Peak shaving method and system based on capacity increasing and power generation of hydroelectric generating set, electronic equipment and storage medium

Abstract

The invention belongs to the technical field of power grid peak regulation, and discloses a peak regulation method and system based on capacity increasing and power generation of a hydroelectric generating set, electronic equipment and a storage medium. The method comprises the following steps: acquiring historical load data and real-time load information of a power grid, and performing rolling prediction on the power demand of a future preset time period by adopting a time sequence prediction algorithm to obtain a prediction result of the peak regulation demand of the power grid; obtaining water inflow prediction data of the hydropower station, and establishing a collaborative optimization scheduling model of the hydropower station, the pumped storage power station and the thermal power generating unit in combination with a power grid peak regulation demand prediction result; and based on the collaborative optimization scheduling model and a power grid peak regulation demand prediction result, completing peak regulation based on capacity increasing and generation increasing of the hydroelectric generating set. According to the peak regulation based on capacity increasing and generation increasing of the hydroelectric generating set, the defects in the prior art are effectively overcome through the measures of improving the prediction accuracy, optimizing the scheduling strategy, enhancing the flexibility and the like, and a new solution is provided for peak regulation of a power system.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid peak shaving, and particularly relates to a peak shaving method, system, electronic device and storage medium based on capacity increase and power generation increase of hydropower units. Background Technique

[0002] With the transformation of the energy structure and the reform of the power market, the power system's demand for peak shaving capacity is increasing day by day. At the same time, the proportion of clean energy (such as hydropower, wind power, photovoltaic, etc.) in the power system is gradually increasing, but its power generation has intermittency and uncertainty, bringing new challenges to the power system peak shaving. Therefore, it is of great significance to study the peak shaving method based on capacity increase and power generation increase of hydropower units.

[0003] In the current power system peak shaving technology, there are the following defects: insufficient prediction accuracy: traditional power demand prediction methods may not be able to accurately capture the short-term fluctuations and long-term trends of the load, resulting in inaccurate prediction results and affecting the formulation of peak shaving strategies. Single scheduling model: Some scheduling models only consider a single type of power source or simply combine multiple power sources, lacking the consideration of collaborative optimization between different types of power sources, resulting in poor peak shaving effects. Lack of flexibility: In the face of sudden load changes or the uncertainty of new energy power generation, the existing peak shaving methods may lack sufficient flexibility and cannot adjust the scheduling plan in time to meet the challenges. Summary of the Invention

[0004] The present invention provides a peak shaving method, system, electronic device and storage medium based on capacity increase and power generation increase of hydropower units, and effectively solves the defects in the prior art through measures such as improving prediction accuracy, optimizing scheduling strategies and enhancing flexibility, providing a new solution for the peak shaving of the power system.

[0005] A peak shaving method based on capacity increase and power generation increase of hydropower units, the method includes:

[0006] Obtain the historical load data and real-time load information of the power grid, and use the time series prediction algorithm to perform rolling prediction on the power demand in a preset future period to obtain the prediction result of the power grid peak shaving demand;

[0007] Based on the pre-obtained historical water inflow data and meteorological prediction data of the hydropower station, use the weighted sum of the prediction results of the AM-LSTM model and the CatBoost model to obtain the predicted water inflow data of the hydropower station;

[0008] Based on the predicted water inflow data of the hydropower station combined with the predicted power grid peak shaving demand result, use the mixed integer programming model to establish a collaborative optimization scheduling model of the hydropower station, pumped storage power station and thermal power unit;

[0009] Based on the collaborative optimization scheduling model and the prediction results of the power grid peak shaving demand, an improved particle swarm optimization algorithm is used to solve the collaborative optimization scheduling model, and the optimized output scheduling plans of hydropower stations, pumped-storage power stations and thermal power units in each period are obtained, thus completing the peak shaving based on the capacity increase and power generation increase of hydropower units.

[0010] Preferably, the method for obtaining the prediction results of the power grid peak shaving demand includes:

[0011] Perform outlier processing and missing value filling on the obtained historical power grid load data and real-time load information;

[0012] Use the Prophet model to perform time series analysis on the processed historical power grid load data and establish a load prediction model;

[0013] Input the processed real-time load information into the load prediction model to predict the power demand in a preset future period and obtain the short-term load prediction results;

[0014] Based on the short-term load prediction results, use a sliding window method to perform rolling updates on the preset period to obtain medium and long-term load prediction results;

[0015] Based on the weighted average method, fuse the short-term load prediction results and the medium and long-term load prediction results to obtain the final load prediction results;

[0016] Based on the final load prediction results, analyze the load peaks and valleys of the power grid at different times, and combine the power grid regulation capabilities to obtain the prediction results of the power grid peak shaving demand.

