Hydropower station group flood control scheduling scheme evaluation method, device, equipment and medium

Abstract

The invention relates to the technical field of flood control and benefit-making scheduling, and discloses a hydropower station group flood control scheduling scheme evaluation method, device, equipment and medium, and the method comprises the steps: obtaining an evaluation index of a scheduling scheme and a characteristic value of the evaluation index, calculating the relative membership of the evaluation index based on the characteristic value, and generating a relative membership matrix; calculating the information entropy weight of the evaluation index based on the relative optimal genus degree of the evaluation index, and determining the semantic weight of the evaluation index based on the occurrence frequency of the evaluation index; fusing the information entropy weight and the semantic weight, and determining a combined weight of the evaluation index; an objective function is determined according to the weighted distance optimal distance and the weighted distance inferior distance of the scheduling scheme, the membership degree of the scheduling scheme is determined based on the solving result of the objective function, and the membership degree is used for determining a target scheduling scheme. The evaluation indexes are subjected to comprehensive weighting based on the minimum identification information principle, the evaluation model of the scheme is generated, and subjectivity and objectivity of the result are both considered.

Description

Technical Field

[0001] The invention relates to the technical field of flood control and benefit dispatching, and in particular to a method, device, equipment and medium for evaluating flood control dispatching schemes of a hydropower station group. Background Art

[0002] Flood disasters are one of the most damaging natural disasters in the world today. More than 60% of the losses from various natural disasters worldwide each year are caused by flood disasters. Therefore, it is necessary to adopt effective management methods to regulate controllable projects in the basin and reduce flood losses in the basin. The reservoir flood dispatching problem is actually a special type of complex system evaluation problem with action plans as the evaluation object. The essence of system comprehensive evaluation is how to reasonably convert multi-level and multi-dimensional complex system evaluation indicators into single-level one-dimensional system evaluation indicators. This process requires fully exploring the indicator data structure that reflects the main characteristic information of the evaluation object and the value judgment information of the evaluation subject, and requires an operational and appropriate comprehensive evaluation method that integrates qualitative analysis and quantitative calculation. Based on this, how to select the best solution from many solutions is a problem that needs to be solved urgently. Summary of the invention

[0003] In view of this, the present invention provides a method, device, equipment and medium for evaluating a flood control scheduling plan of a hydropower station group, so as to solve the problem of evaluating a flood control scheduling plan of a hydropower station group.

[0004] In a first aspect, the present invention provides a method for evaluating a flood control scheduling scheme for a hydropower station group, the method comprising:

[0005] Obtaining the evaluation index of the scheduling scheme and the characteristic value of the evaluation index, and calculating the relative superiority of the evaluation index based on the characteristic value to generate a relative superiority matrix; calculating the information entropy weight of the evaluation index based on the relative superiority of the evaluation index, and determining the semantic weight of the evaluation index based on the occurrence frequency of the evaluation index;

[0006] The information entropy weight and the semantic weight are integrated to determine the combined weight of the evaluation index;

[0007] An objective function is determined according to the weighted superior distance and the weighted inferior distance of the scheduling scheme, and the membership of the scheduling scheme is determined based on the solution result of the objective function, the membership is used to determine the target scheduling scheme, the weighted superior distance and the weighted inferior distance are determined based on the combined weights of the evaluation indicators, the weighted superior distance is used to characterize the first weighted generalized distance between the scheduling scheme and the first preset scheme, the weighted inferior distance is used to characterize the second weighted generalized distance between the scheduling scheme and the second preset scheme, and the first preset scheme and the second preset scheme are determined based on the relative superiority matrix.

[0008] In a second aspect, the present invention provides a device for evaluating flood control scheduling schemes for a hydropower station group, the device comprising:

[0009] An indicator acquisition module, used to obtain the evaluation indicator of the scheduling scheme and the characteristic value of the evaluation indicator, and calculate the relative superiority of the evaluation indicator based on the characteristic value to generate a relative superiority matrix; a weight determination module, used to calculate the information entropy weight of the evaluation indicator based on the relative superiority of the evaluation indicator, and determine the semantic weight of the evaluation indicator based on the frequency of occurrence of the evaluation indicator;

[0010] A combined weight determination module, used to fuse the information entropy weight and the semantic weight to determine the combined weight of the evaluation index;

[0011] A membership determination module is used to determine the objective function according to the weighted superior distance and weighted inferior distance of the scheduling scheme, and determine the membership of the scheduling scheme based on the solution result of the objective function, the membership is used to determine the target scheduling scheme, the weighted superior distance and the weighted inferior distance are determined based on the combined weights of the evaluation indicators, the weighted superior distance is used to characterize the first weighted generalized distance between the scheduling scheme and the first preset scheme, the weighted inferior distance is used to characterize the second weighted generalized distance between the scheduling scheme and the second preset scheme, and the first preset scheme and the second preset scheme are determined based on the relative superiority matrix.

[0012] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0013] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to cause a computer to execute the method of the first aspect or any corresponding embodiment thereof.

