Operation state prediction method of pumped storage unit and related equipment

Abstract

The invention provides a running state prediction method of a pumped storage unit and related equipment. The method comprises the following steps: acquiring a plurality of corresponding predicted running states of each unit in a future time period; on the basis of the multiple predicted operation states corresponding to each unit, an objective function is constructed with the goal of minimizing the start-stop times of all the units, and multiple constraint conditions corresponding to the objective function are constructed; and based on the multiple constraint conditions, solving the target function by using a simulated annealing algorithm to obtain a target predicted operation state corresponding to each unit, thereby solving the technical problem that the operation state prediction of the pumped storage unit is unreasonable in the prior art, and achieving the purpose of accurately predicting the operation state of the unit.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method for predicting the operating status of a pumped storage unit and related equipment. Background Art

[0002] As the proportion of renewable energy generation increases, the dispatch complexity of the power system is also increasing. Pumped-storage power stations, as an important form of energy storage, have become an important means of balancing the supply and demand of the power system due to their good regulation performance. By rationally dispatching pumped-storage units, we can effectively cope with the fluctuations in power supply and demand caused by the access of new energy. At the same time, in order to adjust the fluctuations in new energy, pumped-storage units face more frequent unit starts and stops and operating mode conversions, which increase the operating intensity and fatigue damage of the units, seriously affecting the operating life of the units and the reasonable operation of the power station. In the prior art, the prediction of the operating status of pumped-storage units mainly relies on user experience, but user experience has certain limitations, and the reasonable determination of the operating status of the units in pumped-storage power stations needs to be solved urgently. Summary of the invention

[0003] In view of this, the purpose of the present application is to propose a method for predicting the operating status of a pumped storage unit and related equipment to overcome all or part of the deficiencies in the prior art.

[0004] Based on the above-mentioned purpose, the present application provides a method for predicting the operating status of a pumped-storage unit, including: obtaining multiple predicted operating statuses corresponding to each unit in a future period; based on the multiple predicted operating statuses corresponding to each unit, constructing an objective function with the goal of minimizing the number of starts and stops of all units, and constructing multiple constraints corresponding to the objective function; based on the multiple constraints, solving the objective function using a simulated annealing algorithm to obtain the target predicted operating status corresponding to each unit.

[0005] Optionally, the multiple predicted operating states include a power generation state, a pumping state and a shutdown state; the objective function is constructed based on the multiple predicted operating states corresponding to each unit with the goal of minimizing the number of starts and stops of all units, including: determining the objective function by the following formula: Among them, Minimize Z means minimizing the number of starts and stops of all units, Z is the number of starts and stops of all units, N is the total number of all units, T is the number of scheduling periods included in the future period, u i (t) is the predicted operating status of unit i in the scheduling period t, u i (t) = 1 means that unit i is in the power generation state during the scheduling period t, u i (t) = -1 means that unit i is in the pumping state during the dispatching period t, u i(t) = 0 means that unit i is in the shutdown state during the scheduling period t, u i (t-1)=1 means that unit i is in the power generation state in the scheduling period t-1, u i (t-1)=-1 means that unit i is in the pumping state during the scheduling period t-1, u i (t-1)=0 indicates that unit i is in the shutdown state during the scheduling period t-1.

[0006] Optionally, the multiple constraints include: power balance constraint, output range constraint, minimum operation and downtime constraint, power station output limit and water balance constraint, and upper reservoir capacity constraint; the multiple constraints corresponding to the objective function are constructed based on the multiple predicted operating states corresponding to each unit, including: determining the power balance constraint by the following formula: Where T is the number of dispatch periods included in the future period, L(t) is the total load demand of all units in the dispatch period t, P i (t) is the load assigned to each unit, and N is the total number of all units; the output range constraint is determined by the following formula: Among them, P i hmin is the minimum power limit of unit i when the predicted operating state is the power generation state, P i hmax is the maximum power limit of unit i when the predicted operating state is the power generation state, P i pmin is the minimum power limit of unit i when the predicted operating state is the pumping state, P i pmax is the maximum power limit of unit i when the predicted operating state is the pumping state, u i (t) = 1 means that unit i is in the power generation state during the scheduling period t, u i (t) = -1 means that unit i is in the pumping state during the dispatching period t, P i (t) is the load assigned to unit i in the scheduling period t; the minimum operation and downtime constraints are determined by the following formula: Among them, P i on (t) is the operating time of unit i in the scheduling period t, P i off (t) is the shutdown time of unit i in the scheduling period t, T i on is the scheduled operating time of unit i in the scheduling period t, T i offis the scheduled shutdown time of unit i in the scheduling period t; the power station output limit and water balance constraint are determined by the following formula: in, is the power generation flow of unit i in the dispatching period t, P i h (t) is the power generation power of unit i in the dispatching period t, H(t) is the power generation head in the dispatching period t, a0, a1, a2 are the binomial coefficients of the flow-power relationship when the predicted operating state is the power generation state, is the pumping flow of unit i in the dispatching period t, P i p (t) is the pumping power of unit i in the dispatching period t, b0, b1, b2 are the binomial coefficients of the relationship between flow and head when the predicted operating state is the pumping state, c0, c1, c2 are the binomial coefficients of the relationship between power and flow when the predicted operating state is the pumping state; the upper reservoir capacity constraint is determined by the following formula: V t up,min ≤V t up ≤V t up,max , Among them, V t up,min is the minimum storage capacity limit of the reservoir in the dispatching period t, V t up is the storage capacity limit of the reservoir during the dispatching period t, V t up,max is the maximum storage capacity limit of the reservoir during the dispatching period t, is the storage capacity limit of the reservoir in the dispatching period t+1, It is the water consumption of the reservoir for power generation or water pumping during the dispatching period t+1. It is positive during power generation and negative during water pumping.

