricity purchase) as the input of the model, and the model will analyze the time series characteristics of these data, including trends, seasonality and random fluctuations. By fitting these historical data, the ARIMA model can capture the law of data changes over time and predict future data points accordingly.

[0110] Step 5: Construct the objective function of decision-making assistance, with the goal of maximizing benefits. Input the predicted data to solve the strategy for decision-making reference. The objective function is as follows:

[0111]

[0112] In the formula, H电价 Indicates the unit electricity price, Q 购电 Indicates the amount of electricity purchased, C 成本 represents the total cost, including the cost of wind, solar, water, fire and storage. is the fluctuation coefficient, reflecting the impact of weather conditions on stability, ΔU j The change of the weather data of the jth sort is calculated as follows:

[0113]

[0114] Where U j (t 2 ) is the jth sorted weather data at time t 2 The amount of data, U j (t 1 ) The jth sorted weather data is at time t 2 The time before t 1 The amount of data.

[0115] Total cost C 成本 The calculation of is as follows:

[0116] C 成本 =C 风电 +C 光电 +C 水电 +C 火电 +C 储能 ;

[0117] In the formula, C 风电 The cost of wind power generation is calculated by the following formula:

[0118]

[0119] Among them, P dynamic_cost is the dynamic investment cost of wind farm, T O&M is the operation time of the wind farm, D deprectation is the depreciation of fixed assets of the wind farm, P O&M is the operation and maintenance cost of the wind farm, R tax is the income tax rate for wind farms, R discount is the discount rate, V restdualvaiue is the residual value of fixed assets of the wind farm, E annual is the annual power generation of the wind farm, Q 风电_发电 is the power generation of the wind turbine.

[0120] C 光电 The photovoltaic power generation cost is calculated by the following formula:

[0121]

[0122] Among them, P dynamic_cost_gis the dynamic investment cost of the photovoltaic field, T O&M_g is the operation time of the photovoltaic power plant, D deprectation_g is the depreciation of the fixed assets of the photovoltaic power plant, P O&M_g is the operation and maintenance cost of the photovoltaic power plant, R tax_g is the income tax rate of the photovoltaic field, R discount is the discount rate, V restdualvaiue_g is the residual value of the fixed assets of the photovoltaic power plant, E annual_g is the annual power generation of the photovoltaic field, Q 光电_发电 The power generated by the photovoltaic generator set.

[0123] C 水电 represents the cost of hydroelectric power generation, calculated by the following formula:

[0124]

[0125] In the formula, C 建设 is the construction cost of the hydropower station, C 运营维护 is the operation and maintenance cost of the hydropower station, C 折旧 is the depreciation cost of the hydropower station, C 财务 is the financial cost of the hydropower station, E 年 is the annual power generation of the hydropower station, N is the operating life of the hydropower station, Q 水电_发电 The power generation of the hydroelectric generator.

[0126] C 火电 represents the cost of thermal power generation, which is calculated by the following formula:

[0127]

[0128] In the formula, C n represents the cost expenditure in the nth year, Q n represents the electricity generated in the nth year, r represents the internal rate of return, or the discount rate, Q 火电_发电 is the power generation of the wind turbine.

[0129] C 储能 represents the energy storage cost, which is calculated by the following formula:

[0130]

[0131] Where η is the efficiency of the energy storage system, P c is the rated power of the energy storage system, T is the life cycle of the project, n c (t) is the number of cycles in year t, r is the discount rate, O&M(t) is the operation and maintenance cost in year t, C E is the energy storage cost of the energy storage system, C P is the power storage cost of the energy storage system, d is the service life of the energy storage system, P 输出is the output power of energy storage, t h is time, which is hours in this embodiment and is the unit used for synchronous energy storage cost and other costs.

[0132] Based on the objective function, the following constraints are set, including the budget constraint:

[0133] C 成本 ≤B;

[0134] Where B is the available budget.

[0135] Next, the objective function is solved. This embodiment uses the gradient ascent algorithm. The gradient ascent method is an iterative method that gradually adjusts the parameters along the direction of the objective function gradient to find the maximum value of the function. Figure 5 As shown, the following are the specific steps of the gradient ascent method:

[0136] Step 1: Get the data set for decision making and randomly select an initial point as the starting point;

[0137] Step 2: Calculate the gradient of the objective function Z at the current point;

[0138] Step 3: Update the parameters along the direction of the gradient, define the learning rate, and control the step size;

[0139] Step 4: Check whether the magnitude of the gradient is less than a preset threshold, or check whether the value of the objective function changes very little in several consecutive iterations. If so, the algorithm is considered to have converged.

