Hydropower dispatching optimization method and system considering cascade reservoir group coupling

Abstract

The invention relates to the technical field of reservoir scheduling, solves the technical problems that in the prior art, energy consumption of hydropower scheduling of a reservoir group is large, and an analysis result is not an optimal strategy, and particularly relates to a hydropower scheduling optimization method and system considering cascade reservoir group coupling. The method comprises the following steps: S1, acquiring a power generation function Emax of each hydropower station in the cascade reservoir group, and constraining related variables of the power generation function Emax to obtain a constraint condition set; according to the method, the power generation condition of the cascade reservoir group is comprehensively obtained through multiple limiting conditions, the water level and the power generation amount of the reservoir are more comprehensively measured, the optimal power generation strategy can be obtained, the influence of the water level of the reservoir group on the ecology can be monitored, and the power generation efficiency of the cascade reservoir group is improved. The survival condition of animals and plants around the reservoir is ensured, and the efficiency of reservoir group scheduling is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of reservoir dispatching, and in particular to a hydropower dispatching optimization method and system considering the coupling of cascade reservoir groups. Background Art

[0002] A cascade reservoir group generally refers to a series of stepped reservoirs and hydropower stations built from the upstream to the downstream of a river or a river section in a water conservancy and hydropower development plan in order to make full use of water conservancy and hydropower resources. The group formed is a cascade reservoir group. The hydropower scheduling of the cascade reservoir group not only affects the power generation and power generation efficiency, but also has an important impact on the ecology of the environment on both sides of the river. If the scheduling is unbalanced, it is easy to cause ecological environmental damage, seriously affecting the lives of residents and the growth and survival of surrounding animals and plants. The existing hydropower scheduling optimization method of cascade reservoir group coupling is generally carried out through a variety of sensors. However, this method is prone to complex detection equipment, difficult maintenance and huge energy consumption when scheduling multiple reservoirs. For the intelligent analysis model using population algorithm, since only the optimization strategy in the same iteration is considered in the analysis process, and no reference is made to all optimization strategies, the selected optimization strategy is not the optimal strategy. Summary of the invention

[0003] In view of the shortcomings of the prior art, the present invention provides a hydropower scheduling optimization method and system taking into account the coupling of cascade reservoir groups, which solves the technical problems in the prior art that the energy consumption of hydropower scheduling of reservoir groups is high and the analysis results are not optimal strategies, and achieves the purpose of obtaining the optimal scheduling strategy and reducing energy consumption through diversified calculations.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a hydropower dispatch optimization method considering the coupling of cascade reservoir groups, the method comprising the following steps:

[0005] S1. Obtain the power generation function E of each hydropower station in the cascade reservoir group max , and the power generation function E max Constrain the relevant variables to obtain the constraint condition set;

[0006] S2. Take each hydropower station as a sample, divide multiple samples and initialize them respectively to obtain the first sample group And the second sample group

[0007] S3. Calculate the sample balance Ph according to the constraint set g ;

[0008] S4, according to the balance Ph g Calculate the weight coefficient w for each sample j , and determine the first initial optimal set and the second initial preference set

[0009] S5. Perform a diversification operation on the neighborhood of each sample in the first initial preference set and the second initial preference set to obtain a diversified sample set

[0010] S6. Calculate the preference degree of the diversified sample set and, based on the preference degree replace the samples in the first sample group and the second sample group to obtain the optimal set Z;

[0011] S7. Obtain the iteration threshold X through the maximum likelihood estimation method based on the historical data of the hydropower station, and perform iteration on the optimal set Z;

[0012] If k + 1 = X, end the iteration and obtain the optimal scheduling strategy based on the optimal set Z;

[0013] If k + 1 < X, return to step S3.

[0014] Preferably, in step S1, the specific implementation steps are as follows:

[0015] S11. Obtain the relevant variables of each hydropower station in the cascade reservoir group at different time periods t after preprocessing. The relevant variables include the output coefficient A a , the generated flow rate L a，t , the water head H a，t and the number of hours t j ;

[0016] S12. Calculate the power generation function E max according to the relevant variables. The calculation formula is:

[0017]

[0018] where A a represents the output coefficient of the ath hydropower station, L a，t represents the generated flow rate of the ath hydropower station in the tth time period, H a，t represents the water head of the ath hydropower station in the tth time period, and t j represents the jth number of hours;

[0019] S13. Define the constraint conditions for the generated flow rate L a，t and the water head H a，t . The expression is:

[0020] ​

[0021] in, and L a，t They represent the upper and lower limits of the power generation flow of the a-th hydropower station in the t-th time period, and H a，t They represent the upper and lower limits of the water head of the a-th hydropower station in the t-th time period;

[0022] S14, the constraints on the relevant variables also include the water level SW a，t Water level constraints and hydropower bandwidth DK a，t The bandwidth constraint is generated and the constraint condition set is expressed as:

[0023]

[0024] in, and SW a，t They represent the upper and lower limits of the water level of the a-th hydropower station in the t-th time period, and DK a，t They respectively represent the upper and lower limits of the hydropower bandwidth of the a-th hydropower station in the t-th time period.

