Electricity market settlement method, system, equipment and medium based on high hydropower share

Abstract

The present invention discloses a method, system, equipment and medium for electricity market settlement based on a high proportion of hydropower, the method comprising: collecting hydrological information data of a preset area within a preset time; preprocessing the collected hydrological information data to obtain preprocessed data; inputting the preprocessed data into a trained random forest model to obtain a predicted value of water inflow in a future time period; calculating the degree of deviation between the predicted value and the actual value of water inflow, and setting a dynamic adjustment factor according to the degree of deviation; adjusting the capacity replenishment of hydropower installed capacity and the transaction price, transaction volume and market settlement of the electricity market according to the dynamic adjustment factor. By setting the dynamic adjustment factor to adjust the rules and mechanisms of hydropower installed capacity replenishment and electricity market transaction price, the ability to respond to changes in water inflow is effectively improved, and the rationality and stability of hydropower resource utilization and electricity market transactions are optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of electricity market settlement, and in particular to an electricity market settlement method, system, equipment and medium based on a high proportion of hydropower. Background Art

[0002] In the settlement of the electricity spot market with a high proportion of hydropower, the high proportion of hydropower installed capacity, the difficulty in predicting water inflow, and the large difference in power generation between wet and dry seasons directly affect the stability of power market transactions. Among them, the high proportion of hydropower installed capacity makes the power supply heavily dependent on hydropower, and the stability of the market and the balance of power supply are easily affected by the fluctuation of hydropower output. The difficulty in predicting water inflow makes it impossible for power generation companies to accurately estimate the power generation and for power users to accurately estimate the cost of electricity, making it difficult to determine the quotation and trading strategy in the market. The large difference in power generation between wet and dry seasons is reflected in two aspects. First, a large amount of hydropower flows into the market during the wet season, and there may even be a phenomenon of power abandonment, which damages the profits of power generation companies. Second, power generation drops sharply during the dry season, power is tight, and other energy sources such as thermal power bring cost changes. The huge gap between different periods makes it difficult for settlement prices to balance the interests of all parties in fluctuations. Summary of the invention

[0003] The purpose of the present invention is to provide a method, system, equipment and medium for electricity market settlement based on a high proportion of hydropower, so as to solve the problem of large fluctuations in settlement prices in the electricity market with a high proportion of hydropower.

[0004] The present invention is achieved through the following technical solutions:

[0005] In a first aspect, an embodiment of the present invention provides a method for electricity market settlement based on a high proportion of hydropower, including:

[0006] Collect hydrological information data of the preset area within the preset time;

[0007] Preprocessing the collected hydrological information data to obtain preprocessed data;

[0008] The preprocessed data is input into the trained random forest model to obtain the predicted value of water inflow in the future time period;

[0009] Calculating the degree of deviation between the predicted value and the actual value of the incoming water, and setting a dynamic adjustment factor according to the degree of deviation;

[0010] The capacity replenishment of the hydropower installed capacity and the transaction price, transaction volume and market settlement of the electricity market are adjusted respectively according to the dynamic adjustment factor.

[0011] In a second aspect, an embodiment of the present invention provides a method for electricity market settlement based on a high proportion of hydropower, including: a data acquisition module, a preprocessing module, a prediction module, an adjustment factor setting module and a dynamic adjustment module, wherein the data acquisition module is used to collect hydrological information data of a preset area within a preset time;

[0012] The preprocessing module is used to preprocess the collected hydrological information data to obtain preprocessed data;

[0013] The prediction module is used to input the preprocessed data into the trained random forest model to obtain the predicted value of water inflow in the future time period;

[0014] The adjustment factor setting module is used to calculate the degree of deviation between the predicted value and the actual value of the incoming water, and set the dynamic adjustment factor according to the degree of deviation;

[0015] The dynamic adjustment module is used to adjust the capacity replenishment of the hydropower installed capacity and the transaction price, transaction volume and market settlement of the electricity market according to the dynamic adjustment factor.

[0016] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a processor, an input device, an output device and a memory, wherein the processor is connected to the input device, the output device and the memory, respectively, the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method described in the above embodiment.

[0017] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the method described in the above embodiment.