[0140] Step 5: If there is no convergence, return to step 2 and continue iterating;

[0141] Step 6: When the algorithm converges, output the value of the current decision.

[0142] The gradient ascent method is an intuitive optimization method with relatively low computational cost, which is suitable for the case where the objective function is relatively simple and continuously differentiable. This is a common solution method in this field, and will not be described in detail here. In addition, in actual use, a more suitable objective function solution algorithm can also be used based on the data situation, etc.

[0143] In summary, the present invention first collects power grid data, weather data and transaction data; then obtains the correlation between weather data and power grid data and transaction data, obtains the ranking of the correlation between weather data and power grid data and transaction data, and then obtains a comprehensive ranking, and assigns a value to each ranking; then obtains the forecast data of power grid data and weather data; finally, constructs the objective function of decision-making assistance, takes the maximization of benefits as the goal, and inputs the forecast data to solve the strategy for decision-making reference, providing more accurate decision-making assistance data for decision-makers. Moreover, the present invention considers the coefficient of fluctuation in the objective function, that is, the impact of weather conditions on stability, so that decision-makers can choose the decision with the lowest cost and the best benefit on the basis of being as unaffected by the environment as possible. The correlation between weather conditions and power purchase, power generation and electricity prices is also reflected in the objective function through the coefficient of fluctuation, so that the dimensions considered by the strategy obtained by solving this objective function are more comprehensive, and the decision-making reference obtained is better.

[0144] Those of ordinary skill in the art will appreciate that the units of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0145] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored, etc.

[0146] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0147] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nlyMemory), random access memory (RAM, RandomAccessMemory), mobile hard disk, magnetic disk or optical disk, etc., which can store program code.

[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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A decision support method based on association analysis, characterized in that: The following steps are involved: Collect power grid data, weather data, and transaction data; Obtain the correlation between weather data, power grid data and transaction data, and derive the ranking of the correlation between weather data, power grid data and transaction data, and then derive the comprehensive ranking Y = [y1, y2, ..., y j , …, y m ], and assign each sorting value L = [l1, l2, ..., l j ,…,l m ], where y j Indicates the sorting situation, l j Indicates the assignment situation, m is the total number of sorts; Get forecast data for power grid data and weather data; Construct the objective function of decision-making assistance, with the goal of maximizing benefits. Input the predicted data to solve the strategy for decision-making reference. The objective function is as follows: In the formula, H 电价 Indicates the unit electricity price, Q 购电 Indicates the amount of electricity purchased, C 成本 represents the total cost, including the cost of wind, solar, water, fire and storage. is the fluctuation coefficient, ΔU j is the rate of change of the j-th sorted weather data.

2. The decision support method based on association analysis according to claim 1, characterized in that: The power grid data includes the power generation and total power generation of wind, photovoltaic, hydropower, and thermal power generating units at different sampling times, and the output power of energy storage. The weather data includes weather temperature, weather humidity, wind speed, precipitation, light intensity, and season at different sampling times. The transaction data includes electricity prices and electricity purchase amounts at different sampling times.

3. The decision support method based on association analysis according to claim 1, characterized in that: The steps to obtain the correlation ranking between weather data and total power generation are as follows: All features and total power generation in weather data are numerically encoded, including weather temperature, weather humidity, wind speed, light intensity, and season; Format the data into transaction datasets, where each transaction contains a set of feature items; Calculate the support of the item, and then use the minimum support threshold Support(X) min , select the support greater than or equal to Support(X) min The calculation formula of the support of the item is as follows: Where X is an item set, N(X) is the number of transactions containing item set X, and N total is the total number of transactions; For each frequent item set, a conditional pattern base and a conditional FP tree are constructed to mine deeper frequent item sets; Use FP-tree to recursively mine frequent itemsets until no more frequent itemsets can be found; Based on the frequent item sets, association rules are generated and the confidence of each rule is calculated. The calculation formula of the confidence is as follows: In the formula, X is the antecedent of the rule, Y is the consequent of the rule, Support(X∪Y) is the frequency of item sets X and Y appearing at the same time, and Support(X) is the frequency of item set X appearing; Select a confidence level greater than or equal to the minimum confidence threshold min The rules are then sorted according to their confidence.