[0025] Preferably, in step S2, the specific implementation steps are as follows:

[0026] S21. Obtain the power generation benefit DY of each sample b , calculate the power generation benefit DY b The average The calculation formula is:

[0027]

[0028] in, Indicates power generation efficiency DY b The average value, DY b represents the bth power generation benefit, n represents the power generation benefit DY b the number of

[0029] S22, based on the average And sample DY b Divide multiple samples;

[0030] like It is divided into the first sample set;

[0031] like It is divided into the second sample set;

[0032] S23, obtaining the data quantity E of the first sample set by counting method c and the number of data in the second sample set E d ;

[0033] S24, respectively calculate the decision values ​​of the upper and lower limits of the data in the relevant variables and Jc f , the calculation formula is as follows:

[0034]

[0035] in, and Jc f Respectively represent the decision values ​​of the upper and lower limits of the data in the relevant variables;

[0036] S25, performing initialization operation on the first sample set and the second sample set to obtain a first sample group And the second sample group The expression is:

[0037]

[0038] in, represents the e-th sample in the k-th iteration of the first sample group, represents the fth sample in the kth iteration of the second sample group, β 1 and β 2 They represent random numbers uniformly distributed in the interval [0,1].

[0039] Preferably, in step S3, the specific implementation steps are as follows:

[0040] S31, arbitrarily select a time period t d , get time period t d The values ​​within the internal constraint set, including the generation flow Water head Water Level and hydropower bandwidth

[0041] S32. Obtain different balance factors B beyond the constraint set through regularization method cm ;

[0042] like or Then get the balance factor B c1 ;

[0043] like or Then get the balance factor B c2 ;

[0044] like or Then get the balance factor B c3 ;

[0045] like or Then get the balance factor B c4 ;

[0046] S33, the first sample group And the second sample group The union of The expression is:

[0047]

[0048] in, Represents a sample of the population.

[0049] S34, according to the power generation function E max Calculate the overall sample with multiple balance factors The balance degree Ph of each sample in g , the calculation formula is:

[0050]

[0051] Among them, Ph g Indicates the balance of the sample, B cm represents the mth balance factor, The relevant variable value of the sample that exceeds the constraint condition, M represents the balance factor B cm The number of

[0052] Preferably, in step S4, the specific implementation steps are as follows:

[0053] S41, according to the balance Ph g Calculate the overall sample The weight coefficient w of each sample in j , the calculation formula is as follows:

[0054]

[0055] Among them, w j Represents the overall sample The weight coefficient of each sample in It represents the balance degree of the hth sample in the kth iteration of the total sample. Min and max represent the minimum and maximum values ​​selected from multiple balance degrees respectively.

[0056] S42. In the overall sample According to the balance Ph g Determine the optimal sample The expression is:

[0057]

[0058] in, Represents the overall sample Medium Balance Ph g The largest sample;

[0059] S43. In the overall sample First, randomly select a sample as the central sample

[0060] S44, in the center sample Determine a distance center sample nearby Recent reference samples

[0061] S45. For the first sample group And the second sample group According to the balance Ph g Sort them in descending order and set the balance Ph g The largest 50% is used as the first initial preferred set and the second initial priority set

[0062] Preferably, in step S5, the specific implementation steps are as follows:

[0063] S51, calculate the optimal samples respectively and center sample Perception coefficient V a and V b , the calculation formula is:

[0064]

[0065] Among them, V a and V b Represent the optimal samples and center sample The perception coefficient, and Represent the optimal samples and reference samples The Euclidean distance of and reference samples The Euclidean distance of

[0066] S52, obtain a uniformly distributed random threshold Q between [0,1] through a random number generator f and the random number g 1 , g 2 , g 3 and g 4 ;

[0067] S53, the first initial optimal set Perform diversified operations;

[0068] If g 4 ≤Q f , the calculation formula is:

[0069]

[0070] in, represents the first initial optimal set after the diversification operation;

[0071] If g 4 >Q f , the calculation formula is:

[0072]

[0073] Among them, g 1 , g 2 , g 3 and g 4 Respectively represent random numbers between [0,1];

[0074] S54, for the second initial priority set Perform diversified operations;

[0075] If g 4 ≤Q f , the calculation formula is:

[0076]

[0077] in, represents the second initial optimal set after the diversification operation;

[0078] If g 4 >Q f , the calculation formula is:

[0079]

[0080] Among them, V a and V b Represent the optimal samples and center sample Perception coefficient;

[0081] S55, based on the first initial optimal set after the diversified operation and the second initial preferred set Get a diverse sample set

[0082] Preferably, in step S6, the specific implementation steps are as follows:

[0083] S61, according to the balance Ph gThe calculation formula for calculating the diversified sample set The preference of each sample in The calculation formula is:

[0084]

[0085] in, Represents a diverse sample set The preference degree, E dy Representation and Diversified Sample Sets The corresponding power generation function, B dy Representation and Diversified Sample Sets The corresponding balance factor, u represents the balance factor B dy the number of

[0086] S62, according to the preference For the overall sample The samples are replaced;

[0087] like but It is not the optimal value, replace the corresponding overall sample

[0088] like but is the optimal value, not the overall sample To carry out replacement;

[0089] S63, repeat step S62 until the total sample All samples in are replaced and the optimal set Z is obtained.

[0090] Preferably, the specific content of step S7 is: the samples in the optimal set Z are sorted according to the degree of preference. Arrange from large to small, and select The largest sample is taken as the optimal scheduling strategy.

[0091] The technical solution also provides a system for hydropower dispatch optimization method, the system comprising:

[0092] The power generation constraint module is used to obtain the power generation function E of each hydropower station in the cascade reservoir group. max , and the power generation function E max Constrain the relevant variables to obtain the constraint condition set;

[0093] The initialization module is used to take each hydropower station as a sample, divide multiple samples and initialize them separately to obtain the first sample group And the second sample group

[0094] The balance module is used to calculate the balance Ph of the sample according to the constraint set. g ;

[0095] The initial optimization module is used to select the optimal balance according to the degree of balance Ph. g Calculate the weight coefficient w for each sample j , and determine the first initial optimal set and the second initial priority set

[0096] A diversification module is used to select the first initial optimal set and the second initial priority set Each sample in the neighborhood performs a diversification operation and obtains a diversified sample set

[0097] The most optimized module for computing diverse sample sets The preference And according to the preference For the first sample group And the second sample group The samples are replaced and the optimal set Z is obtained;

[0098] The iteration module is used to obtain the iteration threshold X through the maximum likelihood estimation method according to the historical data of the hydropower station, and iterate the optimal set Z.

[0099] By means of the above technical solution, the present invention provides a method and system for optimizing hydropower dispatching considering the coupling of cascade reservoir groups, which has at least the following beneficial effects:

[0100] 1. The present invention calculates the degree of balance through multiple constraints, and can obtain the power generation situation of the cascade reservoir group in an all-round way, measure the reservoir water level and power generation more comprehensively, and facilitate the control of the ecological environment around the reservoir group by controlling the power generation and water level. It can not only obtain the optimal power generation strategy, but also monitor the impact of the water level of the reservoir group on the ecology, ensure the survival of animals and plants around the reservoir, and improve the efficiency of reservoir group scheduling.

[0101] 2. By performing diversified operations on the reservoir group, the present invention can make the balance of the reservoir group refer not only to the data of samples in the same set, but also to the sample data of the whole set, thereby accelerating the convergence of the model to the optimal solution. While improving the data diversification and globality of the reservoir group, it can also improve the speed of obtaining the optimal strategy and shorten the time of obtaining the optimal strategy.

[0102] 3. The present invention can screen and optimize samples with lower preference by calculating and replacing the preference of diversified samples, so that the optimization strategy after each iteration replaces the strategy with lower preference, so as to quickly obtain the optimal set and improve the work efficiency of obtaining the optimal strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0103] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0104] Figure 1 A flow chart of a hydropower dispatch optimization method considering coupling of cascade reservoir groups according to the present invention;

[0105] Figure 2 This is a structural block diagram of a hydropower dispatch optimization system considering the coupling of cascade reservoir groups according to the present invention. DETAILED DESCRIPTION

[0106] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific implementation methods, so that the implementation process of how the present application uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly.