[0017] Preferably, the method for obtaining the predicted data of the incoming water volume of the hydropower station includes:

[0018] Preprocess the obtained historical incoming water volume data and meteorological prediction data of the hydropower station;

[0019] Input the preprocessed historical incoming water volume data and meteorological prediction data of the hydropower station into the AM-LSTM model and the CatBoost model respectively to obtain the first predicted value and the second predicted value respectively;

[0020] Establish the weight coefficients of each predicted value, and based on the weight coefficients, perform weighted summation of the first predicted value and the second predicted value to obtain a reconstruction result as the predicted data of the incoming water volume of the hydropower station.

[0021] Preferably, the construction method of the collaborative optimization scheduling model includes:

[0022] Based on the predicted data of the incoming water volume of the hydropower station and the prediction results of the power grid peak shaving demand, use a mixed integer programming model to establish a collaborative optimization scheduling model for multiple types of power stations including hydropower stations, pumped-storage power stations and thermal power units;

[0023] Among them, the decision variables of the collaborative optimal scheduling model for multi-type power stations include the power generation of hydropower stations, the power generation and water pumping volume of pumped-storage power stations, the power generation of thermal power units, and the start-stop status of the units;

[0024] The constraint conditions include power balance constraints, unit output constraints, water inflow constraints of hydropower stations, capacity constraints of pumped-storage power stations, and operation constraints of thermal power units;

[0025] The objective functions include minimizing the power generation cost, maximizing the environmental benefits, minimizing the minimum technical output of thermal power, minimizing the installed capacity demand for power supply guarantee of thermal power, and maximizing the consumption of new energy in the power grid.

[0026] Preferably, the method for obtaining the peak shaving result includes:

[0027] Based on the collaborative optimal scheduling model, judge whether the predicted water inflow data of the hydropower station meets the predicted peak shaving demand of the power grid. If not, obtain the geographical conditions and capacity parameters of the pumped-storage power station, and establish an optimal pumping strategy;

[0028] Obtain the efficiency curves and wear characteristics of hydropower units and pumped-storage units, and establish the mapping relationship between unit status and energy consumption and service life through the support vector machine algorithm; based on the collaborative optimal scheduling model and the mapping relationship, obtain the unit output adjustment strategy based on the capacity increase and power increase of hydropower units;

[0029] Based on the optimal pumping strategy and the unit output adjustment strategy, complete the peak shaving based on the capacity increase and power increase of hydropower units.

[0030] The present invention also provides a peak shaving system based on the capacity increase and power increase of hydropower units. The system is used to implement the above method and includes:

[0031] A peak shaving demand prediction module, which is used to obtain the historical load data and real-time load information of the power grid, and adopt a time series prediction algorithm to perform rolling prediction on the power demand in a preset future period to obtain the peak shaving demand prediction result of the power grid;

[0032] A water inflow prediction module, which is used to obtain the predicted water inflow data of the hydropower station by weighted summation of the prediction results of the AM-LSTM model and the CatBoost model based on the pre-obtained historical water inflow data and meteorological prediction data of the hydropower station;

[0033] A scheduling model construction module, which is used to establish a collaborative optimal scheduling model of hydropower stations, pumped-storage power stations and thermal power units by using a mixed integer programming model based on the predicted water inflow data of the hydropower station and the predicted peak shaving demand result of the power grid;

[0034] The peak shaving module is used to solve the collaborative optimization scheduling model by using an improved particle swarm optimization algorithm based on the collaborative optimization scheduling model and the prediction result of the power grid peak shaving demand, so as to obtain the optimized output scheduling plans of hydropower stations, pumped-storage power stations and thermal power units in each period, and complete the peak shaving based on the capacity increase and power generation increase of hydropower units.

[0035] Preferably, the peak shaving demand prediction module includes:

[0036] The data processing unit is used to perform outlier processing and missing value filling on the acquired historical power grid load data and real-time load information;

[0037] The prediction model construction unit is used to perform time series analysis on the processed historical power grid load data by using the Prophet model to establish a load prediction model;

[0038] The short-term prediction unit is used to input the processed real-time load information into the load prediction model to predict the power demand in a preset future period and obtain a short-term load prediction result;

[0039] The medium- and long-term prediction unit is used to perform rolling update on the preset period in a sliding window manner based on the short-term load prediction result to obtain a medium- and long-term load prediction result;

[0040] The load prediction unit is used to fuse the short-term load prediction result and the medium- and long-term load prediction result based on the weighted average method to obtain a final load prediction result;

[0041] Based on the final load prediction result, analyze the load peaks and valleys of the power grid in different time periods, and combine the power grid regulation ability to obtain the prediction result of the power grid peak shaving demand.

