Value reporting optimization method and system of thermal power generating unit, and electronic equipment

Abstract

The invention relates to the field of thermal power, and provides a value reporting optimization method and system of a thermal power generating unit and electronic equipment. The method comprises the following steps: determining a first corresponding relationship between historical data of a spot market of a thermal power generating unit and corresponding meteorological data, and determining a second corresponding relationship between historical data of a frequency modulation market of the thermal power generating unit and the corresponding meteorological data; determining a spot market predicted price of the target time period, and determining a frequency modulation market predicted price of the target time period; based on the spot market price predicted value and the frequency modulation market price predicted value, determining the reported value of the thermal power generating unit in the target time period; and optimizing the reported value by taking profit maximization as an optimization target. The method is used for solving the defect that a traditional mode cannot accurately predict the power demand and determine the quotation, the new energy power generation efficiency can be represented in combination with meteorological factors, the demand for the thermal power generating unit can be specifically deduced, the reasonable quotation can be provided, and the profit of the thermal power generating unit is maximized.

Description

Technical Field

[0001] The present invention relates to the field of thermal power technology, and in particular to a method and system for optimizing the quotation value of a thermal power unit, and electronic equipment. Background Art

[0002] With the continuous advancement of the development of new energy, the number of hours of power generation by coal-fired power units has gradually decreased. The lower spot market price of new energy has had a huge impact on the profits of coal-fired power units. However, new energy power generation cannot meet the electricity demand of the entire power grid. Therefore, thermal power units still have a need to exist and profit space.

[0003] For power generation companies of thermal power units, making reasonable quotations plays a significant role in their own profits. In related technologies, when making quotations, thermal power units mostly predict the power demand on the day to be predicted based on the power demand on the day before or in the previous period of time, and make quotations accordingly. However, the power demand forecast made in this way is not accurate enough, and thus a reasonable quotation cannot be determined, resulting in a low profit margin for thermal power units. Summary of the invention

[0004] The present invention provides a method and system for optimizing the quotation value of a thermal power unit, and electronic equipment, which are used to solve the defect that the traditional method cannot accurately predict the power demand and determine a reasonable quotation. The scheme of the present application can characterize the efficiency of new energy power generation in combination with meteorological factors, and specifically infer the demand for thermal power units, which can accurately predict the power demand and provide a reasonable quotation to maximize the profit of the thermal power unit.

[0005] The present invention provides a method for optimizing the quotation value of a thermal power unit, comprising:

[0006] Determine a first correspondence between historical data of the spot market of the thermal power unit and corresponding meteorological data, and determine a second correspondence between historical data of the frequency regulation market of the thermal power unit and corresponding meteorological data;

[0007] Determine the spot market forecast price for the target time period based on the first corresponding relationship and the meteorological data for the target time period, and determine the frequency modulation market forecast price for the target time period based on the second corresponding relationship and the meteorological data for the target time period;

[0008] Determine the bid value of the thermal power unit in the target time period based on the spot market price forecast value and the frequency regulation market price forecast value;

[0009] Taking profit maximization as the optimization goal, the quoted value is optimized.

[0010] According to the method for optimizing the quoted value of a thermal power unit provided by the present invention, determining the predicted spot market price of the target time period based on the first corresponding relationship and the meteorological data of the target time period includes:

[0011] Based on the random forest algorithm and the first corresponding relationship, a spot market prediction model is constructed;

[0012] The meteorological data of the target time period is input into the spot market prediction model to obtain the spot market prediction price of the target time period.

[0013] According to the method for optimizing the quotation value of a thermal power unit provided by the present invention, the method of determining the frequency modulation market forecast price of the target time period based on the second corresponding relationship and the meteorological data of the target time period includes:

[0014] Based on the meteorological data of the target time period, determining a similar time period corresponding to the target time period, and constructing a frequency modulation market prediction model based on the similar time period and the second corresponding relationship;

[0015] The meteorological data of the target time period is input into the frequency modulation market prediction model to obtain the frequency modulation market prediction price of the target time period.

[0016] According to the method for optimizing the quotation value of a thermal power unit provided by the present invention, determining a similar time period corresponding to the target time period based on the meteorological data of the target time period includes:

[0017] Determining a number of historical time periods before the target time period;

[0018] Calculating a dynamic time warping value between the target time period and each of the historical time periods;

[0019] A plurality of historical time periods with the smallest dynamic time warping values ​​are determined as similar time periods corresponding to the target time period.

[0020] According to the method for optimizing the bid value of a thermal power unit provided by the present invention, the bid value of the thermal power unit in a target time period is determined based on the spot market price forecast value and the frequency modulation market price forecast value, including:

[0021] Determining an operation constraint range of a thermal power unit, wherein the operation constraint range represents power generation performance of the thermal power unit;

[0022] Based on the operation constraint range of the thermal power unit, the spot market price forecast value and the frequency regulation market price forecast value, the quotation value of the thermal power unit in the target time period is determined.

