Method, device, equipment and storage medium for estimating power resource declared quantity

Abstract

The embodiments of this specification provide a method, device, equipment and storage medium for estimating the declared amount of electric power resources. The method includes: obtaining the first electric power resource value and the second electric power resource value of each historical period within a time period, and calculating the value difference between the first electric power resource value and the second electric power resource value; based on the value difference of each historical period, using a parameter calculation method, determining the parameters corresponding to each historical period; partitioning the estimated period corresponding to each historical period according to the parameters and parameter thresholds of the historical period according to a predetermined strategy, and obtaining the partition results corresponding to each estimated period; based on the partition results of the estimated period, the historical power load statistical data corresponding to the historical period, and the risk preference coefficient, estimating the declared amount of electric power resources corresponding to each estimated period, and obtaining an estimated value of the declared amount of electric power resources. The present disclosure reduces the prediction error, improves the quality of the strategy, and ensures the accuracy of the estimation results.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a method, device, equipment and storage medium for estimating the declared amount of electric power resources. Background Art

[0002] With the liberalization of the power sales market, the establishment of specialized entities such as power sales companies and load aggregators has been promoted, which has promoted the full exploration of demand response potential. While taking into account the main business of power sales, power sales companies help users adjust their electricity consumption behavior to obtain economic returns by exploring demand potential and signing demand response agreements for users according to the characteristics of market electricity prices. Under the existing power market trading mechanism, the user side (power sales companies or power users directly involved in transactions, etc.) can strategically arbitrage at different prices of the same subject in day-ahead transactions. Therefore, a systematic high-frequency analysis of a large number of transaction subjects and an organic integration of opportunity discovery and risk avoidance have become an indispensable requirement.

[0003] At present, in the formulation of strategies for power resource declaration, the prices of each period of the day-ahead and real-time markets are generally predicted separately, and the load is predicted through the historical power load of each period. Finally, the day-ahead declaration amount is calculated based on the difference between the day-ahead and real-time predicted prices, the load prediction value, and the upper limit of the positive and negative deviation of the trading rules. However, this method has a large prediction error, the number of variables that need to be predicted increases, the prediction model is highly sensitive to changes in external factors, and there is a problem that the strategy results are relatively single. Summary of the invention

[0004] In view of this, the embodiments of the present disclosure provide a method, device, equipment and storage medium for estimating the declared amount of electric power resources to solve the problems existing in the prior art, such as large prediction errors, increased prediction variables, and the prediction model being greatly affected by external factors, resulting in low accuracy of estimation results and relatively single strategy results.

[0005] According to a first aspect of an embodiment of the present disclosure, a method for estimating the declared amount of electric power resources is provided, comprising: obtaining a first electric power resource value and a second electric power resource value corresponding to each historical time period within a preset time period, and calculating the value difference between the first electric power resource value and the second electric power resource value; determining the parameters corresponding to each historical time period using a preset parameter calculation method based on the value difference corresponding to each historical time period; partitioning the estimated time period corresponding to each historical time period according to a predetermined strategy based on the parameters corresponding to the historical time period and a preset parameter threshold, and obtaining a partition result corresponding to each estimated time period; estimating the declared amount of electric power resources corresponding to each estimated time period based on the partition result of the estimated time period, the historical electricity load statistical data corresponding to the historical time period, and the risk preference coefficient, and obtaining an estimated value of the declared amount of electric power resources.

[0006] According to a second aspect of an embodiment of the present disclosure, there is provided an estimation device for the declared amount of electric power resources, comprising: an acquisition module, configured to acquire a first electric power resource value and a second electric power resource value corresponding to each historical time period within a preset time period, and calculate a value difference between the first electric power resource value and the second electric power resource value; a calculation module, configured to determine the parameters corresponding to each historical time period based on the value difference corresponding to each historical time period and using a preset parameter calculation method; a partitioning module, configured to partition the estimated time period corresponding to each historical time period according to a predetermined strategy based on the parameters corresponding to the historical time period and a preset parameter threshold, and obtain a partition result corresponding to each estimated time period; an estimation module, configured to estimate the declared amount of electric power resources corresponding to each estimated time period based on the partition result of the estimated time period, the historical electricity load statistical data corresponding to the historical time period, and the risk preference coefficient, and obtain an estimated value of the declared amount of electric power resources.

