Comprehensive evaluation method for watershed cascade water-light complementary system

Abstract

The invention provides a watershed cascade water-light complementary system comprehensive evaluation method, and relates to the technical field of data processing, and the method comprises the steps: obtaining watershed cascade hydropower stations and photovoltaic power stations of a target watershed, and the watershed cascade hydropower stations comprise K hydropower stations; performing simultaneous sequence power generation monitoring data; obtaining a water-light complementary generating capacity sequence; determining a system power supply deviation factor; obtaining power generation cost of K hydropower stations, power generation cost of a photovoltaic power station, earnings of the K hydropower stations and earnings of the photovoltaic power station; and calling a revenue evaluation network layer to analyze the system power supply deviation factor, the power generation cost of the K hydropower stations, the power generation cost of the photovoltaic power station, the revenue of the K hydropower stations and the revenue of the photovoltaic power station, and determining a target revenue comprehensive evaluation result. The technical problem that income evaluation is inaccurate due to the lack of fluctuation analysis of the generating capacity in the prior art can be solved, and the technical effect of improving the accuracy of income evaluation of the water-light complementary system is achieved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a comprehensive evaluation method for a watershed cascade water-photovoltaic complementary system. Background Art

[0002] As global energy demand continues to grow, the development and utilization of clean and renewable energy sources are becoming increasingly important. The hydropower-photovoltaic complementary power generation model has gradually gained attention, which combines hydropower and photovoltaic power generation to achieve complementary advantages through reasonable scheduling and management. This model can not only improve power generation efficiency, but also reduce the overall operating cost of the system. However, the existing technology still has some shortcomings in the optimization scheduling of the hydropower-photovoltaic complementary system, especially in the aspects of power supply capacity assessment, power generation cost calculation and benefit analysis.

[0003] In the existing technology, the profit evaluation is often carried out based on the average power generation over a period of time. However, the power generation fluctuates with the influence of factors such as seasons and environment. Therefore, in the evaluation process, the output reliability and general power generation of each hydropower station and photovoltaic power station should be comprehensively considered to obtain a more reliable and accurate evaluation result.

[0004] In summary, the prior art has a technical problem of inaccurate revenue assessment due to the lack of fluctuation analysis of power generation. Summary of the invention

[0005] The purpose of this application is to provide a comprehensive evaluation method for a watershed cascade water-photovoltaic complementary system, so as to solve the technical problem in the prior art of inaccurate benefit evaluation due to the lack of fluctuation analysis of power generation.

[0006] In view of the above problems, the present application provides a comprehensive evaluation method for a watershed cascade hydro-photovoltaic complementary system, including: obtaining the watershed cascade hydropower stations and photovoltaic power stations in the target watershed, wherein the watershed cascade hydropower stations include K hydropower stations; traversing the K hydropower stations and photovoltaic power stations in a preset window to perform simultaneous power generation monitoring data collection, including K hydropower station time series monitoring data sequences and photovoltaic power station time series monitoring data sequences, and the photovoltaic power station time series monitoring data and the hydropower station time series monitoring data are in a many-to-one mapping relationship; using power generation as an index, the K hydropower station time series monitoring data sequences and the photovoltaic power station time series monitoring data sequences are simultaneously extracted to obtain the water-photovoltaic complementary power generation. sequence; obtain the demand load sequence of the preset window, perform power supply deviation trend analysis in combination with the hydro-photovoltaic complementary power generation sequence, and determine the system power supply deviation factor; collect the water-photovoltaic complementary system operation data of the K hydropower stations and the photovoltaic power stations in the preset window according to the preset indicator set, perform power generation cost and benefit analysis according to the collection results, and obtain the power generation cost of the K hydropower stations, the power generation cost of the photovoltaic power station, the benefits of the K hydropower stations and the benefits of the photovoltaic power station; call the benefit evaluation network layer to analyze the system power supply deviation factor, the power generation cost of the K hydropower stations, the power generation cost of the photovoltaic power station, the benefits of the K hydropower stations and the benefits of the photovoltaic power station, and determine the comprehensive evaluation result of the target benefit.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The target river basin cascade hydropower stations and photovoltaic power stations are obtained, wherein the cascade hydropower stations include K hydropower stations; the K hydropower stations and photovoltaic power stations are traversed in a preset window to collect simultaneous power generation monitoring data, including K hydropower station time series monitoring data sequences and photovoltaic power station time series monitoring data sequences, and the photovoltaic power station time series monitoring data and the hydropower station time series monitoring data are in a many-to-one mapping relationship; the K hydropower station time series monitoring data sequences and the photovoltaic power station time series monitoring data sequences are simultaneously extracted with power generation as an index to obtain a water-photovoltaic complementary power generation sequence; the demand load sequence of the preset window is obtained. The power supply deviation trend analysis is performed in combination with the water-photovoltaic complementary power generation sequence to determine the system power supply deviation factor; the water-photovoltaic complementary system operation data of the K hydropower stations and the photovoltaic power stations in the preset window are collected according to the preset indicator set, and the power generation cost and benefit analysis is performed according to the collection results to obtain the power generation cost of the K hydropower stations, the power generation cost of the photovoltaic power stations, the benefits of the K hydropower stations and the benefits of the photovoltaic power stations; the benefit evaluation network layer is called to analyze the system power supply deviation factor, the power generation cost of the K hydropower stations, the power generation cost of the photovoltaic power stations, the benefits of the K hydropower stations and the benefits of the photovoltaic power stations to determine the comprehensive evaluation result of the target benefit. By collecting the power generation monitoring data of K hydropower stations and photovoltaic power stations, performing power supply deviation analysis in combination with the demand load sequence, determining the system power supply deviation factor, analyzing the power generation cost and benefit at the same time, and using the benefit evaluation network layer to calculate the comprehensive evaluation result of the target benefit, the technical effect of improving the accuracy of the benefit evaluation of the water-photovoltaic complementary system is achieved.