[0023] According to the method for optimizing the bid value of a thermal power unit provided by the present invention, the bid value is optimized with profit maximization as the optimization goal, and includes:

[0024] Performing a differential mutation operation on the quoted value to obtain a variation value of the quoted value;

[0025] Crossing the quoted value and the variation value of the quoted value to obtain a test value of the quoted value;

[0026] The quoted value is compared with the profit corresponding to the trial value of the quoted value. If the profit corresponding to the trial value of the quoted value is higher than the profit corresponding to the quoted value, the trial value of the quoted value is used to replace the quoted value.

[0027] The method for optimizing the quotation value of a thermal power unit provided by the present invention further includes:

[0028] If the profit corresponding to the trial value of the quoted value is not higher than the profit corresponding to the quoted value, the profit corresponding to the quoted value is determined to be the maximum profit.

[0029] According to the method for optimizing the quoted value of a thermal power unit provided by the present invention, the profit of the thermal power unit includes the profit of the long-term market, the profit of the spot market and the profit of the frequency regulation market.

[0030] The present invention also provides a report value optimization system for a thermal power unit, comprising:

[0031] A correlation determination module is used to perform correlation analysis on historical data of the spot market of thermal power units and corresponding meteorological data to determine a first corresponding relationship; perform correlation analysis on historical data of the frequency regulation market of thermal power units and corresponding meteorological data to determine a second corresponding relationship;

[0032] A price prediction module, configured to determine the spot market prediction price for the target time period based on the first corresponding relationship and the meteorological data for the target time period, and to determine the frequency modulation market prediction price for the target time period based on the second corresponding relationship and the meteorological data for the target time period;

[0033] A quotation determination module, used to determine the quotation value of the thermal power unit in the target time period based on the spot market price forecast value and the frequency modulation market price forecast value;

[0034] The quotation optimization module is used to optimize the quotation value by applying a differential algorithm with profit maximization as the optimization goal.

[0035] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, any one of the above-mentioned methods for optimizing the reporting value of a thermal power unit is implemented.

[0036] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for optimizing the quotation value of any thermal power unit described above is implemented.

[0037] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned methods for optimizing the quotation value of a thermal power unit.

[0038] In the quotation value optimization method of the thermal power unit provided by the present invention, a first correspondence between meteorological data and historical data of the spot market and a second correspondence between meteorological data and historical data of the frequency modulation market can be determined respectively, wherein meteorological data can be used to characterize the efficiency of new energy power generation such as photovoltaic and wind power, so that the first correspondence is equivalent to the correspondence between the efficiency of new energy power generation and the spot market of the thermal power unit, and the second correspondence is the correspondence between the efficiency of new energy power generation and the frequency modulation market of the thermal power unit. When performing spot market price forecasting and frequency modulation market price forecasting, the meteorological data of the target time period to be predicted reflects the efficiency of new energy power generation in the target time period. The efficiency of new energy power generation can intuitively determine the amount of electricity still in short supply in the power grid system, that is, the power demand for thermal power units. The scheme of the present application starts with meteorological data, can accurately predict the power demand of thermal power units, and can then help thermal power units to make accurate price forecasts and help determine reasonable quotations. After that, the differential algorithm can be applied to optimize the quotations to maximize the profits of thermal power units. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 This is one of the flow diagrams of the method for optimizing the quotation value of a thermal power unit provided by an embodiment of the present invention;

[0041] Figure 2 This is a second flow chart of a method for optimizing the quotation value of a thermal power unit provided by an embodiment of the present invention;

[0042] Figure 3 is a structural schematic diagram of a report value optimization system for a thermal power unit provided by an embodiment of the present invention;

[0043] Figure 4 It is a schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings 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.

[0045] Figure 1 The present invention is a flowchart of a method for optimizing the quotation value of a thermal power unit provided in an embodiment of the present invention.

[0046] Figure 2 This is the second flow chart of the method for optimizing the quotation value of a thermal power unit provided in an embodiment of the present invention.

[0047] like Figure 1 and Figure 2 As shown, this embodiment provides a method for optimizing the quotation value of a thermal power unit, comprising:

[0048] Step 101, determining a first correspondence between historical data of the spot market of the thermal power unit and corresponding meteorological data, and determining a second correspondence between historical data of the frequency regulation market of the thermal power unit and corresponding meteorological data;

[0049] Step 102, determining the spot market forecast price of the target time period based on the first corresponding relationship and the meteorological data of the target time period, and determining the frequency modulation market forecast price of the target time period based on the second corresponding relationship and the meteorological data of the target time period;

[0050] Step 103, determining the bid value of the thermal power unit in the target time period based on the spot market price forecast value and the frequency modulation market price forecast value;

[0051] Step 104, optimizing the bid value with profit maximization as the optimization goal.

