Cascade optimization scheduling method and system for flood control power generation

Abstract

The invention discloses a cascade optimization scheduling method and system for flood control power generation, and relates to the hydropower station scheduling and data processing technology, and the method comprises the steps: carrying out the grouping of historical storage data, drainage data and water level data according to a set time period, so as to obtain an initial sample; expanding the initial sample based on the distribution condition of the water level data in the data group to obtain a training sample; constructing a scheduling optimization model based on the LSTM; according to historical rainfall data, marks are added to all grouped data of the training samples so as to train the scheduling optimization model; and obtaining current data of the cascade drainage basin, and performing prediction based on the trained scheduling optimization model so as to perform scheduling optimization according to a prediction result. The method is used for fully exerting the combined retaining effect of the cascade reservoirs, flood control safety of the drainage basin can be guaranteed, and the power generation efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of hydropower station dispatching and data processing, and in particular to a cascade optimization dispatching method and system for flood control power generation. Background Art

[0002] At present, the flood control storage capacity of water conservancy hubs is set for the flood control safety of dams or downstream protection objects, mainly through the independent operation of water conservancy hubs to defend against standard floods and ensure the flood control safety of specific protection objects. Domestic and foreign research also focuses on analyzing the operation mode of single or cascade reservoirs for specific flood control tasks, and there is less quantitative research on the role of flood control scheduling of sub-district cascade reservoirs in flood defense in the whole basin.

[0003] Although the existing technology is trying to form an overall defense plan when defending against flood problems in the whole basin, the joint operation mode of the water conservancy hub group needs to be improved, and it is difficult to give full play to the regulation and storage role of the zoned controlled reservoirs; when solving the flood control problem in the basin, the existing technology still adopts the method of lowering the operating water level of the reservoir to the flood limit water level and reserving the planned flood control storage capacity, which cannot take into account the comprehensive benefits of the cascade reservoirs and cannot achieve efficient use of water resources in the basin. In the actual application of the existing technology, each water conservancy hub still needs to reach the pre-set flood control limit water level to defend against floods. When defending against different types of flood problems in the whole basin, it is difficult to give full play to the regulation and storage role of the zoned controlled reservoirs. Summary of the invention

[0004] The embodiments of the present application provide a cascade optimization scheduling method and system for flood control and power generation, which are used to optimize the scheduling of cascade river basins by combining flood control and power generation, give full play to the joint interception and storage role of cascade reservoirs, ensure flood control safety in the river basin, and improve power generation efficiency.

[0005] The embodiment of the present application proposes a cascade optimization scheduling method for flood control power generation, including: Obtain historical inflow data, discharge data, and water level data during flood season in cascade basins; According to the set time period, the historical storage data, drainage data and water level data are grouped to obtain the initial sample; Determine a data group exceeding the warning water level from various types of data in the initial sample, and expand the initial sample based on the distribution of water level data in the data group to obtain a training sample; Constructing a scheduling optimization model based on LSTM, wherein the scheduling optimization model includes a three-way branch model, and any branch model includes an LSTM module, wherein any branch model is used to perform prediction separately according to storage data, drainage data or water level data in a set of input data; and, An attention mechanism is provided between the three-way branch models, and the attention mechanism is used to compare the peak deviations of the feature information extracted by the corresponding branch models, so as to assign weights to the extracted feature information according to the comparison results to splice the extracted feature information, wherein the greater the peak deviation of the feature information extracted by any branch, the greater the weight assigned to any branch; adding tags to each grouped data of the training sample according to the historical rainfall data to train the scheduling optimization model; The current inflow data, drainage data and water level data of the cascade basin are obtained, and prediction is performed based on the trained scheduling optimization model to perform scheduling optimization according to the prediction results.

[0006] Optionally, historical storage data, drainage data, and water level data are grouped according to a set period, including: Set the inflow limit, water level deviation limit and drainage limit of the inflow data respectively; In any period of time, when one of the inflow, water level deviation and discharge reaches the corresponding limit, the other data are intercepted based on the same time and grouped as a set of data.