[0107] Due to the technical problems of high energy consumption and non-optimal analysis results of hydropower dispatching in existing technologies for reservoir groups, please refer to Figure 1 and Figure 2 This embodiment provides a hydropower dispatch optimization method considering the coupling of cascade reservoir groups, which can obtain the optimal dispatch strategy and reduce energy consumption through diversified calculations. The method includes the following steps:

[0108] S1. Obtain the power generation function E of each hydropower station in the cascade reservoir group max , and the power generation function E max The constraints on the relevant variables are obtained to obtain the constraint condition set; in the calculation of power generation, it is also necessary to consider factors such as water level and flow rate related to power generation and ecological factors. In step S1, the specific implementation steps are as follows:

[0109] S11, obtain the relevant variables of each hydropower station in the cascade reservoir group after preprocessing in different time periods t, the relevant variables include the output coefficient A a , power generation flow L a，t , water head H a，t and hours t jThe output coefficient refers to the ratio of the average total output power of a unit or power station to the rated power of the unit or power station during the statistical period; the power generation flow rate refers to the amount of water used for power generation per unit time; the head refers to the mechanical energy of unit weight of water at any section of the water flow; the number of hours is generally one hour as a unit of measurement to measure related variables, and physical quantities of multiple different time periods can be generated in the measurement.

[0110] S12. Calculate the power generation function E based on relevant variables max , the calculation formula is:

[0111]

[0112] Among them, A a represents the output coefficient of the ath hydropower station, L a，t represents the power generation flow of the a-th hydropower station in the t-th time period, H a，t represents the water head of the a-th hydropower station in the t-th time period, t j represents the jth hour;

[0113] S13, power generation flow L a，t and water head H a，t To define the constraints, the expression is:

[0114]

[0115]

[0116] in, and L a，t They represent the upper and lower limits of the power generation flow of the a-th hydropower station in the t-th time period, and H a，t They represent the upper and lower limits of the water head of the a-th hydropower station in the t-th time period; the power generation flow L of the hydropower stations in multiple reservoir groups a，t and water head H a，t Conditions are limited. Once these conditions are exceeded, the balance factor will be used for calculation in the subsequent calculation steps. The setting of the condition range can be based on the historical power generation flow L of the hydropower station. a，t and water head H a，t As a reference, the scope was determined through the experience of local staff.

[0117] S14, the constraints on the relevant variables also include the water level SW a，t Water level constraints and hydropower bandwidth DK a，t The bandwidth constraint is generated and the constraint condition set is expressed as:

[0118]

[0119] in, and SW a，t They represent the upper and lower limits of the water level of the a-th hydropower station in the t-th time period, and DK a，t They represent the upper and lower limits of the hydropower bandwidth of the a-th hydropower station in the t-th time period, and the water level SW a，t Constraints and bandwidth DK for hydropower a，t Generally, the water level and hydropower bandwidth can affect the power generation situation, so the water level SW a，t and hydropower bandwidth DK a，t To constrain.

[0120] This embodiment constrains multiple physical quantities around the hydropower station to facilitate all-round detection of the overall situation of the reservoir group and the implementation of subsequent steps. By calculating the balance degree through multiple constraints, the power generation situation of the cascade reservoir group can be obtained in an all-round way, and the water level and power generation of the reservoir can be measured more accurately. It is also convenient to control the ecological environment around the reservoir group by controlling the power generation and water level. It can not only obtain the optimal power generation strategy, but also monitor the impact of the water level of the reservoir group on the ecology, ensure the survival of animals and plants around the reservoir, and improve the efficiency of reservoir group scheduling.

[0121] S2. Take each hydropower station as a sample, divide multiple samples and initialize them respectively to obtain the first sample group And the second sample group In order to enable the hydropower dispatching to be flexibly calculated and analyzed, multiple hydropower stations in the reservoir group are taken as samples. In step S2, the specific implementation steps are as follows:

[0122] S21. Obtain the power generation benefit DY of each sample b , calculate the power generation benefit DY b The average The calculation formula is:

[0123]

[0124] in, Indicates power generation efficiency DY b The average value, DY b represents the bth power generation benefit, n represents the power generation benefit DY b The power generation benefit generally refers to the economic value and social benefits created for the society by the hydropower station in providing electricity, electricity and other functions. The samples can be divided according to the power generation benefit.

[0125] S22, DY based on the average value b Divide multiple samples;

[0126] like It is divided into the first sample set;

[0127] like It is divided into the second sample set;

[0128] S23, obtaining the data quantity E of the first sample set by counting method c and the number of data in the second sample set F d ;

[0129] S24, respectively calculate the decision values ​​of the upper and lower limits of the data in the relevant variables and Jc f , the calculation formula is as follows:

[0130]

[0131] in, and Jc f They respectively represent the decision values ​​of the upper and lower limits of the data in the relevant variables; the decision values ​​of the upper and lower limits of the data are the average values ​​of the upper or lower limits of multiple relevant variables in the constraint set.

[0132] S25, performing initialization operation on the first sample set and the second sample set to obtain a first sample group And the second sample group The expression is:

[0133]

[0134] in, represents the e-th sample in the k-th iteration of the first sample group, represents the fth sample in the kth iteration of the second sample group, β 1 and β 2 They represent random numbers uniformly distributed in the interval [0,1]. Random numbers are generally generated by a random generator and meet the uniform distribution conditions.