[0052] In practical applications, a thermal power unit refers to a device that uses coal, oil or combustible gas as fuel to heat water in a boiler to generate steam, and uses pressurized steam to drive a turbine to generate electricity.

[0053] In the electricity scenario, the spot market refers to the market for business entities to carry out electricity transactions. Furthermore, the spot market for thermal power units refers to the market for business entities to carry out thermal power transactions.

[0054] The frequency regulation market in the power scenario refers to automatic power generation control. Specifically, frequency regulation means that the dispatching center selects units to participate in frequency regulation services in the form of dispatching instructions based on the capabilities of the generating units and the actual needs of the power grid, following the principle of "calling on demand" and compensating the units participating in the frequency regulation afterwards. The frequency regulation market is a market where users can make profits by participating in frequency regulation.

[0055] In actual applications, for each generator set, it is necessary to give the power generation and the corresponding quotation in advance. After that, the dispatching center of the power grid decides the winning generator set based on the quotation of each generator set. The winning generator set can participate in transactions in the spot market and the frequency regulation market. In other words, if the quotation of the generator set is too high, it will be difficult to win the bid. If the quotation is too low, it will result in too little profit margin or even no profit. Therefore, it is crucial to determine a reasonable quotation.

[0056] The meteorological data in this embodiment may include data such as temperature, humidity, cloud cover, light intensity and wind speed. The difference in these meteorological data will directly affect the efficiency of photovoltaic and wind power generation. For example, when the cloud cover is large, the photovoltaic efficiency will be low, and when the wind speed is high, the wind power efficiency will be higher. In this embodiment, the efficiency of renewable energy power generation is indirectly reflected through meteorological data. In this way, when the efficiency of renewable energy power generation is high, it means that the demand for thermal power is not large. When making quotations, thermal power units can provide lower quotations to improve market competitiveness. When meteorological data indicates that the efficiency of renewable energy power generation is low, the power grid has a higher demand for thermal power. When making quotations, thermal power units can increase their quotations to obtain higher profits.

[0057] In the quotation value optimization method for thermal power units provided in this embodiment, a first correspondence between meteorological data and historical data of the spot market and a second correspondence between meteorological data and historical data of the frequency modulation market can be determined respectively, wherein meteorological data can be used to characterize the efficiency of new energy power generation such as photovoltaic and wind power. In this way, the first correspondence is equivalent to the correspondence between the efficiency of new energy power generation and the spot market of thermal power units, and the second correspondence is the correspondence between the efficiency of new energy power generation and the frequency modulation market of thermal power units. When performing spot market price forecasting and frequency modulation market price forecasting, the meteorological data of the target time period to be predicted reflects the efficiency of new energy power generation in the target time period. The power demand for thermal power units can be intuitively determined through the efficiency of new energy power generation. Starting from the meteorological data, the power demand of thermal power units can be accurately predicted, which can help thermal power units to make accurate price forecasts and help determine reasonable quotations. After that, the differential algorithm can be applied to optimize the quotations to maximize the profits of thermal power units.

[0058] In an exemplary embodiment, when determining the first corresponding relationship between the historical data of the spot market of the thermal power unit and the corresponding meteorological data, the historical data of the spot market of the thermal power unit and the meteorological data of the corresponding period can be subjected to correlation analysis and feature extraction based on the Spearman correlation coefficient, and the process conforms to the following formula (1):

[0059]

[0060] Among them, x t,mi , They represent the values ​​and mean values ​​of the m vector matrices of temperature, humidity, cloudiness, light amplitude, wind speed, etc. of the weather forecast at time t=1, 2, 3...24, respectively. and are the spot price and mean value corresponding to time t respectively; It is the correlation coefficient between the temperature, humidity, cloudiness, light amplitude, wind speed, etc. of the weather forecast and the spot price. Its value is between -1 and +1. It indicates that the two variables are positively correlated; if This indicates that the two variables are negatively correlated. The larger the absolute value of This indicates that there is no linear relationship between the two. The absolute value of 0.4-0.6 indicates moderate correlation, 0.6-0.8 indicates strong correlation, and 0.8-1 indicates extremely strong correlation.