[0007] Optionally, determining a data group exceeding a warning water level from various types of data of the initial sample, and expanding the initial sample based on the distribution of water level data in the data group includes: Detecting the water level distribution in the data group containing data exceeding the warning water level, and eliminating the data group in which the proportion of the time when the water level data exceeds the warning water level in the data group is greater than a preset threshold; According to the detected water level distribution, the discharge interval and the maximum inflow of the cascade basin are used as constraints to generate data points for the inflow data and the discharge data in the remaining data groups; Fit the water level at the corresponding time according to the generated inflow data and discharge data to obtain an extended sample; The expansion is repeated until the proportion of time that the water level data in the remaining groups exceeds the warning water level is greater than the preset threshold, or the number of samples reaches the preset number.

[0008] Optionally, generating data points for the incoming data and the outgoing data in the remaining groups includes: Selecting inflow data points or discharge data points from the data groups whose time proportion is greater than a preset threshold, wherein the larger the single point value of the inflow data point or the discharge data point is, the greater the probability of selection is; Based on the selected inflow data points or discharge data points, the discharge data points or inflow data points are generated according to corresponding constraints.

[0009] Optionally, adding labels to each group of training sample data according to historical rainfall data includes: Obtain historical rainfall data of the main stream and tributaries of the cascade river basin; According to the geographical location, the main stream and its tributaries are divided into sections; According to the segment relationship, the time delay of the historical rainfall data in the corresponding segment is configured. The farther any tributary is from the current basin, the longer the time delay is. According to the historical rainfall data of each segment and the time delay of the segment, each group data of the training sample is marked.

[0010] Optionally, the constructed LSTM-based scheduling optimization model also includes a fully connected layer set after the three-way branch model and the attention mechanism, wherein the fully connected layer has an output node number of 3 for combining and outputting predicted data group results.

[0011] Optionally, performing prediction based on the trained scheduling optimization model to perform scheduling optimization according to the prediction result includes: Obtain the prediction result at the most recent time and calculate the deviation relationship between the prediction result and the current storage data, drainage data and water level data; According to the deviation relationship, mapping is performed based on a preset scheduling relationship to obtain a scheduling direction; According to the dispatching direction, combined with the current power generation information and gate opening information, optimized dispatching is performed.

[0012] Optionally, the dispatching direction includes increasing the displacement, maintaining the displacement, and reducing the displacement; According to the dispatching direction, combined with the current power generation information and gate opening information, the optimized dispatching is performed including: A plurality of groups of gate and / or power generation scheduling data are generated according to the deviation relationship, and a data group closest to the current power generation data is determined from the plurality of groups of gate and / or power generation scheduling data as the recommended scheduling data.

[0013] The embodiment of the present application also proposes a cascade optimization scheduling system for flood control power generation, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, the steps of the cascade optimization scheduling method for flood control power generation as described above are implemented.

[0014] The embodiment of the present application combines flood control and power generation to optimize the scheduling of cascade river basins, giving full play to the joint interception and storage function of cascade reservoirs, which can ensure the flood control safety of the river basin and improve the overall power generation efficiency of the cascade river basin.

[0015] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings: Figure 1 The basic process diagram of the cascade optimization scheduling method for flood control power generation of this embodiment is shown. DETAILED DESCRIPTION

[0017] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0018] The present application embodiment proposes a cascade optimization scheduling method for flood control power generation, such as Figure 1 As shown, the following steps are included: In step S101, historical inflow data, drainage data, and water level data of the cascade basin during the flood season are obtained. In some embodiments, the inflow data is the inflow flow of the basin at this level. In a specific example, it can be determined in combination with the drainage data of the tributaries and the upper basin. The drainage data in the embodiment of the present application includes water for power generation and flood discharge data of the flood gate. In a specific example, the relationship between the opening of the flood gate and the flood discharge can be established in advance to determine the flood discharge data. The corresponding guide vane opening can be found according to the power generation to determine the power generation drainage, and the drainage data can be accumulated and calculated. The water level data can be measured by, for example, a water level sensor.

[0019] In step S102, historical storage data, drainage data and water level data are grouped according to a set time period to obtain an initial sample.

[0020] In step S103, data groups exceeding the warning water level are determined from the various types of data in the initial sample, and the initial sample is expanded based on the distribution of water level data in the data group to obtain a training sample. In a specific example, the data group exceeding the warning water level in the initial sample is used for expansion, which can increase the number of samples in the flood season, better simulate the flood conditions that may exist in the flood season, and improve the expected effect of optimized scheduling.

