A cascade reservoir optimal scheduling algorithm based on genetic algorithm and simulation program

Abstract

The application discloses a kind of based on genetic algorithm and simulation program's cascade reservoir optimal scheduling algorithm, including, by genetic algorithm, initial population is generated;Based on the initial population, fitness is solved using simulation program;Evolution operation is completed in genetic algorithm;Iteration is finished, terminate algorithm.This method can eliminate the influence of seismic source wavelet, solve the problem that traditional free surface related multiple wave suppression processing technology cannot adapt to the seismic data collected by seabed node observation mode.The genetic algorithm and simulation program algorithm proposed in the application have stable and high output in different sizes of cascade reservoirs, can significantly improve the total power generation of cascade reservoirs and ensure output, and the optimization effect is good.The "soil leveling" algorithm is added in the proposed genetic algorithm and simulation program, which can significantly improve the total power generation and ensure the output result, and can reduce the water abandonment of the four cascade reservoirs to 0.

Description

Technical Field

[0001] This invention relates to the field of intelligent algorithm technology, and in particular to a cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program. Background Technology

[0002] Reservoirs, as a crucial means of water resource regulation and utilization, play an irreplaceable role in ensuring human survival and development. However, with the increase in global population and economic development, the contradiction between water supply and demand is becoming increasingly prominent, making better utilization of water resources an urgent issue. In the water conservancy and hydropower development planning of a river, a series of cascaded reservoirs and hydropower stations are constructed from upstream to downstream to fully utilize water resources. This is an important method for developing and utilizing river water resources. Reservoir scheduling refers to the planned storage and release of water based on known inflow conditions, utilizing the reservoir's own regulatory capacity. Optimal reservoir scheduling, as a key means of water resource utilization, can improve reservoir utilization efficiency, achieve water and energy conservation, reduce operating costs and environmental pollution, and ultimately achieve sustainable economic, social, and environmental development goals through optimized scheduling schemes. However, cascade reservoirs are complex systems composed of multiple interconnected reservoirs. The states of each reservoir are interrelated, and the state of each reservoir not only affects current decisions but also future decisions and the decisions of other reservoirs.

[0003] The optimal scheduling of cascade hydropower stations is a focus of attention in academia and engineering due to the multidimensional decision variable equations, nonlinearity, numerous constraints, input uncertainties, and the dynamic and complex relationships between variables such as water storage, head, and output. Furthermore, it requires the coordination of multiple scheduling objectives, such as power generation, flood control, and water supply. Therefore, how to comprehensively consider various constraints, balance the contradictions between different objectives, and solve the optimal scheduling scheme has always been a focus of attention in academia and engineering. Summary of the Invention

[0004] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0005] In view of the aforementioned existing problems, the present invention is proposed.

[0006] Therefore, this invention provides a cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program, which can solve the shortcomings of traditional genetic algorithm, such as getting trapped in local optima, requiring a lot of computing resources and time, and being dependent on chromosome encoding methods and operations.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program, comprising:

[0008] The initial population is generated using a genetic algorithm;

[0009] Based on the initial population, a simulation program is used to solve for fitness.

[0010] The evolutionary operation is performed in the genetic algorithm;

[0011] The algorithm terminates when the number of iterations ends.

[0012] As a preferred embodiment of the cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program described in this invention, the generation of the initial population specifically includes generating an initial population with the reservoir capacity within the range based on upper and lower limit constraints, with the objective function of maximizing reservoir power generation and ensuring maximum output.

[0013] As a preferred embodiment of the cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program described in this invention, the objective function includes:

[0014]

[0015] Where: T is the total number of time periods, N is the number of cascade reservoirs, W1 and W2 are the target weights, F is the guaranteed output of this cascade, and P is the target weight. it The power output of reservoir i during time period t is expressed in MW.

[0016] As a preferred embodiment of the cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program described in this invention, the upper and lower limit constraints include water balance constraints, reservoir capacity and outflow constraints, guaranteed output constraints, and reservoir output constraints.