[0042] The present invention also provides an electronic device, including a memory, a processor and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the method described above is implemented.

[0043] The present invention also provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, and when the computer program is executed, the method described above is implemented.

[0044] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0045] Improve prediction accuracy: By using a time series prediction algorithm to perform rolling prediction on future power demand, the load change trend can be captured more accurately, providing a reliable basis for formulating peak shaving strategies.

[0046] Optimized scheduling strategy: Establish a collaborative optimization scheduling model for hydropower stations, pumped-storage power stations and thermal power units, which can comprehensively consider the characteristics and constraints of different types of power sources, achieve complementary advantages and efficient collaboration among power sources, and improve the peak shaving effect.

[0047] Enhanced flexibility: This method can dynamically adjust the scheduling plan according to the actual situation to cope with sudden load changes or the uncertainty of new energy power generation, and improve the stability and reliability of the power system.

[0048] In summary, the peak shaving method based on the capacity increase and power increase of hydropower units effectively solves the defects in the prior art through measures such as improving prediction accuracy, optimizing scheduling strategies and enhancing flexibility, and provides a new solution for the peak shaving of power systems. Brief Description of the Drawings

[0049] In order to more clearly illustrate the technical solutions of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0050] Figure 1 It is a flowchart of a peak shaving method based on the capacity increase and power increase of hydropower units according to an embodiment of the present invention;

[0051] Figure 2 It is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

[0052] Description of the reference numerals:

[0053] 1010, processor; 1020, memory; 1030, input / output interface; 1040, communication interface; 1050, bus. Detailed Embodiments

[0054] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the protection scope of the present invention.

[0055] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present invention should have the ordinary meanings understood by those of ordinary skill in the field to which the present invention belongs. The "first", "second" and similar terms used in the embodiments of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Words such as "including" or "comprising" mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Words such as "connected" or "linked" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right", etc. are only used to represent relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0056] To make the above objects, features and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0057] Embodiment 1

[0058] As Figure 1 shown, the embodiments of the present invention provide a peak shaving method based on the capacity increase and power generation increase of a hydropower unit. The method includes:

[0059] S1: Obtain the historical load data and real-time load information of the power grid, and use the time series prediction algorithm to perform rolling prediction on the power demand in a future preset time period to obtain the prediction result of the power grid peak shaving demand. A further implementation method is that the method for obtaining the prediction result of the power grid peak shaving demand includes:

[0060] S11: Perform outlier processing and missing value filling on the obtained historical load data and real-time load information of the power grid;

[0061] S12: Use the Prophet model to perform time series analysis on the processed historical load data of the power grid and establish a load prediction model. In this embodiment, as a time series prediction algorithm based on an additive regression model, the Prophet model is more suitable for processing data with multiple periodicities and holiday effects. Since the power load has intra-day, intra-week and seasonal variations, the Prophet model is selected for prediction.

[0062] S13: Input the processed real-time load information into the load prediction model to predict the power demand in a future preset time period and obtain a short-term load prediction result;

[0063] S14: Based on the short-term load prediction result, use the sliding window method to perform rolling update on the preset time period to obtain a medium- and long-term load prediction result;

[0064] S15: Based on the weighted average method, fuse the short-term load forecasting results and the medium- and long-term load forecasting results to obtain the final load forecasting result; in this embodiment, the short-term and medium- and long-term forecasting results are weighted and then the average value is taken. The distribution of weights is determined according to factors such as the reliability of the forecasting results and the accuracy of historical data.

[0065] S16: Based on the final load forecasting result, analyze the load peaks and valleys of the power grid at different time periods, and combine the power grid regulation capacity to obtain the power grid peak shaving demand forecasting result.

[0066] S2: Based on the pre-acquired historical water inflow data and meteorological forecasting data of the hydropower station, use the weighted sum of the forecasting results of the AM-LSTM model and the CatBoost model to obtain the water inflow forecasting data of the hydropower station; obtain the historical water inflow data and meteorological forecasting data (rainfall, temperature) of the hydropower station, and use the long short-term memory neural network model to forecast the water inflow of the hydropower station to obtain the water inflow forecasting result of the hydropower station. The water inflow forecasting of the hydropower station is an important basis for the power system dispatching.

