Dynamic scheme optimization method, device, electronic device and storage medium based on electricity price prediction

Abstract

The present invention discloses a dynamic scheme optimization method, device, electronic device and storage medium based on electricity price forecast. The method includes: determining target power data and resource consumption data; determining target power generation cost data according to resource consumption data; performing scheduling optimization through an optimization model according to target power data, target power generation cost data and target power unit operation data to obtain target optimization results; optimizing the power generation strategy of the power generation enterprise according to the target optimization results. The method determines the target optimization results according to the target power data and the target power generation cost, and optimizes the power generation strategy according to the target optimization results, which can effectively help the power generation enterprise to make timely responses to market fluctuations, can minimize the power generation cost, and can also adapt to the complexity and dynamics of the power market, thereby improving the power generation enterprise's ability to change.

Description

Technical Field

[0001] The present invention relates to the technical field of power generation cost calculation, and in particular to a dynamic scheme optimization method, device, electronic equipment and storage medium based on electricity price prediction. Background Art

[0002] In the electricity market, power generation companies face the complex challenge of participating in multiple markets, such as the spot market, the medium- and long-term market, and the ancillary service market to trade electricity. With the continuous development of the electricity market and the improvement of policies, the value of these markets generally follows the volatility and uncertainty caused by the supply and demand relationship, which may cause significant differences in the power generation costs and revenues of companies in different markets. Traditional power generation scheduling and trading strategies usually rely on static electricity prices and cost data. This decision-making method based on historical and fixed data is difficult to adapt to the dynamically changing market environment. Due to the inability to respond to fluctuations in market value in a timely manner, companies may face the risk of reduced profits and increased operating costs.

[0003] Under traditional dispatch strategies, power generation companies usually formulate power generation plans and trading strategies based on fixed value estimates and long-term power generation costs. However, as the power market becomes increasingly complex, market value is affected by a variety of factors, all of which can cause significant fluctuations in value. In this case, dispatch strategies that rely on static data are difficult to accurately capture real-time market dynamics, which may cause power generation companies to fail to fully utilize market opportunities and may even suffer large economic losses when market value is unfavorable. In addition, with the rapid development of new energy and the continuous improvement of market mechanisms, uncertainties in the power market have further intensified. New energy power generation is intermittent and uncontrollable, which increases the volatility of power supply and demand and makes market value more difficult to predict. Traditional dispatch strategies lack the ability to respond to these uncertainties in real time and cannot provide companies with flexible response plans, which to a certain extent limits the competitiveness of companies in the power market. Summary of the invention

[0004] The present invention provides a method, device, electronic device and storage medium for dynamic scheme optimization based on electricity price forecasting, so as to solve the problem that when the electricity market fluctuates, power generation enterprises cannot adjust their power generation strategies in time, thus causing waste of resources.

[0005] According to one aspect of the present invention, a dynamic scheme optimization method based on electricity price prediction is provided, comprising:

[0006] Determine target power data and resource consumption data; the target power data is used to characterize the value of electric energy generated by power generation enterprises in the power market within a preset time period; the resource consumption data is used to characterize the resource consumption generated by power generation enterprises when generating electricity;

[0007] Determine target power generation cost data according to the resource consumption data; the target power generation cost data is used to characterize the value of energy consumed by the power generation enterprise;

[0008] According to the target power data, the target power generation cost data and the target power unit operation data, the scheduling optimization is performed through the optimization model to obtain the target optimization result; the optimization model is configured with a constraint function and an objective function, the constraint function is used to constrain the output result of the optimization model, and the objective function provides an optimization target for the optimization model;

[0009] The power generation strategy of the power generation enterprise is optimized through the target optimization result.