[0018] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0019] The embodiments of the present invention provide a method, system, device and medium for electricity market settlement based on a high proportion of hydropower. The method collects and pre-processes hydrological information data in a preset area within a preset time, inputs the data into a trained random forest model to predict future water inflow conditions, and sets a dynamic adjustment factor based on the degree of deviation between the calculated predicted value and the actual value. The hydropower installed capacity replenishment and electricity market transaction price rule mechanism are adjusted based on the factor, thereby effectively improving the ability to respond to changes in water inflow and optimizing the rationality and stability of hydropower resource utilization and electricity market transactions. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings:

[0021] Figure 1 A flow chart of a method for electricity market settlement based on a high proportion of hydropower provided by the first embodiment of the present invention;

[0022] Figure 2 is a specific flow chart of step S3;

[0023] Figure 3 is a specific flow chart of step S32;

[0024] Figure 4 is a specific flow chart of step S4;

[0025] Figure 5 is a specific flow chart of step S5;

[0026] Figure 6 A structural block diagram of a power market settlement system based on a high hydropower ratio provided by another embodiment of the present invention;

[0027] Figure 7 A structural block diagram of an electronic device provided in another embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0029] Example 1

[0030] like Figure 1 As shown, a first embodiment of the present invention provides a method for electricity market settlement based on a high proportion of hydropower, comprising the following steps:

[0031] S1. Collect hydrological information data of the preset area within the preset time.

[0032] In this embodiment, the time and location range of collection are determined according to needs, and the monitoring data of each hydrological monitoring station in the area is obtained from the local hydrological monitoring system, including river water level, flow, rainfall, evaporation, etc.; meteorological data of the area is collected, including temperature, humidity, wind direction, wind speed and other meteorological data; satellite remote sensing technology can also be used to obtain a wide range of hydrological information, such as surface water area, soil moisture, etc.

[0033] S2: Preprocess the collected hydrological information data to obtain preprocessed data.

[0034] The acquired data is preprocessed to obtain preprocessed data, and the preprocessing includes: identifying and processing outliers in the data, processing missing values ​​in the data, adjusting the mean and standard deviation of the data to specific values, and mapping the data values ​​to a specific interval.

[0035] S3. Input the preprocessed data into the trained random forest model to obtain the predicted value of water inflow in the future.

[0036] like Figure 2 As shown, step S3 specifically includes the following steps:

[0037] S31. Obtain historical hydrological information data related to water supply conditions in a preset area, and preprocess the acquired historical hydrological information data to obtain preprocessed historical data.

[0038] First, collect historical hydrological information data related to the water supply situation in the area as the input features of the model, such as rainfall, river water level, evaporation, temperature, soil moisture, etc. in the past years. Preprocess the collected data, including data cleaning, and remove outliers and missing values. For missing values, methods such as mean filling and interpolation can be used to process them. Standardize or normalize the data to make the numerical ranges of different features comparable and avoid certain features from having too much impact on model training.

[0039] S32. Filter target feature data based on the preprocessed historical data.

[0040] like Figure 3 As shown, step S32 specifically includes the following steps:

[0041] S321. Initializing the preprocessed hydrological information data, the initialized feature set includes all hydrological features;

[0042] S322. Use the feature data and target variables corresponding to the current feature set to train the random forest model, perform iterative calculations, and calculate the importance score of each feature in the current feature set according to the random forest model;

[0043] S323. Eliminate the least important features from the current feature set according to the importance score to obtain an updated feature set;

[0044] S324. When the iteration stop condition is met, the final feature set is selected as the target feature data.

[0045] Specifically, we collect and organize hydrological data containing multiple features. Let the data set be D, which contains m samples and n features, denoted by X = (x1, x2, ..., x n ), the corresponding target variable is y.

[0046] The initial feature set is set to S0, which is usually initialized to all features, that is, S0 = {1, 2, ..., n}, indicating that all n features are included.