[0021] In step S104, a scheduling optimization model based on LSTM is constructed, wherein the scheduling optimization model includes a three-way branch model, and any branch model includes an LSTM module, wherein any branch model is used to perform prediction separately according to storage data, drainage data or water level data in a set of input data. In a specific example, the embodiment of the present application sets an attention mechanism between the three-way branch models, and the attention mechanism is used to compare the peak deviations of the feature information extracted by the corresponding branch models, so as to assign weights to the extracted feature information according to the comparison results to splice the extracted feature information, wherein the greater the peak deviation of the feature information extracted by any branch, the greater the weight assigned to any branch. The peak deviation referred to in the embodiment of the present application refers to the deviation between the maximum values ​​in the data group. For example, in a 6-hour long data group, the peak value (maximum value and minimum value) deviation of the segmented storage data is greater than the storage threshold, and other deviations are within the normal range. It is considered that the current storage data belongs to the main factor affecting flood control scheduling, so as to assign a higher weight, and cooperate with the scheduling optimization model of the three-way branch LSTM of the embodiment of the present application to jointly train and output the scheduling optimization results. In some examples, the prediction can be performed step by step according to the interception and storage effect of the cascade power station at the prediction moment. In some embodiments, the constructed scheduling optimization model based on LSTM also includes a fully connected layer set after the three-way branch model and the attention mechanism, wherein the fully connected layer has an output node number of 3, which is used to combine and output the predicted data group results.

[0022] In the specific example, the application makes full use of the characteristics of LSTM to predict the incoming data, drainage data and water level data respectively, and introduces changing weights to highlight the proportion of a certain type of data in the current data group to reflect the dominant data in the data. For example, when the incoming data is higher, the incoming data has a greater weight, which is convenient for outputting the final prediction result based on the prediction of each LSTM, thereby improving the actual application effect of the model.

[0023] In step S105, each group of data of the training sample is labeled according to the historical rainfall data to train the scheduling optimization model.

[0024] In step S106, the current inflow data, drainage data and water level data of the cascade basin are obtained, and prediction is performed based on the trained scheduling optimization model to perform scheduling optimization according to the prediction results.

[0025] The embodiment of the present application combines flood control and power generation to optimize the scheduling of cascade river basins, giving full play to the joint interception and storage function of cascade reservoirs, which can ensure the flood control safety of the river basin and improve the overall power generation efficiency of the cascade river basin.

[0026] In some embodiments, grouping the historical storage data, drainage data, and water level data according to a set time period includes: Set the inflow limit, water level deviation limit and drainage limit of the inflow data respectively; In any period of time, when one of the inflow, water level deviation and discharge reaches the corresponding limit, the other data are intercepted based on the same time and grouped as a set of data.

[0027] That is, in the embodiment of the present application, the time interval of any data group may be different. For example, the upper limit value of the inflow flow, the upper limit value of the water level deviation, and the limit value of the drainage rate may be set, so that when any value reaches, for example, the upper limit value of the inflow flow in a certain period of time, it is intercepted as a data group.

[0028] In some embodiments, determining a data group exceeding a warning water level from various types of data in the initial sample, and expanding the initial sample based on the distribution of water level data in the data group includes: The water level distribution in the data group containing the data exceeding the warning water level is detected, and the data group in which the water level data exceeds the warning water level for a time period greater than a preset threshold is eliminated. In some embodiments, for example, if the water level data in a 3-hour data group continuously exceeds the warning water level by 70%, it is considered that this group of data has lost the expansion space and is eliminated in this example, so that sample expansion is performed according to the remaining data groups. In this way, the adaptability and rationality of the expanded sample to the basin can be greatly improved, and data distortion can be greatly avoided.

[0029] According to the detected water level distribution, data points are generated for the inflow data and discharge data in the remaining data groups, taking the discharge range and the maximum inflow of the cascade basin as constraints.

[0030] The water level at the corresponding moment is fitted according to the generated inflow data and outflow data to obtain an extended sample, that is, the inflow data and outflow data are replaced for fitting to obtain new water level data to improve the extended data set.

[0031] The expansion is repeated until the proportion of time that the water level data in the remaining groups exceeds the warning water level is greater than the preset threshold, or the number of samples reaches the preset number.