4. The decision support method based on association analysis according to claim 3 is characterized in that: The process of obtaining the comprehensive ranking Y and the ranking assignment L is as follows: S301: Assign values ​​to the ranking of the correlation between weather data, power grid data, and transaction data, respectively, expressed as: x i =r i , where x i is the ranking, r i It is a ranking assignment, and the higher the ranking, the higher the assignment; S302: Calculate the comprehensive ranking coefficient of each weather data, as follows: R 综合 =λ1r i +λ2r i +λ3r i +λ4r i In the formula, R 综合 It represents the comprehensive ranking coefficient. λ1, λ2, λ3, and λ4 are the weight coefficients of the four dimensions of total power generation, energy storage output power, electricity price, and power purchase. They can be set and adjusted according to actual conditions. i It is the sorting assignment of the currently calculated weather data in the corresponding dimension; S303: further sorting based on the value of the comprehensive sorting coefficient of each weather data. The higher the value, the higher the sorting. The same value corresponds to the same sorting, which is expressed as follows: Y=[y1,y2,…,y j ,…,y m ]; S304: Based on the comprehensive ranking Y, assign a value L to each ranking, where L = [l1, l2, ..., l j ,…,l m ], where y j Indicates the sorting situation, l j Indicates the assignment status. The higher the ranking, the greater the assignment value. m is the total number of rankings, that is, the number of weather data.

5. The decision support method based on association analysis according to claim 1, characterized in that: The prediction data of the power grid data is obtained by the constructed data prediction model, and the construction process of the data prediction model is as follows: Determine the ARIMA model parameters: Draw the autocorrelation function and partial autocorrelation function graphs to determine the parameters of the ARIMA model, namely the autoregressive term p, the difference order d, and the moving average term q; use the grid search method to traverse different combinations of p, d, and q to find the optimal model parameters; Model building and training: Define the ARIMA model based on the determined parameters; fit the model using the training data set; Model evaluation: Check whether the residual is white noise to evaluate the model fitting effect and calculate the prediction error; Model prediction: Use the fitted model to predict future data.

6. The decision support method based on association analysis according to claim 1, characterized in that: The forecast data of weather data is obtained through the meteorological forecast platform.

7. The decision support method based on association analysis according to claim 1, characterized in that: There are also constraints on the objective function, including a budget constraint: C 成本 ≤B; Where B is the available budget.

8. The decision support method based on association analysis according to claim 1, characterized in that: Total cost C 成本 The calculation of is as follows: C 成本 =C 风电 +C 光电 +C 水电 +C 火电 +C 储能 ; In the formula, C 风电 The cost of wind power generation is calculated by the following formula: Among them, P dynamic_cost is the dynamic investment cost of wind farm, T O&M is the operation time of the wind farm, D deprectation is the depreciation of fixed assets of the wind farm, P O&M is the operation and maintenance cost of the wind farm, R tax is the income tax rate for wind farms, R discount is the discount rate, V restdualvaiue is the residual value of fixed assets of the wind farm, E annual is the annual power generation of the wind farm, Q 风电_发电 is the power generation of the wind turbine; C 光电 The photovoltaic power generation cost is calculated by the following formula: Among them, P dynamic_cost_g is the dynamic investment cost of the photovoltaic field, T O&M_g is the operation time of the photovoltaic power plant, D deprectation_g is the depreciation of the fixed assets of the photovoltaic power plant, P O&M_g is the operation and maintenance cost of the photovoltaic power plant, R tax_g is the income tax rate of the photovoltaic field, R discount is the discount rate, V restdualvaiue_g is the residual value of the fixed assets of the photovoltaic power plant, E annual_g is the annual power generation of the photovoltaic field, Q 光电_发电 The power generation of the photovoltaic generator set; C 水电 represents the cost of hydroelectric power generation, calculated by the following formula: In the formula, C 建设 is the construction cost of the hydropower station, C 运营维护 is the operation and maintenance cost of the hydropower station, C 折旧 is the depreciation cost of the hydropower station, C 财务 is the financial cost of the hydropower station, E 年 is the annual power generation of the hydropower station, N is the operating life of the hydropower station, Q 水电_发电 The power generation of the hydroelectric generator; C 火电 represents the cost of thermal power generation, which is calculated by the following formula: In the formula, C n represents the cost expenditure in the nth year, Q n represents the electricity generated in the nth year, r represents the internal rate of return, or the discount rate, Q 火电_发电 is the power generation of the wind turbine; C 储能 represents the energy storage cost, which is calculated by the following formula: Where η is the efficiency of the energy storage system, P c is the rated power of the energy storage system, T is the life cycle of the project, n c (t) is the number of cycles in year t, r is the discount rate, O&M(t) is the operation and maintenance cost in year t, C E is the energy storage cost of the energy storage system, C P is the power storage cost of the energy storage system, d is the service life of the energy storage system, P 输出 is the output power of energy storage, t h is the unit of time used to synchronize energy storage costs and other costs.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the decision-making assistance method based on association analysis according to any one of claims 1 to 8.

10. A processor, characterized in that: The processor is used to run a program, wherein the program, when running, executes the decision-making assistance method based on association analysis as described in any one of claims 1 to 8.

Images