[0014] The flood control dispatching scheme evaluation method of a hydropower station group provided in this embodiment includes obtaining the evaluation index of the dispatching scheme and the characteristic value of the evaluation index, and calculating the relative superiority of the evaluation index based on the characteristic value to generate a relative superiority matrix; calculating the information entropy weight of the evaluation index based on the relative superiority of the evaluation index, and determining the semantic weight of the evaluation index based on the occurrence frequency of the evaluation index; fusing the information entropy weight and the semantic weight to determine the combined weight of the evaluation index; determining the objective function by the weighted superior distance and the weighted inferior distance of the dispatching scheme, and determining the membership of the dispatching scheme based on the solution of the objective function, the membership is used to determine the target dispatching scheme, and the weighted superior distance and the weighted inferior distance are determined based on the combined weight of the evaluation index. This scheme comprehensively weights the evaluation index based on the minimum discriminant information principle, generates an evaluation model (i.e., the objective function) of the scheme, and thus can select a dispatching scheme so that the result takes into account both subjectivity and objectivity. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 is a flow chart of a method for evaluating a flood control dispatching scheme for a hydropower station group according to an embodiment of the present invention;

[0017] Figure 2 is a schematic diagram of a scheduling scheme evaluation index system according to an embodiment of the present invention;

[0018] Figure 3 is a flow chart of a method for evaluating a flood control dispatching scheme for a hydropower station group according to an embodiment of the present invention;

[0019] Figure 4 is a structural block diagram of a device for evaluating a flood control scheduling scheme for a hydropower station group according to an embodiment of the present invention;

[0020] Figure 5 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0022] Flood is a complex natural phenomenon that is affected by astronomy, geography, human production and social activities, and interacts with each other. The study of flood phenomena has existed since ancient times. Humans initially avoided floods and chose to live in high places. Floods submerged barren river beaches or uninhabited floodplains. With the progress of society and the development of productivity, floodplains were occupied and cultivated by humans, and flood disasters occurred. It can be seen that flood disasters are essentially a specific reflection of the uncoordinated development of the relationship between humans and the natural environment, and reflect the restrictions and constraints of nature on human production activities. Flood disasters are one of the most damaging natural disasters in the world today. More than 60% of the losses from various natural disasters worldwide each year are caused by flood disasters. Taking effective operation and management methods to regulate controllable projects in the basin can reduce flood losses in the basin.

[0023] The reservoir flood dispatching problem is actually a special type of complex system evaluation problem with action plans as the evaluation object. The essence of system comprehensive evaluation is how to reasonably convert the multi-level and multi-dimensional complex system evaluation indicators into single-level and one-dimensional system evaluation indicators. This process requires fully exploring the indicator data structure that reflects the main characteristic information of the evaluation object and the value judgment information of the evaluation subject, and requires an operational and appropriate comprehensive evaluation method that integrates qualitative analysis and quantitative calculation.

[0024] According to an embodiment of the present invention, an embodiment of a method for evaluating a flood control scheduling scheme for a group of hydropower stations is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] In this embodiment, a method for evaluating flood control scheduling schemes for a hydropower station group is provided, which can be used on terminals such as computers, tablet computers, and mobile phones. Figure 1 is a flow chart of a method for evaluating a flood control scheduling scheme for a hydropower station group according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0026] Step S101, obtaining evaluation indicators of the scheduling scheme and eigenvalues ​​of the evaluation indicators, and calculating relative superiority of the evaluation indicators based on the eigenvalues ​​to generate a relative superiority matrix.

[0027] The dispatching scheme refers to the coordinated dispatching scheme for flood control and benefit development of cascade hydropower stations, which can be used to solve multi-objective decision-making problems. In different dispatching schemes, the actual situation is required to determine one or more requirements that the dispatching scheme needs to meet. For example, when considering the safety of downstream flood control, the smaller the discharge flow, the better, and the water level rises at this time. When considering the safety of the reservoir itself and the flood control requirements, the lower the water level, the better. When considering the power generation benefits of the reservoir, the higher the reservoir water level, the better. Different expectations for different needs will make the dispatching of reservoirs complicated, and the contradiction between flood control and benefit development will be prominent. One or more reservoirs can be involved in a reservoir dispatching scheme.

[0028] The evaluation index of the dispatching scheme refers to the requirements that need to be met in the dispatching scheme. As an example, the evaluation index may include the highest water level in the reservoir dispatching process, the maximum discharge flow in the reservoir dispatching process, the water level at the end of flood regulation, the utilization rate of the reservoir flood control storage capacity, and the benefit of the reservoir. The characteristic value of the evaluation index represents the specific value of the evaluation index in a dispatching scheme. Taking the evaluation index as the highest water level in the reservoir dispatching process as an example, the characteristic value of the evaluation index refers to the value of the highest water level in the dispatching process of each reservoir. The evaluation indexes of each dispatching scheme that has been determined are stored in advance, and the characteristic values ​​of the evaluation indexes can be calculated or directly obtained.

[0029] Since the scheduling scheme may involve multiple reservoirs, the characteristic value of any evaluation indicator can be calculated from the sub-characteristic values ​​of the sub-indicators of multiple reservoirs. For example, when the evaluation indicator is the highest water level, the sub-characteristic value (the value of the highest water level) of the sub-indicator (highest water level) of reservoir k1 is C1 meters, and the sub-characteristic value (the value of the highest water level) of the sub-indicator (highest water level) of reservoir k2 is C2 meters. The two are combined to obtain the characteristic value of the highest water level in the evaluation scheme. Among them, the method of integrating the sub-characteristic values ​​of the sub-indicators of the reservoir can be set according to actual needs, for example, it can be generated by calculating the average value or combining the reservoir weight.

