CN108009672A - Water light complementation power station daily trading planning preparation method based on bi-level optimal model - Google Patents

Abstract

The present invention provides a method for preparing a daily power generation plan of a hydro-photovoltaic hybrid power station based on a double-layer optimization model, which is characterized in that it includes: Step 1: Predict the process of photoelectric next-day output, and generate multiple photoelectric output scenarios based on the photoelectric output uncertainty model And calculate the corresponding probability; Step 2: Predict the runoff process of the reservoir entering the reservoir the next day, and determine the daily available water or electricity according to the medium and long-term dispatch plan; Step 3: Establish a two-layer optimization model, and the outer model considers the requirements of the power system to optimize the available water or electricity. For the distribution of electricity in time, the optimization goal is that the total output process of the hydro-solar hybrid power station has the greatest correlation with the typical daily load curve; the inner model considers the operation efficiency of the hydropower station to optimize the distribution of water among the units, and the optimization goal is the operation of the hydropower station under multiple scenarios The highest efficiency; Step 4: Solve the model, the outer layer uses intelligent algorithms to determine the power generation flow of the power station at each time period and the number of units to start up, and the inner layer uses the dynamic programming method to determine the optimal load distribution strategy.

Description

Compilation method of daily power generation plan for hydro-solar hybrid power station based on double-layer optimization model

technical field

The invention belongs to the intersecting field of renewable energy utilization and reservoir dispatching, and specifically relates to a method for preparing daily power generation plan of a hydro-photoelectric complementary power station based on a double-layer optimization model.

technical background

The development of solar photovoltaic power generation is an important measure to alleviate the future energy crisis and improve the energy structure. However, photoelectricity is a new energy that cannot be dispatched, and it is easily affected by various meteorological factors, and its output presents strong intermittency, volatility and randomness. The direct connection of photovoltaics to the grid will have an impact on the safe and stable operation of the grid. Hydropower has the characteristics of flexible start, fast adjustment speed, and low operating cost. It is an ideal regulated power source. The implementation of water-solar complementary power generation, connecting violently fluctuating photovoltaics to hydropower stations, using the rapid adjustment capabilities of hydropower stations to compensate, and then sending the superimposed stable output to the power grid can greatly reduce the adverse impact on the operation of the power grid. The compilation of daily power generation plan of hydropower station is a basic subject of economic operation of hydropower station.

The preparation of traditional hydropower generation plan is to maximize the power generation or minimize the water consumption of the hydropower station by formulating a reasonable start-up and shutdown sequence and a load distribution strategy among units under the given daily total water or daily electricity conditions. As random photoelectricity is connected to hydropower stations, hydropower dispatching decisions will become uncertain, resulting in the power generation plan formulated by traditional methods being unable to effectively guide the actual operation of hydropower hybrid power stations. How to formulate a daily power generation plan under the condition of uncertainty in the photovoltaic output forecast to make the hydro-solar hybrid power station operate safely and economically is an urgent problem to be solved in the implementation of hydro-solar hybrid dispatch.

Contents of the invention

The present invention is made to solve the above problems, and the purpose is to provide a method for preparing a daily power generation plan of a water-solar hybrid power station based on a two-layer optimization model.

In order to achieve the above object, the present invention adopts the following scheme:

The invention provides a method for preparing a daily power generation plan of a water-photoelectric complementary power station based on a double-layer optimization model, which is characterized in that it includes the following steps: Step 1: Predict the output process of the photoelectric next day, and generate a variety of photoelectric power plants based on the photoelectric output uncertainty model Scenarios and calculate the probability corresponding to each scenario; Step 2: Predict the runoff process of the reservoir entering the reservoir the next day, and determine the daily available water volume or daily available electricity according to the medium and long-term dispatch plan; Step 3: Establish a two-layer optimization model, and the outer model considers electricity The system requires optimizing the distribution of available water or daily available electricity in terms of time; the inner model considers the operation efficiency of the hydropower station to optimize the distribution of water among units; the outer optimization goal is the correlation between the total output process of the hydro-solar hybrid power station and the typical daily load curve Maximum, the calculation formula is: The inner optimization objective is the highest operating efficiency of the hydropower station under multiple scenarios, and the calculation formula is: In the formula: R is the correlation coefficient between the total output process of hydro-photovoltaic hybrid power station and the typical daily load curve; T is the total number of scheduling periods; t is the number of scheduling periods; is the total output of hydro-photovoltaic hybrid power station in period t; is the average output of the hydro-solar hybrid power station; D _t is the per unit value of the typical daily load curve t period; is the average per unit value of the typical daily load curve; η is the average power generation efficiency coefficient of the hydropower station; M is the number of photovoltaic scenarios; m is the number of photovoltaic scenarios; ρ _m is the probability corresponding to the mth photovoltaic scenario; is the output of the hydropower station at the t-th moment under the m scenario; R _m,t is the power generation flow of the hydropower station at the t-th moment under the m scenario; η is the average power generation efficiency coefficient of the hydropower station; Step 4: Solve the double-layer optimization model, The outer layer uses an intelligent algorithm to determine the power generation flow of the power station at each time period and the number of units to start up, and the inner layer uses a dynamic programming method to determine the optimal load distribution strategy.

The daily power generation planning method of hydro-photovoltaic hybrid power station based on the double-layer optimization model provided by the present invention can also have the following characteristics: In step 2: first, use a mathematical statistical model or a physical model to predict the photoelectric output process (P _t , t=1,...,T); Secondly, assume that the photoelectric prediction error e obeys the normal distribution N(0,σ ² ); consider three kinds of prediction errors, that is, the prediction is small (e ₁ =-σ), the prediction is accurate ( e ₁ ＝0) and the prediction is too large (e ₃ ＝+σ), the different photoelectric output scenarios can be obtained by subtracting different prediction error values from the predicted value; finally, the discrete probability distribution is used instead of the continuous probability distribution to calculate the The probability ρ ₁ , ρ ₂ , ρ ₃ corresponding to the scenario:

The daily power generation planning method of hydro-photovoltaic hybrid power station based on the double-layer optimization model provided by the present invention can also have the following characteristics: in step 2, firstly, a mathematical statistical model or a hydrological model is used to predict the inflow flow process of the reservoir in the next day ( I _t , t=1,..., T); secondly, distribute the amount of water to be discharged in the mid- and long-term dispatching plan evenly to each day, so as to determine the daily available water amount.

The daily power generation plan preparation method of hydro-solar hybrid power station based on the double-layer optimization model provided by the present invention can also have the following characteristics: in step 3: In the formula: N is the number of hydroelectric units; n is the number of the unit; u _n,t is the switch state of the hydroelectric unit (1 is on, 0 is off); is the output of the hydropower unit n in the t-th period under the m scenario; is the output of the photovoltaic power station in the m-th scenario of the t-period; f _rph is the relationship between the unit flow rate, output and water head in the dynamic characteristic curve of the hydroelectric unit; f _vz is the water level-storage capacity relationship; f _qz is the discharge flow-tail Water level relationship; r _m,n,t is the power generation reference flow of the nth hydropower unit in the tth period in the mth scenario; h _m,t , are the net water head, water level in front of the dam, tail water level and head loss in the t-th period in the m-th scenario; v _m,t and v _m,t+1 are the beginning and end of the t-th period in the m-th scenario reservoir capacity.

The daily power generation planning method of hydro-photovoltaic hybrid power station based on the double-layer optimization model provided by the present invention can also have the following features: in step 4, an intelligent algorithm is used to determine the power generation flow [q ₁ ,...,q _T ] of the power station at each time period And when the number of units starting up [y ₁ ,…,y _T ], the coding method of the intelligent algorithm solution is expressed by the following formula: solution=[q ₁ ,…,q _T ,y ₁ ,…,y _T ], using dynamic programming When the load is optimally distributed, the two-stage recurrence equation is: In the formula: for the total load of The optimal water consumption allocated among d units, f _rph (p _d,t ,h _t ) is the water consumption of unit d when the load is p _{d, t} head is h _t , for the total load of The optimal water consumption allocated among d-1 units.