[0007] Optionally, based on the multiple constraints, the objective function is solved using a simulated annealing algorithm to obtain a target predicted operating state corresponding to each unit, including: randomly determining a solution to the objective function to obtain an initial predicted operating state, and calculating an initial fitness value corresponding to the initial predicted operating state; based on the initial predicted operating state and the initial fitness value, performing multiple iterative searches on the solution of the objective function, and for each iterative search: randomly changing the initial predicted operating state to obtain a changed predicted operating state, and calculating a changed fitness value corresponding to the changed predicted operating state; counting the current iterative search times; and in response to determining that the current iterative search times is greater than or equal to a predetermined number, exiting the iterative search. Based on the initial fitness value and the changed fitness value, the target predicted operating state is determined; in response to determining that the current iterative search number is less than the predetermined number, and determining that the initial fitness value is greater than the changed fitness value, the changed predicted operating state is used as the initial predicted operating state for the next iterative search, and the changed fitness value is used as the initial fitness value for the next iterative search; in response to determining that the current iterative search number is less than the predetermined number, and determining that the initial fitness value is less than or equal to the changed fitness value, the changed predicted operating state is used as the initial predicted operating state for the next iterative search according to dynamic probability, and the changed fitness value is used as the initial fitness value for the next iterative search.

[0008] Optionally, determining the target predicted operating state based on the initial fitness value and the changed fitness value includes: in response to determining that the initial fitness value is greater than the changed fitness value, determining the changed predicted operating state as the target predicted operating state; in response to determining that the initial fitness value is less than or equal to the changed fitness value, determining the initial predicted operating state as the target predicted operating state.

[0009] Optionally, calculating the initial fitness value corresponding to the initial predicted operating state includes: determining the initial fitness value by the following formula: Wherein, f is the initial fitness value, Z' is the number of starts and stops of the unit in the initial predicted operating state, and λ k is the penalty factor, g k (x) indicates whether the kth constraint is satisfied. k (x) is denoted as a negative number. There are m constraints in total, and x is a variable in the constraints.

[0010] Optionally, the method further includes: determining the dynamic probability by the following formula: Where G is the dynamic probability, exp represents the natural exponential function, and f newis the fitness value of the change, f current is the initial fitness value, and Te is the current temperature.

[0011] Based on the same inventive concept, the present application also provides an operating status prediction device for a pumped-storage unit, including: an acquisition module, configured to obtain multiple predicted operating states corresponding to each unit in a future period; a construction module, configured to construct an objective function based on the multiple predicted operating states corresponding to each unit, with the goal of minimizing the number of starts and stops of all units, and to construct multiple constraints corresponding to the objective function; a solution module, configured to solve the objective function based on the multiple constraints using a simulated annealing algorithm to obtain the target predicted operating state corresponding to each unit.

[0012] Based on the same inventive concept, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method as described above when executing the computer program.

[0013] Based on the same inventive concept, the present application also provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute the method as described above.

[0014] From the above, it can be seen that the operating state prediction method and related equipment of the pumped storage unit provided in the present application include obtaining a plurality of predicted operating states corresponding to each unit in the future time period. Based on the multiple predicted operating states corresponding to each unit, an objective function is constructed with the goal of minimizing the number of starts and stops of all units, and a plurality of constraints corresponding to the objective function are constructed, which helps to reduce operating costs and unit wear and extend the life of the unit. At the same time, reducing the number of starts and stops of the unit can improve the stability of the pumped storage power station system, optimize operating efficiency, and reduce environmental impact. Based on the multiple constraints, the objective function is solved using a simulated annealing algorithm to obtain the target predicted operating state corresponding to each unit, thereby achieving the purpose of accurately determining the target predicted operating state of each unit in the future time period. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1A schematic diagram of a flow chart of a method for predicting an operating state of a pumped storage unit according to an embodiment of the present application;

[0017] Figure 2 A schematic flow chart of a method for predicting the operating state of a pumped storage unit according to another embodiment of the present application;

[0018] Figure 3 A schematic diagram of load dispatching requirements of a power grid according to an embodiment of the present application;

[0019] Figure 4 A schematic diagram of the power dispatch results of each unit in an embodiment of the present application;

[0020] Figure 5 A schematic diagram of the overall load distribution of the pumped storage power station system according to an embodiment of the present application;

[0021] Figure 6 A schematic diagram of the structure of an operating state prediction device for a pumped storage unit according to an embodiment of the present application;

[0022] Figure 7 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0024] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0025] As described in the background technology section, with the increase in the proportion of renewable energy power generation, the scheduling complexity of the power system is also increasing. As an important energy storage method, pumped-storage power stations have become an important means of balancing the supply and demand of the power system due to their good regulation performance. By rationally dispatching pumped-storage units, it is possible to effectively cope with the fluctuations in power supply and demand caused by the access of new energy. At the same time, in order to regulate the fluctuations in new energy, pumped-storage units are faced with more frequent unit starts and stops and operating mode conversions, which increases the operating intensity and fatigue damage of the units, seriously affecting the operating life of the units and the reasonable operation of the power station. In the prior art, the prediction of the operating status of pumped-storage units mainly relies on user experience, but user experience has certain limitations, and the reasonable determination of the operating status of the units in pumped-storage power stations needs to be solved urgently.