[0017] As a preferred embodiment of the cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program described in this invention, wherein: the water balance constraint includes,

[0018]

[0019]

[0020] Among them, V i,t+1 Let V be the reservoir capacity of reservoir i in time period t+1. it Let V be the reservoir capacity of reservoir i during time period t. i,0 Let V be the initial capacity of reservoir i. i,T Let i be the final storage capacity of reservoir i. These represent the initial and final storage capacities of reservoir i during the scheduling period, in millions of cubic meters. 3 Q it Let m be the outflow from reservoir i during time period t. 3 / s;I it Let Q be the interval runoff of reservoir i during time period t. jt The outflow from the previous reservoir, in cubic meters per second (m³). 3 / s; Ω(I) is the upstream connected reservoir of reservoir i; Δt=1 is the time interval, in days;

[0021] The storage capacity and outbound flow constraints include:

[0022]

[0023] in, The dead storage capacity of reservoir i, in millions of cubic meters. 3 ; This represents the upper limit of reservoir i's capacity. During the flood season, it is the capacity corresponding to the flood control limit water level of the reservoir, and during the dry season, it is the capacity corresponding to the normal storage water level. The upper and lower limits of the outflow from reservoir i during time period t, in m³. 3 / s;

[0024] The guaranteed output constraint includes:

[0025]

[0026] The reservoir output constraints include:

[0027] P it ≤A i ·Q it ·h it (6)

[0028] The reservoir's output P it Limited by different water heads:

[0029]

[0030] Right now

[0031]

[0032] in, For reservoir i at water head h it Below, the coefficients of the linear equation fitted by the maximum power generation flow limit curve;

[0033] in,

[0034]

[0035]

[0036] A i The power generation coefficient of reservoir i is given by the unit: MW·s / m 4 h it Let i be the water head of reservoir i at time t; Let h be the power generation capacity of reservoir i during time period t. it The function; For V it and V i,t+1 The average value; These are the upstream water level and downstream water level of reservoir i at time t, respectively, determined by the reservoir capacity water level curve (ZV) and the downstream water level curve (ZQ); α i β i , χ² is the linear fitting coefficient of the ZV curve; i , δ i , The linear fitting coefficients for the ZQ curve are given.

[0037] As a preferred embodiment of the cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program described in this invention, wherein: the calculation of fitness includes,

[0038] Based on the initial population, the randomly generated reservoir capacity is used as the input to the simulation program, which solves for fitness. The simulation program proceeds sequentially from the upstream reservoir to the downstream reservoir.

[0039] As a preferred embodiment of the cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program described in this invention, wherein: the simulation program includes,

[0040] If minimizing water waste is not a condition, the following steps are performed:

[0041] Fix the initial and final storage capacity as

[0042]

[0043] Using the storage capacity V as the decision variable, and taking the initial population obtained from the genetic algorithm as input in the first iteration, let...

[0044] Here, we consider the reservoir capacity V of reservoir i at time t+1. i,t+1 Apply upper and lower limit constraints.

[0045]

[0046] Input the constrained reservoir capacity V, and solve for the outflow rate Q using the water balance constraint formula (2).it Equation (2) can be converted to:

[0047] Then, upper and lower limit constraints are applied to the calculated outbound flow rate.

[0048] Then, the storage capacity V and the outbound flow Q are calculated. it As input, calculate the head value h. it ;

[0049] Once the head value is known, calculate the output of the cascade reservoirs and convert the formula to...

[0050] Seek out effort, Then, it is determined whether to use the leveling algorithm to minimize water loss. If the leveling algorithm is not used, the second iteration begins.

[0051] The outbound flow rate Q obtained from the first cycle it As input, the water balance constraint formula is transformed

[0052] Replace with the formula for updating library capacity:

[0053] Add a condition, condition In other words, it determines whether the storage capacity converges before and after the number of iterations.

[0054] If convergence occurs, exit the loop; otherwise, continue iterating until convergence occurs.

[0055] As a preferred embodiment of the cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program described in this invention, the simulation level further includes:

[0056] If minimizing water loss is the condition, then the leveling algorithm is used, and the specific steps are as follows:

[0057] A forward-pushing method is used to absorb wastewater, and boundary conditions are set.