[0010] According to another aspect of the present invention, a dynamic scheme optimization device based on electricity price prediction is provided, comprising:

[0011] A data determination module is used to determine target power data and resource consumption data; the target power data is used to characterize the value of the electric energy generated by the power generation enterprise in the power market within a preset time period; the resource consumption data is used to characterize the resource consumption generated by the power generation enterprise when generating electricity;

[0012] A target power generation cost data determination module is used to determine target power generation cost data according to the resource consumption data; the target power generation cost data is used to characterize the value of energy consumed by the power generation enterprise;

[0013] a target optimization result determination module, used to perform scheduling optimization through an optimization model according to the target power data, the target power generation cost data and the target power unit operation data, and obtain a target optimization result; the optimization model is configured with a constraint function and an objective function, the constraint function is used to constrain the output result of the optimization model, and the objective function provides an optimization target for the optimization model;

[0014] The optimization module is used to optimize the power generation strategy of the power generation enterprise through the target optimization result.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the dynamic scheme optimization method based on electricity price prediction described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the dynamic scheme optimization method based on electricity price prediction described in any embodiment of the present invention when executed.

[0020] The technical solution of the embodiment of the present invention determines the target power data and resource consumption data. The determination of the target power data can clearly characterize the change in the value of electric energy, and provide a basis for the optimization of the subsequent power generation strategy; the target power generation cost data is determined according to the resource consumption data; the scheduling optimization is performed through the optimization model according to the target power data, the target power generation cost data and the target power unit operation data to obtain the target optimization result; the power generation strategy of the power generation enterprise is optimized according to the target optimization result. The method determines the target optimization result according to the target power data and the target power generation cost, and optimizes the power generation strategy according to the target optimization result, which can effectively help the power generation enterprise to respond promptly to market fluctuations, and can minimize the power generation cost while adapting to the complexity and dynamics of the power market, thereby improving the power generation enterprise's ability to change.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A flowchart of a dynamic scheme optimization method based on electricity price prediction provided by an embodiment of the present invention;

[0024] Figure 2 A schematic diagram of the structure of a dynamic scheme optimization device based on electricity price prediction provided by an embodiment of the present invention;

[0025] Figure 3 A schematic diagram of the structure of an electronic device for implementing a dynamic scheme optimization method based on electricity price prediction according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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 should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Figure 1 The present invention provides a flowchart of a method for dynamic scheme optimization based on electricity price forecasting. This embodiment is applicable to the situation where power generation enterprises adjust their power generation strategies when the power market fluctuates. The method can be executed by a dynamic scheme optimization device based on electricity price forecasting. The dynamic scheme optimization device based on electricity price forecasting can be implemented in the form of hardware and / or software. The dynamic scheme optimization device based on electricity price forecasting can be configured in any electronic device with network communication function. Figure 1 As shown, the method includes:

[0029] S110: Determine target power data and resource consumption data.

[0030] The target power data is used to characterize the value of the electric energy generated by the power generation enterprises in the power market within a preset time period. The resource consumption data is used to characterize the resource consumption generated by the power generation enterprises when generating electricity.

[0031] Specifically, the market disclosure data of the current time period is determined from the power market, and the market disclosure data is preprocessed and feature constructed to obtain the power load data. The target power data is predicted based on the power load data. The resource consumption data is directly obtained from the power generation enterprise.

[0032] S120. Determine target power generation cost data according to resource consumption data.

[0033] Among them, the target power generation cost data is used to characterize the value of the energy consumed by power generation enterprises.

[0034] Specifically, the fuel combustion cost, carbon dioxide emission cost and maintenance cost are calculated according to the resource consumption data, and the fuel combustion cost, carbon dioxide emission cost and maintenance cost are integrated to obtain the target power generation cost data.

[0035] Furthermore, the fuel combustion cost can be obtained by the following formula:

[0036] Cf=(Ed / Ef)*Pf;

[0037] Among them, Cf is the fuel consumption cost (yuan); Ed is the power generation (MWh); Ef is the electricity generated per ton of fuel (MWh / ton); Pf is the fuel price (yuan / ton).