[0067] A further implementation manner lies in that the method for obtaining the water inflow forecasting data of the hydropower station includes:

[0068] S21: Specifically, first perform standardization processing on the acquired data. The main purpose of standardization is to scale data with different dimensions into the same range, reduce the influence caused by dimensions, and at the same time maintain the distribution of the original data. Avoid the problem that due to the large variation in the value ranges of different variables in the collected original data, the high eigenvalues dominate and the influence of the low eigenvalues on the model is weakened.

[0069] S22: The preprocessed data is predicted by the AM-LSTM model to obtain the first prediction value; and predicted by the CatBoost model to obtain the second prediction value. Reconstruct the first prediction value of the AM-LSTM model and the second prediction value of the CatBoost model to more deeply explore the relationship between features and obtain the prediction sequence.

[0070] Among them, the structure of the AM-LSTM model includes:

[0071] LSTM layer: Construct an LSTM layer to capture the long-term dependencies in the time series. The LSTM layer contains multiple LSTM units, and each unit controls the flow of information through the forget gate, input gate, and output gate.

[0072] Attention mechanism layer: Add an attention mechanism layer after the LSTM layer to assign different weights to the outputs of different time steps. The attention mechanism can help the model pay more attention to the important input parts, thereby improving the prediction accuracy.

[0073] Output layer: used to output the first prediction value.

[0074] When the CatBoost model obtains the second prediction value, it is necessary to first select CatBoostRegressor for initialization according to the regression requirements of the prediction task. Set the parameters of the CatBoost model according to the data characteristics and prediction requirements, including the number of iterations, learning rate, tree depth, subsample ratio, etc.

[0075] In the selection of reconstruction metrics, mainly consider three commonly used metrics, namely MAE, RMSE, and MAPE, as reconstruction parameters. MAPE mainly measures the error and ratio between the predicted value and the true value. RMSE measures the deviation between the observed value and the true value. The main meaning of MAE is that it can accurately reflect the magnitude of the actual prediction error.

[0076] S23: Use weighted average to establish the weight coefficients of each prediction value, multiply the weight coefficients by the corresponding prediction values, and add the two multiplication results to obtain the final reconstruction result. Use the selected reconstruction metrics to evaluate the reconstruction result.

[0077] S3: Based on the prediction results of the incoming water volume of the hydropower station and the prediction results of the power grid peak shaving demand, use a mixed-integer programming model to establish a collaborative optimal scheduling model for multiple types of power stations including hydropower stations, pumped-storage power stations, and thermal power units; in this embodiment, the mixed-integer programming model can simultaneously consider the characteristics of hydropower, pumped-storage, and thermal power to achieve overall optimality. Specifically, use the branch and bound method to solve the mixed-integer programming model: decompose the solution problem into a series of sub-problems, and gradually approach the optimal solution by constructing a branch tree. The branch and bound method mainly includes three steps: branching, bounding, and pruning.

[0078] In the branching step, decompose the current problem into two or more sub-problems. By selecting an integer variable and considering all its possible integer values. For each integer value, create a new sub-problem where the value of this variable is fixed to this integer value, thus transforming the original problem into a smaller but still possibly complex sub-problem. In the bounding step, calculate a lower bound (for a minimization problem) or an upper bound (for a maximization problem) for each sub-problem. This bound is based on an estimate of the possible optimal value of the solution to the sub-problem. In the pruning step, the algorithm uses the bounds obtained in the bounding step to exclude those branches that cannot contain the optimal solution. If the bound of a sub-problem has exceeded the currently known optimal solution, then this branch can be safely pruned because it cannot produce a better solution than the current optimal solution.

[0079] Specifically, for a mixed-integer programming problem, all integer constraints are removed from the initial model to obtain the linear programming relaxation of the original model. Next, this linear programming relaxation (LP) is solved. If the obtained solution exactly satisfies all integer constraints, then this solution is the optimal solution of the original model and the operation terminates. If the solution does not satisfy all integer constraints, then a variable for which an integer constraint actually gives a fractional value needs to be selected for "branching" to generate a search tree. The mixed integers generated during the search process are called the nodes of the tree. The leaf nodes are all the nodes that have not been branched. If the solutions of all leaf nodes satisfy the integer constraints of the original model, then the original model problem has been solved.