[0058]

[0059] Fixed initial storage capacity V i0 Unfixed final storage capacity V iT ;

[0060] The post-pull method is used to absorb wastewater; boundary conditions are set.

[0061]

[0062] Fixed final storage capacity V iT The initial storage capacity V is not fixed. i0 The time periods are in reverse order and are restricted to t = T-1, T-2, ..., 1; the updated storage capacity formula is modified as follows:

[0063]

[0064] Using the forward-looking method, the initial and final storage capacities are fixed, and the time period T = 0…T-1 is not restricted;

[0065] by Update outbound traffic;

[0066] Then use the updated outbound flow as input.

[0067] As a preferred embodiment of the cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program described in this invention, wherein: the evolutionary operation includes,

[0068] Selection, crossover, and mutation;

[0069] Selection is based on the fitness level from the previous step, choosing the individual with the highest fitness.

[0070] Crossover is controlled by crossover probability to generate new individuals;

[0071] Mutation is another operation to generate new individuals. First, mutations are generated randomly, and then the original basis of the mutation points is inverted according to the mutation probability.

[0072] As a preferred embodiment of the cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program described in this invention, the termination algorithm further includes:

[0073] If the iteration count is not completed, the fitness needs to be solved again, and the subsequent steps are repeated until the iteration count is completed, at which point the algorithm terminates.

[0074] The beneficial effects of this invention are as follows: The genetic algorithm and simulation program proposed in this invention have stable and high outputs in cascade reservoirs of different sizes, which can significantly improve the total power generation and guaranteed output of the cascade reservoirs, and the optimization effect is very good. The addition of the "soil leveling" algorithm to the proposed genetic algorithm and simulation program can significantly improve the results of total power generation and guaranteed output, and can reduce the water wastage of the four cascade reservoirs to 0, as can be seen from Table 1. Attached Figure Description

[0075] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0076] Figure 1A schematic diagram of a cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program is provided as an embodiment of the present invention;

[0077] Figure 2 This is a schematic diagram of the simulation program flow of a cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program, provided as an embodiment of the present invention.

[0078] Figure 3 A hydraulic connection diagram of a cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program provided in one embodiment of the present invention;

[0079] Figure 4 The maximum power generation flow curve fitting diagram is provided for a cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program in one embodiment of the present invention. Detailed Implementation

[0080] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0081] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0082] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0083] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0084] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used solely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0085] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0086] Example 1

[0087] Reference Figures 1-3 This is the first embodiment of the present invention, which provides a cascade reservoir optimization scheduling algorithm based on genetic algorithms and simulation programs, including:

[0088] S1: Generate the initial population using a genetic algorithm;

[0089] The objective function is to maximize the reservoir's power generation and ensure maximum output.

[0090]

[0091] Where: T=12 is the total number of time periods, N=4 is the number of cascade reservoirs, W1 and W2 are the target weights, F is the guaranteed output of this cascade, and P... it The power output of reservoir i during time period t is expressed in MW.

[0092] It should be noted that the hydraulic connections of the four cascade reservoirs are shown below. Figure 3 The scheduling cycle is one year, with one month (30 days) as an optimization period. The objective function is to maximize the power generation of the reservoir and ensure the maximum output.

[0093] Furthermore, using a genetic algorithm, an initial population is generated regarding the storage capacity within this range, based on upper and lower bound constraints;

[0094] The constraints include:

[0095] Water balance constraints:

[0096]

[0097]

[0098] Among them, V it+1 Let V be the reservoir capacity of reservoir i in time period t+1. it Let V be the reservoir capacity of reservoir i during time period t. i,0 Let V be the initial capacity of reservoir i. i,T Let i be the final storage capacity of reservoir i. These represent the initial and final storage capacities of reservoir i during the scheduling period, in millions of cubic meters. 3 Q it Let m be the outflow from reservoir i during time period t. 3 / s;I it Let Q be the interval runoff of reservoir i during time period t. jt The outflow from the previous reservoir, in cubic meters per second (m³). 3 / s; Ω(I) is the upstream connected reservoir of reservoir i; Δt=1 is the time interval, in days;

[0099] Storage capacity and outbound flow constraints:

[0100]

[0101] in, The dead storage capacity of reservoir i, in millions of cubic meters. 3 ; is the upper limit of reservoir i's capacity. During the flood season, it is the capacity corresponding to the flood control limit water level of the reservoir, and during the dry season, it is the capacity corresponding to the normal storage water level. The upper and lower limits of the outflow from reservoir i during time period t, in m³. 3 / s.