[0030] The highest water level in the reservoir dispatching process refers to the highest water level reached in front of the reservoir dam during the process of regulating a flood. If the highest water level is too high, it will be detrimental to the safety of the reservoir itself and there will be a risk of dam breach. The highest water level in the reservoir dispatching process is selected as an indicator to ensure the safety of the reservoir itself. The maximum discharge of the reservoir is an important indicator for protecting downstream flood control objects, which reflects the flood interception and storage capacity of the dispatching scheme in the flood control process. The maximum discharge of the reservoir dispatching process is selected as an indicator to ensure the safety of the downstream protection area. The water level at the end of flood regulation refers to the reservoir water level at the end of a flood regulation when the scheme is adopted. In the flood control and benefit dispatching system, the water level at the end of flood regulation needs to meet both flood control safety requirements and benefit power generation requirements. The higher the water level at the end of flood regulation, the more beneficial it is to benefit, but it will cause flood control danger. The lower the water level at the end of flood regulation, the more beneficial it is to flood control safety, but it will affect the benefit of the reservoir. Coordinating the water level at the end of flood regulation to ensure the flood control safety and benefit of the reservoir is a key issue in dispatching. Taking the final water level of flood control as an indicator can meet the requirements of coordinated dispatching of flood control and benefit of cascade hydropower stations. The utilization rate of reservoir flood control storage capacity is the storage capacity corresponding to the highest water level reached by each cascade reservoir during the flood control process minus the storage capacity corresponding to the flood control limit water level of the reservoir, divided by the total flood control storage capacity of the reservoir. In a single flood control process, the smaller the index, the smaller the storage capacity used, and more storage capacity is reserved to cope with the next flood that may come later. The utilization rate of reservoir flood control storage capacity is used as an indicator to meet flood control safety. The benefit of the reservoir can be used as an indicator to evaluate the benefit of the power generation of the reservoir in a flood control process. The larger the index, the better, to ensure the optimal utilization of water resources.

[0031] When constructing an evaluation index system for coordinated flood control and benefit-generating dispatching schemes for cascade hydropower stations, Figure 2 As shown in Figure 1, following the hierarchical relationship framework of "decision-making-criteria-indicators", the reservoir operation scheme optimization index system is divided into three layers: decision-making layer, criterion layer and indicator layer. The decision-making layer is the optimal operation scheme pursued by multi-objective decision-making; the criterion layer is the various dimensions of the evaluation of the operation scheme (i.e., evaluation indicators), such as Figure 2 The highest water level, maximum downstream flow, etc.; the indicator layer is the characteristic value of the evaluation indicator.

[0032] Assume that this scheme involves comprehensive evaluation of multiple scheduling schemes, each scheduling scheme has one or more evaluation indicators, and each evaluation indicator has its corresponding characteristic value. Since the dimensions of each evaluation indicator are different, the optimization characteristics of each evaluation indicator in different scheduling schemes are relative. In order to eliminate the incommensurability caused by different dimensions and units and facilitate calculation and optimization analysis, the absolute quantity of the evaluation indicator should be converted into a relative quantity, that is, relative superiority, before making a decision.

[0033] Relative superiority is a concept used in decision analysis and fuzzy optimization theory, which is used to quantify the degree of membership of the characteristic value of the evaluation index of a decision plan relative to the optimal one. Quantitative indicators include indicators where the larger the better and indicators where the smaller the better. The relative superiority of the evaluation index is calculated according to the type of evaluation index or pre-set characteristics. The relative superiority matrix is ​​generated according to all the evaluation indicators of all scheduling plans. The elements of the relative superiority matrix are the relative superiority of any evaluation indicator of any scheduling plan.

[0034] Step S102, calculating the information entropy weight of the evaluation indicator based on the relative superiority of the evaluation indicator, and calculating the semantic weight of the evaluation indicator based on the occurrence frequency of the evaluation indicator.

[0035] The information entropy weight and semantic weight involved in this step are objective weights. According to the impact of the changes in the values ​​of each indicator on the whole, the entropy value of the indicator is calculated, and then the information entropy weight is determined.

[0036] The frequency of occurrence of the evaluation index is determined by collecting the frequency of occurrence of the evaluation index in the pre-selected database. The specific method of obtaining the frequency of occurrence is not limited in this embodiment, and can be obtained by semantic analysis, data mining, etc. The semantic weight represents the proportion of the frequency of occurrence of the evaluation index in all frequencies.

[0037] Step S103, fusing the information entropy weight and the semantic weight to determine the combined weight of the evaluation index.

[0038] Based on the Minimum Discrimination Information Principle (MDIP), the information entropy weight and semantic weight are fused, an optimization model is constructed based on the information entropy weight and semantic weight, and the optimization model is solved to obtain the combined weight of the evaluation index. In this way, a more balanced and comprehensive weight distribution can be achieved to more accurately reflect the multidimensional nature of the decision-making problem.