[0080] Among them, the decision variables of the collaborative optimal scheduling model for multi-type power stations include the power generation of hydropower stations, the power generation and water pumping volume of pumped-storage power stations, the power generation of thermal power units, and the unit start-stop status;

[0081] The constraint conditions include power balance constraints, unit output constraints, water inflow constraints of hydropower stations, capacity constraints of pumped-storage power stations, and operation constraints of thermal power units;

[0082] The objective functions include minimizing the power generation cost, maximizing the environmental benefits, minimizing the minimum technical output of thermal power, minimizing the installed capacity demand of power supply thermal power, and maximizing the consumption of new energy in the power grid.

[0083] S4: Based on the collaborative optimal scheduling model and the prediction results of the power grid peak shaving demand, an improved particle swarm optimization algorithm is used to solve the collaborative optimal scheduling model to obtain the optimized output scheduling plans of hydropower stations, pumped-storage power stations, and thermal power units in each period, and complete the peak shaving based on the capacity increase and power increase of hydropower units.

[0084] A further implementation manner lies in that the method for obtaining the peak shaving result includes:

[0085] S41: Based on the collaborative optimization scheduling model, determine whether the predicted water inflow data of the hydropower station meets the predicted peak shaving demand of the power grid. If not, obtain the geographical conditions and capacity parameters of the pumped-storage power station and establish an optimal pumping strategy. In this embodiment, under the guidance of the optimal pumping strategy, when the power grid load is at a low valley, electrical energy is converted into water energy, and water is pumped from the lower reservoir to the upper reservoir for storage through the pumped-storage power station. When the power grid load is at a peak, the stored water energy in the upper reservoir is used to generate electricity and release power to the power grid to make up for the insufficient peak shaving capacity of the hydropower station. During the dry season, the water inflow of the hydropower station is small and the power generation capacity is limited. At this time, by reasonably dispatching the pumped-storage power station, pumping energy storage is carried out during the low valley of the power grid load, and power is released during the peak, giving full play to the peak shaving role of the pumped-storage power station and ensuring the stable operation of the power grid. The deep reinforcement learning algorithm is used to continuously interact with the environment, learn and optimize the scheduling strategy of the pumped-storage power station, so that it can adaptively adjust the pumping and power generation strategies according to the power grid load change and the predicted result of the water inflow of the hydropower station, improving the peak shaving efficiency and the economy of the power grid operation. Apply the optimized scheduling strategy of the pumped-storage power station to the actual power grid scheduling, monitor the power grid load change and the water inflow change of the hydropower station, and adjust the operation state of the pumped-storage power station in real time to ensure that when the peak shaving capacity of the hydropower station is insufficient, power can be released in time to meet the peak shaving demand of the power grid and ensure the safe and stable operation of the power system.

[0086] S42: Obtain the efficiency curves and wear characteristics of the hydro-generating units and pumped-storage units, and establish the mapping relationship between the unit state and energy consumption and life through the support vector machine algorithm; based on the collaborative optimization scheduling model and combined with the mapping relationship, obtain the unit output adjustment strategy based on the capacity increase and power increase of the hydro-generating units;

[0087] Specifically, it is first necessary to obtain the historical operation data of the units, including the efficiency curves and equipment wear characteristics under different working conditions. These data reflect the performance of the units in various operating states and are the basis for subsequent modeling. For example, the Francis turbine of a certain hydropower station has the highest efficiency of 96% at 70% of the rated load, while the efficiency drops to 85% at 30% of the load. Data preprocessing is an important link to ensure the quality of the model. By means of removing outliers, filling in missing values, normalization, etc., the data quality can be significantly improved. For example, unifying the efficiency data to the 0-1 interval is convenient for comparing indicators with different dimensions. After data cleaning in a certain pumped-storage power station, it is found that about 2% of the efficiency data is abnormal, which may be caused by sensor failures. Removing these data can improve the accuracy of subsequent modeling. The support vector machine maps low-dimensional data to a high-dimensional space through a kernel function. The SVM can capture the complex relationship between the unit state and energy consumption and life. During the model training process, the grid search and cross-validation methods are used to optimize the kernel function parameters and penalty factors, effectively improving the generalization ability of the model.

[0088] In this embodiment, an improved particle swarm optimization algorithm is used to solve the collaborative optimization scheduling model of multi-type power stations, and the optimized output scheduling plans of hydropower stations, pumped-storage power stations, and thermal power units for each period are obtained:

[0089] First, initialize the particle swarm. Randomly generate a group of particles in the solution space. Each particle represents a possible scheduling plan, including the output plans of hydropower stations, pumped-storage power stations, and thermal power units for each period. The initialization parameters include the particle swarm size, the maximum number of iterations, the inertia weight, and the learning factors.