[0135] This embodiment can divide the samples and initialize the sample group through this step, which is convenient for the calculation of the subsequent steps and improves the accuracy and calculation efficiency of the model.

[0136] S3. Calculate the sample balance Ph according to the constraint set g The balance degree is the power generation of the hydropower station under the constraints of the constraint condition set. According to the hydraulic connection from upstream to downstream, each hydropower station is adjusted and calculated in a water-based power-determining manner. During the processing, the constraints are constrained during the scheduling period. In step S3, the specific implementation steps are as follows:

[0137] S31, arbitrarily select a time period t d , get time period td The values ​​within the internal constraint set, including the generation flow Water head Water Level and hydropower bandwidth

[0138] S32. Obtain different balance factors B beyond the constraint set through regularization method cm ;

[0139] like or Then get the balance factor B c1 ;

[0140] like or Then get the balance factor B c2 ;

[0141] like or Then get the balance factor B c3 ;

[0142] like or Then get the balance factor B c4 ; If the condition is exceeded, it means that the amount of the item does not meet the requirement and needs to be adjusted through the balance factor. The balance factor is the penalty factor after the constraint is violated.

[0143] S33, the first sample group And the second sample group The union of The expression is:

[0144]

[0145] in, It means that the overall sample will merge the two sample groups to facilitate the calculation of balance.

[0146] S34, according to the power generation function E max Calculate the overall sample with multiple balance factors The balance degree Ph of each sample in g , the calculation formula is:

[0147]

[0148] Among them, Ph g Indicates the balance of the sample, B cm represents the mth balance factor, The relevant variable value of the sample that exceeds the constraint condition, M represents the balance factor B cm The number of

[0149] In this embodiment, the balance Ph g The calculation can link multiple constraints and make a more reasonable analysis of hydropower scheduling. By calculating the balance through multiple constraints, the power generation situation of the cascade reservoir group can be obtained in an all-round way, and the water level and power generation of the reservoir can be measured more comprehensively. It is also convenient to control the ecological environment around the reservoir group by controlling the power generation and water level. It can not only obtain the optimal power generation strategy, but also monitor the impact of the water level of the reservoir group on the ecology, ensure the survival of animals and plants around the reservoir, and improve the efficiency of reservoir group scheduling.

[0150] S4, according to the balance Ph g Calculate the weight coefficient w for each sample j , and determine the first initial optimal set and the second initial priority set Since the balance degree is not enough to conduct a deeper analysis on the dispatch of the hydropower station, in step S4, the specific implementation steps are as follows:

[0151] S41, according to the balance Ph g Calculate the overall sample The weight coefficient w of each sample in j , the calculation formula is as follows:

[0152]

[0153] Among them, w j Represents the overall sample The weight coefficient of each sample in It represents the balance degree of the hth sample in the kth iteration of the overall sample. Min and max represent the selection of the minimum and maximum values ​​among multiple balance degrees respectively. The weight coefficient of each sample is calculated through the balance degree, which is helpful for the calculation of subsequent steps.

[0154] S42. In the overall sample According to the balance Ph g Determine the optimal sample The expression is:

[0155]

[0156] in, Represents the overall sample Medium Balance Ph g The largest sample;

[0157] S43. In the overall sample First, randomly select a sample as the central sample

[0158] S44, in the center sample Determine a distance center sample nearby Recent reference samples

[0159] S45. For the first sample group And the second sample group According to the balance Ph g Sort them in descending order and set the balance Ph g The largest 50% is used as the first initial preferred set and the second initial priority set Here, the overall sample is divided twice to avoid ignoring some excellent samples. Analyzing the preferred samples can obtain better strategies.

[0160] S5. For the first initial optimal set and the second initial priority set Each sample in the neighborhood performs a diversification operation and obtains a diversified sample set Since the optimal sample analysis results are not extensive enough, it is necessary to perform diversified operations on the samples to improve the diversity of the samples. In step S5, the specific implementation steps are as follows:

[0161] S51, calculate the optimal samples respectively and center sample Perception coefficient V a and V b , the calculation formula is:

[0162]

[0163] Among them, V a and V b Represent the optimal samples and center sample The perception coefficient, and Represent the optimal samples and reference samples The Euclidean distance of and reference samples Euclidean distance; Euclidean distance generally refers to Euclidean metric or Euclidean distance, which is the true distance between two points in m-dimensional space. The desired result can be directly obtained through Euclidean distance, and Euclidean distance is a common distance calculation method, which will not be elaborated here.