[0007] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the steps of the above method are implemented when the processor executes the program.

[0008] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0009] At least one of the above technical solutions adopted in the embodiments of the present disclosure can achieve the following beneficial effects:

[0010] By obtaining the first power resource value and the second power resource value corresponding to each historical period within a preset time period, and calculating the value difference between the first power resource value and the second power resource value; based on the value difference corresponding to each historical period, using a preset parameter calculation method, determine the parameters corresponding to each historical period; according to the parameters corresponding to the historical period and the preset parameter threshold, partition the estimated period corresponding to each historical period according to a predetermined strategy, and obtain the partition result corresponding to each estimated period; based on the partition result of the estimated period, the historical power load statistical data corresponding to the historical period, and the risk preference coefficient, estimate the power resource declaration amount corresponding to each estimated period, and obtain the estimated value of the power resource declaration amount. The present disclosure reduces the error of predicting the power resource declaration amount, improves the quality of the strategy, the estimation result is less affected by external factors, and the accuracy of the estimation result is high. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0012] Figure 1 It is a flowchart of a method for estimating the declared amount of electric power resources provided by an embodiment of the present disclosure;

[0013] Figure 2 It is a schematic diagram of the result of partitioning time periods according to the strategy provided by the embodiment of the present disclosure;

[0014] Figure 3 It is a structural schematic diagram of a device for estimating the reported amount of electric power resources provided in an embodiment of the present disclosure;

[0015] Figure 4 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0016] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0017] With the continuous advancement of my country's power marketization, the power spot market has been gradually developed in various provinces and cities, promoting the change from long-term electricity transactions (year, quarter, month, ten-day, week) to short-term electricity transactions (most markets use 15 minutes as a trading clearing period), which fully reflects the commodity attributes of electricity with different prices under different supply and demand relationships, transportation conditions and other factors. On the other hand, due to the instantaneous balance and difficulty in storage of electricity commodities, in order to ensure the stability of the power system and improve the constraints on the temporary and large changes in the power generation side, the power spot market is usually designed as a day-ahead market and a real-time market. According to different clearing conditions, such as the forecast of the power load of the entire market and the forecast of the output of new energy, the same target period is cleared at different prices in the day-ahead market and the real-time market. Under this trading mechanism, the user side (power sales companies and power users directly involved in the transaction) can strategically arbitrage at different prices of the same target during day-ahead transactions. Therefore, a systematic high-frequency analysis of a large number of trading targets and an organic integration of opportunity discovery and risk avoidance have become an indispensable requirement.

[0018] Taking the existing power trading market rules as an example, the existing day-ahead trading declaration strategy is explained, which can specifically include the following contents:

[0019] Market clearing mechanism: In the day-ahead market, the power dispatching agency adopts the safety-constrained unit combination program and the safety-constrained economic dispatch program on the bidding day (D-1), combined with the market subject declaration information and the grid operation boundary conditions on the operation day (D-1), with the goal of minimizing the power generation cost of the entire network, and clears the 96 trading periods of D-1 (with 15 minutes as a trading clearing period, hereinafter referred to as "period") for a period of 15 minutes. In the real-time market on D-1, based on the declaration information sealed in the day-ahead market, according to ultra-short-term load forecasts, new energy power generation forecasts and other conditions, the safety-constrained economic dispatch program is adopted, with the goal of minimizing the power generation cost of the entire network, and the real-time market trading results of the 96 periods of D-1 are obtained.

[0020] Day-ahead transactions on the user side: On D-1, the user side needs to estimate the total electricity consumption in each period on D-day and declare it before the day-ahead market is cleared. The profit and loss of the day-ahead transaction is calculated based on the price difference between the day-ahead and real-time market clearing prices and the difference between the day-ahead declaration and actual electricity consumption.