[0038] Furthermore, the emission cost of carbon dioxide can be obtained by the following formula:

[0039] Ce=(Ed*Cco2)*Cem;

[0040] Among them, Ce is the emission cost (yuan); Cco2 is the carbon dioxide produced per ton of fuel (ton / ton); Cem is the emission cost per ton of carbon dioxide (yuan / ton).

[0041] Furthermore, the maintenance cost can be obtained by the following formula:

[0042] Cm=T*Pm;

[0043] Among them, Cm is the maintenance cost (yuan); T is the operating time (hours); Pm is the hourly maintenance cost (yuan / hour).

[0044] Furthermore, the target power generation cost data can be obtained by the following formula:

[0045] Ct=Cf+Ce+Cm;

[0046] Among them, Ct is the total change cost (yuan).

[0047] S130, performing scheduling optimization through an optimization model according to target power data, target power generation cost data and target power unit operation data to obtain a target optimization result.

[0048] The optimization model is configured with a constraint function and an objective function. The constraint function is used to constrain the output results of the optimization model, and the objective function provides an optimization target for the optimization model.

[0049] Among them, the target power unit operation data include: downtime, operation time, rated capacity and minimum technical output of the target power unit, as shown in Table 1.

[0050] Table 1 Target power unit operation data

[0051]

[0052]

[0053] Among them, the target optimization result is the output load of the target power unit and the value of the output load. The output load of the target power unit includes: the segment start output load and the segment end output load. As shown in Table 2.

[0054] Table 2 Target optimization results

[0055] Field Name Time granularity unit Segment start output / MW Segment end output / MW Output load value / Yuan / MWH

[0056] Specifically, the target power data and the target power generation cost data are used as input data and input into the optimization model for calculation to obtain the target optimization result.

[0057] S140. Optimize the power generation strategy of the power generation enterprise based on the target optimization result.

[0058] Specifically, the output load of the target power unit of the power generation enterprise is adjusted according to the target optimization result; the fuel combustion amount and carbon dioxide emission are adjusted according to the value of the output load of the target power unit.

[0059] Optionally, determining target power data includes steps A1-A2:

[0060] Step A1: Determine power load data.

[0061] Among them, power load data is used to characterize the amount of electric energy provided by power generation enterprises to power users.

[0062] Specifically, power load data is obtained from the power market.

[0063] Furthermore, before obtaining the power load data, authorization from the power market must be obtained.

[0064] Step A2: matching the target model according to the power load data and the predicted demand, and determining the target power data according to the target model.

[0065] The predicted demand includes: a first preset time value demand and a second preset time value demand, and the second preset time is greater than the second preset time.

[0066] Exemplarily, the first preset time value requirement may be hours, days or weeks; the second preset time value requirement may be months, years, etc.

[0067] Among them, the target model is used to characterize the relationship between power load data and target power data.

[0068] Specifically, a target model is determined from candidate models according to forecasting requirements, power load data is screened according to the forecasting requirements, and the screened power load data is input into the target model for forecasting calculation to obtain target power data.

[0069] Furthermore, the candidate models include: a first model and a second model.

[0070] Among them, the first model is used to determine the target power data under the first preset time value requirement; the second model is used to determine the target power data under the second preset time value requirement.

[0071] The first model includes: a first short-term prediction model and a second short-term prediction model.

[0072] Furthermore, the matching of the first short-term prediction model and the second short-term prediction model is determined according to the power conditions in the region where the power generation enterprise is located.

[0073] Among them, the base model of the first short-term prediction model can adopt the random forest model. The random forest model captures the impact of power load data on target power data. Since the target power data is affected by supply and demand, season, policy and other factors, the random forest can learn the relationship between these variables and integrate the training effect of the decision tree to make predictions.

[0074] Furthermore, the construction process of the first short-term prediction model is as follows: determine the historical power data and the historical power load data, select the training set and the test set according to the ratio of 7:3 of the acquired historical power data and the historical power load data, input the training set data into the random forest model for training, determine the root mean square error based on the predicted power data and the historical power data obtained through training, optimize the parameters of the random forest model based on the root mean square error, and verify the generalization ability of the random forest model through the cross-validation method to obtain the first short-term prediction model.