[0164] S52, obtain a uniformly distributed random threshold Q between [0,1] through a random number generator f and the random number g1 , g 2 , g 3 and g 4 ; In order to increase the diversity of samples, random numbers can be used to assist in achieving this effect. The random number generator is a method that can obtain random numbers within a certain range. It can be implemented without additional steps and will not be elaborated here.

[0165] S53, the first initial optimal set Perform diversified operations;

[0166] If g 4 ≤Q f , the calculation formula is:

[0167]

[0168] in, represents the first initial optimal set after the diversification operation;

[0169] If g 4 >Q f , the calculation formula is:

[0170]

[0171] Among them, g 1 , g 2 , g 3 and g 4 Respectively represent random numbers between [0,1];

[0172] S54, for the second initial priority set Perform diversified operations;

[0173] If g 4 ≤Q f , the calculation formula is:

[0174]

[0175] in, represents the second initial optimal set after the diversification operation;

[0176] If g 4 >Q f , the calculation formula is:

[0177]

[0178] Among them, V a and V b Represent the optimal samples and center sample The perceptual coefficient of the image is 0.0447m / s. In the diversified operation, it includes both the situation of the current iterative sample and the situation of all samples, and can perform diversified operations comprehensively.

[0179] S55, based on the first initial optimal set after the diversified operation and the second initial preferred set Get a diverse sample set

[0180] This embodiment performs diversified operations on the reservoir group, so that the balance of the reservoir group not only refers to the data of samples in the same set, but also to the sample data of the whole set, thereby accelerating the convergence of the model to the optimal solution. While improving the data diversity and globality of the reservoir group, it can also improve the speed of obtaining the optimal strategy and shorten the time for obtaining the optimal strategy.

[0181] S6. Calculate the diverse sample set The preference And according to the preference For the first sample group And the second sample group The samples are replaced and the optimal set Z is obtained; since the situation of each sample changes after the diversification operation is completed, in step S6, the specific implementation steps are as follows:

[0182] S61, according to the balance Ph g The calculation formula for calculating the diversified sample set The preference of each sample in The calculation formula is:

[0183]

[0184] in, Represents a diverse sample set The preference degree, E dy Representation and Diversified Sample Sets The corresponding power generation function, B dy Representation and Diversified Sample Sets The corresponding balance factor, u represents the balance factor B dy The number of; Diversified sample sets are calculated by the balance formula Optimization And with preference For reference.

[0185] S62, according to the preference For the overall sample The samples are replaced;

[0186] like but Not the optimal value, replace the corresponding overall sample

[0187] If Then Is the optimal value, do not replace the overall sample For replacement;

[0188] S63. Repeat step S62 until all samples in the overall sample Are replaced, and the optimal set Z is obtained. Through the comparison and replacement of the preference degrees, the optimal selection of samples can be completed, and excellent samples can be left. Through this method, the screening and optimization of samples with lower preference degrees can be realized, so that the optimization strategy after each iteration replaces the strategy with lower preference degrees, so as to quickly obtain the optimal set and improve the working efficiency of obtaining the optimal strategy.

[0189] S7. Obtain the iteration threshold X through the maximum likelihood estimation method according to the historical data of the hydropower station, and perform iteration on the optimal set Z;

[0190] If k + 1 = X, end the iteration and obtain the optimal scheduling strategy based on the optimal set Z;

[0191] If k + 1 < X, return to step S3. The specific content of step S7 is: arrange the samples in the optimal set Z according to the preference degree From large to small, and take the sample with the largest preference degree As the optimal scheduling strategy. Here, since the number of iterations will not be greater than the iteration threshold X, there is no situation of k + 1 > X in the judgment step.

[0192] This embodiment can select the optimal samples in this way. The samples in this method represent the set of various physical quantities of the hydropower stations in the reservoir group. The optimal samples represent the optimal scheduling strategies of the hydropower stations. Through the calculation and replacement of the preference degrees of diverse samples, the screening and optimization of samples with lower preference degrees can be realized, so that the optimization strategy after each iteration replaces the strategy with lower preference degrees, so as to quickly obtain the optimal set and improve the working efficiency of obtaining the optimal strategy.

[0193] Please refer to Figure 2 , which shows the structural block diagram of the hydropower dispatch optimization system provided by this embodiment. The hydropower dispatch optimization system includes a power generation constraint module, an initialization module, a balance degree module, an initial preference module, a diversification module, an optimal selection module, and an iteration module.