[0090] Then calculate the objective function value of each particle and evaluate its quality. For each particle, compare the objective function value at its current position with the personal best (the objective function value at the historical best position of this particle). If the current position is better, update the personal best. Among the personal bests of all particles, find the best one as the global best. Update the velocity and position of the particle to ensure that the updated position is within the solution space and satisfies all constraints.

[0091] Repeat the above steps until the maximum number of iterations is reached or other stopping conditions are met. In each iteration, evaluate the quality of the particles according to the objective function value and update the personal best and the global best. When the algorithm terminates, the position corresponding to the global best is the optimal solution of the collaborative optimization scheduling model of multi-type power stations, that is, the optimized output scheduling plans of hydropower stations, pumped-storage power stations, and thermal power units for each period.

[0092] S43: Based on the optimal pumping strategy and the unit output regulation strategy, complete the peak shaving based on the capacity increase and power generation increase of the hydropower unit.

[0093] It should be noted that the method of the embodiment of the present invention can be executed by a single device, such as a computer or a server. The method of this embodiment can also be applied to a distributed scenario and completed by the cooperation of multiple devices. In this case of a distributed scenario, one of these multiple devices can only execute one or more steps of the method of the embodiment of the present invention, and these multiple devices will interact with each other to complete the described method.

[0094] It should be noted that some embodiments of the present invention have been described above. Other embodiments are within the scope of the appended claims. In some cases, it should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention. The actions or steps recited in the claims may be executed in an order different from that in the above embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0095] Embodiment 2

[0096] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present invention further provides a peak shaving system based on the capacity increase and power generation increase of a hydropower unit, including:

[0097] A peak shaving demand prediction module, configured to obtain the historical load data and real-time load information of the power grid, and use a time series prediction algorithm to perform rolling prediction on the power demand in a preset future period to obtain the peak shaving demand prediction result of the power grid;

[0098] An incoming water volume prediction module, configured to obtain the predicted incoming water volume data of the hydropower station by weighted summing the prediction results of the AM-LSTM model and the CatBoost model based on the historical incoming water volume data and meteorological prediction data of the hydropower station obtained in advance;

[0099] A scheduling model construction module, configured to establish a collaborative optimization scheduling model of the hydropower station, pumped storage power station, and thermal power unit by using a mixed integer programming model based on the predicted incoming water volume data of the hydropower station in combination with the peak shaving demand prediction result of the power grid;

[0100] A peak shaving module, configured to solve the collaborative optimization scheduling model by using an improved particle swarm optimization algorithm based on the collaborative optimization scheduling model and the peak shaving demand prediction result of the power grid, and obtain the optimized output scheduling plan of the hydropower station, pumped storage power station, and thermal power unit in each period, so as to complete the peak shaving based on the capacity increase and power generation increase of the hydropower unit.

[0101] A further embodiment is that the peak shaving demand prediction module includes:

[0102] A data processing unit, configured to perform outlier processing and missing value filling on the obtained historical load data and real-time load information of the power grid;

[0103] A prediction model construction unit, configured to perform time series analysis on the processed historical load data of the power grid by using the Prophet model to establish a load prediction model;

[0104] A short-term prediction unit, configured to input the processed real-time load information into a load prediction model, predict the power demand for a preset future period, and obtain a short-term load prediction result;

[0105] A medium- and long-term prediction unit, configured to perform rolling updates on a preset period in a sliding window manner based on the short-term load prediction result, and obtain a medium- and long-term load prediction result;

[0106] A load prediction unit, configured to fuse the short-term load prediction result and the medium- and long-term load prediction result based on the weighted average method to obtain a final load prediction result;

[0107] Based on the final load prediction result, analyze the load peak and valley of the power grid at different time periods, and combine the grid regulation capacity to obtain a prediction result of the power grid peak shaving demand.

[0108] The system of the above embodiment is used to implement the corresponding peak shaving method based on the capacity increase and power generation increase of the hydropower unit in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0109] It should be noted that the above peak shaving system based on the capacity increase and power generation increase of the hydropower unit is embodied in the form of functional units. The term "module" here can be implemented in software and / or hardware forms, and no specific limitation is made thereto.

[0110] For example, the "module" can be a software program, a hardware circuit, or a combination of the two that implements the above functions. The hardware circuit may include an application specific integrated circuit (ASIC), an electronic circuit, a processor (such as a shared processor, a proprietary processor, or a group of processors, etc.) for executing one or more software or firmware programs, a memory, a merged logic circuit, and / or other suitable components that support the described functions.

[0111] Embodiment III

[0112] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the peak shaving method based on the capacity increase and power generation increase of the hydropower unit described in any of the above embodiments.