[0047] Enter the iterative process, for the lth iteration (k-1,2,...), use the current data set S k-1 Corresponding feature data and the target variable y to train a random forest model. For example, if S k-1 ={1,3,5}, then Indicates that the feature data in the 1st, 3rd, and 5th columns of the data set are selected as input to train the random forest model. After the training is completed, the importance score of each feature in the current feature set is calculated according to the random forest model. The importance score of the feature is j The calculation formula is as follows:

[0048]

[0049] Where: I j is the importance score of feature j, N is the number of decision trees in the random forest, is the importance contribution of feature j to node t in the decision tree, and ΔG(t,j) is the change in impurity before and after.

[0050] According to the feature importance scores obtained above, determine the least important feature j in the current feature set min . From the current feature set S k-1 Remove the least important feature j min , get the updated feature set S k =S k-1 -{j min}.

[0051] Reaching the preset number of features: When |S k |=p (p is the preset number of features to be retained in the end) and the iteration is stopped, and the calculation uses the current feature set S kThe performance index of the trained model in the validation set or cross-validation. If the change of the performance index in multiple consecutive iterations is less than a certain threshold, it is considered that the model performance is no longer significantly improved, and the iteration is stopped. The iteration process ends, and the final feature set selected is S k .

[0052] S33. Divide the target feature data into a training set and a test set, use the training set to train the random forest model to obtain a trained model, and adjust the parameters of the random forest model.

[0053] S34. Use the test set to evaluate the trained random forest model to obtain the evaluation result. If the evaluation result meets the requirements, the trained random forest model is obtained.

[0054] The data set after preprocessing and feature selection is divided into a training set and a test set, generally in a ratio of 7:3 or 8:2. The training set data is used to train the random forest model, and the parameters of the random forest model are adjusted, including the number of decision trees, the maximum depth of each decision tree, the minimum number of samples required for node splitting, etc., to optimize the performance of the model. The trained model is evaluated using the test set data. If the model evaluation results meet the requirements, the model can be used to predict the water supply situation in a certain place in the future.

[0055] S4. Calculate the degree of deviation between the predicted value and the actual value of the incoming water, and set a dynamic adjustment factor based on the degree of deviation.

[0056] like Figure 4 As shown, the specific method of step S4 is as follows:

[0057] S41. Calculate the degree of deviation between the predicted value and the actual value of water inflow according to different time scales;

[0058] In this embodiment, different time scales include hourly scale, daily scale and monthly scale, and the formula for calculating the degree of deviation is as follows:

[0059]

[0060] Where: Q p (i) is the water inflow forecast value at the i-th time point or time period, Q a (i) is the corresponding actual value, and n is the number of data points.

[0061] The deviation values ​​calculated at each time point or time period are arranged in chronological order to form a deviation data set, which will be used for subsequent analysis and setting of adjustment factors.

[0062] S42. Divide the intervals into different intervals based on the degree of deviation, and set a corresponding dynamic adjustment factor for each deviation interval.

[0063] According to historical data and actual conditions, the deviation value is divided into different intervals. For example, for hourly scale deviation, it can be divided into intervals such as (-∞,-20], (-20,-10], (-10,0], (0,10], (10,20], (20,+∞) (the values ​​here are only examples). Set a corresponding dynamic adjustment factor for each deviation interval. Generally speaking, the larger the deviation, the larger the absolute value of the adjustment factor. For example, when the deviation is in the interval (-∞,-20], the adjustment factor is set to -0.3; in the interval (20,+∞), the adjustment factor is set to 0.3; in the interval (-10,10], the adjustment factor is set to plus or minus 0.1 (the positive or negative sign is determined by the positive or negative deviation). If the trading rules have upper and lower limits for price fluctuations and electricity adjustments, the setting of the adjustment factor must ensure that the adjusted result is within the specified range. If the water inflow data shows seasonal or cyclical patterns, these factors can be considered when setting the adjustment factor.

[0064] S5. The capacity replenishment of hydropower installed capacity and the trading price rules and mechanisms of the electricity market are adjusted separately according to the dynamic adjustment factors. The trading price rules and mechanisms include: trading price, trading volume and market settlement.

[0065] like Figure 5 As shown, step S5 specifically includes the following steps:

[0066] S51. Determine the linear and nonlinear relationship between the capacity replenishment of hydropower installed capacity and the dynamic adjustment factor.