[0075] Among them, the construction process of the second short-term prediction model is as follows: the historical power data and historical power load data are obtained, and the training set and the test set are selected according to the ratio of 7:3 between training data and test data. The corresponding historical thermal power bidding space and the historical value of electric energy are calculated according to the training set data and the test set data, and the historical thermal power bidding space and the historical value curve of electric energy are classified by the K-MEANS method, and the historical thermal power bidding space is divided into 5 distribution categories, and different categories correspond to different segmentation methods and fitting methods.

[0076] Furthermore, the historical thermal power bidding space and the historical value of electricity are used as two-dimensional features for data classification. The training set data of the same category is used as a new round of training set, and breakpoints and segmented fitting are performed. The root mean square error (RMSE) is used as the evaluation indicator for model tuning, and cross-validation is used to enhance the generalization ability of the model to obtain the second short-term prediction model.

[0077] Among them, the second model can use the multiple regression model as the base model.

[0078] Furthermore, the construction process of the second model is: taking the historical power data as the dependent variable and the historical power load data as the independent variable, fitting is performed, and the fitted model is corrected by the mean square error (MSE) to obtain the second model.

[0079] Furthermore, if the predicted demand is the first preset time value demand, the filtered power load data is shown in Table 3 and Table 4. Table 3 is the input of the first short-term prediction model; Table 4 is the input of the second short-term prediction model.

[0080] Table 3 The power load data corresponding to the first preset time value

[0081]

[0082]

[0083] Table 4 The power load data corresponding to the second preset time value

[0084]

[0085] Furthermore, if the predicted demand is the second preset time value demand, the filtered power load data is as shown in Table 5.

[0086] Table 5 Power load data corresponding to the second preset time value demand

[0087]

[0088] Optionally, determining the power load data includes steps B1-B4:

[0089] Step B1. Determine market disclosure data.

[0090] Among them, the market disclosure data is the electricity production of each power generation enterprise obtained from the electricity market.

[0091] Among them, the market disclosed data include: centralized dispatching load forecast, new energy load forecast, wind power load forecast, photovoltaic load forecast, non-market processing forecast, positive and negative standby capacity forecast of the whole network, total maintenance capacity forecast, maintenance plan and interconnection line plan (external transmission load), etc.

[0092] Specifically, data that can characterize the production capacity of each power generation enterprise is obtained from the electricity market.

[0093] Furthermore, authorization for use was obtained prior to obtaining the market disclosure data.

[0094] Step B2: Clean and complete the market disclosed data to obtain the data to be selected.

[0095] Specifically, the market disclosed data is traversed to obtain outlier data and missing value data, the outliers are removed, and the missing values ​​are filled with the average value or the mean of two adjacent data to obtain the data to be selected.

[0096] Step B3: determine characteristic data according to the data to be selected.

[0097] Among them, the characteristic data at least includes: fire bidding space.

[0098] Furthermore, the characteristic data may also include: supply and demand data, power limit forecast value, typical day, time and other data.

[0099] Among them, typical days are dates with large fluctuations in electricity consumption, which will have a greater impact on the electricity price of the entire market. Therefore, typical days include general working days, weekends, holidays, and special typical days that change with seasonal changes.

[0100] Specifically, the characteristic data is obtained by calculating according to the data to be selected through a corresponding determination method.

[0101] Furthermore, the power limit prediction value can be determined by the following formula:

[0102] The power limit forecast value = unified dispatching load forecast + interconnection line transmission forecast - the sum of the minimum technical output of the thermal power units in the whole network - non-market output - new energy load forecast;

[0103] Among them, the sum of the minimum technical output of all thermal power units in operation in the entire network = the capacity of all thermal power units in the entire network * startup load rate (the default is 50%).