[0039] Exemplarily, the specific process of determining the combination weight is as follows:

[0040] For m evaluation indicators, let the semantic weight be W sub = {W sub (i)|1≤i≤m}, the information entropy weight is W obj = {W obj (i)|1≤i≤m}, the combined weight vector is W = {W(i)|1≤i≤m}. According to the minimum discriminant information principle, the combined weight W(i) should be the same as W sub (i) and W obj The information difference of (i) is the smallest, based on which the following optimization model is established:

[0041]

[0042] The Lagrange multiplier method is used to solve the above model, and the combined weight W(i) of the i-th evaluation index is obtained as follows:

[0043]

[0044] Step S104, determining an objective function according to the weighted superior distance and the weighted inferior distance of the scheduling scheme, and determining the membership degree of the scheduling scheme based on the solution result of the objective function.

[0045] Among them, the degree of membership is used to determine the target scheduling plan, the weighted distance to the best and the weighted distance to the worst are determined based on the combined weights of the evaluation indicators, the weighted distance to the best is used to characterize the first weighted generalized distance between the scheduling plan and the first preset plan, and the weighted distance to the worst is used to characterize the second weighted generalized distance between the scheduling plan and the second preset plan. The first preset plan and the second preset plan are determined based on the relative superiority matrix.

[0046] Extract the maximum and minimum values ​​of each row from the relative superiority matrix, and determine the ideal superior plan (first preset plan) and the ideal inferior plan (second preset plan) based on all the maximum and minimum values. Any scheduling plan is subordinate to the ideal superior plan and the ideal inferior plan with a certain degree of membership, and the degrees of membership are superiority and inferiority, respectively. The difference between the scheduling plan and the ideal superior plan, and the difference between the scheduling plan and the ideal inferior plan are the distance to the superior and the distance to the inferior, respectively. The superiority is used as the weight of the distance to the superior, and the weighted distance to the superior is further obtained; the inferiority is used as the weight of the distance to the inferior, and the weighted distance to the inferior is further obtained.

[0047] The objective function is constructed with the minimum sum of the square of the weighted distance to the best and the square of the weighted distance to the worst of the scheduling scheme as the optimization goal, and the objective function is solved to obtain the membership degree of the scheduling scheme.

[0048] The membership degrees of various scheduling schemes are combined to generate a membership set as a group of relatively satisfactory scheduling schemes for selection.

[0049] The flood control dispatching scheme evaluation method of a hydropower station group provided in this embodiment includes obtaining the evaluation index of the dispatching scheme and the characteristic value of the evaluation index, and calculating the relative superiority of the evaluation index based on the characteristic value to generate a relative superiority matrix; calculating the information entropy weight of the evaluation index based on the relative superiority of the evaluation index, and determining the semantic weight of the evaluation index based on the occurrence frequency of the evaluation index; fusing the information entropy weight and the semantic weight to determine the combined weight of the evaluation index; determining the objective function by the weighted superior distance and the weighted inferior distance of the dispatching scheme, and determining the membership of the dispatching scheme based on the solution of the objective function, the membership is used to determine the target dispatching scheme, and the weighted superior distance and the weighted inferior distance are determined based on the combined weight of the evaluation index. This scheme comprehensively weights the evaluation index based on the minimum discriminant information principle, generates an evaluation model (i.e., the objective function) of the scheme, and thus can select a dispatching scheme so that the result takes into account both subjectivity and objectivity.

[0050] In some optional implementations, step S101 of the above method includes the following steps:

[0051] Step S201, constructing an eigenvalue matrix.

[0052] Assume that there are n non-inferior scheduling schemes, and assume that n scheduling schemes satisfy the preset constraint set to form a scheduling scheme set D, which is as follows:

[0053] D={d 1 ,d 2 ,...,d n}

[0054] Wherein, D represents a scheduling scheme set, d represents the nth scheduling scheme, and the scheduling scheme set includes n scheduling schemes.

[0055] Each scheduling scheme has m evaluation indicators that constitute the evaluation target set P of the scheduling scheme set D, as follows:

[0056] P = {p 1 ,p 2 ,...,p n}

[0057] Among them, P represents the evaluation target set, and p represents the mth evaluation index.

[0058] For each scheduling scheme, the eigenvalues ​​of its m evaluation indicators can be obtained to form the eigenvalue matrix A, as follows:

[0059]

[0060] Among them, A represents the eigenvalue matrix, a mn Represents the characteristic value of the mth evaluation indicator in the nth scheduling scheme.

[0061] Step S202, according to the indicator type of the evaluation indicator, calculate the relative superiority of the evaluation indicator based on the characteristic value of the evaluation indicator.

[0062] The indicator type of the evaluation indicator is pre-set, and based on the indicator type, it can be determined whether the evaluation indicator is a larger indicator or a smaller indicator. The smaller the better indicator is, the smaller the indicator is or the cost-oriented indicator, and the larger the better indicator is, the larger the indicator is or the benefit-oriented indicator.

[0063] In this step, the relative superiority of the characteristic value of the evaluation index is calculated, including a relative superiority of the larger the better and a relative superiority of the smaller the better. The formula corresponding to the superiority is determined according to the type of the evaluation index for calculation.

[0064] The calculation formula of relative superiority is:

[0065]

[0066] Among them, ij represents the characteristic value of the i-th evaluation index of the j-th scheduling scheme, r ij(大) It indicates the relative superiority of the j-th scheduling scheme, where the larger the i-th evaluation index is, the better it is, i = 1, 2, ..., m; j = 1, 2, ..., n.