[0061] In an exemplary embodiment, when determining the second corresponding relationship between the historical data of the frequency regulation market of the thermal power unit and the corresponding meteorological data, the historical data of the frequency regulation market of the thermal power unit and the meteorological data of the corresponding period can be subjected to correlation analysis and feature extraction based on the Spearman correlation coefficient, and the process conforms to the following formula (2):

[0062]

[0063] in, and are the FM market clearing price and mean at time t respectively; It is the correlation coefficient between the temperature, humidity, cloudiness, light amplitude, wind speed, etc. of the weather forecast and the clearing price of the frequency modulation market. Its value is between -1 and +1. It indicates that the two variables are positively correlated; if This indicates that the two variables are negatively correlated. The larger the absolute value of This indicates that there is no linear relationship between the two. The absolute value of 0.4-0.6 indicates moderate correlation, 0.6-0.8 indicates strong correlation, and 0.8-1 indicates extremely strong correlation.

[0064] In an exemplary embodiment, determining the predicted spot market price for the target time period based on the first corresponding relationship and the meteorological data for the target time period includes:

[0065] Based on the random forest algorithm and the first corresponding relationship, a spot market prediction model is constructed;

[0066] The meteorological data of the target time period is input into the spot market prediction model to obtain the spot market prediction price of the target time period.

[0067] The spot market prediction model in this embodiment is established based on the random forest algorithm. The random forest algorithm is an integrated learning algorithm that constructs multiple decision trees to perform classification or regression tasks, and improves the overall accuracy and robustness by aggregating the prediction results of these decision trees. Specifically, the random forest algorithm in this embodiment can randomly extract samples using the bootstrap sampling method, and then adjust the model to obtain the optimal parameters of the random forest regression model. During the parameter adjustment process, oob_score can be used as the standard for model parameter adjustment. oob_score represents the score of out-of-bag samples, and oob_score conforms to the following formula:

[0068]

[0069] Among them, R 2 is oob_score, i.e., the score of samples out of bag, u is the residual sum of squares, v is the total sum of squares, N is the number of samples, i is the sample number, and f is the residual sum of squares. i is the model regression value; y i is the true numerical label of the sample point; is the average of the true value labels.

[0070] In an exemplary embodiment, determining the forecast price of the frequency modulation market in the target time period based on the second corresponding relationship and the meteorological data in the target time period includes:

[0071] Based on the meteorological data of the target time period, determining a similar time period corresponding to the target time period, and constructing a frequency modulation market prediction model based on the similar time period and the second corresponding relationship;

[0072] The meteorological data of the target time period is input into the frequency modulation market prediction model to obtain the frequency modulation market prediction price of the target time period.

[0073] In this embodiment, a regression method based on similar days is used to establish a frequency modulation market prediction model. The so-called regression method based on similar days is to calculate the similarity between each meteorological factor in each historical day and the corresponding meteorological factor in the time period to be predicted based on the data of various meteorological factors in the historical time period. If the similarity is high, it can be determined that the historical day is a similar day to the time period to be predicted. In this way, the frequency modulation clearing price of the day to be predicted can be used as the basis for predicting the frequency modulation clearing price of the day to be predicted. Specifically, the frequency modulation clearing price of the historical day can be used as the frequency modulation clearing price of the day to be predicted. Furthermore, the frequency modulation mileage of the day to be predicted can be predicted based on the frequency modulation mileage of the historical day, the mileage compensation electricity and price of the day to be predicted can be predicted based on the mileage compensation electricity and price of the day to be predicted, and the frequency modulation market cost of the day to be predicted can be predicted based on the frequency modulation market cost of the historical day.

[0074] In actual applications, the target time period to be predicted may not be one day, but may be an unfixed period, such as ten days or half a day. In this case, the length of the corresponding historical day may also be adjusted accordingly.

[0075] In this embodiment, by comparing the meteorological data of historical time periods one by one, the historical time period that is closest to the weather of the target time period to be predicted can be determined as a similar day. Under the premise that the meteorological data is closest, the corresponding frequency modulation market is also the closest, that is, the frequency modulation clearing price, frequency modulation mileage, mileage compensation electricity and price, and frequency modulation market cost are all the closest. That is, based on similar days, the frequency modulation market price of the target time period can be predicted more accurately.

[0076] In an exemplary embodiment, determining a similar time period corresponding to the target time period based on the meteorological data of the target time period includes:

[0077] Determining a number of historical time periods before the target time period;

[0078] Calculating a dynamic time warping value between the target time period and each of the historical time periods;

[0079] A plurality of historical time periods with the smallest dynamic time warping values ​​are determined as similar time periods corresponding to the target time period.