Function and Effect of Invention

The present invention fully considers the randomness characteristics of photoelectric output, and can still provide a robust and efficient power generation plan to guide the actual operation of hydro-photoelectric hybrid power stations even when the photoelectric prediction is inaccurate.

Description of drawings

Fig. 1 is a flowchart of a method for preparing a daily power generation plan of a water-solar hybrid power station based on a two-layer optimization model in an embodiment of the present invention.

Detailed ways

The specific implementation of the daily power generation planning method for hydro-solar hybrid power plants based on the two-layer optimization model involved in the present invention will be described in detail below in conjunction with the accompanying drawings.

<Example>

As shown in Figure 1, the method for preparing the daily power generation plan of the water-solar hybrid power station based on the double-layer optimization model provided by this embodiment includes the following steps:

1. Predict the output process of photovoltaics in the next day, generate multiple photovoltaic output scenarios based on the photovoltaic output uncertainty model and calculate the probability corresponding to each scenario.

First, use a mathematical statistical model or a physical model to predict the photoelectric output process of the next day (P _t , t=1,..., T);

Secondly, assume that the photoelectric prediction error e obeys the normal distribution N(0,σ ² ); consider three kinds of prediction errors, namely small prediction (e ₁ =-σ), accurate prediction (e ₁ =0) and large prediction ( e ₃ ＝+σ), and different photoelectric output scenarios can be obtained by subtracting different prediction error values from the predicted value;

Finally, the probability (ρ ₁ , ρ ₂ , ρ ₃ ) corresponding to each photoelectric scenario can be calculated by using the discrete probability distribution instead of the continuous probability distribution as follows:

2. Predict the runoff process of the reservoir entering the reservoir the next day, and determine the daily water availability according to the medium and long-term scheduling plan.

First, use a mathematical statistical model or a hydrological model to predict the inflow flow process of the reservoir in the next day (I _t , t=1,..., T);

Secondly, the amount of water to be discharged in the medium- and long-term (monthly or ten-day) scheduling plan is evenly distributed to each day to determine the daily available water amount.

3. Establish a double-layer optimization model. The outer model considers the power system requirements to optimize the distribution of available water in time; the inner model considers the operating efficiency of the hydropower station to optimize the distribution of water among units.

The optimization objective of the outer layer is that the total output process of the hydro-solar hybrid power station has the greatest correlation with the typical daily load curve, and the calculation formula is:

In the formula: R is the correlation coefficient between the total output process of hydro-photovoltaic hybrid power station and the typical daily load curve; T is the total number of scheduling periods; t is the number of scheduling periods; is the total output of hydro-photovoltaic hybrid power station in period t; is the average output of the hydro-solar hybrid power station; D _t is the per unit value of the typical daily load curve t period; is the average value per unit of the typical daily load curve; N is the number of hydroelectric units; n is the unit number; u _n,t is the on-off status of the hydroelectric unit (1 is on, 0 is off); m is the photoelectric scene number; is the output of the hydropower unit n in the t-th period under the m scenario; is the output of the photovoltaic power station in the m-th scenario in the t-th period. f _rph is the relationship among unit flow, output and water head in the dynamic characteristic curve of the hydroelectric unit; f _vz is the water level-storage capacity relationship; f _qz is the discharge flow-tail water level relationship; r _m,n,t is the mth type In the scenario, the power generation reference flow of the nth hydropower unit in the tth period; h _m,t , are the net water head, water level in front of the dam, tailwater level and head loss in the t-th period in the m-th scenario; v _m,t and v _m,t+1 are the beginning and end of the t-th period in the m-th scenario reservoir capacity.

The inner optimization objective is the highest operating efficiency of the hydropower station under multiple scenarios, and the calculation formula is:

In the formula: η is the average power generation efficiency coefficient of the hydropower station; M is the total number of photovoltaic scenarios; _m is the number of photovoltaic scenarios; ρm is the probability corresponding to the mth photovoltaic scenario; is the output of the hydropower station at the t-th moment under the m scenario; R _m,t is the power generation flow of the hydropower station at the t-th moment under the m scenario.