[0009] 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 according to the contents of the specification, and 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 application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0011] Figure 1 A schematic diagram of the process of a comprehensive evaluation method for a watershed cascade water-photovoltaic complementary system for this application;

[0012] Figure 2This is a flow chart of determining the system power supply deviation factor in a comprehensive evaluation method for a river basin cascade water-photovoltaic complementary system in this application. DETAILED DESCRIPTION

[0013] This application solves the technical problem of inaccurate benefit evaluation in the prior art due to the lack of fluctuation analysis of power generation by providing a comprehensive evaluation method for cascade water-photovoltaic complementary systems in a watershed. By collecting power generation monitoring data of K hydropower stations and photovoltaic power stations, combining the demand load sequence to perform power supply deviation analysis, determining the system power supply deviation factor, and analyzing the power generation cost and benefit at the same time, and using the benefit evaluation network layer to calculate the comprehensive evaluation result of the target benefit, the technical effect of improving the accuracy of the benefit evaluation of the water-photovoltaic complementary system is achieved.

[0014] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0015] Please refer to the attached Figure 1 This application provides a comprehensive evaluation method for a watershed cascade water-photovoltaic complementary system, which specifically includes the following steps:

[0016] Step 1: Obtain the cascade hydropower stations and photovoltaic power stations in the target river basin, wherein the cascade hydropower stations in the target river basin include K hydropower stations.

[0017] Specifically, the target basin refers to any basin to be comprehensively evaluated for the water-photovoltaic complementary system. In the target basin, the basin cascade hydropower station refers to multiple hydropower stations built in sequence at different locations on the same river, so that the drop and flow of the water flow can be fully utilized to achieve higher power generation efficiency. It includes K hydropower stations, where K is an integer greater than or equal to 1. The photovoltaic power station in the target basin is a facility that converts solar energy into electrical energy, usually composed of an array of photovoltaic modules. After collecting these data, the characteristics of the hydropower station and the photovoltaic power station can be analyzed to compare their performance in terms of power generation efficiency, environmental impact and economy.

[0018] Step 2: In a preset window, traverse the K hydropower stations and photovoltaic power stations to collect simultaneous power generation monitoring data, including K hydropower station time series monitoring data sequences and photovoltaic power station time series monitoring data sequences. The photovoltaic power station time series monitoring data and the hydropower station time series monitoring data are in a many-to-one mapping relationship.

[0019] Specifically, the preset window is a time window preset by professional and technical personnel in this field. Within the preset window, the simultaneous power generation monitoring data of K hydropower stations and photovoltaic power stations in the basin are collected. Time series monitoring data refers to the data sequence that records key indicators such as power generation of the power station at each time node. These data can reflect the real-time power generation status and operating efficiency of the power station. At the same time, the power generation data of the photovoltaic power station will also be collected at the same time to obtain the photovoltaic power station time series monitoring data sequence, including power generation, equipment operating parameters and other data at multiple time nodes. Ultimately, these monitoring data will provide support for further optimization of the benefit assessment in the basin.

[0020] Step 3: Using power generation as an index, perform simultaneous extraction on the K hydropower station time series monitoring data sequences and the photovoltaic power station time series monitoring data sequences to obtain a hydro-photovoltaic complementary power generation sequence.

[0021] Specifically, the power generation is used as an index to extract the K hydropower station time-series monitoring data sequences and the photovoltaic power station time-series monitoring data sequences, that is, the power generation data in the K hydropower station time-series monitoring data sequences and the photovoltaic power station time-series monitoring data sequences are extracted respectively, and then the time nodes are aligned to obtain the power generation data of the K hydropower stations and the power generation data of the photovoltaic power stations corresponding to each time node, and the power generation data are integrated together to generate a water-photovoltaic complementary power generation sequence.

[0022] Step 4: Obtain the demand load sequence of the preset window, perform power supply deviation trend analysis in combination with the hydro-photovoltaic complementary power generation sequence, and determine the system power supply deviation factor.

[0023] Specifically, the demand load sequence refers to the amount of electricity that users demand within a preset window. These data are usually obtained through power monitoring systems or historical electricity consumption data. For example, in a one-hour monitoring window, the demand load for a certain period may be 400MWh, 450MWh, 500MWh, etc. Next, the demand load sequence is compared and analyzed with the hydropower-photovoltaic complementary power generation sequence. The hydropower-photovoltaic complementary power generation sequence refers to the amount of electricity jointly generated by hydropower stations and photovoltaic power stations in the same time period. For example, in the above time window, the hydropower-photovoltaic complementary power generation sequence may be 350MWh, 480MWh, 520MWh. By comparing these two sets of data, the degree of deviation between power supply capacity and demand can be identified. Power supply deviation trend analysis aims to determine the gap between power supply capacity and actual demand, so as to calculate the system power supply deviation factor. The system power supply deviation factor is a key indicator that can quantify the performance of the power system in meeting demand, that is, for each time point, the deviation between power supply and demand load is calculated, thereby providing data support for subsequent benefit evaluation, and facilitating accurate benefit evaluation based on power generation fluctuations.

[0024] Step 5: Collect the operation data of the water-photovoltaic complementary system of the K hydropower stations and the photovoltaic power stations within the preset window according to the preset indicator set, and perform power generation cost and benefit analysis based on the collection results to obtain the power generation cost of the K hydropower stations, the power generation cost of the photovoltaic power station, the benefits of the K hydropower stations and the benefits of the photovoltaic power station.