[0026] In addition, even if the operating status of the unit is determined by calculation, the determination of the operating status of the unit is not reasonable. This is because the traditional optimization method for solving the calculation method is difficult to handle the problems of multiple operating conditions, multiple scenarios, nonlinear constraints, etc. in the dispatch of pumped storage power stations, and the calculation efficiency is low. Existing algorithms such as particle swarm optimization algorithm PSO and genetic algorithm NSGA generally can only handle discrete variables of a single power generation condition, and the global performance of the optimal solution obtained is poor, resulting in these algorithms being unable to meet the needs of multi-condition optimization dispatch in pumped storage power stations. In addition, the above calculation method does not take into account how to minimize the number of unit starts and stops, reduce unit losses and system operating costs, and ensure the flexibility and stability of the operation of the pumped storage power station system while meeting the system power balance.

[0027] In view of this, the present application embodiment proposes a method for predicting the operating state of a pumped storage unit, referring to Figure 1 , including the following steps:

[0028] Step 101, obtaining a plurality of predicted operating states corresponding to each unit in a future period.

[0029] In this step, there are multiple units in the pumped storage power station. Each unit has its corresponding normal operating state, for example, the normal operating state can be a power generation state, a pumping state or a shutdown state. It is foreseeable that the normal operating state corresponding to each unit is also a plurality of predicted operating states corresponding to the unit in the future time period, so the plurality of predicted operating states include a power generation state, a pumping state and a shutdown state. The future time period is the time period for which the user wants to predict the operating state of the unit, depending on the actual application scenario, for example, the future time period can be tomorrow, and for another example, the future time period can be the next month.

[0030] Step 102, based on the multiple predicted operating states corresponding to each unit, an objective function is constructed with the goal of minimizing the number of starts and stops of all units, and multiple constraints corresponding to the objective function are constructed.

[0031] In this step, there are multiple predicted operating states of the unit, but each scheduling period of the unit in the future period corresponds to only one predicted operating state. Therefore, it is necessary to construct an objective function and constraints to solve the operating state of each unit in all scheduling periods in the future period. It should be noted that the future period is relatively long, and the unit may not only have one operating state. Therefore, the future period is divided into multiple scheduling periods, and the scheduling periods correspond to the predicted operating states of the unit one by one. The frequent start and stop of the unit will affect the service life of the unit, wherein the start and stop of the unit includes the switch of the unit and the state transition of the unit. Therefore, considering the stability and flexibility of the unit operation, the present application constructs an objective function with the goal of minimizing the number of starts and stops of all units, and constructs multiple constraints corresponding to the objective function. Exemplarily, when the future time period is one of the future days, the present application constructs an objective function with the goal of minimizing the number of starts and stops of all units in all periods of one day. The objective function constructed by the present application helps to reduce operating costs and unit wear, extend the life of the unit, and at the same time, reducing the number of starts and stops of the unit can improve the stability of the pumped storage power station system, optimize operating efficiency, and reduce environmental impact.

[0032] Step 103: Based on the multiple constraints, the objective function is solved using a simulated annealing algorithm to obtain a target predicted operating state corresponding to each unit.

[0033] In this step, the simulated annealing algorithm is a heuristic search algorithm used to find the global optimal solution of a function, especially when dealing with high-dimensional, nonlinear, and multi-extreme value problems. The algorithm simulates the physical annealing process, and randomly searches in the solution space, accepts better solutions, and accepts worse solutions under certain conditions, thereby avoiding falling into the local optimal solution and eventually tending to the global optimal solution. The objective function in this application is a high-dimensional, nonlinear, and multi-extreme value function. The simulated annealing algorithm can reasonably solve the solution of the objective function, so that the optimal solution is global, so as to obtain the target predicted operating state corresponding to each unit. When all constraints are met, the simulated annealing algorithm is used to solve the solution of the objective function, so as to achieve the purpose of accurately determining the target predicted operating state of each unit in the future period, and subsequent users can arrange the operating state of the unit in the future period according to the solution of the objective function.

[0034] This application can effectively solve complex optimization and scheduling problems such as multiple operating conditions, multiple scenarios, and nonlinear constraints in pumped-storage power stations, reduce operating costs, improve scheduling flexibility, and provide technical support for the scheduling and operation of pumped-storage power stations.

[0035] Through the above scheme, a variety of predicted operating states corresponding to each unit in the future period are obtained. Based on the multiple predicted operating states corresponding to each unit, an objective function is constructed with the goal of minimizing the number of starts and stops of all units, and multiple constraints corresponding to the objective function are constructed, which helps to reduce operating costs and unit wear and extend the life of the unit. At the same time, reducing the number of starts and stops of the unit can improve the stability of the pumped storage power station system, optimize operating efficiency, and reduce environmental impact. Based on the multiple constraints, the objective function is solved using a simulated annealing algorithm to obtain the target predicted operating state corresponding to each unit, thereby achieving the purpose of accurately determining the target predicted operating state of each unit in the future period.