[0104] Furthermore, the fire bidding space can be determined by the following formula:

[0105] Thermal power bidding space = centralized dispatching load forecast + interconnection line transmission forecast - non-market output - new energy load forecast - maintenance capacity forecast.

[0106] Furthermore, the supply and demand data are obtained by processing meteorological data. The meteorological data is affected by the detection time. The first four days are 24 hours / day, and after the fifth day, there are only 8 hours / day. First, the meteorological data needs to be completed. The historical similar day method is used to fill it to 24 hours / day, and then feature processing is performed. After the discrete variables are continuous, they are normalized and feature selection is completed through filtering method to obtain the features used to predict the supply and demand relationship. These features are used to predict the supply and demand data.

[0107] Among them, the characteristics of predicting supply and demand relationship include: surface wind speed, 10m wind speed, 80m wind speed, sunshine duration, temperature, long-wave radiation flux, etc.

[0108] Step B4: Determine the power load data according to the correlation between the data to be selected and the characteristic data.

[0109] Specifically, feature mapping is performed on the data to be selected, the characteristic data and the value of the unified settlement point of the entire network, and the correlation between the data to be selected, the characteristic data and the value is established. The data to be selected and the characteristic data are screened according to the correlation to obtain the power load data.

[0110] Among them, the feature mapping method can use the Pearson correlation coefficient.

[0111] Furthermore, before feature mapping, the selected data and feature data need to be normalized. The normalization formula can be expressed as follows:

[0112]

[0113] Among them, x' is the normalized data to be selected or feature data; max(x) is the maximum value of the data to be selected or feature data; min(x) is the minimum value of the data to be selected or feature data; x is the data to be selected or feature data.

[0114] Optionally, the construction of the optimization model includes steps C1-C2:

[0115] Step C1, determining historical power data, historical power generation cost data and historical operation data of the target power unit.

[0116] Specifically, historical power data, historical power generation cost data and historical operation data of the target power unit are retrieved from the historical database.

[0117] Step C2: embed the objective function and constraint conditions into the preset model, and train it through historical power data and historical power generation cost data, and use the prediction model whose training results meet the preset error as the optimization model.

[0118] The preset model can adopt genetic algorithm, particle swarm optimization algorithm, etc.

[0119] Specifically, the objective function and constraint conditions are embedded in the preset model, the optimal solution that the preset model needs to achieve is provided by the objective function, and the constraint conditions are used as conditions of the preset model to constrain the solution of the preset model.

[0120] Furthermore, historical power data, historical power generation cost data and historical operation data of the target power unit are used as inputs of the preset model, the preset model is trained, the obtained unit output is input into the objective function, calculation is performed, and it is determined whether the obtained unit output satisfies the requirement of minimizing the objective function. If so, the corresponding preset model is used as the optimization model; if not, the parameters of the preset model are optimized until the objective function is minimized.

[0121] Optionally, the objective function construction process includes steps D1-D2:

[0122] Step D1: Subtract the historical declared cost data and the historical resource consumption cost of the target power unit quotation period to obtain the cost difference.

[0123] Specifically, the historical declared price data and the historical resource consumption price of the target power unit quotation period are obtained, and the historical declared price data and the historical resource consumption price of the target power unit quotation period are subtracted to obtain the price difference.

[0124] Step D2: multiply the cost difference by the historical first load and the historical second load of the target power unit quotation period, and sum them to obtain the minimum value to obtain the objective function.

[0125] Among them, the historical first load is the maximum value of the historical load in the quotation period of the target power unit, that is, the rated capacity of the target power unit; the historical second load is the minimum value of the historical load in the quotation period of the target power unit.

[0126] Specifically, the cost difference is multiplied by the historical first load and the historical second load of the target power unit quotation segment to obtain product data, and the product data is summed to obtain sum data. Since the target power unit quotation segment is at least one segment, in order to meet the demand, the sum data is minimized to obtain the objective function.