[0067] S52. When the dynamic adjustment factor is negative, the capacity of the hydropower installed capacity is reduced, and when the dynamic adjustment factor is positive, the capacity of the hydropower installed capacity is increased.

[0068] Assuming that the hydropower installed capacity replenishment C adj It is linearly related to the dynamic adjustment factor f, and the formula C can be established adj =C0(1+kf), where C0 is the initial hydropower installed capacity and k is the proportionality coefficient.

[0069] When the deviation is large, a more complex relationship may be needed to reflect the change in adjustment strength. adj =C0(1+af+bf 2 ), where a and b are coefficients determined based on actual conditions. When the dynamic adjustment factor is larger, the adjustment range of capacity replenishment will be larger.

[0070] When the predicted water inflow is lower than the actual water inflow, it means that the water resources available for hydropower are reduced. At this time, if the dynamic adjustment factor is negative, the hydropower installed capacity replenishment should be appropriately reduced to avoid the problem of tight power supply caused by over-reliance on hydropower generation. If the predicted water inflow is higher than the actual water inflow, more water resources may be available for power generation. At this time, a positive dynamic adjustment factor can increase the hydropower installed capacity replenishment and make full use of water resources for power generation. The actual carrying capacity of hydropower equipment and the absorption capacity of the power grid should also be considered to avoid equipment damage or power grid operation problems caused by excessive power generation. For run-of-river hydropower plants, their power generation capacity mainly depends on the real-time water flow, and the adjustment range of capacity replenishment can be relatively small; for hydropower plants with a certain reservoir regulation capacity, the capacity replenishment can be adjusted more flexibly based on the reservoir's water storage capacity, regulation performance and other factors, combined with the dynamic adjustment factor. When adjusting the hydropower installed capacity replenishment, ensure that the reservoir water level is within a safe range. If increasing the capacity of water replenishment may cause the reservoir water level to be too high, adjustments will need to be made with caution, and it may even be necessary to reduce the capacity of water replenishment. At the same time, coordination with other water demands such as flood control and irrigation must be considered.

[0071] S53. Adjust the transaction price, transaction volume and market settlement of the electricity market according to the dynamic adjustment factor.

[0072] The transaction price, transaction volume and market settlement based on the dynamic adjustment factor are adjusted according to different deviation ranges and different transaction types. For example, the transaction price can modify the electricity price calculation method of the electricity spot market according to the dynamic adjustment factor. If the water inflow forecast deviation is positive and in the medium deviation range, the electricity price of the hydropower enterprise can be multiplied by a dynamic adjustment factor slightly less than 1 to appropriately reduce the electricity price; if it is in a large deviation range, it can be multiplied by a smaller dynamic adjustment factor to reduce the electricity price more significantly. For different types of transactions (such as day-ahead transactions, real-time transactions, medium- and long-term contract transactions, etc.), dynamic adjustment factors are applied to adjust prices according to the correlation with water inflow and sensitivity to market prices. For example, real-time transaction prices may be more sensitive to water inflow deviations, and the adjustment range is relatively large, while medium- and long-term contract transaction prices can be moderately adjusted according to contractual agreements and the long-term trend of water inflow deviations.

[0073] The embodiment of the present invention provides a method for electricity market settlement based on a high proportion of hydropower. The method collects and preprocesses hydrological information data in a preset area within a preset time, inputs the data into a trained random forest model to predict future water inflow conditions, and sets a dynamic adjustment factor according to the degree of deviation between the calculated predicted value and the actual value. The hydropower installed capacity replenishment and electricity market transaction price rule mechanism are adjusted based on this factor, thereby effectively improving the ability to respond to changes in water inflow and optimizing the rationality and stability of hydropower resource utilization and electricity market transactions.

[0074] Embodiment 2

[0075] like Figure 6 As shown, another embodiment of the present invention provides an electricity market settlement system based on a high proportion of hydropower, including: a data acquisition module, a preprocessing module, a prediction module, an adjustment factor setting module and a dynamic adjustment module, the data acquisition module is used to collect hydrological information data of a preset area within a preset time, the preprocessing module is used to preprocess the collected hydrological information data to obtain preprocessed data, the prediction module is used to input the preprocessed data into a trained random forest model to obtain a predicted value of water inflow in a future period of time, the adjustment factor setting module is used to calculate the degree of deviation between the predicted value and the actual value of water inflow, and set a dynamic adjustment factor according to the degree of deviation, and the dynamic adjustment module is used to adjust the capacity replenishment of hydropower installed capacity and the transaction price, transaction volume and market settlement of the electricity market according to the dynamic adjustment factor.