[0021] Trading restrictions: To prevent excessive speculation, the electricity market rules have established a deviation profit recovery mechanism, that is, if the deviation between the electricity consumption reported by the user-side real-time market every hour and the actual electricity consumption exceeds the allowable deviation range, the day-ahead trading arbitrage profits generated by the electricity consumption exceeding 80%-120% of the actual electricity consumption will be recovered.

[0022] From the above mechanism, it can be seen that when market players declare electricity consumption in each period of D day in day-ahead transactions, it is particularly important to estimate the price difference between the day-ahead and real-time markets and the actual electricity consumption.

[0023] In terms of the existing day-ahead trading strategy formulation, the existing methods generally predict the prices of each period in the day-ahead and real-time markets separately. The prediction methods include historical similar day comparison method, machine learning method and high-order linear fitting method, etc.; then the load is predicted through the historical electricity load in each period; finally, the day-ahead declaration amount is calculated based on the difference between the day-ahead and real-time predicted prices, the load prediction value and the upper limit of the positive and negative deviation of the trading rules. For example, when the predicted real-time price for a period of time is higher than the day-ahead price, the load prediction value with a positive deviation upper limit ratio of 120% should be declared to maximize profits. However, this method has the following disadvantages:

[0024] 1) Large prediction error

[0025] Whether it is price or load forecasting, forecast errors are unavoidable. Even in the power trading market with relatively mature rules and high data transparency, the mainstream forecasting method still uses historical clearing results and disclosure information for the entire market as a whole, such as the total power consumption of the market, the total amount of new energy power generation, and the average power generation fuel cost, etc., and does not include the grid structure and specific power distribution in the feature analysis of the forecasting model. Therefore, even if the impact of the subjective behavior of market players on the transaction results is not considered, the price and load forecast errors are unavoidable, thereby reducing the quality of the strategy.

[0026] 2) Ignoring risk management

[0027] This approach does not introduce uncertainty into the strategy model and ignores the possibility of different price levels in different scenarios. As the number of variables to be predicted increases, the ignored uncertainty also increases, and the results of the strategy model are more sensitive to changes in external factors.

[0028] 3) Single strategy results

[0029] When the forecast results are all absolute values, there are only three results for the day-ahead trading declaration strategy, namely 80%, 100% and 120% times the load forecast. However, according to different risk preferences and model calculation results, the declaration strategy ratio range should be any value from 80% to 120%, not three extreme cases.

[0030] Figure 1 FIG. 1 is a flow chart of a method for estimating the reported amount of electric power resources provided in an embodiment of the present disclosure. The method for estimating the reported amount of electric power resources in FIG. 1 may be executed by a server. Figure 1 As shown, the estimation method of the reported amount of electric power resources may specifically include:

[0031] S101, obtaining a first power resource value and a second power resource value corresponding to each historical period within a preset time period, and calculating a value difference between the first power resource value and the second power resource value;

[0032] S102, based on the value difference corresponding to each historical period, using a preset parameter calculation method, determining the parameter corresponding to each historical period;

[0033] S103, partitioning the estimated time period corresponding to each historical time period according to a predetermined strategy based on the parameters corresponding to the historical time period and the preset parameter threshold, to obtain a partition result corresponding to each estimated time period;

[0034] S104, based on the partition results of the estimated time period, the historical power load statistical data corresponding to the historical time period, and the risk preference coefficient, the power resource declaration amount corresponding to each estimated time period is estimated to obtain an estimated value of the power resource declaration amount.

[0035] According to the technical solution provided by the embodiment of the present disclosure, by obtaining the first power resource value and the second power resource value corresponding to each historical period within a preset time period, and calculating the value difference between the first power resource value and the second power resource value; based on the value difference corresponding to each historical period, using the preset parameter calculation method, determine the parameters corresponding to each historical period; according to the parameters corresponding to the historical period and the preset parameter threshold, partition the estimated period corresponding to each historical period according to the predetermined strategy, and obtain the partition result corresponding to each estimated period; based on the partition result of the estimated period, the historical power load statistical data corresponding to the historical period, and the risk preference coefficient, estimate the power resource declaration amount corresponding to each estimated period, and obtain the estimated value of the power resource declaration amount. The present disclosure reduces the error of predicting the power resource declaration amount, improves the quality of the strategy, the estimation result is less affected by external factors, and the accuracy of the estimation result is high.