[0080] This embodiment discloses a specific process for determining a similar time period that is closest to the target time period to be predicted, including calculating the dynamic time bending value of each meteorological factor in each historical time period and the corresponding factor of the prediction day as a similarity index for evaluating the meteorological factor of each historical time period and the target time period to be predicted, selecting three historical time period subsets that are most similar to the meteorological factors of the prediction time period from the historical time period set, that is, the historical time periods corresponding to the first three minimum values ​​after the dynamic time bending value is sorted are proposed as similar time periods, and the average value of the frequency regulation clearing price in the corresponding time period is taken as the prediction result. The same method is used to obtain the prediction values ​​of frequency regulation mileage, mileage compensation electricity and price, frequency regulation market cost, etc. on similar days. The solution expression of the dynamic time bending value is shown in the following formula (6):

[0081] d(i,j)=w j M(i,j)+min{w j-1 d(i-1,j-1),w j d(i-1,j),w j-1 d(i,j-1)} (6)

[0082] Where i = 1, 2, ... m, j = 1, 2, ... n, m and n represent the meteorological factor time series A = {a1, ..., a i ,…,a m} and B={b1,…,b j ,…,b n}, M is the constructed m*n matrix, and the element M(i,j) is a i With b j The distance between them, d(i,j) is the dynamic time warping value of sequence A and sequence B.

[0083] In the above formula, the larger the curvature value, the lower the similarity. The curvature value needs to be verified by backtesting the training set, and the curvature value is inconsistent under different accuracy index requirements. The total curvature value is formed by taking the difference of each meteorological factor and synthesizing the matrix. The purpose is to find the historical day with high similarity to all meteorological factors in the target time period to be predicted.

[0084] In an exemplary embodiment, determining the bid value of the thermal power unit in the target time period based on the spot market price forecast value and the frequency regulation market price forecast value includes:

[0085] Determining an operation constraint range of a thermal power unit, wherein the operation constraint range represents power generation performance of the thermal power unit;

[0086] Based on the operation constraint range of the thermal power unit, the spot market price forecast value and the frequency regulation market price forecast value, the quotation value of the thermal power unit in the target time period is determined.

[0087] In practical applications, the operation constraints of thermal power units can include the upper and lower output limits of each generator unit, climbing constraints, monotonic increase in quotation segments and output winning constraints, segmented constraints on the number of coal mill starts and stops, and power generation task constraints of thermal power units, among which the upper and lower output limits of the generator units conform to the following formula (7):

[0088]

[0089] in is the minimum output and maximum output limit of generator i in time period t.

[0090] The climbing constraint complies with the following formula (8):

[0091]

[0092] Among them, q i,t ,q i,t-1 is the output of generator unit i at time period t and time period t-1; are the maximum ramp-down rate and maximum ramp-up rate of generator unit i, respectively.

[0093] The monotonically increasing bid price and output winning bid constraints conform to the following formulas (9) and (10):

[0094]

[0095] Among them, G and F are the corresponding functions of the segmented line of the thermal power unit quotation, They are the declared price and output corresponding to the generator unit i in the mth section, and M is the total number of sections declared for thermal power; To declare the upper and lower limits of unit output in the spot market in segments; The minimum interval for segmented quotation output; ΔP i min The minimum increment interval of spot price quotations; They are the lower and upper limits of spot market quotations respectively.

[0096] The segmented quotation constraint for the number of starts and stops of the coal mill complies with the following formula (11):

[0097]

[0098] in, is the output of the corresponding unit of j coal mills, are the upper and lower limits of the output of the corresponding unit of j coal mills, is the corresponding price of the segmented quotation when the bid is won in the output range of the j coal mills, and δ is the number of times the spot market clearing price passes through the corresponding price, that is, the threshold value for the number of coal mill starts and stops.

[0099] The power generation task constraint conforms to the following formula (12):

[0100]

[0101] Among them, Q i,min is the power generation index constraint value of the generator unit i in the T period.

[0102] The operation constraints in this embodiment can reflect the performance of the thermal power unit itself.

[0103] In an exemplary embodiment, the optimization of the bid value with profit maximization as the optimization goal includes:

[0104] Performing a differential mutation operation on the quoted value to obtain a variation value of the quoted value;

[0105] Crossing the quoted value and the variation value of the quoted value to obtain a test value of the quoted value;

[0106] The quoted value is compared with the profit corresponding to the trial value of the quoted value. If the profit corresponding to the trial value of the quoted value is higher than the profit corresponding to the quoted value, the trial value of the quoted value is used to replace the quoted value.

[0107] The optimization process in this embodiment specifically includes the following steps:

[0108] For each individual in the g-th generation population Randomly select 3 different parent individuals (r1, r2, r3∈[1, N P ] and r1, r2, r3≠i), perform differential mutation operation according to the following formula (13) to generate mutant individuals

[0109]

[0110] Among them, F is the difference scale factor, which controls the amplitude of the difference variation.

[0111] Then, the following formula (14) is used to calculate the parent individual and variant individuals Perform crossover to generate experimental individuals

[0112]

[0113] Among them, rand() is a uniform random number between [0, 1]; CR∈[0, 1] is the crossover probability, and rand(1, n) is a random integer between [1, n] to ensure that at least one of the test individuals comes from the mutant individual.