[0113] Figure 2FIG. 0 shows a more specific schematic diagram of the hardware structure of the electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. Among them, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other inside the device through the bus 1050.

[0114] The processor 1010 may be implemented in the form of a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0115] The memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0116] The input / output interface 1030 is used to connect to an input / output module to implement information input and output. The input / output module may be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Among them, the input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0117] The communication interface 1040 is used to connect to a communication module (not shown in the figure) to implement communication interaction between this device and other devices. Among them, the communication module may implement communication in a wired manner (such as USB (Universal Serial Bus), network cable, etc.) or in a wireless manner (such as mobile network, WIFI (Wireless Fidelity), Bluetooth, etc.).

[0118] The bus 1050 includes a path for transmitting information between various components of the device (such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0119] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may also only include the components necessary to implement the solution of the embodiments of this specification, and does not necessarily include all the components shown in the figure.

[0120] The system of the above embodiment is used to implement the corresponding peak regulation method based on the capacity increase and power increase of the hydropower unit in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0121] Embodiment 4

[0122] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present invention also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the peak regulation method based on the capacity increase and power increase of the hydropower unit as described in any of the above embodiments.

[0123] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0124] The computer instructions stored in the storage medium of the above embodiment are used to cause the computer to execute the peak regulation method based on the capacity increase and power increase of the hydropower unit as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0125] Those of ordinary skill in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of the present invention (including the claims) is limited to these examples; under the concept of the present invention, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the embodiments of the present invention as described above, and for the sake of brevity, they are not provided in detail.

[0126] In addition, for the sake of simplicity of description and discussion, and in order not to make the embodiments of the present invention difficult to understand, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the accompanying drawings. Further, the devices may be shown in block diagram form in order to avoid making the embodiments of the present invention difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present invention are to be implemented (i.e., these details should be fully within the understanding of those skilled in the art). In the case where specific details (such as circuits) are set forth to describe exemplary embodiments of the present invention, it will be apparent to those skilled in the art that the embodiments of the present invention can be implemented without these specific details or with variations of these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0127] Although the present invention has been described in connection with specific embodiments of the present invention, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art based on the foregoing description. For example, other memory architectures (such as dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0128] Therefore, the units of each example described in the embodiments of the present application can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present application.

[0129] The embodiments of the present invention are intended to cover all such alternatives, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of the present invention shall be included within the protection scope of the present invention.

Claims

1. A peak shaving method based on capacity increase and power generation increase of hydropower units, characterized in that, The method includes: Obtain the historical load data and real-time load information of the power grid, and use the time series prediction algorithm to perform rolling prediction on the power demand in a preset future period to obtain the prediction result of the power grid peak shaving demand; Based on the pre-obtained historical water inflow data and meteorological prediction data of the hydropower station, use the weighted sum of the prediction results of the AM-LSTM model and the CatBoost model to obtain the predicted water inflow data of the hydropower station; Based on the predicted water inflow data of the hydropower station and combined with the predicted power grid peak shaving demand result, use the mixed integer programming model to establish a collaborative optimization scheduling model for the hydropower station, pumped storage power station and thermal power unit; Based on the collaborative optimization scheduling model and the predicted power grid peak shaving demand result, use the improved particle swarm optimization algorithm to solve the collaborative optimization scheduling model to obtain the optimized output scheduling plan of the hydropower station, pumped storage power station and thermal power unit in each period, and complete the peak shaving based on the capacity increase and power generation increase of the hydropower unit.

2. The peak shaving method based on capacity increase and power generation increase of hydropower units according to claim 1, wherein The method for obtaining the predicted power grid peak shaving demand result includes: Perform outlier processing and missing value filling on the obtained historical load data and real-time load information of the power grid; Use the Prophet model to perform time series analysis on the processed historical load data of the power grid to establish a load prediction model; Input the processed real-time load information into the load prediction model to predict the power demand in a preset future period to obtain the short-term load prediction result; Based on the short-term load prediction result, use the sliding window method to perform rolling update on the preset period to obtain the medium and long-term load prediction result; Based on the weighted average method, fuse the short-term load prediction result and the medium and long-term load prediction result to obtain the final load prediction result; Based on the final load prediction result, analyze the load peak and valley values of the power grid in different time periods, and combine the power grid regulation ability to obtain the predicted power grid peak shaving demand result.