[0194] The power generation constraint module is used to obtain the power generation function E of each hydropower station in the cascade reservoir group max , and for the power generation function E maxThe related variables are constrained to obtain a constraint condition set, and the initialization module is used to take each hydropower station as a sample, divide multiple samples and initialize them respectively to obtain a first sample group And the second sample group The balance module is used to calculate the balance Ph of the sample according to the constraint set. g , the initial optimization module is used to calculate the balance Ph g Calculate the weight coefficient w for each sample j , and determine the first initial optimal set and the second initial priority set A diversification module is used to select the first initial optimal set and the second initial priority set Each sample in the neighborhood performs a diversification operation and obtains a diversified sample set The most optimized module for computing diverse sample sets The preference And according to the preference For the first sample group And the second sample group The samples are replaced and the optimal set Z is obtained. The iteration module is used to obtain the iteration threshold X through the maximum likelihood estimation method according to the historical data of the hydropower station and iterate the optimal set Z.

[0195] Those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, so the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0196] The above implementation methods have been described in detail. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A hydropower dispatch optimization method considering the coupling of cascade reservoirs, characterized in that: The method includes the following steps: S1. Obtain the power generation function E of each hydropower station in the cascade reservoir group max , and the power generation function E max Constrain the relevant variables to obtain the constraint condition set; S2. Take each hydropower station as a sample, divide multiple samples and initialize them respectively to obtain the first sample group And the second sample group S3. Based on the first sample group And the second sample group Determine the overall sample And calculate the balance Ph of the sample according to the constraint set g ; S4, according to the balance Ph g Calculate the weight coefficient w for each sample j , and determine the first initial optimal set and the second initial priority set S5. For the first initial optimal set and the second initial priority set Each sample in the neighborhood performs a diversification operation and obtains a diversified sample set S6. Calculate the diverse sample set The preference And according to the preference For the first sample group And the second sample group The samples are replaced and the optimal set Z is obtained; S7. Obtain the iteration threshold X by the maximum likelihood estimation method based on the historical data of the hydropower station, and iterate on the optimal set Z; If k + 1 = X, end the iteration and obtain the optimal scheduling strategy based on the optimal set Z; If k + 1 < X, return to step S3.

2. The hydropower dispatch optimization method according to claim 1, characterized in that: In step S1, the specific implementation steps are as follows: S11, obtain the relevant variables of each hydropower station in the cascade reservoir group after preprocessing in different time periods t, the relevant variables include the output coefficient A a , power generation flow L a，t , water head H a，t and hours t j ; S12. Calculate the power generation function E based on relevant variables max , the calculation formula is: Among them, A a represents the output coefficient of the ath hydropower station, L a，t represents the power generation flow of the a-th hydropower station in the t-th time period, H a，t represents the water head of the a-th hydropower station in the t-th time period, t j represents the jth hour; S13, power generation flow L a，t and water head H a，t To define the constraints, the expression is: in, and L a，t They represent the upper and lower limits of the power generation flow of the a-th hydropower station in the t-th time period, and H a，t They represent the upper and lower limits of the water head of the a-th hydropower station in the t-th time period; S14, the constraints on the relevant variables also include the water level SW a，t Water level constraints and hydropower bandwidth DK a，t The bandwidth constraint is generated and the constraint condition set is expressed as: in, and SW a，t They represent the upper and lower limits of the water level of the a-th hydropower station in the t-th time period, and DK a，t They respectively represent the upper and lower limits of the hydropower bandwidth of the a-th hydropower station in the t-th time period.

3. The hydropower dispatch optimization method according to claim 1, characterized in that: In step S2, the specific implementation steps are as follows: S21. Obtain the power generation benefit DY of each sample b , calculate the power generation benefit DY b The average The calculation formula is: in, Indicates power generation efficiency DY b The average value, DY b represents the bth power generation benefit, n represents the power generation benefit DY b the number of S22, based on the average And sample DY b Divide multiple samples; like It is divided into the first sample set; like It is divided into the second sample set; S23, obtaining the data quantity E of the first sample set by counting method c and the number of data in the second sample set E d ; S24, respectively calculate the decision values ​​of the upper and lower limits of the data in the relevant variables and Jc f , the calculation formula is as follows: in, and Jc f Respectively represent the decision values ​​of the upper and lower limits of the data in the relevant variables; S25, performing initialization operation on the first sample set and the second sample set to obtain a first sample group And the second sample group The expression is: in, represents the e-th sample in the k-th iteration of the first sample group, represents the fth sample in the kth iteration of the second sample group, β1 and β2 represent random numbers uniformly distributed in the interval [0,1].