[0036] In some embodiments, before obtaining the first power resource value and the second power resource value corresponding to each historical time period within a preset time period, the method also includes: determining the time period according to the time corresponding to the estimated time period, and dividing the time period into several historical time periods according to preset time intervals, wherein each trading day within the time period includes multiple historical time periods.

[0037] Specifically, the 30 trading days before the operation date D can be used as the analysis target, that is, the preset time period can be considered as the time period corresponding to the 30 trading days before the operation date D. After the time period is determined according to the operation date D, the above time period is divided into multiple historical periods using the preset trading period. In actual application, 15 minutes can be used as a trading period, that is, the time period is divided into a historical period every 15 minutes.

[0038] In some embodiments, obtaining a first power resource value and a second power resource value corresponding to each historical period within a preset time period includes: for each historical period within the time period, obtaining a first power resource value and a second power resource value corresponding to each historical period from historical transaction data; wherein the first power resource value represents the day-ahead power resource value of the historical period, and the second power resource value represents the actual power resource value of the historical period.

[0039] Specifically, each trading day in the time period can be divided into 96 time periods. Based on the independence of the 96 time periods in the day-ahead transaction, the day-ahead declared electricity quantity in any time period can be determined. The embodiment of the present disclosure aims to determine the optimal declared electricity quantity in a certain time period on the D day, that is, to determine (i represents a trading period, i∈[1,96]).

[0040] Furthermore, according to the historical transaction data, the day-ahead price (i.e., the first power resource value) and the real-time market price (i.e., the second power resource value) of each historical period are obtained, that is, the day-ahead price and the real-time market price of each period in the cycle are counted respectively, and they are expressed as and Calculate the price difference corresponding to each historical period n∈[1,N].

[0041] In some embodiments, based on the value difference corresponding to each historical time period, a preset parameter calculation method is used to determine the parameters corresponding to each historical time period, including: calculating the parameters corresponding to each historical time period in each trading day within the time period according to the value difference corresponding to each historical time period, wherein the parameters include the positive probability of the spread, the average of the positive spread, the average of the negative spread, the ratio of the absolute values ​​of the positive and negative means, and the mean of the spread.

[0042] Specifically, after obtaining the value difference corresponding to each historical period, the preset parameter value is calculated based on the value difference. The calculation process of the above parameters is described in detail below in conjunction with a specific embodiment, which may specifically include the following contents:

[0043] When calculating the positive probability parameter of the spread, the probability that the real-time and day-ahead price difference is positive in each period i of N trading days (i.e., the positive probability of the spread) is calculated, p i , that is, p i =P(△P n.i >0).

[0044] When calculating the parameters of the average of positive price differences, the average of all positive real-time and day-ahead price differences in each period i in N trading days is calculated, that is, Z represents △P in period i n.i >0, z∈[1,Z].

[0045] When calculating the parameters of the average of negative price differences, the average of all negative real-time and day-ahead price differences in each period i in N trading days is calculated, that is, F represents △P in period i n.i < the number of 0, f∈[1,F].

[0046] When calculating the parameters of the positive and negative mean absolute value ratio, the absolute value of the ratio of the positive average and the negative average of all real-time and day-ahead price differences in each period i in N trading days (positive and negative mean absolute value ratio) is calculated, that is,

[0047] When calculating the parameters of the average price difference, the average of all real-time and day-ahead price differences (average price difference) for each period i in N trading days is calculated, that is,

[0048] In some embodiments, based on the parameters corresponding to the historical time period and the preset parameter threshold, the estimated time period corresponding to each historical time period is partitioned according to a predetermined strategy to obtain a partition result corresponding to each estimated time period, including: based on the calculated parameters corresponding to the historical time period, the parameters are compared with the parameter thresholds respectively using a predetermined strategy, and a partition operation is performed on the estimated time period corresponding to the historical time period according to the comparison result to determine the partition result corresponding to the estimated time period; wherein the partition result corresponding to the estimated time period includes an over-holding area, a high-holding area, a reduced-holding area, a low-holding area and a normal area.