[0036] In some embodiments, the multiple predicted operating states include power generation state, pumping state and shutdown state; the objective function is constructed based on the multiple predicted operating states corresponding to each unit with the goal of minimizing the number of starts and stops of all units, including: determining the objective function by the following formula: Among them, Minimize Z means minimizing the number of starts and stops of all units, Z is the number of starts and stops of all units, N is the total number of all units, T is the number of scheduling periods included in the future period, u i (t) is the predicted operating status of unit i in the scheduling period t, u i (t) = 1 means that unit i is in the power generation state during the scheduling period t, u i (t) = -1 means that unit i is in the pumping state during the dispatching period t, u i (t) = 0 means that unit i is in the shutdown state during the scheduling period t, u i (t-1) is the predicted operating status of unit i in the scheduling period t-1, u i (t-1)=1 means that unit i is in the power generation state in the scheduling period t-1, u i (t-1)=-1 means that unit i is in the pumping state during the scheduling period t-1, u i (t-1)=0 indicates that unit i is in the shutdown state during the scheduling period t-1.

[0037] In this embodiment, the same unit in the future period may have multiple operating states. Therefore, the future period is divided into multiple scheduling periods, and the operating state of the unit in each scheduling period is determined. Each period in the future period can be regarded as a scheduling period. In addition, the pumped storage power station includes multiple units, and each unit is numbered and recorded as i. The objective function takes the minimum number of unit start and stop times as the objective function, so the change of the predicted operating state in adjacent scheduling periods needs to be relatively small, that is, the calculated value of the adjacent predicted operating state is relatively small. It should be noted that how the predicted operating state changes specifically needs to be solved by the simulated annealing algorithm. The operating state of the unit determined in the future period is converted into a problem of solving the objective function. The operating state of the unit determined in the future period meets the goal of minimizing the number of start and stop times of all units, ensuring that the formula can be accurately solved while effectively reducing the operating cost and unit wear, thereby extending the service life of the unit. At the same time, it helps to meet the minimum operation and downtime constraints of the unit. The operating state of the pumped storage unit is represented by a discrete variable: the power generation state is 1, the pumping state is -1, and the shutdown state is 0. The adoption of this objective function can help improve the reliability of the pumped storage power station system.

[0038] In some embodiments, the multiple constraints include: power balance constraint, output range constraint, minimum operation and downtime constraint, power station output limit and water balance constraint, and upper reservoir capacity constraint; the multiple constraints corresponding to the objective function are constructed based on the multiple predicted operating states corresponding to each unit, including: determining the power balance constraint by the following formula: Where T is the number of dispatch periods included in the future period, L(t) is the total load demand of all units in the dispatch period t, P i (t) is the load assigned to each unit, and N is the total number of all units; the output range constraint is determined by the following formula: Among them, P i hmin is the minimum power limit of unit i when the predicted operating state is the power generation state, P i hmax is the maximum power limit of unit i when the predicted operating state is the power generation state, P i pmin is the minimum power limit of unit i when the predicted operating state is the pumping state, P i pmax is the maximum power limit of unit i when the predicted operating state is the pumping state, u i (t) = 1 means that unit i is in the power generation state during the scheduling period t, u i (t) = -1 means that unit i is in the pumping state during the dispatching period t, P i(t) is the load assigned to unit i in the scheduling period t; the minimum operation and downtime constraints are determined by the following formula: Among them, P i on (t) is the operating time of unit i in the scheduling period t, P i off (t) is the shutdown time of unit i in the scheduling period t, T i on is the scheduled operating time of unit i in the scheduling period t, T i off is the scheduled shutdown time of unit i in the scheduling period t; the power station output limit and water balance constraint are determined by the following formula: in, is the power generation flow of unit i in the dispatching period t, P i h (t) is the power generation power of unit i in the dispatching period t, H(t) is the power generation head in the dispatching period t, a0, a1, a2 are the binomial coefficients of the flow-power relationship when the predicted operating state is the power generation state, is the pumping flow of unit i in the dispatching period t, P i p (t) is the pumping power of unit i in the dispatching period t, b0, b1, b2 are the binomial coefficients of the relationship between flow and head when the predicted operating state is the pumping state, c0, c1, c2 are the binomial coefficients of the relationship between power and flow when the predicted operating state is the pumping state; the upper reservoir capacity constraint is determined by the following formula: V t up,min ≤V t up ≤V t up,max , Among them, V t up,min is the minimum storage capacity limit of the reservoir in the dispatching period t, V t up is the storage capacity limit of the reservoir during the dispatching period t, V t up,max is the maximum storage capacity limit of the reservoir during the dispatching period t, is the storage capacity limit of the reservoir in the dispatching period t+1, It is the water consumption of the reservoir for power generation or water pumping during the dispatching period t+1. It is positive during power generation and negative during water pumping.

[0039] In this embodiment, the constraints play a vital role in the process of solving the objective function. They not only limit the solution space of the problem, but also guide the feasibility of the solution. In optimization theory, constraints are key factors in determining acceptable solutions. They are imposed on decision variables to ensure that the solution not only optimizes the objective function, but also meets specific requirements or restrictions. These conditions are usually expressed as a set of equations or inequalities. This embodiment optimizes the start-stop scheme of the unit, minimizes the number of start-stops of the unit, and meets the power balance requirements of the power system within a day, and takes into account the operating constraints of the unit (such as maximum power, minimum operating time and downtime, etc.), providing scheduling technical support for the efficient operation of the power station. The multiple constraints in this embodiment include: power balance constraints, output range constraints, minimum operating and downtime constraints, power station output limits and water balance constraints, and upper reservoir capacity constraints. The constraints have a limiting effect on the objective function, which is conducive to accurately finding the solution of the required objective function.