[0114] Compare the fitness values ​​of the parent individuals and the test individuals, and the better ones enter the next generation population. This process conforms to the following formula (15):

[0115]

[0116] In an exemplary embodiment, the method for optimizing the bid value of a thermal power unit further includes:

[0117] If the profit corresponding to the trial value of the quoted value is not higher than the profit corresponding to the quoted value, the profit corresponding to the quoted value is determined to be the maximum profit.

[0118] In an exemplary embodiment, the profit of the thermal power unit includes profit in the long-term market, profit in the spot market and profit in the frequency regulation market.

[0119] In practical applications, the profits of the thermal power units in this embodiment can include three aspects, namely, profits in the long-term market, profits in the spot market, and profits in the frequency modulation market. The long-term market refers to the wholesale electricity activities of market entities such as power generation companies that meet the access conditions through negotiation, centralized trading, etc., in units of many years, years, quarters, months, weeks, and days. Compared with the transactions in the spot market in units of a single day, the transaction cycle of the long-term market is longer. Compared with the higher real-time prices in the spot market, the long-term market can stabilize the market price and the supply and demand relationship. However, in the long-term market, since the price is fixed, power generation companies need to make more accurate price forecasts to obtain greater profits.

[0120] The profit of the thermal power unit described in this embodiment is expressed in the form of formula (16):

[0121]

[0122] Among them, L i (P i ) is the total market profit of all units i of the generator; They are the profits of generator unit i in the medium- and long-term electricity market, spot market and frequency regulation market respectively.

[0123] Profits of thermal power units in the long term market It complies with the following formula (17):

[0124]

[0125] Where T is the total number of dispatch periods, which is usually 24 or 96 periods; are the winning bid power and electricity price of generator unit i in the medium and long-term trading market in period t, is the spot market node price of generator unit i in time period t.

[0126] The profit of thermal power units in the spot market conforms to the following formulas (18) and (19):

[0127]

[0128] Where T is the total number of dispatch periods, which is usually 24 or 96 periods; They are the winning bid power and spot price of generator unit i in the spot market during period t: is the power generation cost of generator i in period t (corresponding to Cost of generating electricity), is the power output of generator i in time period t. i 、b i 、c i is the coefficient of the coal consumption cost function of unit i of the power company.

[0129] Profits of thermal power units in the frequency regulation market It complies with the following formula (20):

[0130]

[0131] N is the number of generator i in the frequency regulation market in different time periods; are the regulation mileage and price of the frequency regulation market of the generator unit i in segment n; R e0 , The electricity price and amount of electricity compensated for mileage in the frequency regulation market; is the operation and maintenance cost of generator unit i in the frequency regulation market within segment n.

[0132] In this embodiment, the profit of the thermal power unit is comprehensively determined from three perspectives: the long-term market, the spot market, and the frequency regulation market. Specifically, when determining the quotation of the thermal power unit in the target time period, the price of the long-term market, the price of the spot market, and the price of the frequency regulation market can be considered to comprehensively determine the most reasonable quotation. For example, when the medium- and long-term holding ratio of the thermal power unit is relatively high, the spot and medium- and long-term transaction price difference can be considered in the spot market. In the high spot price period, more winning bids can be achieved through appropriate quotations, thereby obtaining higher returns. In the low spot price period, high prices are quoted and bids are deliberately not won, so as to choose to earn the medium- and long-term and spot price difference benefits. By comparing the cost changes of the thermal power unit under different load rates, the total profit of the winning bid quantity and price can be maximized.

[0133] The following is a description of the quotation value optimization system for a thermal power unit provided by the present invention. The quotation value optimization system for a thermal power unit described below and the quotation value optimization method for a thermal power unit described above can be referred to each other.

[0134] Figure 3The invention is a schematic diagram of the structure of a system for optimizing the reporting value of a thermal power unit provided by an embodiment of the present invention.

[0135] like Figure 3 As shown, the quotation value optimization system of the thermal power unit provided by the present application includes:

[0136] The correlation determination module 301 is used to perform correlation analysis on the historical data of the spot market of the thermal power unit and the corresponding meteorological data to determine a first corresponding relationship; perform correlation analysis on the historical data of the frequency regulation market of the thermal power unit and the corresponding meteorological data to determine a second corresponding relationship;

[0137] The price prediction module 302 is used to determine the spot market prediction price of the target time period based on the first corresponding relationship and the meteorological data of the target time period, and to determine the frequency modulation market prediction price of the target time period based on the second corresponding relationship and the meteorological data of the target time period;

[0138] The quotation determination module 303 is used to determine the quotation value of the thermal power unit in the target time period based on the spot market price forecast value and the frequency modulation market price forecast value;

[0139] The quotation optimization module 304 is used to optimize the quotation value by applying a differential algorithm with profit maximization as the optimization goal.