[0076] The prediction module includes a model training unit, which obtains historical hydrological information data of water inflow conditions in a preset area, preprocesses the historical hydrological information data to obtain preprocessed historical data, screens target feature data from the preprocessed historical data, divides the target feature data into a training set and a test set, uses the training set to train a random forest model, and adjusts the parameters of the random forest model; uses the test set to evaluate the trained random forest model to obtain an evaluation result, and when the evaluation result meets the requirements, a trained random forest model is obtained.

[0077] The model training unit includes a target feature screening subunit, which screens target feature data from preprocessed historical data, specifically including: initializing the preprocessed historical hydrological information data, the initialized feature set contains all hydrological features, using the feature data and target variables corresponding to the current feature set to train the random forest model, performing iterative calculations, and calculating the importance score of each feature in the current feature set according to the random forest model, removing the feature with the lowest importance score from the current feature set, and obtaining an updated feature set. When the iteration stop condition is met, the iteration process is terminated, and the final feature set is screened as the target feature data.

[0078] The adjustment factor setting module includes a deviation calculation unit and a setting unit. The deviation calculation unit calculates the degree of deviation between the predicted value and the actual value of the incoming water according to different time scales; the setting unit divides different intervals based on the degree of deviation and sets a corresponding dynamic adjustment factor for each deviation interval.

[0079] The dynamic adjustment module includes a relationship determination unit and an adjustment unit. The relationship determination unit is used to determine the linear relationship and nonlinear relationship between the capacity replenishment of the hydropower installed capacity and the dynamic adjustment factor; the adjustment unit is used to reduce the capacity replenishment of the hydropower installed capacity when the dynamic adjustment factor is negative, and increase the capacity replenishment of the hydropower installed capacity when the dynamic adjustment factor is positive, and adjust the transaction price, transaction volume and market settlement of the electricity market according to the dynamic adjustment factor.

[0080] For the specific definition of the system, please refer to the definition of the method above, which will not be repeated here. Each module in the above system can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0081] An embodiment of the present invention provides an electricity market settlement system based on a high proportion of hydropower. The system collects and preprocesses hydrological information data in a preset area within a preset time, inputs the data into a trained random forest model to predict future water inflow conditions, and sets a dynamic adjustment factor based on the degree of deviation between the calculated predicted value and the actual value. Based on this factor, the hydropower installed capacity replenishment and electricity market transaction price rule mechanism are adjusted, thereby effectively improving the ability to respond to changes in water inflow and optimizing the rationality and stability of hydropower resource utilization and electricity market transactions.

[0082] Example 3

[0083] like Figure 7 1 shows a structural block diagram of an electronic device according to another embodiment of the present invention, the device includes a processor, an input device, an output device and a memory, the processor is connected to the input device, the output device and the memory respectively, the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method described in the first embodiment above.

[0084] It should be understood that in the embodiments of the present invention, the processor referred to may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0085] Input devices may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and output devices may include a display (LCD, etc.), a speaker, etc.

[0086] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0087] In a specific implementation, the processor, input device, and output device described in the embodiments of the present invention may execute the implementation described in the method embodiment provided in the embodiments of the present invention, or may execute the implementation described in the system embodiment described in the embodiments of the present invention, which will not be described in detail here.

[0088] Example 4

[0089] Another embodiment of the present invention further provides an embodiment of a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the method described in the first embodiment.

[0090] The computer-readable storage medium may be an internal storage unit of the terminal described in the foregoing embodiments, such as a hard disk or memory of the terminal. The computer-readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Further, the computer-readable storage medium may also include both an internal storage unit of the terminal and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by the terminal. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0091] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0092] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the terminals and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0093] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.