[0040] For each constraint in all constraints: (1) The operation of the unit requires power. Therefore, there is a power balance constraint in all constraints. The load allocated to all units must be equal to the total load demand. When the unit characteristics are the same, in order to achieve a reasonable distribution of the load, the principle of average distribution can be adopted. The total load demand L(t) of the pumped storage power station system in the dispatching period t. In the dispatching period t, each unit i (i.e., u i (t) = 1) The allocated load P i (t) can be evenly distributed using the following formula:

[0041]

[0042] in, It indicates the number of units in the startup state in the scheduling period t. It should be noted that the startup state of the unit includes the power generation state and the pumping state.

[0043] (2) The load assigned to the units in the startup state also has extreme value limits. The load assigned to unit i in the scheduling period t is not greater than the maximum power limit of unit i when the predicted operating state is the power generation state, and is not greater than the maximum power limit of unit i when the predicted operating state is the pumping state. The load assigned to unit i in the scheduling period t is not less than the minimum power limit of unit i when the predicted operating state is the power generation state, and is not less than the minimum power limit of unit i when the predicted operating state is the pumping state. Among them, P i hmin , P i hmax , P i pmin and P ipmax Determined based on historical experience.

[0044] (3) Since the objective function of this application is to minimize the number of starts and stops of all units, it is also necessary to constrain the operation and shutdown time of the units. The operation time of unit i in the scheduling period t must be greater than or equal to the scheduled operation time of unit i in the scheduling period t; the shutdown time of unit i in the scheduling period t must be greater than or equal to the scheduled shutdown time of unit i in the scheduling period t. Among them, T i on and T i off Determined based on historical experience.

[0045] (4) Under a given water head, the power generation output of the unit is nonlinearly related to the flow rate of the unit. Under pumping conditions, there is also a certain relationship between the water head, flow rate, and power, which can be specifically expressed as a quadratic polynomial, where: is a quadratic polynomial related to the power generation state, It is a quadratic polynomial related to the pumping state. The water head refers to the mechanical energy possessed by a unit weight of liquid.

[0046] (5) The upper reservoir is a hydraulic structure that stores water upstream of the power station. The storage capacity of the upper reservoir is used to store water, and water is not inexhaustible. Therefore, there are constraints on the storage capacity of the upper reservoir. The storage capacity limit of the upper reservoir in the dispatching period t+1 must be less than or equal to the maximum storage capacity limit of the upper reservoir in the dispatching period t, and must be greater than or equal to the minimum storage capacity limit of the upper reservoir in the dispatching period t. In addition, the storage capacities of adjacent dispatching periods have an equality relationship. The water consumption of the upper reservoir for power generation or pumping in the dispatching period t+1 is equal to the storage capacity limit of the upper reservoir in the dispatching period t+1 minus the water consumption of the upper reservoir for power generation or pumping in the dispatching period t+1.

[0047] In some embodiments, based on the multiple constraints, the objective function is solved using a simulated annealing algorithm to obtain a target predicted operating state corresponding to each unit, including: randomly determining a solution to the objective function to obtain an initial predicted operating state, and calculating an initial fitness value corresponding to the initial predicted operating state; based on the initial predicted operating state and the initial fitness value, performing multiple iterative searches on the solution to the objective function, and for each iterative search: randomly changing the initial predicted operating state to obtain a changed predicted operating state, and calculating a changed fitness value corresponding to the changed predicted operating state; counting the current iterative search times; and exiting the iterative search in response to determining that the current iterative search times is greater than or equal to a predetermined number of times. search, based on the initial fitness value and the changed fitness value, determine the target predicted operating state; in response to determining that the current iterative search number is less than the predetermined number, and determining that the initial fitness value is greater than the changed fitness value, use the changed predicted operating state as the initial predicted operating state for the next iterative search, and use the changed fitness value as the initial fitness value for the next iterative search; in response to determining that the current iterative search number is less than the predetermined number, and determining that the initial fitness value is less than or equal to the changed fitness value, use the changed predicted operating state as the initial predicted operating state for the next iterative search according to dynamic probability, and use the changed fitness value as the initial fitness value for the next iterative search.

[0048] In this embodiment, the simulated annealing algorithm can use the following process to determine the target predicted operating state: 1) randomly determine the solution of the objective function, obtain the initial predicted operating state, and calculate the initial fitness value corresponding to the initial predicted operating state. In order to generate the initial solution, the state of each unit in each scheduling period is determined by random generation. The specific formula is:

[0049] U current = {u i (t)|u i (t)∈{0,1,-1},i=1,2,…,N,t=1,2,…,T},

[0050] Among them, U current represents the initial predicted operating state, which is an N×T matrix, where N represents the number of pumped storage units in the power station. For example, in this embodiment, N=4, and T is the number of scheduling periods included in the future period, where T=96, and each scheduling period represents 15 minutes; u i (t) is the predicted operating status of unit i in the dispatching period t; L(t) is the equivalent load dispatching demand curve of the power grid, including the load demand of power generation (positive value) and pumping (negative value) of the power station.

[0051] 2) Based on the initial predicted running state and the initial fitness value, perform multiple iterative searches for the solution of the objective function. For each iterative search:

[0052] a) Randomly change the initial predicted running state to obtain a changed predicted running state, and calculate the change fitness value corresponding to the changed predicted running state; from the aforementioned initial predicted running state U current A new solution U is randomly selected from the neighborhood of new , that is, changing the predicted operating state. The neighborhood solution is generated by changing the operating state (generating, pumping or shutting down) of one or more units in certain time periods. Select a generator unit i and a scheduling period t:

[0053]

[0054] Based on the value of the load curve L(t), the new state u of generator set i in the dispatch period t is determined i '(t):

[0055]

[0056] b) Count the number of current iteration searches;

[0057] c) In response to determining that the current iterative search number is greater than or equal to a predetermined number, exit the iterative search, and determine the target predicted operating state based on the initial fitness value and the changed fitness value. The predetermined number can be determined based on historical experience. For example, the simulated annealing algorithm is related to temperature, and the number of iterations at each temperature is set, and the number of iterations at all temperatures is determined as the predetermined number. After each iteration, the current temperature Te is updated according to the cooling rate α, that is, Te = α × Te. For example, the initial temperature Te0 = 1000 and the minimum temperature Te min =1, cooling rate α=0.9, and maximum number of cycles at each temperature L=500, the predetermined number can be calculated based on the above data. The predetermined number can also be determined directly, for example, the predetermined number is 1000. The predetermined number is the maximum number of required iterative searches.