[0049] Specifically, based on the parameters corresponding to the historical time periods obtained by the above calculations, the estimated time periods corresponding to each historical time period are partitioned using preset parameter thresholds and strategies. The process of partitioning the estimated time periods corresponding to the historical time periods is described in detail below in conjunction with the accompanying drawings and specific embodiments. Figure 2 FIG. 1 is a schematic diagram of the result of partitioning time periods according to a strategy provided by an embodiment of the present disclosure. Figure 2 As shown, the partition results for this period include the following:

[0050] According to the following strategy, time period i can be divided into five partitions. The partition strategies corresponding to these five partitions are described in detail below, which may include the following contents:

[0051] When the positive probability of the spread and the absolute value ratio of the positive and negative mean are both greater than the corresponding overholding threshold, and the mean of the spread is positive, that is, This period is divided into the overholding zone;

[0052] When the positive probability of the spread and the absolute value ratio of the positive and negative mean are both greater than the corresponding high holding threshold and less than any over holding threshold, and the mean of the spread is positive, that is, This period is divided into a high holding zone;

[0053] When the positive probability of the spread and the absolute value ratio of the positive and negative mean are both less than the corresponding reduction threshold, and the mean of the spread is negative, that is, Then the period is divided into the reduction zone;

[0054] When the positive probability of the spread and the absolute value ratio of the positive and negative mean are both less than the corresponding low holding threshold and greater than any of the reduction thresholds, and the mean of the spread is negative, that is, This period is divided into a low holding zone;

[0055] When the above conditions are not met, the time period is classified as the normal period.

[0056] In some embodiments, the method further includes: determining the range of parameter thresholds using an optimization calculation method according to a preset objective function and constraints, the parameter thresholds including a positive price difference probability threshold and a positive and negative mean absolute value ratio threshold.

[0057] Specifically, when using the policy model to perform policy partitioning of time periods, p o and r o As the judgment threshold, the value of the judgment threshold can be a fixed value, or it can be calculated using a more scientific optimization algorithm. The specific algorithm is as follows:

[0058] Set the objective function to maximize the day-ahead transaction revenue of N trading days, that is, the objective function is i∈[1,96],n∈[1,N];

[0059] Set decision variables, positive spread probability threshold: 0≤p o ≤1; positive and negative mean absolute value ratio threshold: 0≤r o ≤5;

[0060] Set constraints and calculate the day-ahead transaction revenue for each period as the product of the price difference, actual electricity consumption and the declaration coefficient of a certain partition, that is, When the probability of positive price difference and the absolute value ratio of positive and negative mean in period i are both greater than the threshold, S = 20%; otherwise S = 0, which is converted into a linear programming mathematical expression: p i ≥p o –(0.2–S)*M,p i <p o +S*M,r i ≥r o –(0.2–S)*M,r i <r o +S*M, M=100000 (relative infinite value).

[0061] In some embodiments, based on the partition results of the estimated time period, the historical electricity load statistics data corresponding to the historical time period, and the risk preference coefficient, the declared amount of electric power resources corresponding to each estimated time period is estimated, including: statistics are collected on the historical electricity load data corresponding to the historical time period within the time period corresponding to the estimated time period to obtain the historical electricity load statistics data corresponding to the historical time period, and the quantile and median corresponding to the historical electricity load statistics data are determined; according to the pre-configured declaration amount calculation formula corresponding to the partition result, the quantile or median corresponding to the historical electricity load statistics data, and the risk preference coefficient are used to calculate the estimated value of the declared amount of electric power resources corresponding to the partition result of each estimated time period.