[0140] In an exemplary embodiment, the price prediction module 302 is further configured to:

[0141] Based on the random forest algorithm and the first corresponding relationship, a spot market prediction model is constructed;

[0142] The meteorological data of the target time period is input into the spot market prediction model to obtain the spot market prediction price of the target time period.

[0143] In an exemplary embodiment, the price prediction module 302 is further configured to:

[0144] Based on the meteorological data of the target time period, determining a similar time period corresponding to the target time period, and constructing a frequency modulation market prediction model based on the similar time period and the second corresponding relationship;

[0145] The meteorological data of the target time period is input into the frequency modulation market prediction model to obtain the frequency modulation market prediction price of the target time period.

[0146] In an exemplary embodiment, the price prediction module 302 is further configured to:

[0147] Determining a number of historical time periods before the target time period;

[0148] Calculating a dynamic time warping value between the target time period and each of the historical time periods;

[0149] A plurality of historical time periods with the smallest dynamic time warping values ​​are determined as similar time periods corresponding to the target time period.

[0150] In an exemplary embodiment, the quotation determination module 303 is further configured to:

[0151] Determining an operation constraint range of a thermal power unit, wherein the operation constraint range represents power generation performance of the thermal power unit;

[0152] Based on the operation constraint range of the thermal power unit, the spot market price forecast value and the frequency regulation market price forecast value, the quotation value of the thermal power unit in the target time period is determined.

[0153] In an exemplary embodiment, the quotation optimization module 304 is further configured to:

[0154] Performing a differential mutation operation on the quoted value to obtain a variation value of the quoted value;

[0155] Crossing the quoted value and the variation value of the quoted value to obtain a test value of the quoted value;

[0156] The quoted value is compared with the profit corresponding to the trial value of the quoted value. If the profit corresponding to the trial value of the quoted value is higher than the profit corresponding to the quoted value, the trial value of the quoted value is used to replace the quoted value.

[0157] In an exemplary embodiment, the quotation optimization module 304 is further configured to:

[0158] If the profit corresponding to the trial value of the quoted value is not higher than the profit corresponding to the quoted value, the profit corresponding to the quoted value is determined to be the maximum profit.

[0159] The specific implementation method of the quotation value optimization system for thermal power units provided in this embodiment can be implemented with reference to the above-mentioned embodiment, and will not be described in detail here.

[0160] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the report value optimization method of the thermal power unit, and the method includes:

[0161] Determine a first correspondence between historical data of the spot market of the thermal power unit and corresponding meteorological data, and determine a second correspondence between historical data of the frequency regulation market of the thermal power unit and corresponding meteorological data;

[0162] Determine the spot market forecast price for the target time period based on the first corresponding relationship and the meteorological data for the target time period, and determine the frequency modulation market forecast price for the target time period based on the second corresponding relationship and the meteorological data for the target time period;

[0163] Determine the bid value of the thermal power unit in the target time period based on the spot market price forecast value and the frequency regulation market price forecast value;

[0164] Taking profit maximization as the optimization goal, the differential algorithm is applied to optimize the quoted value.

[0165] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of 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 methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), disk or optical disk, etc. Various media that can store program codes.

[0166] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored in a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the method for optimizing the quotation value of the thermal power unit provided by the above methods, the method comprising:

[0167] Determine a first correspondence between historical data of the spot market of the thermal power unit and corresponding meteorological data, and determine a second correspondence between historical data of the frequency regulation market of the thermal power unit and corresponding meteorological data;

[0168] Determine the spot market forecast price for the target time period based on the first corresponding relationship and the meteorological data for the target time period, and determine the frequency modulation market forecast price for the target time period based on the second corresponding relationship and the meteorological data for the target time period;

[0169] Determine the bid value of the thermal power unit in the target time period based on the spot market price forecast value and the frequency regulation market price forecast value;

[0170] Taking profit maximization as the optimization goal, the differential algorithm is applied to optimize the quoted value.

[0171] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for optimizing the quotation value of a thermal power unit provided by the above methods is implemented, and the method comprises:

[0172] Determine a first correspondence between historical data of the spot market of the thermal power unit and corresponding meteorological data, and determine a second correspondence between historical data of the frequency regulation market of the thermal power unit and corresponding meteorological data;

[0173] Determine the spot market forecast price for the target time period based on the first corresponding relationship and the meteorological data for the target time period, and determine the frequency modulation market forecast price for the target time period based on the second corresponding relationship and the meteorological data for the target time period;

[0174] Determine the bid value of the thermal power unit in the target time period based on the spot market price forecast value and the frequency regulation market price forecast value;

[0175] Taking profit maximization as the optimization goal, the differential algorithm is applied to optimize the quoted value.