[0058] d) In response to determining that the current iterative search number is less than the predetermined number, and determining that the initial fitness value is greater than the changed fitness value, the changed predicted running state is used as the initial predicted running state for the next iterative search, and the changed fitness value is used as the initial fitness value for the next iterative search. Check whether the changed predicted running state satisfies the above-mentioned multiple constraints. Assume that the constraint condition is g k(x)≤0 means that the kth constraint condition is satisfied, where k=1,2,…,m represents the kth constraint condition and x represents the variable in the constraint condition. When the initial fitness value is greater than the changed fitness value, it means that the changed predicted running state corresponding to the changed fitness value satisfies relatively more constraints. Therefore, the changed predicted running state needs to be used as the initial predicted running state for the next iterative search, and the changed fitness value needs to be used as the initial fitness value for the next iterative search.

[0059] e) In response to determining that the current iterative search number is less than a predetermined number, and determining that the initial fitness value is less than or equal to the changed fitness value, the changed predicted operating state is used as the initial predicted operating state for the next iterative search according to dynamic probability, and the changed fitness value is used as the initial fitness value for the next iterative search. In order to avoid falling into a local optimum, when the initial fitness value is less than or equal to the changed fitness value, the changed predicted operating state is used as the initial predicted operating state for the next iterative search according to dynamic probability, and the changed fitness value is used as the initial fitness value for the next iterative search according to dynamic probability. It should be noted that this embodiment uses the Metropolis acceptance criterion to determine the dynamic probability.

[0060] The discrete decision variable position update method and global optimization capability provided by the simulated annealing algorithm adopted in this embodiment can effectively solve the complex optimization scheduling problem of the pumped storage power station, effectively reduce the number of start and stop times of the unit, reduce the system operation cost, and extend the life of the unit. The scheduling strategy proposed in this embodiment is highly flexible and can take into account the flexibility of the pumped storage power station system while meeting the power balance, providing a strong guarantee for the efficient and stable operation of the power system.

[0061] In some embodiments, determining the target predicted operating state based on the initial fitness value and the changed fitness value includes: in response to determining that the initial fitness value is greater than the changed fitness value, determining the changed predicted operating state as the target predicted operating state; in response to determining that the initial fitness value is less than or equal to the changed fitness value, determining the initial predicted operating state as the target predicted operating state.

[0062] In this embodiment, when the current iterative search number is greater than or equal to the predetermined number of times, it means that the solution corresponding to the running state of the unit has converged. At this time, the initial predicted running state corresponding to the initial fitness value and the changed predicted running state corresponding to the changed fitness value meet all constraints. However, the present application constructs an objective function with the goal of minimizing the number of starts and stops of all units. The calculation of the fitness value is also related to the number of starts and stops of all units. The number of starts and stops of the unit is proportional to the fitness value. When the number of starts and stops of the unit is relatively small, the fitness value is relatively small. Therefore, when the initial fitness value is greater than the changed fitness value, it means that the number of starts and stops of the unit in the changed predicted running state corresponding to the changed fitness value is relatively small, and the changed predicted running state is determined as the target predicted running state. When the initial fitness value is less than or equal to the changed fitness value, it means that the number of starts and stops of the unit in the initial predicted running state corresponding to the initial fitness value is relatively small, and the initial predicted running state is determined as the target predicted running state. By comparing the initial fitness value with the changed fitness value, the predicted running state with relatively few starts and stops of the unit is accurately determined, ensuring the reasonable determination of the running state of the unit.

[0063] In some embodiments, the calculating the initial fitness value corresponding to the initial predicted operating state includes: determining the initial fitness value by the following formula: Wherein, f is the initial fitness value, Z' is the number of starts and stops of the unit in the initial predicted operating state, and λ k is the penalty factor, g k (x) indicates whether the kth constraint is satisfied. k (x) is denoted as a negative number. There are m constraints in total, and x is a variable in the constraints.

[0064] In this embodiment, the application constructs the objective function with the goal of minimizing the number of starts and stops of all units. Therefore, the initial fitness value is related to the number of starts and stops of the units. An increase in the number of starts and stops will increase the initial fitness value. The fitness value corresponding to the target predicted operating state must meet the constraint conditions. Therefore, the calculation of the initial fitness value is also related to whether the constraint conditions are met. Assuming that the kth constraint condition is met, g k (x) is a negative number. When more constraints are satisfied, g k The smaller (x) is, the greater the max(0,g k (x)) means taking 0 and g k Large values ​​of (x), for example, 0, are greater than g k (x), max(0,g k (x)) = 0; 0 is less than g k (x), max(0,g k(x)) = g k (x). In addition, in g k When (x) is greater than 0, it means that the constraint condition is not met. k The larger (x) is, the more unsatisfied constraints are. Therefore, a penalty factor is introduced to make max(0,g k (x)) increases, thereby increasing the initial fitness value. The smaller the initial fitness value, the closer it is to the fitness value corresponding to the target predicted operating state. The initial fitness value is digitized to make the determined initial fitness value more accurate. It should be noted that the calculation method for changing the fitness value is the same as the calculation method for the initial fitness value, which will not be repeated here.