[0062] Specifically, according to the historical electricity load statistics of N trading days corresponding to the i period, the risk preference coefficient α (α∈[0,20]), and combined with the above strategy partition results, the final day-ahead declared quantity Q is calculated. i The specific calculation process is as follows:

[0063] First, the 25th percentile of the historical power load in each period i is calculated. median, 75th percentile,

[0064] a) For the calculation of the declared amount of power resources during the over-holding period, the following formula can be used:

[0065] Upper limit of reporting amount,

[0066] The minimum reporting amount,

[0067] The final declared amount is:

[0068] b) For the calculation of the declared amount of power resources during the high-holding period, the following formula can be used:

[0069] Upper limit of reporting amount,

[0070] The minimum reporting amount,

[0071] The final declared amount is:

[0072] c) For the calculation of the declared amount of power resources in the reduction zone period, the following formula can be used:

[0073] Upper limit of reporting amount,

[0074] The minimum reporting amount,

[0075] The final declared amount is:

[0076] d) For the calculation of the declared amount of power resources during the low-holding period, the following formula can be used:

[0077] Upper limit of reporting amount,

[0078] The minimum reporting amount,

[0079] The final declared amount is:

[0080] e) For the calculation of the declared amount of power resources in the general period, the following formula can be used:

[0081] The final declared amount is:

[0082] According to the technical solution provided by the embodiment of the present disclosure, the embodiment of the present disclosure is aimed at the day-ahead trading in the electricity spot market, and takes into account factors such as trading rule constraints and risk preferences of trading strategy makers, and optimizes the day-ahead declared quantity in each period of the trading day to maximize the day-ahead trading revenue. The day-ahead declared quantity is optimized in a multi-stage manner. First, the historical price difference is statistically analyzed and the parameter threshold (p o and r o ) divides the strategy into five major areas, namely, the over-holding area, the high-holding area, the normal area, the low-holding area and the under-holding area; and then calculates the final day-ahead declaration amount through the statistics of historical electricity consumption and risk preference α. The general expression is: Taking the maximization of day-ahead transaction revenue as the objective function, the optimal strategy variable value (i.e. parameter threshold p) is determined by linear programming algorithm. o and r o ).

[0083] The following are embodiments of the device disclosed herein, which can be used to execute the method embodiments disclosed herein. For details not disclosed in the device embodiments disclosed herein, please refer to the method embodiments disclosed herein.

[0084] Figure 3 Schematic diagram of the structure of the device for estimating the reported amount of electric power resources provided by the embodiment of the present disclosure. Figure 3 As shown, the estimation device of the power resource declared amount includes:

[0085] The acquisition module 301 is configured to acquire the first power resource value and the second power resource value corresponding to each historical period within a preset time period, and calculate the value difference between the first power resource value and the second power resource value;

[0086] The calculation module 302 is configured to determine the parameter corresponding to each historical period based on the value difference corresponding to each historical period using a preset parameter calculation method;

[0087] The partitioning module 303 is configured to partition the estimated time period corresponding to each historical time period according to the parameters corresponding to the historical time period and the preset parameter threshold according to a predetermined strategy, and obtain a partition result corresponding to each estimated time period;

[0088] The estimation module 304 is configured to estimate the declared amount of electric power resources corresponding to each estimated time period based on the partition results of the estimated time period, the historical power load statistics data corresponding to the historical time period, and the risk preference coefficient, and obtain an estimated value of the declared amount of electric power resources.

[0089] In some embodiments, Figure 3 Before acquiring the first power resource value and the second power resource value corresponding to each historical period within a preset time period, the acquisition module 301 determines the time period according to the time corresponding to the estimated period, and divides the time period into several historical periods according to the preset time intervals, wherein each trading day within the time period includes multiple historical periods.

[0090] In some embodiments, Figure 3 The acquisition module 301 acquires, for each historical period within a time period, a first power resource value and a second power resource value corresponding to each historical period from historical transaction data; wherein the first power resource value represents the day-ahead power resource value of the historical period, and the second power resource value represents the actual power resource value of the historical period.

[0091] In some embodiments, Figure 3 The calculation module 302 calculates the parameters corresponding to each historical period in each trading day within the time period according to the value difference corresponding to each historical period, wherein the parameters include the positive probability of the spread, the average of the positive spread, the average of the negative spread, the absolute value ratio of the positive and negative means, and the mean of the spread.