[0102] Output constraints must be guaranteed.

[0103]

[0104] Reservoir output constraints:

[0105] P it ≤A i ·Q it ·h it (6)

[0106] The reservoir's output P it Limited by different water heads:

[0107]

[0108] Right now

[0109]

[0110] in, For reservoir i at water head hit Below, the coefficients of the linear equation fitted based on the maximum power generation flow limit curve are as follows: Figure 4 As shown;

[0111] in,

[0112]

[0113]

[0114] A i The power generation coefficient of reservoir i is given by the unit: MW·s / m 4 h it Let i be the water head of reservoir i at time t; Let h be the power generation capacity of reservoir i during time period t. it The function; For V it and V i,t+1 The average value; These are the upstream water level and downstream water level of reservoir i at time t, respectively, determined by the reservoir capacity water level curve (ZV) and the downstream water level curve (ZQ); α i β i , χ² is the linear fitting coefficient of the ZV curve; i , δ i , The linear fitting coefficients for the ZQ curve are given.

[0115] S2: Solve for fitness based on the initial population;

[0116] Based on the initial population, randomly generated library capacity is used as input to the simulation program, and fitness is then solved within the simulation program. Figure 2 As shown. The simulation program will proceed sequentially from the upstream reservoir to the downstream reservoir, with the specific steps as follows:

[0117] • If minimizing water waste is not a condition, proceed with the following steps:

[0118] (1) Fix the initial and final storage capacity as

[0119] (2) Using the storage capacity V as the decision variable, and taking the initial population obtained from the genetic algorithm as the input in the first iteration, let...

[0120] (3) Here, the reservoir capacity V of reservoir i at time t+1 is given. i,t+1 Apply upper and lower limit constraints, as shown in formula (4).

[0121] (4) Input the constrained storage capacity V, use the water balance constraint formula (2) to solve for the outflow Qiit, and convert formula (2) into:

[0122] (5) Then apply upper and lower limit constraints to the calculated outbound flow rate, as shown in formula (4).

[0123] (6) Then, the storage capacity V and the outflow rate Q are calculated. it As the input, the head h is calculated according to the water formulas (9) and (10). it .

[0124] (7) Once the head value is known, calculate the output of the cascade reservoirs using formulas (6) and (7), and then convert the formulas to...

[0125] (8) After calculating the output, add a judgment to see if the "leveling" algorithm is used to minimize the water loss. If the "leveling" algorithm is not used, start the second iteration.

[0126] (9) The outbound flow rate Q obtained from the first cycle it As input, the water balance constraint formula (2) is converted into V i,t+1 :=V it +(∑Q jt +I it -Q it Update the storage capacity by (Δt·0.24×0.36).

[0127] (10) Add a conditional statement, conditional statement In other words, it determines whether the storage capacity before and after the number of cycles converges and tends to stabilize.

[0128] (11) If convergence occurs, exit the loop; if convergence does not occur, iterate from (2) to (10) until convergence occurs.

[0129] • If the condition is to minimize water loss, then the "leveling" algorithm is used. The "leveling" algorithm is added to the steps (2)-(9). The specific steps are as follows:

[0130] ① Employing the "forward push method" to absorb wastewater, and setting boundary conditions.

[0131] Fixed initial storage capacity V i0 Unfixed final storage capacity V iT .

[0132] It should be noted that the "forward method" is... Figure 2 Go through the process again;

[0133] ② The "post-pull method" is used to absorb the wastewater, and boundary conditions are set.

[0134] Fixed final storage capacity V iT The initial storage capacity V is not fixed. i0 The time periods are in reverse order and are restricted to t = T-1, T-2, ..., 1.