[0065] In some embodiments, the method further includes: determining the dynamic probability by the following formula: Where G is the dynamic probability, exp represents the natural exponential function, and f new is the fitness value of the change, f current is the initial fitness value, and Te is the current temperature.

[0066] In this embodiment, the basic idea of ​​the simulated annealing algorithm is derived from the annealing process of solid materials. In the physical annealing process, the material is first heated to melt and then slowly cooled. When heated, the particles inside the material become disordered as the temperature rises, and the internal energy increases. When slowly cooled, the particles gradually tend to be ordered, reaching an equilibrium state at each temperature, and finally reaching the ground state at room temperature, and the internal energy is reduced to a minimum. Therefore, when using the simulated annealing algorithm, there is a change in temperature, and the temperature changes according to the cooling rate α. Through dynamic probability, the simulated annealing algorithm is prevented from falling into a local optimum.

[0067] In another embodiment provided in the present application, Figure 2 As shown, the pumped storage power station includes units, and the objective function is constructed by minimizing the number of unit start-up and shutdown times, that is, establishing the objective function of the pumped storage power station optimization scheduling mathematical model. Set the algorithm parameters. For example, assume that the number of units in the pumped storage power station system is N; the rated power of each unit P i max (Unit: MW), where i = 1, 2, ..., N; the upper reservoir capacity limit is [V max ,V min ]; the minimum operating time of the unit is T down , the minimum downtime of the unit is T up; The scheduling time scale of the system in the future period is T, t = 1, 2, ..., T. The equivalent load scheduling demand curve of the power grid is L (t), including the load demand of power station power generation (positive value) and pumping (negative value). The operating state of the pumped storage unit is represented by a discrete variable: the power generation state is 1, the pumping state is -1, and the shutdown state is 0. Scheme initialization: Randomly generate the initial predicted operating state U current . Domain Search: Generate a new solution U new , that is, change the predicted operating state. Pumped storage unit power distribution: evenly distribute load demand. Calculation scheme target value: Z current and Z new , and f current and f new If f new Less than f current , receive U new Or receive U according to Metropolis acceptance guidelines new . Determine whether the number of iterations has been reached. If the number of iterations has been reached, determine whether the termination condition has been met. If the termination condition has been met, output U new If the termination condition is not met, the temperature is reduced and iterated, the temperature is updated according to the cooling rate α, and the domain search and its subsequent steps are continued. If the number of iterations is not reached, the domain search and its subsequent steps are continued.

[0068] The load dispatching requirements of the power grid refer to Figure 3 For a pumped storage power station with four 300MW pump-turbine units of the same model, the maximum and minimum power limits under power generation conditions are 120MW and 300MW respectively, and the maximum and minimum power limits under pumping conditions are -190MW and -210MW respectively. The simulated annealing algorithm is used to optimize the system scheduling. The power scheduling results of each unit are calculated. Figure 4 ; For the overall load distribution of the pumped storage power station system, see Figure 5 It can be seen that the total number of starts and stops of the four units in the pumped storage power station of this embodiment is 32 times, and the average number of starts and stops per day is 2 pumping and 2 generating / unit, which meets the requirements. Figure 3 In addition, the loads of each unit under power generation and pumping conditions are within the constraints, which reflects the feasibility of the model and the reliability of the results.

[0069] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0070] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0071] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides an operating status prediction device for a pumped-storage unit.

[0072] refer to Figure 6 , the operating state prediction device of the pumped storage unit comprises:

[0073] The acquisition module 10 is configured to acquire a plurality of predicted operating states corresponding to each unit in a future period.

[0074] The construction module 20 is configured to construct an objective function based on the multiple predicted operating states corresponding to each unit with the goal of minimizing the number of starts and stops of all units, and to construct multiple constraints corresponding to the objective function.

[0075] The solving module 30 is configured to solve the objective function based on the multiple constraints using a simulated annealing algorithm to obtain a target predicted operating state corresponding to each unit.

[0076] Through the above-mentioned device, a variety of predicted operating states corresponding to each unit in the future period are obtained. Based on the multiple predicted operating states corresponding to each unit, an objective function is constructed with the goal of minimizing the number of starts and stops of all units, and multiple constraints corresponding to the objective function are constructed, which helps to reduce operating costs and unit wear and extend the life of the unit. At the same time, reducing the number of starts and stops of the unit can improve the stability of the pumped storage power station system, optimize operating efficiency, and reduce environmental impact. Based on the multiple constraints, the objective function is solved using a simulated annealing algorithm to obtain the target predicted operating state corresponding to each unit, thereby achieving the purpose of accurately determining the target predicted operating state of each unit in the future period.

[0077] In some embodiments, the construction module 20 is further configured such that the multiple predicted operating states include power generation state, pumping state and shutdown state; and the objective function is determined by the following formula: Among them, Minimize Z means minimizing the number of starts and stops of all units, Z is the number of starts and stops of all units, N is the total number of all units, T is the number of scheduling periods included in the future period, u i (t) is the predicted operating status of unit i in the scheduling period t, u i (t) = 1 means that unit i is in the power generation state during the scheduling period t, u i (t) = -1 means that unit i is in the pumping state during the dispatching period t, u i (t) = 0 means that unit i is in the shutdown state during the scheduling period t, u i (t-1)=1 means that unit i is in the power generation state in the scheduling period t-1, u i (t-1)=-1 means that unit i is in the pumping state during the scheduling period t-1, u i (t-1)=0 indicates that unit i is in the shutdown state during the scheduling period t-1.