[0176] The device embodiments described above are merely illustrative, wherein 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, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0177] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0178] 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 make equivalent replacements for some of the technical features therein. However, 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 invention.

Claims

1. A method for optimizing the quotation value of a thermal power unit, characterized in that: include: Determine a first correspondence between historical data of the spot market of the thermal power unit and corresponding meteorological data, and determine a second correspondence between historical data of the frequency regulation market of the thermal power unit and corresponding meteorological data; Determine the spot market forecast price for the target time period based on the first corresponding relationship and the meteorological data for the target time period, and determine the frequency modulation market forecast price for the target time period based on the second corresponding relationship and the meteorological data for the target time period; Determine the bid value of the thermal power unit in the target time period based on the spot market price forecast value and the frequency regulation market price forecast value; Taking profit maximization as the optimization goal, the quoted value is optimized.

2. The method for optimizing the quotation value of a thermal power unit according to claim 1, characterized in that: The step of determining the predicted spot market price for the target time period based on the first corresponding relationship and the meteorological data for the target time period includes: Based on the random forest algorithm and the first corresponding relationship, a spot market prediction model is constructed; The meteorological data of the target time period is input into the spot market prediction model to obtain the spot market prediction price of the target time period.

3. The method for optimizing the quotation value of a thermal power unit according to claim 1, characterized in that: The step of determining the frequency modulation market forecast price for the target time period based on the second corresponding relationship and the meteorological data for the target time period includes: Based on the meteorological data of the target time period, determining a similar time period corresponding to the target time period, and constructing a frequency modulation market prediction model based on the similar time period and the second corresponding relationship; The meteorological data of the target time period is input into the frequency modulation market prediction model to obtain the frequency modulation market prediction price of the target time period.

4. The method for optimizing the quotation value of a thermal power unit according to claim 3, characterized in that: The determining, based on the meteorological data of the target time period, a similar time period corresponding to the target time period comprises: Determining a number of historical time periods before the target time period; Calculating a dynamic time warping value between the target time period and each of the historical time periods; A plurality of historical time periods with the smallest dynamic time warping values ​​are determined as similar time periods corresponding to the target time period.

5. The method for optimizing the quotation value of a thermal power unit according to claim 1, characterized in that: The step of determining the bid value of the thermal power unit in the target time period based on the spot market price forecast value and the frequency modulation market price forecast value comprises: Determining an operation constraint range of a thermal power unit, wherein the operation constraint range represents power generation performance of the thermal power unit; Based on the operation constraint range of the thermal power unit, the spot market price forecast value and the frequency regulation market price forecast value, the quotation value of the thermal power unit in the target time period is determined.

6. The method for optimizing the quotation value of a thermal power unit according to claim 1, characterized in that: The optimization of the bid value with profit maximization as the optimization goal includes: Performing a differential mutation operation on the quoted value to obtain a variation value of the quoted value; Crossing the quoted value and the variation value of the quoted value to obtain a test value of the quoted value; The quoted value is compared with the profit corresponding to the trial value of the quoted value. If the profit corresponding to the trial value of the quoted value is higher than the profit corresponding to the quoted value, the trial value of the quoted value is used to replace the quoted value.

7. The method for optimizing the quotation value of a thermal power unit according to claim 6, characterized in that: Also includes: If the profit corresponding to the trial value of the quoted value is not higher than the profit corresponding to the quoted value, the profit corresponding to the quoted value is determined to be the maximum profit.

8. The method for optimizing the quotation value of a thermal power unit according to any one of claims 1 to 7, characterized in that: The profits of the thermal power units include profits in the long-term market, profits in the spot market and profits in the frequency regulation market.

9. The quote value optimization system of thermal power units is characterized by: include: A correlation determination module is used to perform correlation analysis on historical data of the spot market of thermal power units and corresponding meteorological data to determine a first corresponding relationship; Conduct correlation analysis on historical data of the frequency regulation market of thermal power units and corresponding meteorological data to determine the second corresponding relationship; A price prediction module, configured to determine the spot market prediction price of the target time period based on the first corresponding relationship and the meteorological data of the target time period, and to determine the frequency modulation market prediction price of the target time period based on the second corresponding relationship and the meteorological data of the target time period; A quotation determination module, used to determine the quotation value of the thermal power unit in the target time period based on the spot market price forecast value and the frequency modulation market price forecast value; The quotation optimization module is used to optimize the quotation value with profit maximization as the optimization goal.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the reporting value optimization method of the thermal power unit as described in any one of claims 1 to 8 is implemented.

Images