[0025] Specifically, the preset indicator set contains data items of multiple dimensions to comprehensively reflect the operation of the hydro-photovoltaic complementary system. These indicators are usually divided into cost-effectiveness indicators, energy utilization efficiency indicators, system performance stability indicators, and system volatility indicators. When collecting operating data, the preset window needs to be defined first. For example, one month is set as the collection window, and the power generation and related data are recorded according to the preset indicator set to capture the volatility of power generation and the dynamics of revenue, and obtain the collected data. Then, the power generation cost and revenue analysis is performed based on the collection results. The power generation cost refers to the various expenses required by the power station in the process of producing electric energy, including fixed costs and variable costs. Fixed costs usually refer to equipment depreciation, maintenance costs, etc., while variable costs include fuel costs (for hydropower, mainly water resource utilization costs) and operating costs. Revenue is the income obtained by the power station from the sale of electric energy, which is usually related to power generation and electricity prices. Specifically, by acquiring historical data for analysis, the relationship between power generation cost and benefit and the preset indicator set is established, and an analysis model is constructed based on historical data and existing neural network model training. The collected results are then input into the prediction model for analysis to obtain the power generation cost of K hydropower stations, the power generation cost of photovoltaic power stations, the income of K hydropower stations and the income of photovoltaic power stations.

[0026] Step 6: Call the benefit evaluation network layer to analyze the system power supply deviation factor, the power generation cost of the K hydropower stations, the power generation cost of the photovoltaic power station, the benefits of the K hydropower stations and the benefits of the photovoltaic power station to determine the comprehensive evaluation result of the target benefit.

[0027] Specifically, the benefit evaluation network layer usually adopts multivariate regression, neural network or other data analysis algorithms, aiming to integrate multiple input factors into a comprehensive evaluation result of target benefit. First, prepare the input data required for analysis, including system power supply deviation factor, power generation cost of K hydropower stations, power generation cost of photovoltaic power stations, benefits of K hydropower stations and benefits of photovoltaic power stations. For example, assuming that the system power supply deviation factor is 20MWh, indicating that the power supply capacity is slightly higher than the demand within a specific time, then collect the power generation cost and benefits of K hydropower stations. As mentioned above, assuming that the power generation cost of K hydropower stations is 20 yuan / MWh, 18 yuan / MWh and 22 yuan / MWh respectively, and the benefits are 500,000 yuan, 400,000 yuan and 450,000 yuan respectively, with a total benefit of 1,350,000 yuan; similarly, the power generation cost and benefits of photovoltaic power stations should also be included in the analysis. Assuming that the power generation cost of photovoltaic power stations A and B is 25 yuan / MWh and 23 yuan / MWh respectively, the benefits are 350,000 yuan and 300,000 yuan respectively, with a total benefit of 650,000 yuan. After integrating these data, the benefit evaluation network layer will analyze according to the preset model. For example, using the weighted method, each factor is assigned a corresponding weight to reflect their importance in the comprehensive evaluation. Assuming that the weight of the power supply deviation factor is 0.2, the power generation cost weight of K hydropower stations is 0.1, the power generation cost weight of photovoltaic power stations is 0.1, the benefit weight of K hydropower stations is 0.3, and the benefit weight of photovoltaic power stations is 0.3, by multiplying each factor with its weight and summing them, the target benefit comprehensive evaluation result can be calculated. Ultimately, the target benefit comprehensive evaluation result will provide an important basis for the optimization decision of the power system.

[0028] Further, step three of this application includes:

[0029] The power generation of the K hydropower stations' time-series monitoring data sequences and the photovoltaic power stations' time-series monitoring data sequences under the first time-series is extracted to obtain the power generation of the K first-series hydropower stations and the first-series photovoltaic power stations; the power generation of the K first-series hydropower stations and the first-series photovoltaic power stations are superimposed to obtain the water-photovoltaic complementary power generation sequence.

[0030] Specifically, the first time series refers to any time series node. The power generation corresponding to the first time series is extracted from the K hydropower station time series monitoring data series and the photovoltaic power station time series monitoring data series to obtain the power generation of K first time series hydropower stations and the power generation of the first time series photovoltaic power stations; the power generation of the K first time series hydropower stations and the power generation of the first time series photovoltaic power stations are superimposed, that is, the power of the hydropower station and the photovoltaic power station are added together, so as to obtain the water-photovoltaic complementary power generation corresponding to the first time series, thereby traversing all time series to obtain the water-photovoltaic complementary power generation sequence. Assume that in the first time series, the power generation data of the K hydropower stations are: the power generation of hydropower station 1 is 500MWh, the power generation of hydropower station 2 is 800MWh, and the power generation of hydropower station 3 is 600MWh. At the same time, the power generation data of the photovoltaic power station is 220MWh. Next, these power generation are superimposed to obtain the water-photovoltaic complementary power generation sequence. The water-photovoltaic complementary power generation sequence refers to the sum of the power generation of the hydropower station and the photovoltaic power station in the same time period, which can reflect the comprehensive power generation capacity under the time series. For example, in the first time series, the power generation of each power station can be superimposed: the total power generation of hydropower stations 1, 2 and 3 is 500MWh+800MWh+600MWh=1900MWh, and the total power generation of photovoltaic power stations A and B is 220MWh. Therefore, the total power generation of the hydro-photovoltaic complementary power generation sequence in the first time series is 1900MWh+220MWh=2120MWh. Through this process, we can clearly see the combined power generation capacity of hydropower and photovoltaic power in a specific period of time. This data superposition and analysis provides data support for subsequent benefit evaluation.

[0031] Furthermore, the present application also includes the following steps:

[0032] Acquire K layout positions of the K hydropower stations, and arrange the K hydropower stations in the direction of water flow from high to low according to the K layout positions combined with the water flow direction of the target watershed to obtain K hydropower station layout numbers; determine K influencing neighborhoods and K neighborhood influence weight sets of the K hydropower stations based on the sizes of the K hydropower station layout numbers; perform hydropower station reliability analysis based on the K influencing neighborhoods and K neighborhood influence weight sets, as well as the K hydropower station time series monitoring data sequences, to determine the K hydropower station reliability factors; correct the K hydropower station time series monitoring data sequences based on the K hydropower station reliability factors to obtain K corrected hydropower station time series monitoring data sequences; perform simultaneous sequential extraction of the K corrected hydropower station time series monitoring data sequences and the photovoltaic power station time series monitoring data sequences with power generation as an index, and update the water-photovoltaic complementary power generation sequence according to the extraction results.