The constraints considered by the established two-tier optimization model are: water balance constraints, daily water consumption constraints (or daily power generation constraints), storage capacity constraints, unit flow constraints, unit output constraints, load reserve constraints, and output fluctuations. Constraints, minimum start and stop constraints, and vibration zone constraints.

v _m,t+1 ＝v _m,t +(I _t -R _m,t -L _m,t )Δt (11)

In the formula: v _m,t and v _m,t+1 are the storage capacity of the reservoir at the beginning and end of the period t under the m-th scenario respectively; I _t is the inflow flow of the reservoir in the period t; L _m,t is the reservoir capacity Abandoned water flow; ΔW is the daily available water volume (if the power generation plan is based on the daily available electricity, here it is changed to hydropower daily available electricity); and are the lower limit and upper limit of storage capacity respectively; and are the lower limit and upper limit of the generating flow of the nth unit in the tth period, respectively; and are the lower limit and upper limit of unit output respectively; the load reserve value of LR _t hydropower station in the tth period; p _m,n,t and p _m,n,t-1 are respectively The output value of time period and t-1 period; Δp ^d and Δp ^u are the upper limit values of the output drop and rise speed of the hydropower station respectively; SU _n and SD _n are the minimum duration of the start-up and shutdown states of the hydropower units; su _n,t are the unit start-up Process indication state (1 means start, 0 means no start); sd _{n, t} is the indication state of the unit shutdown process (1 means turn off, 0 means no turn off); and are the lower limit and upper limit of the vibration zone of the unit, respectively.

4. Solve the double-layer optimization model. The outer layer uses intelligent algorithms (such as genetic algorithm, cuckoo algorithm) to determine the power generation flow of the power station at each time period and the number of units to start.

When the intelligent algorithm is used to determine the power generation flow ([q ₁ ,…,q _T ]) of the power station at each time period and the number of units started ([y ₁ ,…,y _T ]), the coding method of the intelligent algorithm solution (individual) can be adopted The following formula represents:

solution＝[q ₁ ,…,q _T ,y ₁ ,…,y _T ] (21)

When the dynamic programming method is used to optimize the load distribution strategy in the inner layer, this part of the calculation can be completed in advance because the calculation of dynamic programming takes a long time. That is to calculate the optimal distribution strategy of all loads under all possible water heads (the load and power generation flow borne by each unit) under different numbers of start-up units. When performing double-layer optimization, the relevant calculation results can be directly called. When dynamic programming is used for optimal load distribution, the two-stage recurrence equation is:

In the formula: for the total load The optimal water consumption allocated among d units; f _rph (p _d,t ,h _t ) is the water consumption of unit d when the load is p _{d, and the t} head is h _t ; for the total load of The optimal water consumption allocated among d-1 units.

The above embodiments are merely illustrations for the technical solution of the present invention. The daily power generation planning method of hydro-solar hybrid power station based on the double-layer optimization model involved in the present invention is not limited to the content described in the above embodiments, but is subject to the scope defined in the claims. Any modifications, supplements or equivalent replacements made by those skilled in the art of the present invention on the basis of the embodiments are within the protection scope of the claims of the present invention.

Claims (5)