[0135] It should be noted that the "rear pull method" only requires... Figure 2 The capacity update formula in the middle is changed to:

[0136]

[0137] The remaining constraints simply require swapping all the storage capacity indices 't' and 't+1'; the process remains the same. Figure 2

[0138] ③ The “forward push method” is adopted, which fixes both the initial and final storage capacity and does not restrict the time period T = 0…T-1.

[0139] ④ with Update outbound traffic

[0140] Finally, using the updated outbound flow as input, proceed with steps (9)-(11).

[0141] S3: Perform the evolutionary operation in the genetic algorithm;

[0142] Selection, crossover, mutation.

[0143] It should be noted that selection is based on the fitness value from the previous step, choosing the individual with the highest fitness. Crossover is controlled by the crossover probability to generate new individuals. Mutation is another operation for generating new individuals. It involves first randomly generating mutations, and then, based on the mutation probability, inverting the original values ​​of the mutated points.

[0144] S4: The iteration count ends, and the algorithm terminates;

[0145] If the iteration count is not completed, the fitness needs to be solved again, and the subsequent steps are repeated until the iteration count is completed, at which point the algorithm terminates.

[0146] Example 2

[0147] As one embodiment of the present invention, a cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program is provided. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0148] The table below shows a comparison of the scheduling results of the two algorithms invented by our company in practical applications:

[0149] Table 1 Comparison of guaranteed power output, power generation, and water waste processes between the two algorithms

[0150]

[0151] This shows that without minimizing water discharge, the guaranteed output and total power generation of cascade reservoirs in dry, normal, and wet years are all lower than after minimizing water discharge.

[0152] Therefore, by incorporating the "soil leveling" algorithm (minimizing water waste) into the genetic algorithm and simulation program proposed in this invention, the results of total power generation and guaranteed output can be significantly improved. This can reduce the water waste of the four cascade reservoirs to zero and greatly improve the water resource utilization rate.

[0153] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program, characterized in that: include, The initial population is generated using a genetic algorithm; Based on the initial population, a simulation program is used to solve for fitness. The evolutionary operation is performed in the genetic algorithm; The algorithm terminates when the number of iterations ends. The generation of the initial population specifically includes, With the objective functions of maximizing reservoir power generation and ensuring maximum output, a genetic algorithm is used to generate an initial population of reservoirs within the specified range, based on upper and lower bound constraints. Calculate fitness, including, Based on the first-generation population, the randomly generated reservoir capacity is used as the input to the simulation program, and the fitness is solved in the simulation program. The simulation program will proceed from the upstream reservoir to the downstream reservoir in sequence. The simulation program includes, If minimizing water waste is not a condition, the following steps are performed: Fix the initial and final storage capacity as ， in, For reservoir The initial storage capacity, Reservoirs The initial and final storage capacity during the scheduling period. For reservoir The final storage capacity; Using the storage capacity V as the decision variable, and taking the initial population obtained from the genetic algorithm as input in the first iteration, let... ; in, Reservoir During the period The physical storage capacity value in the 0th iteration. For reservoir During the period Storage capacity; Here, we examine the reservoir capacity of reservoir i at time t+1. Apply upper and lower limit constraints: ， in, For reservoir Dead storage capacity, For reservoir During the period The maximum storage capacity; Input the constrained reservoir capacity V, and use the water balance constraint formula to solve for the outflow rate. Convert the formula to: ， in, For reservoir During the period Outbound flow For reservoir During the period Inter-regional runoff, The outflow from the previous reservoir, in units of: , The time interval is in days. For reservoir During the period Storage capacity; Then, upper and lower limit constraints are applied to the calculated outbound flow rate. ， in, For reservoir During the period Upper and lower limits of outbound flow, unit: ; Then, the storage capacity V and the outbound flow Q are calculated. As input, calculate the head value. ; Once the head value is known, calculate the output of the cascade reservoirs and convert the formula to: ， in, Indicates the power output of the reservoir. For reservoir The power generation coefficient, For reservoir During the period water head, For reservoir At the water's head Below, the coefficients of the linear equation fitted by the maximum power generation flow limit curve; Calculate the output and determine whether to use the leveling algorithm to minimize water loss. If the leveling algorithm is not used, start the second iteration. Outbound flow rate obtained from the first cycle As input, the water balance constraint formula is transformed into an updated reservoir capacity formula: ， Add a condition, condition In other words, it determines whether the storage capacity converges before and after the number of iterations. If convergence occurs, exit the loop; if convergence does not occur, continue iterating until convergence occurs. The degree of simulation also includes, If minimizing water loss is the condition, then the leveling algorithm is used, and the specific steps are as follows: A forward-pushing method is used to absorb wastewater, and boundary conditions are set. ， in, Reservoirs The initial and final storage capacity during the scheduling period. For reservoir The initial storage capacity; Fixed initial storage capacity Unfixed final storage capacity ; The post-pull method is used to absorb wastewater; boundary conditions are set. ， in, For reservoir The final storage capacity; Fixed final storage capacity The initial storage capacity is not fixed. The time periods are in reverse order and are restricted to t=T-1, T-2,…,1; the updated storage capacity formula is modified as follows: ， The forward-looking method is used to fix the initial and final storage capacities, without limiting the time period T=0…T-1; by Update outbound traffic; Then use the updated outbound flow as input.