[0033] Specifically, after obtaining the K layout locations of K hydropower stations, these hydropower stations can be arranged in the direction of water flow from high to low in combination with the water flow direction of the target basin to obtain the layout numbers of the K hydropower stations. The layout location refers to the specific geographical coordinates of the hydropower station in the basin, and the water flow direction is the key factor that determines the power generation efficiency of the hydropower station. For example, if hydropower station 1 is located in the upper reaches of the basin, hydropower station 2 is located in the middle reaches, and hydropower station 3 is located in the lower reaches, then the layout numbers will be 1, 2, and 3. Based on the size of the layout number, the influence neighborhood of each hydropower station can be determined. The influence neighborhood refers to other hydropower stations and regions affected by the operation of a hydropower station, and the transmission effect of water flow is usually considered. In addition, in order to quantify the relationship between the influencing neighborhoods, it is necessary to establish K neighborhood influence weight sets, which reflect the interaction intensity between hydropower stations. For example, the operation of the first hydropower station and the second hydropower station located before the third hydropower station will affect its water flow, so the third influencing neighborhood is the first hydropower station and the second hydropower station. In turn, the weight is inversely proportional to the distance, that is, the farther away from it, the lower the weight and the smaller the impact. For example, the influence weight of hydropower station 1 on hydropower station 2 is 0.6, and the influence weight on hydropower station 3 is 0.3. Specifically, when obtaining the neighborhood influence weight set corresponding to any influence neighborhood of any hydropower station, the distance from the hydropower station in any influence neighborhood to any hydropower station can be calculated, and each distance is divided by the sum of the distances, and the result is the neighborhood influence weight set.

[0034] Further, a reliability analysis of the hydropower station is performed based on the K influencing neighborhoods and the K neighborhood influence weight sets, as well as the K hydropower station time series monitoring data sequences, to determine the reliability factors of the K hydropower stations. The reliability factor is an indicator that measures the difference between the power generation capacity of a hydropower station and expectations, and can be calculated by comparing the actual power generation with the theoretical power generation. For example, if the theoretical power generation of hydropower station 1 is 700MWh and the actual power generation is 650MWh, the reliability factor is 650 / 700=0.93. Once the reliability factors of the K hydropower stations are obtained, the K hydropower station time series monitoring data sequences can be corrected by the K hydropower station reliability factors to obtain K corrected hydropower station time series monitoring data sequences, that is, the K hydropower station reliability factors are multiplied by the power generation data in the K hydropower station time series monitoring data sequences to complete the correction. Finally, with power generation as the index, K corrected hydropower station time-series monitoring data sequences and photovoltaic power station time-series monitoring data sequences are extracted simultaneously. In this way, the hydro-photovoltaic complementary power generation sequence can be updated to ensure that the sequence can more truly reflect the power generation capacity under different conditions and effectively improve the accuracy of benefit evaluation.

[0035] Furthermore, the present application also includes the following steps:

[0036] The K hydropower stations' time-series monitoring data sequences are traversed to perform data fluctuation analysis to obtain monitoring fluctuation coefficients of the K hydropower stations; the K hydropower stations' monitoring fluctuation coefficients are mapped and matched based on the K influencing neighborhoods to obtain a set of K influencing hydropower stations' monitoring fluctuation coefficients; the K influencing hydropower stations' monitoring fluctuation coefficients are weightedly calculated based on the K neighborhood influence weight sets to obtain the K hydropower stations' reliability factors.

[0037] Specifically, the specific steps for determining the reliability factors of K hydropower stations include: first, calculating the monitoring fluctuation coefficients of the K hydropower stations of the time series monitoring data sequences of the K hydropower stations. The monitoring fluctuation coefficient of the hydropower station is an indicator used to measure the relative volatility of the data, which is usually calculated by the ratio of the standard deviation to the mean value. For example, for a certain hydropower station, its power generation monitoring data may be [600MWh, 620MWh, 580MWh, 610MWh], its average power generation is 605MWh, and the standard deviation is 15MWh. Therefore, the fluctuation coefficient is 15 / 605≈0.025, which means that the power generation fluctuation of the hydropower station is relatively small. Next, based on the previously determined K influencing neighborhoods, the monitoring fluctuation coefficients of the K hydropower stations are mapped and matched. In layman's terms, the fluctuation coefficient of each hydropower station is associated with the fluctuation coefficients of other hydropower stations in its influencing neighborhood. Assuming that the fluctuation coefficient of hydropower station 1 is 0.025, and its influencing neighborhoods include hydropower stations 2 and 3, with fluctuation coefficients of 0.030 and 0.028, respectively, these fluctuation coefficients are aggregated to form a set of K monitoring fluctuation coefficients affecting hydropower stations. Subsequently, based on the K neighborhood influence weight sets, the K monitoring fluctuation coefficient sets affecting hydropower stations are weighted to obtain the reliability factor of each hydropower station. Through this weighted calculation, an important indicator reflecting the reliability of a hydropower station in its neighborhood can be obtained. These reliability factors help to evaluate the stability of the power generation capacity of each hydropower station in a dynamically changing environment, thereby improving the accuracy of the hydropower station benefit assessment.

[0038] Further, as attached Figure 2 As shown, step 4 of this application includes:

[0039] The demand load sequence and the hydro-photovoltaic complementary power generation sequence are traversed to calculate the power supply deviation difference, so as to obtain a power supply deviation difference sequence; a two-dimensional deviation trend analysis space is constructed based on the power supply deviation difference sequence, wherein the horizontal axis of the two-dimensional deviation trend analysis space is time, and the vertical axis is the power supply deviation difference, and the two-dimensional deviation trend analysis space includes a plurality of analysis particles, each of which corresponds to a power supply deviation difference; a centralized trend analysis is performed on the plurality of analysis particles in the two-dimensional deviation trend analysis space to determine the power supply deviation factor of the system.