1. A method for preparing daily power generation plan of hydro-solar hybrid power station based on double-layer optimization model, characterized in that it comprises the following steps: Step 1: Predict the output process of photovoltaics in the next day, generate multiple photovoltaic output scenarios based on the photovoltaic output uncertainty model and calculate the probability corresponding to each scenario; Step 2: Predict the runoff process of the reservoir entering the reservoir the next day, and determine the daily available water volume or daily available electricity according to the medium and long-term dispatch plan; Step 3: Establish a two-layer optimization model. The outer model considers the requirements of the power system to optimize the distribution of available water or daily available electricity in time; the inner model considers the operating efficiency of the hydropower station to optimize the distribution of water among units; The optimization objective of the outer layer is that the total output process of the hydro-solar hybrid power station has the greatest correlation with the typical daily load curve, and the calculation formula is: <mrow><mi>max</mi><mi>R</mi><mo>=</mo><mfrac><mrow><munderover><mo>&amp;Sigma;</mo><mrow><mi>t</mi><mo>=</mo><mn>1</mn></mrow><mi>T</mi></munderover><mo>&amp;lsqb;</mo><mrow><mo>(</mo><msubsup><mi>P</mi><mi>t</mi><mrow><mi>s</mi><mi>g</mi></mrow></msubsup><mo>-</mo><msup><mover><mi>P</mi><mo>&amp;OverBar;</mo></mover><mrow><mi>s</mi><mi>g</mi></mrow></msup><mo>)</mo></mrow><mo>&amp;CenterDot;</mo><mrow><mo>(</mo><msub><mi>D</mi><mi>t</mi></msub><mo>-</mo><mover><mi>D</mi><mo>&amp;OverBar;</mo></mover><mo>)</mo></mrow><mo>&amp;rsqb;</mo></mrow><msqrt><mrow><munderover><mo>&amp;Sigma;</mo><mrow><mi>t</mi><mo>=</mo><mn>1</mn></mrow><mi>T</mi></munderover><msup><mrow><mo>(</mo><msubsup><mi>P</mi><mi>t</mi><mrow><mi>s</mi><mi>g</mi></mrow></msubsup><mo>-</mo><msup><mover><mi>P</mi><mo>&amp;OverBar;</mo></mover><mrow><mi>s</mi><mi>g</mi></mrow></msup><mo>)</mo></mrow><mn>2</mn></msup><mo>&amp;CenterDot;</mo><munderover><mo>&amp;Sigma;</mo><mrow><mi>t</mi><mo>=</mo><mn>1</mn></mrow><mi>T</mi></munderover><msup><mrow><mo>(</mo><msub><mi>D</mi><mi>t</mi></msub><mo>-</mo><mover><mi>D</mi><mo>&amp;OverBar;</mo></mover><mo>)</mo></mrow><mn>2</mn></msup></mrow></msqrt></mfrac><mo>,</mo></mrow> The inner optimization objective is the highest operating efficiency of the hydropower station under multiple scenarios, and the calculation formula is: <mrow><mi>m</mi><mi>a</mi><mi>x</mi><mi>&amp;eta;</mi><mo>=</mo><munderover><mo>&amp;Sigma;</mo><mrow><mi>m</mi><mo>=</mo><mn>1</mn></mrow><mi>M</mi></munderover><msub><mi>&amp;rho;</mi><mi>m</mi></msub><munderover><mo>&amp;Sigma;</mo><mrow><mi>t</mi><mo>=</mo><mn>1</mn></mrow><mi>T</mi></munderover><mfrac><msubsup><mi>P</mi><mrow><mi>m</mi><mo>,</mo><mi>t</mi></mrow><mi>s</mi></msubsup><mrow><msub><mi>R</mi><mrow><mi>m</mi><mo>,</mo><mi>t</mi></mrow></msub><mi>&amp;Delta;</mi><mi>t</mi></mrow></mfrac><mo>,</mo></mrow> In the formula: R is the correlation coefficient between the total output process of the ^hydro -photovoltaic hybrid power station and the typical daily load curve; T is the total number of dispatching periods; _t