[0067] The calculation formula of relative superiority is:

[0068]

[0069] Among them, r uj(小) It indicates the relative superiority of the j-th scheduling scheme, where the smaller the i-th evaluation index is, the better it is.

[0070] Step S203, replacing the eigenvalue matrix to determine the relative superiority matrix.

[0071] By calculating the relative superiority of each evaluation index and replacing the elements in the eigenvalue matrix, the relative superiority matrix R is obtained, as follows:

[0072]

[0073] Among them, R represents the relative superiority matrix, r mn It represents the relative superiority of the mth evaluation index of the nth scheduling scheme.

[0074] This implementation can eliminate the incommensurability of evaluation indicators caused by different dimensions and units, and convert the absolute quantity of the evaluation indicators into a relative quantity, which is convenient for subsequent calculation and analysis.

[0075] In some optional embodiments, when the number of reservoirs involved in the scheduling plan is more than one, the above Figure 1 The method shown also includes determining a characteristic value of the evaluation index based on the sub-characteristic value of the sub-indicator of the reservoir, specifically comprising the following steps:

[0076] Step S301, obtaining the relative importance of the reservoir, and determining the reservoir weight based on the relative importance of the reservoir.

[0077] The relative importance is used to characterize the importance of any reservoir compared with the preset target reservoir, where the preset target reservoir represents the most important reservoir. The relative importance can include equally important, slightly important, obviously important, very important, extremely important, incomparable, etc.

[0078] The importance of each reservoir is calculated by relative importance, as follows:

[0079]

[0080] Among them, W′ represents the importance set of reservoirs, w′ represents the importance of the lth reservoir, u 1 Indicates the relative importance of Reservoir No. 1 compared to the preset target reservoir (Reservoir No. 1).

[0081] The importance is normalized to obtain the weight of each reservoir. Normalization is to scale the data to a specified numerical range to eliminate the dimensional differences between different features or data so that they can be compared and calculated on the same scale, as follows:

[0082]

[0083] Among them, represents the collection of reservoir weights, w represents the weight of the lth reservoir, l represents the number of reservoirs, and w′ represents the importance of the kth reservoir.

[0084] Step S302, determining the characteristic value of the evaluation index based on the product sum of the reservoir weight and the sub-characteristic value of the sub-indicator of the reservoir.

[0085] Get the sub-characteristic value of each reservoir under its corresponding sub-indicator, as follows:

[0086]

[0087] In the formula, a ij represents the characteristic value of the i-th evaluation index of the j-th scheduling scheme, C ijk is the sub-characteristic value of the kth reservoir under the i-th evaluation index of the j-th scheduling scheme, w ik is the weight of the kth reservoir under the ith evaluation index.

[0088] In some optional implementations, calculating the semantic weight of the evaluation indicator based on the occurrence frequency of the evaluation indicator in step S102 of the above method includes the following steps:

[0089] Step S401, obtaining the occurrence frequency of the evaluation index in the target database.

[0090] Among them, the frequency of occurrence is determined based on semantic analysis, and the frequency of occurrence corresponds to the evaluation index one by one.

[0091] The frequency of occurrence of evaluation indicators in the target database is determined through semantic analysis and data mining. The target database includes various existing databases containing published documents. When an evaluation indicator appears, it indicates that the evaluation indicator has been recognized and practiced as a target indicator in the field. This implementation method includes two parts: information statistics and semantic analysis, and data mining. Information statistics and semantic analysis refer to quantifying the evaluation indicators, counting the word frequency, and performing semantic analysis on high-frequency keywords and similar words to obtain research hotspots and focus points in the professional field. Data mining refers to deep mining of evaluation indicators in multiple documents, guided by the results of semantic analysis, and determining the frequency of occurrence of high-frequency keywords in the documents through further analysis and clustering.

[0092] The frequency of occurrence includes not only the evaluation indicator itself, but also the frequency of occurrence of words similar to the evaluation indicator. The frequency of occurrence of keywords can be collected by setting the keywords of the evaluation indicator to further determine the frequency of occurrence of the evaluation indicator.

[0093] Step S402: obtaining the semantic weight of the evaluation indicator based on the ratio of the occurrence frequency of the evaluation indicator to the sum of the occurrence frequencies of all evaluation indicators.

[0094] The semantic weight is determined according to the following formula:

[0095]

[0096] Among them, w sub (i) represents the semantic weight (i.e., subjective weight) of the i-th evaluation indicator, p i Indicates the frequency of occurrence of the evaluation indicator.

[0097] In some optional implementations, calculating the information entropy weight of the evaluation indicator based on the relative superiority of the evaluation indicator in step S102 of the above method includes the following steps:

[0098] Step S501: determine the proportion of the evaluation indicator in the scheduling solution based on the relative superiority of the evaluation indicator.

[0099] The information entropy weight is an objective weight that can reflect the data characteristics of the cascade hydropower station group, extract information from the data to allocate the weight of the evaluation index, and reduce human intervention. The proportion of the evaluation index in the dispatching plan is determined according to the following formula:

[0100]

[0101] Among them, represents the proportion of the evaluation index in the scheduling scheme, j represents the jth scheduling scheme, n represents the number of scheduling schemes, and r ij It represents the relative superiority of the i-th evaluation index of the j-th scheduling scheme.