[0127] Furthermore, the objective function can be expressed as follows:

[0128]

[0129] Where: Q max Indicates the first load of the target power unit, Q min represents the second load of the target power unit, P 申报,i Indicates that the target power unit output is Q i The declared value at the time, P代价,i Indicates that the target power unit output is Q i The cost.

[0130] Optionally, the constraints include: the length of the target power unit quotation segment is greater than or equal to the percentage of the difference between the maximum load and the minimum load of the unit; the declared price of each target quotation segment conforms to a monotonically increasing trend.

[0131] Furthermore, the target power unit quotation segment length is greater than or equal to the percentage of the difference between the maximum load and the minimum load of the unit:

[0132]

[0133] Among them, Q0 represents the starting load of the first quotation period of the target power unit, Q 10 Indicates the end load of the last bidding period of the target power unit, Q i represents the target power unit quotation section load, Q min Indicates the minimum load of the target power unit, Q max represents the maximum load of the target power unit; α is a parameter, and the value of α can be 1.

[0134] The declared price of each target quotation segment conforms to the monotonically increasing trend:

[0135]

[0136] Among them, P1 represents the first bidding segment value of the target power unit, P 10 represents the last bidding segment value of the target power unit, P i represents the target power unit quotation segment value, P max Indicates the upper limit of declared value.

[0137] Furthermore, the constraints include:

[0138] The starting load of each output segment of the target power unit quotation segment should be equal to the ending load of the previous quotation segment, and the starting load of the first quotation segment should be equal to the minimum load of the unit:

[0139] Q0=Q min ,

[0140] Q 10 =Q max .

[0141] The first quote segment has a quote equal to 0:

[0142] P1=0;

[0143] The last quotation segment's quotation is less than or equal to the declared value limit:

[0144] P10 ≤P max .

[0145] Optionally, the power generation strategy of the power generation enterprise is optimized according to the target optimization result, including steps E1-E2:

[0146] Step E1: adjusting the output load of the target power unit in the power generation enterprise according to the target optimization result.

[0147] Specifically, the output load of the target power unit in the power generation enterprise is adjusted according to the output load of the target power unit.

[0148] Step E2: adjusting the fuel combustion amount and carbon dioxide emission amount according to the output load.

[0149] Specifically, the fuel combustion amount and the carbon dioxide emission amount are adjusted according to the output load and the value of the output load of the target power unit.

[0150] The technical solution of this embodiment determines the target power data and resource consumption data. The determination of the target power data can clearly characterize the changes in the value of electric energy, and provide a basis for the optimization of subsequent power generation strategies; the target power generation cost data is determined according to the resource consumption data; the scheduling optimization is performed through the optimization model according to the target power data, the target power generation cost data and the target power unit operation data to obtain the target optimization result; the power generation strategy of the power generation enterprise is optimized according to the target optimization result. This method determines the target optimization result according to the target power data and the target power generation cost, and optimizes the power generation strategy according to the target optimization result, which can effectively help power generation enterprises to respond promptly to market fluctuations, and can minimize the power generation cost while adapting to the complexity and dynamics of the power market, thereby improving the power generation enterprise's ability to change.

[0151] Figure 2 The following is a schematic diagram of a structure of a dynamic scheme optimization device based on electricity price prediction provided by an embodiment of the present invention. This embodiment is applicable to the situation where power generation enterprises adjust their power generation strategies when the power market fluctuates. The dynamic scheme optimization device based on electricity price prediction can be implemented in the form of hardware and / or software. The dynamic scheme optimization device based on electricity price prediction can be configured in any electronic device with network communication function. Figure 2 As shown, the device includes: a data determination module 210, a target power generation cost data determination module 220, a target optimization result determination module 230 and an optimization module 240, wherein:

[0152] Data determination module 210: used to determine target power data and resource consumption data; the target power data is used to characterize the value of the electric energy generated by the power generation enterprise in the power market within a preset time period; the resource consumption data is used to characterize the resource consumption generated by the power generation enterprise when generating electricity;