2. The cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program as described in claim 1, characterized in that: The objective function includes, (1)， in: This represents the total number of time periods. The number of cascade reservoirs. For the target weight, To ensure the output of this cascade For reservoir During the period Power output, unit: MW.

3. The cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program as described in claim 2, characterized in that: The upper and lower limit constraints include, Water balance constraints, reservoir capacity and outflow constraints, guaranteed output constraints, and reservoir output constraints.

4. The cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program as described in claim 3, characterized in that: The water balance constraint includes, (2)， (3)， in, For reservoir During the period Storage capacity, For reservoir During the period Storage capacity, For reservoir The initial storage capacity, For the reservoir The final storage capacity, Reservoirs Initial and final storage capacity during the scheduling period, in millions. ; For reservoir During the period Outbound flow rate, unit: ; For reservoir During the period Inter-regional runoff, The outflow from the previous reservoir, in units of: ; For reservoir The upstream connection to the reservoir; The time interval is in days. The storage capacity and outbound flow constraints include: (4)， in, For reservoir Dead storage capacity, unit: million ; For reservoir The upper limit of the reservoir capacity is the reservoir capacity corresponding to the flood control limit water level during the flood season, and the reservoir capacity corresponding to the normal storage water level during the dry season. For reservoir During the period Upper and lower limits of outbound flow, unit: ; The guaranteed output constraint includes: (5)， The reservoir output constraints include: (6)， The output of the reservoir Limited by different water heads: (7)， Right now (8)， in, For reservoir At the water's head Below, the coefficients of the linear equation fitted by the maximum power generation flow limit curve; in, (9)， (10)， For reservoir Power generation coefficient, unit: ; For reservoir During the period water head; For reservoir During the period The power generation capacity is the head of the water The function; for and The average value; These are reservoirs During the period The water levels in front of the dam and the tailwater level are determined by the reservoir capacity water level curve (ZV) and the tailwater level curve (ZQ), respectively. , The linear fitting coefficients of the ZV curve; , The linear fitting coefficients for the ZQ curve are given.

5. The cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program as described in claim 1, characterized in that: The evolutionary operation includes, Selection, crossover, and mutation; Selection is based on the fitness level from the previous step, choosing the individual with the highest fitness. Crossover is controlled by crossover probability to generate new individuals; Mutation is another operation to generate new individuals. First, mutations are generated randomly, and then the original basis of the mutation points is inverted according to the mutation probability.

6. The cascade reservoir optimization scheduling algorithm based on genetic algorithm and simulation program as described in claim 1, characterized in that: The termination algorithm also includes, If the iteration count is not completed, the fitness needs to be solved again, and the subsequent steps are repeated until the iteration count is completed, at which point the algorithm terminates.

Images