[0092] In some embodiments, Figure 3 The partitioning module 303 compares the parameters with the parameter thresholds respectively according to the calculated parameters corresponding to the historical time period using a predetermined strategy, and performs a partitioning operation on the estimated time period corresponding to the historical time period according to the comparison result, so as to determine the partitioning result corresponding to the estimated time period; wherein the partitioning result corresponding to the estimated time period includes an over-holding area, a high-holding area, a reduced-holding area, a low-holding area and a normal area.

[0093] In some embodiments, Figure 3The partitioning module 303 determines the range of parameter thresholds using an optimization calculation method according to a preset objective function and constraints. The parameter thresholds include a positive price difference probability threshold and a positive and negative mean absolute value ratio threshold.

[0094] In some embodiments, Figure 3 The estimation module 304 counts the historical power load corresponding to the historical time period within the time period corresponding to the estimated time period, obtains the historical power load statistical data corresponding to the historical time period, and determines the quantile and median corresponding to the historical power load statistical data; according to the pre-configured declaration quantity calculation formula corresponding to the partition result, using the quantile or median corresponding to the historical power load statistical data, and the risk preference coefficient, calculate the estimated value of the power resource declaration quantity corresponding to the partition result of each estimated time period.

[0095] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure.

[0096] Figure 4 Schematic diagram of the structure of the electronic device 4 provided by the embodiment of the present disclosure. Figure 4 As shown, the electronic device 4 of this embodiment includes: a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. When the processor 401 executes the computer program 403, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 401 executes the computer program 403, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0097] Exemplarily, the computer program 403 may be divided into one or more modules / units, which are stored in the memory 402 and executed by the processor 401 to complete the present disclosure. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 403 in the electronic device 4.

[0098] The electronic device 4 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 4 may include, but is not limited to, a processor 401 and a memory 402. Those skilled in the art will appreciate that Figure 4 It is only an example of the electronic device 4 and does not constitute a limitation of the electronic device 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0099] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0100] The memory 402 may be an internal storage unit of the electronic device 4, for example, a hard disk or memory of the electronic device 4. The memory 402 may also be an external storage device of the electronic device 4, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 4. Further, the memory 402 may also include both an internal storage unit and an external storage device of the electronic device 4. The memory 402 is used to store computer programs and other programs and data required by the electronic device. The memory 402 may also be used to temporarily store data that has been output or is to be output.

[0101] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0102] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0103] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. 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 this disclosure.

[0104] In the embodiments provided in the present disclosure, it should be understood that the disclosed apparatus / computer equipment and methods can be implemented in other ways. For example, the apparatus / computer equipment embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. Multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection of the apparatus or unit, which may be electrical, mechanical or other forms.

[0105] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0106] In addition, each functional unit in each embodiment of the present disclosure 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.

[0107] If the integrated module / 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 present disclosure implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. The computer program may include computer program code, and the computer program code may be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0108] The above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them. Although the present disclosure 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 make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should all be included in the protection scope of the present disclosure.