[0153] The target power generation cost data determination module 220 is used to determine the target power generation cost data according to the resource consumption data; the target power generation cost data is used to characterize the value of the energy consumed by the power generation enterprise;

[0154] The target optimization result determination module 230 is used to perform scheduling optimization through the optimization model according to the target power data, the target power generation cost data and the target power unit operation data to obtain the target optimization result; the optimization model is configured with a constraint function and an objective function, the constraint function is used to constrain the output result of the optimization model, and the objective function provides an optimization target for the optimization model;

[0155] Optimization module 240: used to optimize the power generation strategy of the power generation enterprise through the target optimization result.

[0156] Optionally, the data determination module 210 includes:

[0157] Power load data determination unit: used to determine power load data; power load data is used to characterize the amount of electric energy provided by power generation enterprises to power users;

[0158] Target power data determination unit: used to match the target model according to the power load data and the predicted demand, and determine the target power data according to the target model; the predicted demand includes: a first preset time value demand and a second preset time value demand, the second preset time is greater than the second preset time; the target model is used to characterize the relationship between the power load data and the target power data.

[0159] Optionally, the power load data determination unit comprises:

[0160] Market disclosure data determination unit: used to determine market disclosure data; market disclosure data is the electric energy production of each power generation enterprise obtained from the power market;

[0161] Unit for determining data to be selected: used for cleaning and completing the market disclosed data to obtain the data to be selected;

[0162] Characteristic data determination unit: used to determine characteristic data according to the data to be selected; the characteristic data at least includes: fire bidding space;

[0163] The power load data determination unit is used to determine the power load data according to the correlation between the data to be selected and the characteristic data.

[0164] Optionally, the target optimization result determination module 230 includes:

[0165] Historical data determination unit: used to determine historical power data, historical power generation cost data and historical operation data of target power units;

[0166] Optimization model determination unit: used to embed the objective function and constraints into the preset model, and train it through historical power data and historical power generation cost data, and use the prediction model whose training results meet the preset error as the optimization model.

[0167] Optionally, the optimization model determination unit includes:

[0168] The cost difference determination subunit is used to make a difference between the historical declared cost data and the historical resource consumption cost of the target power unit quotation segment to obtain the cost difference;

[0169] Objective function determination subunit: used to multiply the cost difference by the historical first load and the historical second load of the target power unit quotation segment, and sum and take the minimum value to obtain the objective function.

[0170] Optionally, the optimization model determination unit includes constraints, wherein:

[0171] The constraints include: the length of the target power unit quotation segment is greater than or equal to the percentage of the difference between the maximum load and the minimum load of the unit; the declared price of each target quotation segment conforms to a monotonically increasing trend.

[0172] Optionally, the optimization module 240 includes:

[0173] Output load determination unit: used to adjust the output load of the target power unit in the power generation enterprise according to the target optimization result;

[0174] Adjustment unit: used to adjust the fuel combustion amount and carbon dioxide emission according to the output load.

[0175] The dynamic scheme optimization device based on electricity price prediction provided in the embodiments of the present invention can execute the dynamic scheme optimization method based on electricity price prediction provided in any of the above embodiments of the present invention, and has the corresponding functions and beneficial effects of executing the dynamic scheme optimization method based on electricity price prediction. For detailed process, please refer to the relevant operations of the dynamic scheme optimization method based on electricity price prediction in the above embodiments.

[0176] Figure 3A schematic diagram of the structure of an electronic device for implementing a dynamic scheme optimization method based on electricity price forecasting according to an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0177] like Figure 3 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0178] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0179] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a dynamic scheme optimization method based on electricity price prediction.

[0180] In some embodiments, the dynamic scheme optimization method based on electricity price prediction can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the dynamic scheme optimization method based on electricity price prediction described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the dynamic scheme optimization method based on electricity price prediction in any other appropriate manner (for example, by means of firmware).