4. The hydropower dispatch optimization method according to claim 1, characterized in that: In step S3, the specific implementation steps are as follows: S31, arbitrarily select a time period t d , get time period t d The values ​​within the internal constraint set, including the generation flow Water head Water Level and hydropower bandwidth S32. Obtain different balance factors B beyond the constraint set through regularization method cm ; like or Then get the balance factor B c1 ; like or Then get the balance factor B c2 ; like or Then get the balance factor B c3 ; like or Then get the balance factor B c4 ; S33, the first sample group And the second sample group The union of The expression is: in, Represents a sample of the population. S34, according to the power generation function E max Calculate the overall sample with multiple balance factors The balance degree Ph of each sample in g , the calculation formula is: Among them, Ph g Indicates the balance of the sample, B cm represents the mth balance factor, The relevant variable value of the sample that exceeds the constraint condition, M represents the balance factor B cm The number of 5. The hydropower dispatch optimization method according to claim 1, characterized in that: In step S4, the specific implementation steps are as follows: S41, according to the balance Ph g Calculate the overall sample The weight coefficient w of each sample in j , the calculation formula is as follows: Among them, w j Represents the overall sample The weight coefficient of each sample in It represents the balance degree of the hth sample in the kth iteration of the total sample. Min and max represent the minimum and maximum values ​​selected from multiple balance degrees respectively. S42. In the overall sample According to the balance Ph g Determine the optimal sample The expression is: in, Represents the overall sample Medium Balance Ph g The largest sample; S43. In the overall sample First, randomly select a sample as the central sample S44, in the center sample Determine a distance center sample nearby Recent reference samples S45. For the first sample group And the second sample group According to the balance Ph g Sort them in descending order and set the balance Ph g The largest 50% is used as the first initial preferred set and the second initial priority set 6. The hydropower dispatch optimization method according to claim 1, characterized in that: In step S5, the specific implementation steps are as follows: S51, calculate the optimal samples respectively and center sample Perception coefficient V a and V b , the calculation formula is: Among them, V a and V b Represent the optimal samples and center sample The perception coefficient, and Represent the optimal samples and reference samples The Euclidean distance of and reference samples The Euclidean distance of S52, obtain a uniformly distributed random threshold Q between [0,1] through a random number generator f and random numbers g1, g2, g3 and g4; S53, the first initial optimal set Perform diversified operations; If g4≤Q f , the calculation formula is: in, represents the first initial optimal set after the diversification operation; If g4>Q f , the calculation formula is: wherein, g1, g2, g3, and g4 respectively represent random numbers between [0, 1]; S54, for the second initial priority set Perform diversified operations; If g4≤Q f , the calculation formula is: in, represents the second initial optimal set after the diversification operation; If g4>Q f , the calculation formula is: Among them, V a and V b Represent the optimal samples and center sample Perception coefficient; S55, based on the first initial optimal set after the diversified operation and the second initial preferred set Get a diverse sample set 7. The hydropower dispatch optimization method according to claim 1, characterized in that: In step S6, the specific implementation steps are as follows: S61, according to the balance Ph g The calculation formula for calculating the diversified sample set The preference of each sample in The calculation formula is: in, Represents a diverse sample set The preference degree, E dy Representation and Diversified Sample Sets The corresponding power generation function, B dy Representation and Diversified Sample Sets The corresponding balance factor, u represents the balance factor B dy the number of S62, according to the preference For the overall sample The samples are replaced; like but It is not the optimal value, replace the corresponding overall sample like but is the optimal value, not the overall sample To carry out replacement; S63, repeat step S62 until the total sample All samples in are replaced and the optimal set Z is obtained.

8. The hydropower dispatch optimization method according to claim 1, characterized in that: The specific content of step S7 is: the samples in the optimal set Z are sorted according to the degree of preference. Arrange from large to small, and select The largest sample is taken as the optimal scheduling strategy.

9. A system for implementing the hydropower dispatch optimization method according to any one of claims 1 to 8, characterized in that: The system includes: The power generation constraint module is used to obtain the power generation function E of each hydropower station in the cascade reservoir group. max , and the power generation function E max Constrain the relevant variables to obtain the constraint condition set; The initialization module is used to take each hydropower station as a sample, divide multiple samples and initialize them separately to obtain the first sample group And the second sample group The balance module is used to calculate the balance Ph of the sample according to the constraint set. g ; The initial optimization module is used to select the optimal balance according to the balance degree Ph. g Calculate the weight coefficient w for each sample j , and determine the first initial optimal set and the second initial priority set A diversification module is used to select the first initial optimal set and the second initial priority set Each sample in the neighborhood performs a diversification operation and obtains a diversified sample set The most optimized module for computing diverse sample sets The preference And according to the preference For the first sample group And the second sample group The samples are replaced and the optimal set Z is obtained; An iteration module, configured to obtain the iteration threshold X by the maximum likelihood estimation method based on the historical data of the hydropower station, and iterate on the optimal set Z.

Images