[0102] Step S502: Calculate the entropy value of the evaluation index based on the proportion, and determine the information entropy weight of the evaluation index according to the ratio of the entropy value to the sum of the entropy values ​​of all the evaluation indexes.

[0103] The entropy value of the evaluation index is determined according to the following formula:

[0104]

[0105] Among them, H i Represents the entropy value of the i-th evaluation index.

[0106] The information entropy weight of the evaluation index is determined according to the following formula:

[0107]

[0108]

[0109] Among them, W obj (i) represents the information entropy weight of the i-th evaluation index, and m represents the number of evaluation indicators.

[0110] In some optional implementations, in step S104 of the above method, determining the objective function according to the weighted superior distance and the weighted inferior distance of the scheduling scheme includes the following steps:

[0111] Step S601: Obtain a first preset solution and a second preset solution.

[0112] Extract the maximum value of each row from the relative superiority matrix and record it as:

[0113] r g =(r g1 , r g2 , ..., r gm )=(maxr 1j , maxr 2j , ..., maxr mj ) = (1, 1, ..., 1)

[0114] Among them, r g represents the first preset solution (ideal optimal solution), r gm represents the maximum relative superiority of the mth evaluation index, r mj It represents the relative superiority of the mth evaluation index of the jth scheduling scheme.

[0115] Extract the minimum value of each row from the relative superiority matrix, recorded as:

[0116] r b =(r b1 , r b2 , ..., r bm )=(minr 1j , minr 2j , ..., minr mj )=(0,0,...,0)

[0117] Among them, r g represents the second preset solution (ideal inferior solution), r bm It represents the minimum relative superiority of the mth evaluation index.

[0118] Step S602: determining the superiority and inferiority of the scheduling scheme based on the membership of the scheduling scheme relative to the first preset scheme and the second preset scheme.

[0119] For any scheduling scheme j, with a certain membership degree u gj 、u bj Belongs to the first preset plan g and the second preset solution r b ,u gj 、u bj are respectively the superiority and inferiority of scheduling scheme j. The superiority and inferiority can be calculated using corresponding formulas, which will not be repeated here.

[0120] Step S603, based on the relative superiority and combined weight of the evaluation index, respectively determine the distance to the best and the distance to the worst, and use the superiority and the inferiority as weights, respectively, to determine the weighted distance to the best and the weighted distance to the worst on the basis of the distance to the best and the distance to the worst.

[0121] The difference between each scheduling scheme and the ideal superior and inferior schemes can be expressed by generalized weighted distance, referred to as the superior distance and inferior distance, as follows:

[0122]

[0123]

[0124] Among them, d jg represents the optimal distance, d jbrepresents the distance to inferiority, w i represents the combined weight of the i-th evaluation index, r ij It represents the relative superiority of the i-th evaluation index of the j-th scheduling scheme, and p represents the distance parameter (which can be 1).

[0125] Assume that the relative membership of scheduling scheme j to the first preset scheme, i.e., the relative superiority of scheduling scheme j, is u j Indicates that the relative membership of the second preset solution is According to the definition of the complement in fuzzy set theory, we have:

[0126]

[0127] The relative membership is defined as the weight, then the weighted distance D between the scheduling scheme j and the first preset scheme is jg for:

[0128] D jg =u j d jg

[0129] The weighted inferior distance between scheduling scheme j and the second preset scheme is:

[0130]

[0131] Step S604, constructing an objective function with the minimum sum of the square of the weighted distance to the best value and the square of the weighted distance to the worst value as the optimization goal.

[0132] In order to solve the relative membership degree u of scheduling scheme j j The optimal value of is established, and the following optimization criterion is established: the sum of the square of the weighted distance from the best and the square of the weighted distance from the worst of scheduling scheme i is minimized, and the objective function is obtained as follows:

[0133]

[0134] untie

[0135]

[0136] The membership degree is solved as

[0137]

[0138] Among them, r bi represents the minimum relative superiority of the i-th evaluation index, r gi It represents the maximum relative superiority of the i-th evaluation index.

[0139] According to the above formula, the membership of each scheme can be calculated, and the scheme membership set is

[0140] U * =(u 1 ,u 2 ,…,u n )

[0141] As a specific implementation method, a method for evaluating flood control scheduling schemes of a hydropower station group is provided in this embodiment. Figure 3 It is a flow chart of the evaluation method of the flood control scheduling scheme of a hydropower station group according to an embodiment of the present invention. In this embodiment, a fuzzy comprehensive evaluation method for the flood control scheduling scheme of a cascade hydropower station group based on the principle of minimum discriminant information is provided, and the construction of the evaluation model of the flood control and benefit scheduling scheme of the cascade hydropower station group includes: constructing an evaluation index system for the flood control and benefit coordinated scheduling scheme of the cascade hydropower station group; determining the relative superiority matrix of the evaluation index of the criterion layer; determining the weight of the index layer; determining the weight of the criterion layer; and constructing the evaluation model of the flood control and benefit scheduling scheme of the cascade hydropower station according to the weight of the index layer and the weight of the criterion layer. Among them, the weight of the multiple reservoirs in the evaluation index of the index layer weight design can be determined by the binary fuzzy comparison method. The objective weight can be determined by the entropy weight method, the subjective weight can be determined based on semantic analysis and data mining, and the comprehensive weight can be determined based on the principle of minimum discriminant information after combining the objective weight and the subjective weight.