is the number of dispatching periods; is the average output of the hydro-solar hybrid power station; D _t is the per unit value of the typical daily load curve t period; is the average per unit value of the typical daily load curve; η is the average power generation efficiency coefficient of the hydropower station; M is the number of photovoltaic scenarios; m is the number of photovoltaic scenarios; ρ _m is the probability corresponding to the mth photovoltaic scenario; is the output of the hydropower station at the t-th moment under the m scenario; R _m,t is the power generation flow of the hydropower station at the t-th moment under the m scenario; η is the average power generation efficiency coefficient of the hydropower station; Step 4: Solve the double-layer optimization model. The outer layer uses intelligent algorithms to determine the power generation flow and the number of units to start up in each period of the power station, and the inner layer uses dynamic programming to determine the optimal load distribution strategy. 2. The daily power generation planning method of hydro-solar hybrid power station based on the double-layer optimization model according to claim 1, characterized in that: Among them, in step two: first, adopt mathematical statistical model or physical model to predict the photoelectric output process (P _t , t=1,..., T) of the future day; secondly, assume photoelectric prediction error e obeys normal distribution N(0 ,σ ² ); Considering three types of prediction errors, namely small prediction (e ₁ ＝-σ), accurate prediction (e ₁ ＝0) and large prediction (e ₃ ＝+σ), the predicted value is subtracted by different Different photoelectric output scenarios can be obtained by predicting the error value; finally, the probability (ρ ₁ , ρ ₂ , ρ ₃ ) corresponding to each photoelectric scenario is calculated by using the discrete probability distribution instead of the continuous probability distribution: <mrow><mfenced open = "{" close = ""><mtable><mtr><mtd><mrow><msub><mi>&amp;rho;</mi><mn>1</mn></msub><mo>+</mo><msub><mi>&amp;rho;</mi><mn>2</mn></msub><mo>+</mo><msub><mi>&amp;rho;</mi><mn>3</mn></msub><mo>=</mo><mn>1</mn></mrow></mtd></mtr><mtr><mtd><mrow><msub><mi>&amp;rho;</mi><mn>1</mn></msub><msub><mi>e</mi><mn>1</mn></msub><mo>+</mo><msub><mi>&amp;rho;</mi><mn>2</mn></msub><msub><mi>e</mi><mn>2</mn></msub><mo>+</mo><msub><mi>&amp;rho;</mi><mn>3</mn></msub><msub><mi>e</mi><mn>3</mn></msub><mo>=</mo><msubsup><mo>&amp;Integral;</mo><mrow><mo>-</mo><mi>&amp;infin;</mi></mrow><mrow><mo>+</mo><mi>&amp;infin;</mi></mrow></msubsup><mi>f</mi><mrow><mo>(</mo><mi>e</mi><mo>)</mo></mrow><msup><mi>e</mi><mn>1</mn></msup><mi>d</mi><mi>e</mi><mo>=</mo><mn>0</mn></mrow></mtd></mtr><mtr><mtd><mrow><msub><mi>&amp;rho;</mi><mn>1</mn></msub><msubsup><mi>e</mi><mn>1</mn><mn>2</mn></msubsup><mo>+</mo><msub><mi>&amp;rho;</mi><mn>2</mn></msub><msubsup><mi>e</mi><mn>2</mn><mn>2</mn></msubsup><mo>+</mo><msub><mi>&amp;rho;</mi><mn>3</mn></msub><msubsup><mi>e</mi><mn>3</mn><mn>2</mn></msubsup><mo>=</mo><msubsup><mo>&amp;Integral;</mo><mrow><mo>-</mo><mi>&amp;infin;</mi></mrow><mrow><mo>+</mo><mi>&amp;infin;</mi></mrow></msubsup><mi>f</mi><mrow><mo>(</mo><mi>e</mi><mo>)</mo></mrow><msup><mi>e</mi><mn>2</mn></msup><mi>d</mi><mi>e</mi><mo>=</mo><msup><mi>&amp;sigma;</mi><mn>2</mn></msup></mrow></mtd></mtr></mtable></mfenced><mo>.