Claims

1. A method for estimating the declared amount of electric power resources, characterized in that: include: Obtaining a first power resource value and a second power resource value corresponding to each historical period within a preset time period, and calculating a value difference between the first power resource value and the second power resource value; Based on the value difference corresponding to each of the historical time periods, a preset parameter calculation method is used to calculate the parameters corresponding to each of the historical time periods in each trading day within the time period, wherein the parameters include a positive probability of a price difference, an average of positive price differences, an average of negative price differences, a ratio of absolute values ​​of positive and negative means, and an average price difference; According to the parameters corresponding to the historical period and the preset parameter thresholds, the estimated period corresponding to each of the historical period is partitioned according to a predetermined strategy to obtain the partition results corresponding to each of the estimated period, and the partition results corresponding to the estimated period include over-holding area, high-holding area, under-holding area, under-holding area and ordinary area; wherein, when the positive probability of the price difference and the absolute value ratio of the positive and negative mean are both greater than the corresponding over-holding threshold, and the mean of the price difference is positive, the period is divided into the over-holding area; when the positive probability of the price difference and the absolute value ratio of the positive and negative mean are both greater than the corresponding over-holding threshold, the period is divided into the over-holding area; When the corresponding high holding threshold is less than any over-holding threshold, and the average price difference is positive, the period is divided into the high holding area; when the positive probability of the price difference and the absolute value ratio of the positive and negative mean are both less than the corresponding reduction threshold, and the average price difference is negative, the period is divided into the reduction area; when the positive probability of the price difference and the absolute value ratio of the positive and negative mean are both less than the corresponding low holding threshold and greater than any reduction threshold, and the average price difference is negative, the period is divided into the low holding area; when the period that does not meet the conditions of the over-holding area, high holding area, reduction area, and low holding area is divided into the ordinary area; Based on the partition result of the estimated time period, the historical power load statistical data corresponding to the historical time period, and the risk preference coefficient, the power resource declaration amount corresponding to each estimated time period is estimated to obtain an estimated value of the power resource declaration amount, including: Performing statistics on the historical power load corresponding to the historical time period within the time period corresponding to the estimated time period, obtaining the historical power load statistical data corresponding to the historical time period, and determining the quantile and median corresponding to the historical power load statistical data; According to a pre-configured declaration amount calculation formula corresponding to the partition result, using the quantile or median corresponding to the historical power load statistical data and the risk preference coefficient, calculate the estimated value of the power resource declaration amount corresponding to the partition result for each estimated time period; Among them, according to the historical electricity load statistics of N trading days corresponding to the i period, the risk preference coefficient α, α∈[0,20], and combined with the partition results, the final day-ahead declaration amount is calculated The process is as follows: Count the 25th percentile of the historical power load in each period i, median, 75th percentile, a) For the calculation of the declared amount of power resources during the over-holding period, the following formula is used: Upper limit of reporting amount, The minimum reporting amount, The final declared amount is: b) For the calculation of the declared amount of power resources during the high-holding period, the following formula is used: Upper limit of reporting amount, The minimum reporting amount, The final declared amount is: c) For the calculation of the declared amount of power resources in the reduction zone period, the following formula is used: Upper limit of reporting amount, The minimum reporting amount, The final declared amount is: d) For the calculation of the declared amount of power resources during the low-holding period, the following formula is used: Upper limit of reporting amount, The minimum reporting amount, The final declared amount is: e) For the calculation of the declared amount of power resources in the general period, the following formula is used: The final declared amount is: The method further comprises: According to the preset objective function and constraints, the range of the parameter threshold is determined by using an optimization calculation method, and the parameter threshold includes a positive price difference probability threshold and a positive and negative mean absolute value ratio threshold.

2. The method according to claim 1, characterized in that Before obtaining the first power resource value and the second power resource value corresponding to each historical period within the preset time period, the method further includes: The time period is determined according to the time corresponding to the estimated time period, and the time period is divided into a plurality of historical time periods according to a preset time interval, wherein each trading day within the time period includes a plurality of the historical time periods.

3. The method according to claim 1, characterized in that The obtaining of the first power resource value and the second power resource value corresponding to each historical period within a preset time period includes: For each of the historical time periods within the time period, obtaining a first power resource value and a second power resource value corresponding to each of the historical time periods from historical transaction data; The first power resource value represents the day-ahead power resource value of the historical period, and the second power resource value represents the actual power resource value of the historical period.

4. A device for estimating the declared amount of electric power resources, used to implement the method according to any one of claims 1 to 3, characterized in that: include: An acquisition module is configured to acquire a first power resource value and a second power resource value corresponding to each historical period within a preset time period, and calculate a value difference between the first power resource value and the second power resource value; A calculation module is configured to determine the parameter corresponding to each of the historical periods based on the value difference corresponding to each of the historical periods using a preset parameter calculation method; A partitioning module is configured to partition the estimated time period corresponding to each of the historical time periods according to the parameters corresponding to the historical time periods and the preset parameter thresholds according to a predetermined strategy, and obtain a partitioning result corresponding to each of the estimated time periods; The estimation module is configured to estimate the declared amount of electric power resources corresponding to each of the estimated time periods based on the partition results of the estimated time periods, the historical power load statistics data corresponding to the historical time periods, and the risk preference coefficient, so as to obtain an estimated value of the declared amount of electric power resources.

5. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 3 when executing the program.

6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images