[0040] Specifically, the specific steps for determining the system power supply deviation factor include: first, traversing the demand load sequence and the hydro-photovoltaic complementary power generation sequence to calculate the power supply deviation difference. The power supply deviation difference refers to the difference between the actual power generation and the demand load at a specific time point, and is calculated as follows: deviation difference = hydro-photovoltaic complementary power generation - demand load. For example, if the demand load is 400MWh in a certain period of time, and the hydro-photovoltaic complementary power generation is 350MWh, then the power supply deviation difference is 350MWh-400MWh=-50MWh. This process will generate a deviation difference for each time point, and finally form a power supply deviation difference sequence. Based on the power supply deviation difference sequence, a two-dimensional deviation trend analysis space can be constructed. In this analysis space, the horizontal axis represents time and the vertical axis represents the power supply deviation difference. By plotting the power supply deviation difference at each time point as an analysis particle, the distribution of multiple analysis particles in the two-dimensional space is formed. For example, assuming that the power supply deviation difference sequence calculated over a period of time is: -50MWh, 30MWh, -20MWh, 40MWh, then in the two-dimensional deviation trend analysis space, these values ​​are marked at the corresponding time points to form multiple analysis particles.

[0041] Furthermore, in the two-dimensional deviation trend analysis space, a central tendency analysis is performed on multiple analysis particles to determine the system power supply deviation factor. Central tendency analysis is a statistical method that is usually used to evaluate the center position of a data set. For example, the system power supply deviation factor can be obtained by calculating the mean of the power supply deviation difference sequence. Through such analysis, potential power supply shortages or surpluses can be identified, thereby providing data support for benefit evaluation, facilitating evaluation based on power supply deviations, and improving the accuracy of benefit evaluation.

[0042] Furthermore, the present application also includes the following steps:

[0043] Extract the first analysis particle and the second analysis particle corresponding to the maximum and minimum ordinate values ​​of the multiple analysis particles, calculate the ordinate difference between the first analysis particle and the second analysis particle, and obtain the starting ordinate value; take a straight line passing through the starting ordinate value and parallel to the abscissa axis of the two-dimensional deviation trend analysis space as the starting straight line; in the two-dimensional deviation trend analysis space, perform iterative analysis on the starting straight line in a first direction and a second direction according to a preset moving step size, respectively, to determine a target upward straight line and a target downward straight line, wherein the first direction is above the starting straight line and the second direction is below the starting straight line; perform mean calculation on the ordinates of multiple analysis particles in the space between the target upward straight line and the target downward straight line, and determine the system power supply deviation factor.

[0044] Specifically, the multiple analysis particles are subjected to a centralized trend analysis in the two-dimensional deviation trend analysis space, and the specific steps of determining the system power supply deviation factor include: extracting the maximum value of the ordinate among the multiple analysis particles and recording it as the first analysis particle, and extracting the minimum value of the ordinate and recording it as the second analysis particle. The first analysis particle represents the maximum value of the power supply deviation, while the second analysis particle corresponds to the minimum value. By calculating the difference between the ordinates of the first analysis particle and the second analysis particle, the starting ordinate value can be obtained, which reflects the overall fluctuation range of the power supply deviation. Next, a straight line parallel to the horizontal axis of the two-dimensional deviation trend analysis space is drawn with the starting ordinate value as a constraint, which is called the starting straight line. This straight line is used as a reference line in the analysis to help identify the changing trend of the power supply deviation.

[0045] In the two-dimensional deviation trend analysis space, the starting straight line is iteratively analyzed according to the preset moving step, and moves upward and downward respectively to form a target upward straight line and a target downward straight line. Here, the first direction represents the top of the starting straight line, and the second direction represents the bottom. For example, if the set moving step is 10MWh, the target upward straight line may be the starting straight line plus 10MWh, and the target downward straight line is the starting straight line minus 10MWh. Among them, the preset moving step is set by the professional and technical personnel in this field. For example, the minimum ordinate difference between any two particles in the multiple analysis particles can be used as the preset moving step. By calculating the mean of the ordinates of multiple analysis particles in the space between the target upward straight line and the target downward straight line, the system power supply deviation factor can be determined. Specifically, the average value of the ordinates of all analysis particles in the space between the target upward straight line and the target downward straight line can be calculated to reflect the overall stability of the power supply capacity and the degree of power supply deviation. The system power supply deviation factor can quantify the relationship between the power supply capacity and demand of the power system under specific conditions, provide data support for benefit evaluation, and improve the reliability of the overall benefit evaluation.

[0046] Furthermore, the present application also includes the following steps:

[0047] Move the starting straight line in a first direction by a preset moving step length to obtain a first upward straight line; count the number of multiple analysis particles located between the first upward straight line and the starting straight line to obtain a first upward particle quantity; iterate the first upward straight line in the first direction again according to the preset moving step length to obtain a second upward straight line; count the number of multiple analysis particles located between the first upward straight line and the second upward straight line to obtain a second upward particle quantity; determine whether the difference between the second upward particle quantity and the first upward particle quantity is less than or equal to the preset difference, if not, continue to iterate the second upward straight line in the first direction according to the preset moving step length; if so, stop the iteration and use the second upward straight line as the target upward straight line; iteratively analyze the starting straight line in the second direction according to the preset moving step length to obtain the target downward straight line.