[0142] This fuzzy comprehensive evaluation method for flood control and beneficial dispatching of cascade hydropower stations is based on the weights obtained by various weight fuzzy determination methods (binary fuzzy comparison method, entropy weight method and weight determination method based on semantic analysis and data mining), and uses the membership function of fuzzy set theory (using the relative superiority calculation formula to calculate the relative superiority of each target) as a bridge to quantify fuzzy information, calculate the membership of each plan, and finally determine the membership of each plan for decision makers to choose. Make full use of various weight calculation methods to assign values ​​to the multi-layer indicators of the dispatching plan, so that the target weight takes into account both subjective weight and objective weight, reflects the knowledge and experience of experts in the field and the data characteristics of the reservoir, generates a fuzzy evaluation model for flood control and dispatching plans of cascade hydropower stations, selects the best plan from multiple plans, and completes the coordinated dispatching of flood control and beneficial dispatching of cascade hydropower stations.

[0143] In this embodiment, a device for evaluating flood control scheduling schemes for a hydropower station group is also provided, and the device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0144] This embodiment provides a device for evaluating flood control scheduling schemes of a hydropower station group. Figure 4 As shown, including:

[0145] An indicator acquisition module, used to obtain the evaluation indicator of the scheduling scheme and the characteristic value of the evaluation indicator, and calculate the relative superiority of the evaluation indicator based on the characteristic value to generate a relative superiority matrix; a weight determination module, used to calculate the information entropy weight of the evaluation indicator based on the relative superiority of the evaluation indicator, and determine the semantic weight of the evaluation indicator based on the frequency of occurrence of the evaluation indicator;

[0146] A combined weight determination module, used to fuse the information entropy weight and the semantic weight to determine the combined weight of the evaluation index;

[0147] A membership determination module is used to determine the objective function according to the weighted superior distance and weighted inferior distance of the scheduling scheme, and determine the membership of the scheduling scheme based on the solution result of the objective function, the membership is used to determine the target scheduling scheme, the weighted superior distance and the weighted inferior distance are determined based on the combined weights of the evaluation indicators, the weighted superior distance is used to characterize the first weighted generalized distance between the scheduling scheme and the first preset scheme, the weighted inferior distance is used to characterize the second weighted generalized distance between the scheduling scheme and the second preset scheme, and the first preset scheme and the second preset scheme are determined based on the relative superiority matrix.

[0148] In some optional embodiments, when the number of reservoirs involved in the scheduling plan is more than one, the device further includes:

[0149] A characteristic determination unit is used to determine the characteristic value of the evaluation index based on the sub-characteristic value of the sub-indicator of the reservoir.

[0150] In some optional implementations, the feature determination unit includes:

[0151] A relative importance acquisition subunit, used to acquire the relative importance of the reservoir and determine the reservoir weight based on the relative importance of the reservoir;

[0152] The characteristic value determination subunit is used to determine the characteristic value of the evaluation index based on the product sum of the reservoir weight and the sub-characteristic value of the sub-indicator of the reservoir.

[0153] In some optional implementations, the indicator acquisition module includes:

[0154] An eigenvalue matrix construction unit, used to construct an eigenvalue matrix;

[0155] A relative superiority calculation unit, used to calculate the relative superiority of the evaluation indicator based on the indicator type of the evaluation indicator and the characteristic value of the evaluation indicator;

[0156] The matrix determination unit is used to replace the eigenvalue matrix to determine the relative superiority matrix.

[0157] In some optional implementations, the weight determination module includes:

[0158] A proportion calculation unit, used to determine the proportion of the evaluation indicator in the scheduling scheme based on the relative superiority of the evaluation indicator;

[0159] An information entropy weight determination unit is used to calculate the entropy value of the evaluation indicator based on the proportion, and determine the information entropy weight of the evaluation indicator according to the ratio of the entropy value to the sum of the entropy values ​​of all evaluation indicators.

[0160] In some optional implementations, the weight determination module includes:

[0161] A frequency acquisition unit, used to acquire the occurrence frequency of the evaluation indicator in the target database, wherein the occurrence frequency is determined based on semantic analysis, and the occurrence frequency corresponds to the evaluation indicator one by one;

[0162] The semantic weight determination unit is used to obtain the semantic weight of the evaluation indicator based on the ratio of the occurrence frequency of the evaluation indicator to the sum of the occurrence frequencies of all the evaluation indicators.

[0163] In some optional implementations, the membership determination module includes:

[0164] A solution acquisition unit, configured to acquire the first preset solution and the second preset solution;

[0165] A membership calculation unit, configured to determine a superiority and an inferiority based on the membership of the scheduling scheme relative to the first preset scheme and the second preset scheme;

[0166] A distance calculation unit, used to determine the distance to the best and the distance to the worst based on the relative superiority and the combined weight of the evaluation index, and use the superiority and the inferiority as weights to determine the weighted distance to the best and the weighted distance to the worst based on the distance to the best and the distance to the worst;

[0167] The objective function determination unit is used to construct an objective function with the minimization of the sum of the square of the weighted distance to the best and the square of the weighted distance to the worst as the optimization goal.

[0168] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0169] The flood control scheduling scheme evaluation device for a group of hydropower stations in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0170] The embodiment of the present invention also provides a computer device having the above Figure 4 The device shown.