[0032] In a specific example, generating data points for the incoming data and the outgoing data in the remaining groups includes: An inflow data point or a discharge data point is selected from the data groups whose time proportion is greater than a preset threshold, wherein the larger the single point value of the inflow data point or the discharge data point is, the greater the probability of selection is.

[0033] Based on the selected inflow data points or discharge data points, the discharge data points or inflow data points are generated according to the corresponding constraints. In some examples, the present application uses the data groups whose time proportion is greater than the preset threshold to exclude more flood information, selects data points, and generates the discharge data points or inflow data points according to the corresponding constraints, thereby further improving the authenticity of the extended sample.

[0034] In some embodiments, adding a label to each group of data of the training sample according to the historical rainfall data includes: Obtain historical rainfall data of the main stream and tributaries of the cascade river basin; The main stream and its tributaries are divided into sections according to their geographical locations. For example, in some examples, some cascade basins cover a large area or have a long basin, so they can be divided into multiple sections.

[0035] According to the segment relationship, the time delay of the historical rainfall data in the corresponding segment is configured. The farther any tributary is from the current basin, the longer the time delay. By configuring the time delay, the amount of rainfall entering the reservoir can be reflected as much as possible to the period that directly affects the water level.

[0036] According to the historical rainfall data of each segment and the time delay of the segment, each group data of the training sample is marked. For example, if there is heavy rainfall in a certain area and the corresponding time delay is 1 hour, the flow caused by the corresponding heavy rainfall will be added to the inflow flow 1 hour later.

[0037] In some embodiments, performing prediction based on the trained scheduling optimization model to perform scheduling optimization according to the prediction result includes: Obtain the prediction result at the most recent moment and calculate the deviation relationship between the current storage data, drainage data and water level data. For example, the deviation relationship may include the positive and negative deviations of the storage data, the positive and negative deviations of the drainage data and the positive and negative deviations of the water level data in the prediction result.

[0038] According to the deviation relationship, mapping is performed based on the preset scheduling relationship to obtain the scheduling direction. Since the scheduling method is essentially to control power generation and flood control gates, that is, to control the discharge volume, in some examples, the scheduling direction includes increasing the discharge volume, maintaining the discharge volume, and reducing the discharge volume.

[0039] According to the dispatching direction, combined with the current power generation information and gate opening information, optimized dispatching is performed.

[0040] In some embodiments, according to the scheduling direction, combined with current power generation information and gate opening information, performing optimized scheduling includes: Multiple groups of gate and / or power generation scheduling data are generated according to the deviation relationship, and the data group closest to the current power generation data is determined from the multiple groups of gate and / or power generation scheduling data as the recommended scheduling data. In some specific examples, the flood control gate scheduling data can be further recommended to the user in combination with the current power generation plan, so as to achieve the optimal scheduling of flood control and power generation during the flood season.

[0041] The embodiment of the present application also proposes a cascade optimization scheduling system for flood control power generation, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, the steps of the cascade optimization scheduling method for flood control power generation as described above are implemented.

[0042] In addition, although exemplary embodiments have been described herein, the scope includes any and all embodiments based on the present disclosure with equivalent elements, modifications, omissions, combinations (e.g., various embodiments intersecting schemes), adaptations or changes. It is not limited to the examples described in this specification or during the implementation of this application, and its examples will be interpreted as non-exclusive.

[0043] The above description is intended to be illustrative rather than restrictive. For example, the above examples (or one or more of them) can be used in combination with each other. For example, those of ordinary skill in the art may use other embodiments when reading the above description.

[0044] The above embodiments are merely exemplary embodiments of the present disclosure. Those skilled in the art may make various modifications or equivalent substitutions to the present invention within the essence and protection scope of the present disclosure, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present invention.