[0048] Specifically, first, the starting straight line is moved in the first direction by a preset moving step length to obtain a first upward straight line. The upward movement of this straight line reflects the change in the upper limit of the power supply deviation. For example, if the ordinate value of the starting straight line is 90MWh and the set moving step length is 10MWh, the ordinate of the first upward straight line is 100MWh. Next, it is necessary to count the number of multiple analysis particles located between the first upward straight line and the starting straight line. These particles represent the power supply deviation in this area. Assuming that 20 analysis particles are found within this range, the first upward particle quantity is 20. Then, the first upward straight line is iterated upward again according to the preset moving step length to obtain a second upward straight line. It continues to move up by 10MWh, and the ordinate of the second upward straight line is 110MWh. At this time, the number of analysis particles located between the first upward straight line and the second upward straight line is counted again. Assuming that the number obtained this time is 21, the second upward particle quantity is 22. Next, it is determined whether the difference between the second upward particle amount and the first upward particle amount is less than or equal to the preset difference. If the difference between the second upward particle amount and the first upward particle amount is less than or equal to the preset difference, the iteration is stopped, and the second upward straight line is regarded as the target upward straight line, which will provide a new reference point for subsequent analysis. The preset difference is a condition for determining whether to stop the iteration, which is set by professional and technical personnel in this field and is generally a very small value.

[0049] Finally, the same method is used to iteratively analyze the starting straight line according to the preset moving step and the second direction, and move downward to obtain the target downward moving straight line. This target downward moving straight line will define an analysis area of ​​power supply deviation together with the target upward moving straight line, which is convenient for subsequent analysis of the stability and effectiveness of power supply capacity. Through this series of steps, the upper and lower limits of power supply deviation can be clearly drawn, providing the necessary basic data for further power supply deviation factor analysis, thereby improving the accuracy of benefit evaluation.

[0050] Further, step five of this application includes:

[0051] Obtain cost-effectiveness indicators, wherein the cost-effectiveness indicators include the operation and maintenance cost of a hydropower station, the operation and maintenance cost of a photovoltaic power station, power generation income, internal rate of return and payback period; obtain energy utilization efficiency indicators, wherein the energy utilization efficiency indicators include water energy utilization rate / water energy utilization improvement rate, new energy consumption rate, new energy output ratio, new energy power generation ratio, new energy effective utilization rate, and power generation water consumption rate; obtain system performance stability indicators, wherein the system performance stability indicators include dispatch response time, load tracking capability, spare capacity, line load rate, system availability, and equipment failure rate; obtain system volatility indicators, wherein the volatility indicators include residual load power fluctuation, residual load peak-valley difference, peak-valley difference rate, and output volatility rate; use the cost-effectiveness indicator, energy utilization efficiency indicator, system performance stability indicator and system volatility indicator as the preset indicator set.

[0052] Specifically, the cost-effectiveness indicators include the operation and maintenance costs of hydropower stations, the operation and maintenance costs of photovoltaic power stations, power generation income, internal rate of return and investment payback period. Among them, the operation and maintenance costs of hydropower stations refer to the fixed and variable costs required for the operation and maintenance of hydropower stations, including equipment maintenance, staff salaries, water resource costs, etc.; the operation and maintenance costs of photovoltaic power stations refer to the costs of cleaning, testing, component replacement, etc. involved in the maintenance of photovoltaic power stations; power generation income refers to the economic return obtained through electricity sales; the internal rate of return refers to the financial indicator for measuring project returns, reflecting the efficiency of investment returns; the investment payback period refers to the time required for the project to recover the initial investment, which is used to judge the economic feasibility of the project.

[0053] Energy efficiency indicators include water energy utilization rate / water energy utilization improvement rate, new energy consumption rate, new energy output ratio, new energy power generation ratio, new energy effective utilization rate, and power generation water consumption rate. Among them, water energy utilization rate / water energy utilization improvement rate is used to measure the power generation conversion efficiency of water resources and its optimization degree; new energy consumption rate is used to evaluate the power generation system's acceptance and utilization capacity of new energy. The new energy output ratio refers to the proportion of new energy power generation in total power generation. The new energy power generation ratio refers to the ratio of new energy power generation to total power generation within a certain period of time, and also includes the new energy access rate and comprehensive line loss rate. The new energy effective utilization rate refers to the ratio of the actual output of new energy power generation to the theoretical power generation. The power generation water consumption rate refers to the amount of water resources consumed per unit of electricity, reflecting the resource utilization efficiency of the hydropower station.

[0054] The system performance stability indicators include dispatch response time, load tracking capability, spare capacity, line load rate, system availability, and equipment failure rate. Among them, dispatch response time refers to the response speed of the power station to load changes; load tracking capability refers to the ability to meet changes in user demand; spare capacity refers to the additional power generation capacity available when power demand increases; line load rate refers to the ratio of the actual load of the transmission line to the designed capacity; system availability refers to the proportion of system equipment in an available state within a period of time; equipment failure rate refers to the frequency of equipment failures during operation, reflecting the reliability of the equipment.

[0055] System volatility indicators include residual load power fluctuation, residual load peak-to-valley difference, peak-to-valley difference rate, and output fluctuation rate. Among them, residual load power fluctuation refers to the fluctuation range of excess power generation; residual load peak-to-valley difference refers to the difference between the peak value and valley value of the power supply surplus, the smaller the better; peak-to-valley difference rate refers to the ratio of the peak-to-valley difference to the average value, indicating the degree of fluctuation; output fluctuation rate refers to the rate and amplitude of change of power generation output.

[0056] The above-mentioned cost-effectiveness indicators, energy utilization efficiency indicators, system performance stability indicators and system volatility indicators are included in the preset indicator set to provide basic data for a comprehensive evaluation of the system's operation, revenue, stability and volatility.

[0057] Furthermore, step six of this application includes:

[0058] A plurality of sample system power supply deviation factors, a plurality of sample hydropower station power generation costs, a plurality of sample photovoltaic power station power generation costs, a plurality of sample hydropower station revenues and a plurality of sample photovoltaic power station revenues, as well as a plurality of sample target revenue comprehensive evaluation results are collected as sample data sets; a convolutional neural network is used as a framework, and the framework is supervised and trained using the sample data set, and the framework parameters are adjusted according to the training results until convergence, so as to obtain the trained revenue evaluation network layer.