[0171] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 5 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0172] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0173] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0174] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0175] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0176] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0177] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0178] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the present invention.

Claims

1. A method for evaluating flood control scheduling schemes for a hydropower station group, characterized in that: The method comprises: Obtaining the evaluation index of the scheduling scheme and the characteristic value of the evaluation index, and calculating the relative superiority of the evaluation index based on the characteristic value to generate a relative superiority matrix; calculating the information entropy weight of the evaluation index based on the relative superiority of the evaluation index, and determining the semantic weight of the evaluation index based on the occurrence frequency of the evaluation index; The information entropy weight and the semantic weight are integrated to determine the combined weight of the evaluation index; An objective function is determined according to the weighted superior distance and the weighted inferior distance of the scheduling scheme, and the membership of the scheduling scheme is determined based on the solution result of the objective function, the membership is used to determine the target scheduling scheme, the weighted superior distance and the weighted inferior distance are determined based on the combined weights of the evaluation indicators, the weighted superior distance is used to characterize the first weighted generalized distance between the scheduling scheme and the first preset scheme, the weighted inferior distance is used to characterize the second weighted generalized distance between the scheduling scheme and the second preset scheme, and the first preset scheme and the second preset scheme are determined based on the relative superiority matrix.

2. The method according to claim 1, characterized in that When the scheduling plan involves more than one reservoir, the method further includes: The characteristic value of the evaluation index is determined based on the sub-characteristic value of the sub-indicator of the reservoir.

3. The method according to claim 2, characterized in that The determining the characteristic value of the evaluation index based on the sub-characteristic value of the sub-indicator of the reservoir comprises: Obtaining the relative importance of the reservoir, and determining the reservoir weight based on the relative importance of the reservoir; The characteristic value of the evaluation index is determined based on the product sum of the reservoir weight and the sub-characteristic value of the sub-indicator of the reservoir.

4. The method according to claim 1, characterized in that: The step of calculating the relative superiority of the evaluation index based on the eigenvalue to generate a relative superiority matrix includes: Construct eigenvalue matrix; According to the indicator type of the evaluation indicator, the relative superiority of the evaluation indicator is calculated based on the characteristic value of the evaluation indicator; The eigenvalue matrix is ​​replaced to determine the relative superiority matrix.

5. The method according to claim 1, characterized in that The calculating the information entropy weight of the evaluation index based on the relative superiority of the evaluation index comprises: Determining the proportion of the evaluation index in the scheduling scheme based on the relative superiority of the evaluation index; The entropy value of the evaluation indicator is calculated based on the proportion, and the information entropy weight of the evaluation indicator is determined according to the ratio of the entropy value to the sum of the entropy values ​​of all evaluation indicators.

6. The method according to claim 1, characterized in that The determining the semantic weight of the evaluation indicator based on the occurrence frequency of the evaluation indicator includes: Obtaining the occurrence frequency of the evaluation indicator in the target database, wherein the occurrence frequency is determined based on semantic analysis, and the occurrence frequency corresponds to the evaluation indicator one by one; The semantic weight of the evaluation indicator is obtained based on the ratio of the occurrence frequency of the evaluation indicator to the sum of the occurrence frequencies of all the evaluation indicators.

7. The method according to any one of claims 1, characterized in that The determining of the objective function according to the weighted superior distance and the weighted inferior distance of the scheduling scheme includes: Obtaining the first preset solution and the second preset solution; Determining superiority and inferiority based on the membership of the scheduling scheme relative to the first preset scheme and the second preset scheme; Determine the distance to the best and the distance to the worst based on the relative superiority and the combined weight of the evaluation index, and use the superiority and the inferiority as weights to determine the weighted distance to the best and the weighted distance to the worst based on the distance to the best and the distance to the worst; The objective function is constructed with the minimization of the sum of the square of the weighted distance to the best and the square of the weighted distance to the worst as the optimization goal.

8. A flood control scheduling scheme evaluation device for a hydropower station group, characterized in that: The device comprises: An indicator acquisition module, used to obtain the evaluation indicator of the scheduling scheme and the characteristic value of the evaluation indicator, and calculate the relative superiority of the evaluation indicator based on the characteristic value to generate a relative superiority matrix; a weight determination module, used to calculate the information entropy weight of the evaluation indicator based on the relative superiority of the evaluation indicator, and determine the semantic weight of the evaluation indicator based on the frequency of occurrence of the evaluation indicator; A combined weight determination module, used to fuse the information entropy weight and the semantic weight to determine the combined weight of the evaluation index; A membership determination module is used to determine the objective function according to the weighted superior distance and weighted inferior distance of the scheduling scheme, and determine the membership of the scheduling scheme based on the solution result of the objective function, the membership is used to determine the target scheduling scheme, the weighted superior distance and the weighted inferior distance are determined based on the combined weights of the evaluation indicators, the weighted superior distance is used to characterize the first weighted generalized distance between the scheduling scheme and the first preset scheme, the weighted inferior distance is used to characterize the second weighted generalized distance between the scheduling scheme and the second preset scheme, and the first preset scheme and the second preset scheme are determined based on the relative superiority matrix.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for evaluating flood control scheduling schemes for a group of hydropower stations as described in any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for evaluating flood control scheduling plans for a group of hydropower stations according to any one of claims 1 to 7.

Images