</mo></mrow> 3. The daily power generation planning method of hydro-solar complementary power station based on the double-layer optimization model according to claim 1, characterized in that: Among them, in step 2, firstly, use a mathematical statistical model or a hydrological model to predict the inflow flow process of the reservoir in the next day (I _t , t=1,..., T); Evenly distributed to the daily, in order to determine the daily water availability. 4. The daily power generation planning method of hydro-solar hybrid power station based on the double-layer optimization model according to claim 1, characterized in that: Among them, in step three: <mrow><msubsup><mi>P</mi><mi>t</mi><mrow><mi>s</mi><mi>g</mi></mrow></msubsup><mo>=</mo><munderover><mo>&amp;Sigma;</mo><mrow><mi>n</mi><mo>=</mo><mn>1</mn></mo>mrow><mi>N</mi></munderover><msub><mi>u</mi><mrow><mi>n</mi><mo>,</mo><mi>t</mi></mrow></msub><msubsup><mi>p</mi><mrow><mi>m</mi><mo>,</mo><mi>n</mi><mo>,</mo><mi>t</mi></mrow><mi>s</mi></msubsup><mo>+</mo><msubsup><mi>p</mi><mrow><mi>m</mi><mo>,</mo><mi>t</mi></mrow><mi>g</mi></msubsup><mo>,</mo><mi>m</mi><mo>=</mo><mn>1</mn><mo>,</mo><mn>2</mn><mo>,</mo><mn>3</mn><mo>,</mo></mrow> <mrow><msubsup><mi>p</mi><mrow><mi>m</mi><mo>,</mo><mi>n</mi><mo>,</mo><mi>t</mi></mrow><mi>s</mi></msubsup><mo>=</mo><msub><mi>f</mi><mrow><mi>r</mi><mi>p</mi><mi>h</mi></mrow></msub><mrow><mo>(</mo><msub><mi>r</mi><mrow><mi>m</mi><mo>,</mo><mi>n</mi><mo>,</mo><mi>t</mi></mrow></msub><mo>,</mo><msub><mi>h</mi><mrow><mi>m</mi><mo>,</mo><mi>t</mi></mrow></msub><mo>)</mo></mrow><mo>,</mo></mrow> <mrow><msub><mi>h</mi><mrow><mi>m</mi><mo>,</mo><mi>t</mi></mrow></msub><mo>=</mo><msubsup><mi>z</mi><mrow><mi>m</mi><mo>,</mo><mi>t</mi></mrow><mrow><mi>u</mi><mi>p</mi></mrow></msubsup><mo>-</mo><msubsup><mi>z</mi><mrow><mi>m</mi><mo>,</mo><mi>t</mi></mrow><mrow><mi>d</mi><mi>o</mi><mi>w</mi><mi>n</mi></mrow></msubsup><mo>-</mo><msubsup><mi>h</mi><mrow><mi>m</mi><mo>,</mo><mi>t</mi></mrow><mrow><mi>l</mi><mi>o</mi><mi>s</mi><mi>s</mi></mrow></msubsup><mo>,</mo></mrow> <mrow><msubsup><mi>z</mi><mrow><mi>m</mi><mo>,</mo><mi>t</mi></mrow><mrow><mi>u</mi><mi>p</mi></mrow></msubsup><mo>=</mo><msub><mi>f</mi><mrow><mi>v</mi><mi>z</mi></mrow></msub><mrow><mo>(</mo><mfrac><mrow><msub><mi>v</mi><mrow><mi>m</mi><mo>,</mo><mi>t</mi></mrow></msub><mo>+</mo><msub><mi>v</mi><mrow><mi>m</mi><mo>,</mo><mi>t</mi><mo>+</mo><mn>1</mn></mrow></msub></mrow><mn>2</mn></mfrac><mo>)</mo></mrow><mo>,</mo></mrow> <mrow><msubsup><mi>z</mi><mrow><mi>m</mi><mo>,</mo><mi>t</mi></mrow><mrow><mi>d</mi><mi>o</mi><mi>w</mi><mi>n</mi></mrow></msubsup><mo>=</mo><msub><mi>f</mi><mrow><mi>q</mi><mi>z</mi></mrow></msub><mrow><mo>(</mo><msub><mi>u</mi><mrow><mi>n</mi><mo>,</mo><mi>t</mi></mrow></msub><mo>&amp;times;</mo>mo><msub><mi>r</mi><mrow><mi>m</mi><mo>,</mo><mi>n</mi><mo>,</mo><mi>t</mi></mrow></msub><mo>)</mo></mrow><mo>,</mo></mrow> <mrow><msubsup><mi>P</mi><mrow><mi>m</mi><mo>,</mo><mi>t</mi></mrow><mi>s</mi></msubsup><mo>=</mo><munderover><mo>&amp;Sigma;</mo><mrow><mi>n</mi><mo>=</mo><mn>1</mn></mrow><mi>N</mi></munderover><msub><mi>u</mi><mrow><mi>n</mi