[0059] Specifically, when establishing the benefit evaluation network layer, it is first necessary to collect multiple sample data, including multiple sample system power supply deviation factors, multiple sample hydropower station power generation costs, multiple sample photovoltaic power station power generation costs, multiple sample hydropower station benefits, multiple sample photovoltaic power station benefits, and multiple sample target benefit comprehensive evaluation results corresponding to these sample data. These data will form a sample data set as the basis for training the convolutional neural network. Next, supervised training is performed using the convolutional neural network as a framework. The convolutional neural network is a deep learning model that is particularly suitable for processing structured data and can automatically extract features from the data through the convolutional layer. During the training process, the sample data set is divided into a training set and a validation set, for example, divided in a ratio of 3:2. The training set is used to adjust the network parameters, and the validation set is used to evaluate the model performance.

[0060] In the initial stage of training, the weight parameters of the network are randomly initialized. Then, the sample data is input into the network, the output of the model is calculated and compared with the comprehensive evaluation results of the sample target benefits to obtain the loss value. The back propagation algorithm is used to calculate the gradient of the loss value relative to the network parameters and update the network parameters. This process will be iterated continuously until the loss value converges, that is, the output of the model stabilizes within an acceptable range. For example, the loss value drops from the initial 1.5 to 0.01, indicating that the model has fitted the training data well. Finally, the trained benefit evaluation network layer will be able to output the corresponding target benefit comprehensive evaluation results based on the input power supply deviation factor, power generation cost and benefit data, providing model support for benefit evaluation.

[0061] In summary, the comprehensive evaluation method for a watershed cascade water-photovoltaic complementary system provided in this application has the following technical effects:

[0062] The target river basin cascade hydropower stations and photovoltaic power stations are obtained, wherein the cascade hydropower stations include K hydropower stations; the K hydropower stations and photovoltaic power stations are traversed in a preset window to collect simultaneous power generation monitoring data, including K hydropower station time series monitoring data sequences and photovoltaic power station time series monitoring data sequences, and the photovoltaic power station time series monitoring data and the hydropower station time series monitoring data are in a many-to-one mapping relationship; the K hydropower station time series monitoring data sequences and the photovoltaic power station time series monitoring data sequences are simultaneously extracted with power generation as an index to obtain a water-photovoltaic complementary power generation sequence; the demand load sequence of the preset window is obtained. The power supply deviation trend analysis is performed in combination with the water-photovoltaic complementary power generation sequence to determine the system power supply deviation factor; the water-photovoltaic complementary system operation data of the K hydropower stations and the photovoltaic power stations in the preset window are collected according to the preset indicator set, and the power generation cost and benefit analysis is performed according to the collection results to obtain the power generation cost of the K hydropower stations, the power generation cost of the photovoltaic power stations, the benefits of the K hydropower stations and the benefits of the photovoltaic power stations; the benefit evaluation network layer is called to analyze the system power supply deviation factor, the power generation cost of the K hydropower stations, the power generation cost of the photovoltaic power stations, the benefits of the K hydropower stations and the benefits of the photovoltaic power stations to determine the comprehensive evaluation result of the target benefit. By collecting the power generation monitoring data of K hydropower stations and photovoltaic power stations, performing power supply deviation analysis in combination with the demand load sequence, determining the system power supply deviation factor, analyzing the power generation cost and benefit at the same time, and using the benefit evaluation network layer to calculate the comprehensive evaluation result of the target benefit, the technical effect of improving the accuracy of the benefit evaluation of the water-photovoltaic complementary system is achieved.

[0063] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0064] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A comprehensive evaluation method for a watershed cascade water-photovoltaic complementary system, characterized in that: The comprehensive evaluation method of the basin cascade water-photovoltaic complementary system comprises: Acquire the cascade hydropower stations and photovoltaic power stations in the target river basin, wherein the cascade hydropower stations in the target river basin include K hydropower stations; Traversing the K hydropower stations and photovoltaic power stations in a preset window to collect simultaneous power generation monitoring data, including K hydropower station time series monitoring data sequences and photovoltaic power station time series monitoring data sequences, and the photovoltaic power station time series monitoring data and the hydropower station time series monitoring data are in a many-to-one mapping relationship; Taking power generation as an index, performing simultaneous sequence extraction on the K hydropower station time series monitoring data sequences and the photovoltaic power station time series monitoring data sequences to obtain a hydro-photovoltaic complementary power generation sequence; Obtaining the demand load sequence of the preset window, performing power supply deviation trend analysis in combination with the hydro-photovoltaic complementary power generation sequence, and determining the system power supply deviation factor; Collect the operation data of the water-photovoltaic complementary system of the K hydropower stations and the photovoltaic power station within the preset window according to the preset indicator set, and perform power generation cost and benefit analysis based on the collected results to obtain the power generation cost of the K hydropower stations, the power generation cost of the photovoltaic power station, the benefits of the K hydropower stations, and the benefits of the photovoltaic power station; The benefit evaluation network layer is called to analyze the system power supply deviation factor, the power generation cost of the K hydropower stations, the power generation cost of the photovoltaic power station, the benefits of the K hydropower stations and the benefits of the photovoltaic power station to determine the comprehensive evaluation result of the target benefit.

2. A comprehensive evaluation method for a watershed cascade water-photovoltaic complementary system as claimed in claim 1, characterized in that: Obtaining the demand load sequence of the preset window, performing power supply deviation trend analysis in combination with the hydro-photovoltaic complementary power generation sequence, and determining the system power supply deviation factor, including: Traversing the demand load sequence and the hydro-photovoltaic complementary power generation sequence to calculate the power supply deviation difference, and obtaining a power supply deviation difference sequence; Based on the power supply deviation difference sequence, a two-dimensional deviation trend analysis space is constructed, wherein the horizontal axis of the two-dimensional deviation trend analysis space is time, the vertical axis is the power supply deviation difference, and the two-dimensional deviation trend analysis space includes a plurality of analysis particles, each analysis particle corresponds to a power supply deviation difference; A central tendency analysis is performed on the plurality of analysis particles in the two-dimensional deviation trend analysis space to determine the system power supply deviation factor.