3. The peak regulation method based on capacity increase and power generation increase of hydropower units according to claim 1, characterized in that, The method for obtaining the predicted water inflow data of the hydropower station includes: Preprocess the obtained historical water inflow data and meteorological prediction data of the hydropower station; Input the preprocessed historical water inflow data and meteorological prediction data of the hydropower station into the AM-LSTM model and the CatBoost model respectively to predict the first prediction value and the second prediction value respectively; Establish the weight coefficients of each prediction value, and based on the weight coefficients, perform weighted summation on the first prediction value and the second prediction value to obtain the reconstruction result as the predicted water inflow data of the hydropower station.

4. The peak shaving method based on capacity increase and power generation increase of hydropower units according to claim 1, wherein, The construction method of the collaborative optimization scheduling model includes: Based on the predicted water inflow data of the hydropower station and the predicted power grid peak shaving demand result, use the mixed integer programming model to establish a collaborative optimization scheduling model for multiple types of power stations including hydropower stations, pumped storage power stations and thermal power units; Among them, the decision variables of the collaborative optimization scheduling model for multiple types of power stations include the power generation of the hydropower station, the power generation and water pumping volume of the pumped storage power station, the power generation of the thermal power unit, and the unit start-stop state; The constraint conditions include power balance constraint, unit output constraint, water inflow constraint of the hydropower station, capacity constraint of the pumped storage power station, and operation constraint of the thermal power unit; The objective function includes minimizing the power generation cost, maximizing the environmental benefits, minimizing the minimum technical output of thermal power, minimizing the installed capacity demand of power supply thermal power, and maximizing the new energy consumption of the power grid.

5. The peak regulation method based on capacity increase and power generation increase of hydropower units according to claim 1, wherein, The methods for obtaining the peak shaving results include: Based on the collaborative optimization scheduling model, judge whether the predicted water inflow data of the hydropower station meets the predicted peak shaving demand of the power grid. If not, obtain the geographical conditions and capacity parameters of the pumped-storage power station and establish an optimal pumping strategy; Obtain the efficiency curves and wear characteristics of the hydropower units and pumped-storage units, and establish the mapping relationship between the unit state and energy consumption and life through the support vector machine algorithm; based on the collaborative optimization scheduling model and the mapping relationship, obtain the unit output adjustment strategy based on the capacity increase and power increase of the hydropower units; Based on the optimal pumping strategy and the unit output adjustment strategy, complete the peak shaving based on the capacity increase and power increase of the hydropower units.

6. A peak shaving system based on capacity increase and power generation increase of a hydropower unit, the system is used to implement the method described in any one of claims 1-5, and is characterized in that, It includes: The peak shaving demand prediction module is used to obtain the historical load data and real-time load information of the power grid, and use the time series prediction algorithm to perform rolling prediction on the power demand in a future preset period to obtain the peak shaving demand prediction result of the power grid; The water inflow prediction module is used to obtain the predicted water inflow data of the hydropower station by weighted summing the prediction results of the AM-LSTM model and the CatBoost model based on the pre-obtained historical water inflow data and meteorological prediction data of the hydropower station; The scheduling model construction module is used to establish a collaborative optimization scheduling model of the hydropower station, pumped-storage power station and thermal power unit by using the mixed integer programming model based on the predicted water inflow data of the hydropower station and the peak shaving demand prediction result of the power grid; The peak shaving module is used to solve the collaborative optimization scheduling model by using the improved particle swarm optimization algorithm based on the collaborative optimization scheduling model and the peak shaving demand prediction result of the power grid, and obtain the optimized output scheduling plan of the hydropower station, pumped-storage power station and thermal power unit in each period, and complete the peak shaving based on the capacity increase and power increase of the hydropower units.

7. The peak shaving system based on the capacity increase and power generation increase of the hydropower unit according to claim 6, characterized in that, The peak shaving demand prediction module includes: The data processing unit is used to perform outlier processing and missing value filling on the obtained historical load data and real-time load information of the power grid; The prediction model construction unit is used to perform time series analysis on the processed historical load data of the power grid by using the Prophet model and establish a load prediction model; The short-term prediction unit is used to input the processed real-time load information into the load prediction model to predict the power demand in a future preset period and obtain the short-term load prediction result; The medium and long-term prediction unit is used to perform rolling update on the preset period in a sliding window manner based on the short-term load prediction result to obtain the medium and long-term load prediction result; The load prediction unit is used to obtain the final load prediction result by fusing the short-term load prediction result and the medium and long-term load prediction result based on the weighted average method; Based on the final load prediction result, analyze the load peaks and valleys of the power grid in different time periods, and combine the power grid regulation ability to obtain the peak shaving demand prediction result of the power grid.

8. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the method according to any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program which, when executed, implements the method according to any one of claims 1 to 5.

Images