><mo>,</mo><mi>t</mi></mrow></msub><msubsup><mi>p</mi><mrow><mi>m</mi><mo>,</mo><mi>n</mi><mo>,</mo><mi>t</mi></mrow><mi>s</mi></msubsup><mo>,</mo></mrow> <mrow><msub><mi>R</mi><mrow><mi>m</mi><mo>,</mo><mi>t</mi></mrow></msub><mo>=</mo><munderover><mo>&amp;Sigma;</mo><mrow><mi>n</mi><mo>=</mo><mn>1</mn></mo>mrow><mi>N</mi></munderover><msub><mi>u</mi><mrow><mi>n</mi><mo>,</mo><mi>t</mi></mrow></msub><msub><mi>r</mi><mrow><mi>m</mi><mo>,</mo><mi>n</mi><mo>,</mo><mi>t</mi></mrow></msub><mo>,</mo></mrow> In the formula: N is the number of hydroelectric units; n is the number of the unit; u _n,t is the switch state of the hydroelectric unit (1 is on, 0 is off); is the output of the hydropower unit n in the t-th period under the m scenario; is the output of the photovoltaic power station in the m-th scenario of the t-period; f _rph is the relationship between the unit flow rate, output and water head in the dynamic characteristic curve of the hydroelectric unit; f _vz is the water level-storage capacity relationship; f _qz is the discharge flow-tail Water level relationship; r _m,n,t is the power generation reference flow of the nth hydropower unit in the tth period in the mth scenario; h _m,t , are the net water head, water level in front of the dam, tail water level and head loss in the t-th period in the m-th scenario; v _m,t and v _m,t+1 are the beginning and end of the t-th period in the m-th scenario reservoir capacity. 5. The daily power generation planning method of hydro-solar hybrid power station based on the double-layer optimization model according to claim 1, characterized in that: Among them, in step 4, when the intelligent algorithm is used to determine the power generation flow [q ₁ ,…,q _T ] of the power station at each time period and the number of generating units [y ₁ ,…,y _T ], the coding method of the intelligent algorithm solution adopts the following formula express: solution=[q ₁ ,...,q _T ,y ₁ ,...,y _T ], When dynamic programming is used for optimal load distribution, the two-stage recurrence equation is: <mrow><msubsup><mi>R</mi><mrow><mi>d</mi><mo>,</mo><mi>t</mi></mrow><mo>*</mo></msubsup><mrow><mo>(</mo><msubsup><mi>&amp;Sigma;</mi><mrow><mi>c</mi><mo>=</mo><mn>1</mn></mrow><mi>d</mi></msubsup><msub><mi>p</mi><mrow><mi>c</mi><mo>,</mo><mi>t</mi></mrow></msub><mo>)</mo></mrow><mo>=</mo><mi>min</mi><mo>{</mo><msub><mi>f</mi><mrow><mi>r</mi><mi>p</mi><mi>h</mi></mrow></msub><mrow><mo>(</mo><msub><mi>p</mi><mrow><mi>d</mi><mo>,</mo><mi>t</mi></mrow></msub><mo>,</mo><msub><mi>h</mi><mi>t</mi></msub><mo>)</mo></mrow><mo>+</mo><msubsup><mi>R</mi><mrow><mi>d</mi><mo>-</mo><mn>1</mn><mo>,</mo><mi>t</mi></mrow><mo>*</mo></msubsup><mrow><mo>(</mo><msubsup><mi>&amp;Sigma;</mi><mrow><mi>c</mi><mo>=</mo><mn>1</mn></mrow><mi>d</mi></msubsup><msub><mi>p</mi><mrow><mi>c</mi><mo>,</mo><mi>t</mi></mrow></msub><mo>-</mo><msub><mi>p</mi><mrow><mi>d</mi><mo>,</mo><mi>t</mi></mrow></msub><mo>)</mo></mrow><mo>}</mo><mo>,</mo></mrow> In the formula: for the total load of The optimal water consumption allocated among d units, f _rph (p _d,t ,h _t ) is the water consumption of unit d when the load is p _{d, and} the head of t is h _t , for the total load of The optimal water consumption allocated among d-1 units.