3. A comprehensive evaluation method for a watershed cascade water-photovoltaic complementary system as claimed in claim 2, characterized in that: include: Extracting a first analysis particle and a second analysis particle corresponding to a maximum ordinate value and a minimum ordinate value from the plurality of analysis particles, calculating a ordinate difference between the first analysis particle and the second analysis particle, and obtaining a starting ordinate value; A straight line passing through the starting ordinate value and parallel to the abscissa axis of the two-dimensional deviation trend analysis space is used as the starting straight line; In the two-dimensional deviation trend analysis space, the starting straight line is iteratively analyzed in a first direction and a second direction according to a preset moving step length to determine a target upward straight line and a target downward straight line, wherein the first direction is above the starting straight line and the second direction is below the starting straight line; The vertical coordinates of a plurality of analysis particles in the space between the target upward movement straight line and the target downward movement straight line are averaged to determine the system power supply deviation factor.

4. A comprehensive evaluation method for a watershed cascade water-photovoltaic complementary system as claimed in claim 3, characterized in that: include: Moving the starting straight line in a first direction by a preset moving step length to obtain a first upward moving straight line; Counting the number of a plurality of analysis particles located between the first upward moving straight line and the starting straight line to obtain a first upward moving particle quantity; Iterating the first upward straight line in the first direction again according to the preset moving step length to obtain a second upward straight line; Counting the number of a plurality of analysis particles located between the first upward moving straight line and the second upward moving straight line to obtain a second upward moving particle quantity; Determine whether the difference between the second amount of particles moved upward and the first amount of particles moved upward is less than or equal to a preset difference, and if not, continue to iterate the second upward straight line in the first direction according to the preset moving step; If yes, the iteration is stopped, and the second upward moving straight line is used as the target upward moving straight line; The starting straight line is iteratively analyzed in the second direction according to the preset moving step length to obtain the target downward moving straight line.

5. A comprehensive evaluation method for a watershed cascade water-photovoltaic complementary system as claimed in claim 1, characterized in that: include: Acquire K layout positions of the K hydropower stations, and arrange the K hydropower stations in a direction of water flow from high to low according to the K layout positions and the water flow direction of the target watershed, to obtain layout serial numbers of the K hydropower stations; Based on the sizes of the layout numbers of the K hydropower stations, determining K impact neighborhoods and K neighborhood impact weight sets of the K hydropower stations; Performing a reliability analysis of the hydropower station according to the K influencing neighborhoods and the K neighborhood influence weight sets, and the K hydropower station time series monitoring data sequences, and determining the K hydropower station reliability factors; Based on the K hydropower station reliability factors, the K hydropower station time series monitoring data sequences are corrected to obtain K corrected hydropower station time series monitoring data sequences; The K modified hydropower station time series monitoring data sequences and the photovoltaic power station time series monitoring data sequences are simultaneously extracted with power generation as an index, and the hydro-photovoltaic complementary power generation sequence is updated according to the extraction results.

6. A comprehensive evaluation method for a watershed cascade water-photovoltaic complementary system as claimed in claim 5, characterized in that: include: Traversing the K hydropower station time series monitoring data sequences to perform data fluctuation analysis and obtain the K hydropower station monitoring fluctuation coefficients; Mapping and matching the K hydropower station monitoring fluctuation coefficients based on the K influencing neighborhoods to obtain a set of K influencing hydropower station monitoring fluctuation coefficients; The K sets of fluctuation coefficients influencing the monitoring of the hydropower station are weightedly calculated based on the K sets of neighborhood influence weights to obtain the reliability factors of the K hydropower stations.

7. A comprehensive evaluation method for a watershed cascade water-photovoltaic complementary system as claimed in claim 1, characterized in that: The K hydropower station time series monitoring data sequences and the photovoltaic power station time series monitoring data sequences are simultaneously extracted with power generation as an index to obtain a hydro-photovoltaic complementary power generation sequence, including: Extracting the power generation of the K hydropower station time series monitoring data sequences and the photovoltaic power station time series monitoring data sequences under the first time series, and obtaining the power generation of the K first time series hydropower stations and the first time series photovoltaic power stations; The power generation of the K first-time-sequence hydropower stations and the power generation of the first-time-sequence photovoltaic power stations are superimposed to obtain the hydro-photovoltaic complementary power generation sequence.

8. A comprehensive evaluation method for a watershed cascade water-photovoltaic complementary system as claimed in claim 1, characterized in that: include: Collect multiple sample system power supply deviation factors, multiple sample hydropower station power generation costs, multiple sample photovoltaic power station power generation costs, multiple sample hydropower station benefits, multiple sample photovoltaic power station benefits, and multiple sample target benefit comprehensive evaluation results as sample data sets; The convolutional neural network is used as a framework, and the sample data set is used to perform supervised training on the framework. The framework parameters are adjusted according to the training results until convergence, thereby obtaining the trained revenue evaluation network layer.

9. A comprehensive evaluation method for a watershed cascade water-photovoltaic complementary system as claimed in claim 1, characterized in that: include: Obtaining cost-effectiveness indicators, wherein the cost-effectiveness indicators include hydropower station operation and maintenance costs, photovoltaic power station operation and maintenance costs, power generation income, internal rate of return and investment payback period; Obtaining energy utilization efficiency indicators, wherein the energy utilization efficiency indicators include water energy utilization rate / water energy utilization improvement rate, new energy consumption rate, new energy output ratio, new energy power generation ratio, new energy effective utilization rate, and power generation water consumption rate; Obtaining system performance stability indicators, wherein the system performance stability indicators include dispatch response time, load tracking capability, spare capacity, line load rate, system availability, and equipment failure rate; Obtaining system volatility indicators, wherein the volatility indicators include residual load power fluctuation, residual load peak-to-valley difference, peak-to-valley difference rate, and output volatility rate; The cost-effectiveness index, the energy utilization efficiency index, the system performance stability index and the system volatility index are used as the preset index set.

Images