[0094] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for electricity market settlement based on high hydropower share, characterized in that: include: Collect hydrological information data of the preset area within the preset time; Preprocessing the collected hydrological information data to obtain preprocessed data; The preprocessed data is input into the trained random forest model to obtain the predicted value of water inflow in the future time period; Calculating the degree of deviation between the predicted value and the actual value of the incoming water, and setting a dynamic adjustment factor according to the degree of deviation; The capacity replenishment of the hydropower installed capacity and the transaction price, transaction volume and market settlement of the electricity market are adjusted respectively according to the dynamic adjustment factor.

2. The method according to claim 1, characterized in that: Also includes: The random forest model is trained by: Obtaining historical hydrological information data of water supply conditions in a preset area, and preprocessing the historical hydrological information data to obtain preprocessed historical data; Filter target feature data from preprocessed historical data; Dividing the target feature data into a training set and a test set, using the training set to train the random forest model, and adjusting the parameters of the random forest model; Use the test set to evaluate the trained random forest model to obtain the evaluation results. If the evaluation results meet the requirements, the trained random forest model is obtained.

3. The method according to claim 2, characterized in that The specific method of screening target feature data from pre-processed historical data includes: Initialize the preprocessed historical hydrological information data, and the initialized feature set contains all the hydrological features; Use the feature data and target variables corresponding to the current feature set to train the random forest model, perform iterative calculations, and calculate the importance score of each feature in the current feature set based on the random forest model; Remove the feature with the lowest importance score from the current feature set to obtain an updated feature set; When the iteration stop condition is met, the iteration process ends and the final feature set is selected as the target feature data.

4. The method according to claim 3, characterized in that: The calculation formula for calculating the importance score of each feature in the current feature set according to the random forest model is: Where: I j is the importance score of feature j, N is the number of decision trees in the random forest, is the importance contribution of feature j to node t in the decision tree, and ΔG(t,j) is the change in impurity before and after.

5. The method according to claim 1, characterized in that The specific method of calculating the deviation degree between the predicted value and the actual value of the incoming water, and setting the dynamic adjustment factor according to the deviation degree includes: Calculate the degree of deviation between the predicted value and the actual value of water inflow according to different time scales; Different intervals are divided based on the degree of deviation, and a corresponding dynamic adjustment factor is set for each deviation interval.

6. The method according to claim 5, characterized in that The different time scales include hourly scale, daily scale and monthly scale. The calculation formula for calculating the deviation between the predicted value and the actual value of water inflow according to different time scales is: Where: Q p (i) is the water inflow forecast value at the i-th time point or time period, Q a (i) is the corresponding actual value, and n is the number of data points.

7. The method according to claim 1, characterized in that The specific method of adjusting the capacity replenishment of hydropower installed capacity and the transaction price, transaction volume and market settlement of the power market according to the dynamic adjustment factor includes: Determine the linear and nonlinear relationship between the capacity replenishment and dynamic adjustment factor of hydropower installed capacity; When the dynamic adjustment factor is negative, the capacity replenishment of hydropower installed capacity is reduced, and when the dynamic adjustment factor is positive, the capacity replenishment of hydropower installed capacity is increased; Adjust the transaction price, transaction volume and market settlement of the electricity market according to the dynamic adjustment factors.

8. A power market settlement system based on a high proportion of hydropower, characterized in that: include: A data acquisition module, a preprocessing module, a prediction module, an adjustment factor setting module and a dynamic adjustment module, wherein the data acquisition module is used to collect hydrological information data of a preset area within a preset time; The preprocessing module is used to preprocess the collected hydrological information data to obtain preprocessed data; The prediction module is used to input the preprocessed data into the trained random forest model to obtain the predicted value of water inflow in the future time period; The adjustment factor setting module is used to calculate the degree of deviation between the predicted value and the actual value of the incoming water, and set the dynamic adjustment factor according to the degree of deviation; The dynamic adjustment module is used to adjust the capacity replenishment of the hydropower installed capacity and the transaction price, transaction volume and market settlement of the electricity market according to the dynamic adjustment factor.

9. An electronic device, characterized in that: The method comprises a processor, an input device, an output device and a memory, wherein the processor is connected to the input device, the output device and the memory respectively, the memory is used to store a computer program, and the computer program comprises program instructions. The method is characterized in that the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 7.

Images