[0181] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0182] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0183] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0184] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0185] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0186] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0187] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0188] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A dynamic scheme optimization method based on electricity price forecasting, characterized in that: include: Determine target power data and resource consumption data; The target power data is used to characterize the value of the electric energy generated by the power generation enterprise in the power market within a preset time period; The resource consumption data is used to characterize the resource consumption generated by the power generation enterprise when generating electricity; Determine target power generation cost data according to the resource consumption data; the target power generation cost data is used to characterize the value of energy consumed by the power generation enterprise; According to the target power data, the target power generation cost data and the target power unit operation data, the scheduling optimization is performed through the optimization model to obtain the target optimization result; the optimization model is configured with a constraint function and an objective function, the constraint function is used to constrain the output result of the optimization model, and the objective function provides an optimization target for the optimization model; The power generation strategy of the power generation enterprise is optimized through the target optimization result.

2. The method according to claim 1, characterized in that: Determine target power data, including: Determine power load data; the power load data is used to characterize the amount of electric energy provided by the power generation enterprise to the power user; A target model is matched according to the power load data and the predicted demand, and the target power data is determined according to the target model; the predicted demand includes: a first preset time value demand and a second preset time value demand, and the second preset time is greater than the second preset time; the target model is used to characterize the relationship between the power load data and the target power data.

3. The method according to claim 2, characterized in that The determining of the power load data comprises: Determine market disclosure data; the market disclosure data is the electric energy production of each power generation enterprise obtained from the power market; Cleaning and completing the market disclosed data to obtain data to be selected; Determine characteristic data according to the data to be selected; the characteristic data at least includes: a fire bidding space; The power load data is determined according to the correlation between the data to be selected and the characteristic data.

4. The method according to claim 1, characterized in that: The construction of the optimization model includes: Determine historical power data, historical power generation cost data and historical operation data of target power units; The objective function and constraint conditions are embedded into a preset model, and training is performed using the historical power data and the historical power generation cost data, and a prediction model whose training results satisfy a preset error is used as an optimization model.

5. The method according to claim 4, characterized in that The process of constructing the objective function includes: Subtract the historical declared price data and historical resource consumption price of the target power unit quotation period to obtain the price difference; The cost difference is multiplied by the historical first load and the historical second load of the target power unit quotation period, and the sum is taken to obtain the minimum value to obtain the objective function.

6. The method according to claim 4, characterized in that The constraints include: the length of the target power unit quotation segment is greater than or equal to the percentage of the difference between the maximum load and the minimum load of the unit; the declared price of each target quotation segment conforms to a monotonically increasing trend.

7. The method according to claim 1, characterized in that Optimizing the power generation strategy of the power generation enterprise by using the target optimization result includes: Adjust the output load of the target power units within the power generation enterprise according to the target optimization results; The amount of fuel burned and the amount of carbon dioxide emitted are adjusted according to the output load.

8. A dynamic scheme optimization device based on electricity price prediction, characterized in that: include: A data determination module, used to determine target power data and resource consumption data; The target power data is used to characterize the value of the electric energy generated by the power generation enterprise in the power market within a preset time period; the resource consumption data is used to characterize the resource consumption generated by the power generation enterprise when generating electricity; A target power generation cost data determination module is used to determine target power generation cost data according to the resource consumption data; the target power generation cost data is used to characterize the value of energy consumed by the power generation enterprise; a target optimization result determination module, used to perform scheduling optimization through an optimization model according to the target power data, the target power generation cost data and the target power unit operation data, and obtain a target optimization result; the optimization model is configured with a constraint function and an objective function, the constraint function is used to constrain the output result of the optimization model, and the objective function provides an optimization target for the optimization model; The optimization module is used to optimize the power generation strategy of the power generation enterprise through the target optimization result.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the dynamic scheme optimization method based on electricity price prediction as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the dynamic scheme optimization method based on electricity price prediction according to any one of claims 1 to 7 when executed.

Images