Claims

1. A cascade optimization scheduling method for flood control power generation, characterized in that: include: Obtain historical inflow data, discharge data, and water level data during flood season in cascade basins; According to the set time period, the historical storage data, drainage data and water level data are grouped to obtain the initial sample; Determine a data group exceeding the warning water level from various types of data in the initial sample, and expand the initial sample based on the distribution of water level data in the data group to obtain a training sample; Constructing a scheduling optimization model based on LSTM, wherein the scheduling optimization model includes a three-way branch model, and any branch model includes an LSTM module, wherein any branch model is used to perform prediction separately according to storage data, drainage data or water level data in a set of input data; as well as, An attention mechanism is provided between the three-way branch models, and the attention mechanism is used to compare the peak deviations of the feature information extracted by the corresponding branch models, so as to assign weights to the extracted feature information according to the comparison results to splice the extracted feature information, wherein the greater the peak deviation of the feature information extracted by any branch, the greater the weight assigned to any branch; adding tags to each grouped data of the training sample according to the historical rainfall data to train the scheduling optimization model; The current inflow data, discharge data and water level data of the cascade basin are obtained, and prediction is performed based on the trained scheduling optimization model to perform scheduling optimization according to the prediction results.

2. The cascade optimization scheduling method for flood control power generation according to claim 1, characterized in that: According to the set time period, the historical storage data, drainage data and water level data are grouped, including: Set the inflow limit, water level deviation limit and drainage limit of the inflow data respectively; In any period of time, when one of the inflow, water level deviation and discharge reaches the corresponding limit, the other data are intercepted based on the same time and grouped as a set of data.

3. The cascade optimization scheduling method for flood control power generation according to claim 2, characterized in that: Determining a data group that exceeds the warning water level from various types of data in the initial sample, and expanding the initial sample based on the distribution of water level data in the data group includes: Detecting the water level distribution in the data group containing data exceeding the warning water level, and eliminating the data group in which the proportion of the time when the water level data exceeds the warning water level in the data group is greater than a preset threshold; According to the detected water level distribution, the discharge interval and the maximum inflow of the cascade basin are used as constraints to generate data points for the inflow data and the discharge data in the remaining data groups; Fit the water level at the corresponding time according to the generated inflow data and discharge data to obtain an extended sample; The expansion is repeated until the proportion of time that the water level data in the remaining groups exceeds the warning water level is greater than the preset threshold, or the number of samples reaches the preset number.

4. The cascade optimization scheduling method for flood control power generation according to claim 3 is characterized in that: Generating data points for the incoming data and outgoing data in the remaining groups includes: Selecting inflow data points or discharge data points from the data groups whose time proportion is greater than a preset threshold, wherein the larger the single point value of the inflow data point or the discharge data point is, the greater the probability of selection is; Based on the selected inflow data points or discharge data points, the discharge data points or inflow data points are generated according to corresponding constraints.

5. The cascade optimization scheduling method for flood control power generation according to claim 4, characterized in that: Adding labels to each group of training samples based on historical rainfall data includes: Obtain historical rainfall data of the main stream and tributaries of the cascade river basin; According to the geographical location, the main stream and its tributaries are divided into sections; According to the segment relationship, the time delay of the historical rainfall data in the corresponding segment is configured. The farther any tributary is from the current basin, the longer the time delay. According to the historical rainfall data of each segment and the time delay of the segment, each group data of the training sample is marked.

6. The cascade optimization scheduling method for flood control power generation according to claim 1, characterized in that: The constructed LSTM-based scheduling optimization model also includes a fully connected layer set after the three-way branch model and the attention mechanism, wherein the fully connected layer has an output node number of 3 for combining and outputting predicted data group results.

7. The cascade optimization scheduling method for flood control power generation according to claim 6, characterized in that: Performing prediction based on the trained scheduling optimization model to perform scheduling optimization according to the prediction result includes: Obtain the prediction result at the most recent time and calculate the deviation relationship between the prediction result and the current storage data, drainage data and water level data; According to the deviation relationship, mapping is performed based on a preset scheduling relationship to obtain a scheduling direction; According to the dispatching direction, combined with the current power generation information and gate opening information, optimized dispatching is performed.

8. The cascade optimization scheduling method for flood control power generation according to claim 7, characterized in that: The dispatching direction includes increasing the displacement, maintaining the displacement and reducing the displacement; According to the dispatching direction, combined with the current power generation information and gate opening information, the optimized dispatching is performed including: A plurality of groups of gate and / or power generation scheduling data are generated according to the deviation relationship, and a data group closest to the current power generation data is determined from the plurality of groups of gate and / or power generation scheduling data as the recommended scheduling data.

9. A cascade optimization dispatching system for flood control power generation, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the cascade optimization scheduling method for flood control power generation according to any one of claims 1 to 8.

Images