[0078] In some embodiments, the construction module 20 is further configured such that the multiple constraints include: power balance constraint, output range constraint, minimum operation and downtime constraint, power station output limit and water balance constraint, and upper reservoir capacity constraint; the power balance constraint is determined by the following formula: Where T is the number of dispatch periods included in the future period, L(t) is the total load demand of all units in the dispatch period t, P i (t) is the load assigned to each unit, and N is the total number of all units; the output range constraint is determined by the following formula: Among them, P i hmin is the minimum power limit of unit i when the predicted operating state is the power generation state, P i hmax is the maximum power limit of unit i when the predicted operating state is the power generation state, P i pmin is the minimum power limit of unit i when the predicted operating state is the pumping state, P i pmax is the maximum power limit of unit i when the predicted operating state is the pumping state, u i (t) = 1 means that unit i is in the power generation state during the scheduling period t, u i (t) = -1 means that unit i is in the pumping state during the dispatching period t, P i(t) is the load assigned to unit i in the scheduling period t; the minimum operation and downtime constraints are determined by the following formula: Among them, P i on (t) is the operating time of unit i in the scheduling period t, P i off (t) is the shutdown time of unit i in the scheduling period t, T i on is the scheduled operating time of unit i in the scheduling period t, T i off is the scheduled shutdown time of unit i in the scheduling period t; the power station output limit and water balance constraint are determined by the following formula: in, is the power generation flow of unit i in the dispatching period t, P i h (t) is the power generation power of unit i in the dispatching period t, H(t) is the power generation head in the dispatching period t, a0, a1, a2 are the binomial coefficients of the flow-power relationship when the predicted operating state is the power generation state, is the pumping flow of unit i in the dispatching period t, P i p (t) is the pumping power of unit i in the dispatching period t, b0, b1, b2 are the binomial coefficients of the relationship between flow and head when the predicted operating state is the pumping state, c0, c1, c2 are the binomial coefficients of the relationship between power and flow when the predicted operating state is the pumping state; the upper reservoir capacity constraint is determined by the following formula: V t up,min ≤V t up ≤V t up,max , Among them, V t up,min is the minimum storage capacity limit of the reservoir in the dispatching period t, V t up is the storage capacity limit of the reservoir during the dispatching period t, V t up,max is the maximum storage capacity limit of the reservoir during the dispatching period t, is the storage capacity limit of the reservoir in the dispatching period t+1, It is the water consumption of the reservoir for power generation or water pumping during the dispatching period t+1. It is positive during power generation and negative during water pumping.

[0079] In some embodiments, the solution module 30 is further configured to randomly determine a solution to the objective function, obtain an initial predicted operating state, and calculate an initial fitness value corresponding to the initial predicted operating state; based on the initial predicted operating state and the initial fitness value, perform multiple iterative searches on the solution to the objective function, and for each iterative search: randomly change the initial predicted operating state to obtain a changed predicted operating state, and calculate a changed fitness value corresponding to the changed predicted operating state; count the current iterative search times; in response to determining that the current iterative search times is greater than or equal to a predetermined number, exit the iterative search, and based on the initial fitness value and the changed fitness value , determine the target predicted operating state; in response to determining that the current iterative search number is less than the predetermined number, and determining that the initial fitness value is greater than the changed fitness value, use the changed predicted operating state as the initial predicted operating state for the next iterative search, and use the changed fitness value as the initial fitness value for the next iterative search; in response to determining that the current iterative search number is less than the predetermined number, and determining that the initial fitness value is less than or equal to the changed fitness value, use the changed predicted operating state as the initial predicted operating state for the next iterative search according to dynamic probability, and use the changed fitness value as the initial fitness value for the next iterative search.

[0080] In some embodiments, the solution module 30 is also configured to, in response to determining that the initial fitness value is greater than the changed fitness value, determine the changed predicted operating state as the target predicted operating state; in response to determining that the initial fitness value is less than or equal to the changed fitness value, determine the initial predicted operating state as the target predicted operating state.

[0081] In some embodiments, the solution module 30 is further configured to determine the initial fitness value by the following formula: Wherein, f is the initial fitness value, Z' is the number of starts and stops of the unit in the initial predicted operating state, and λ k is the penalty factor, g k (x) indicates whether the kth constraint is satisfied. k (x) is denoted as a negative number. There are m constraints in total, and x is a variable in the constraints.

[0082] In some embodiments, the solution module 30 is further configured to determine the dynamic probability by the following formula: Where G is the dynamic probability, exp represents the natural exponential function, and f new is the fitness value of the change, f current is the initial fitness value, and Te is the current temperature.

[0083] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0084] The device of the above embodiment is used to implement the operation state prediction method of the corresponding pumped storage unit in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0085] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for predicting the operating status of the pumped-storage unit as described in any of the above embodiments is implemented.

[0086] Figure 7 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0087] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0088] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0089] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0090] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0091] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0092] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0093] The electronic device of the above embodiment is used to implement the operation state prediction method of the corresponding pumped storage unit in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0094] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the operating status prediction method of the pumped-storage unit as described in any of the above embodiments.

[0095] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0096] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the operating state prediction method of the pumped storage unit as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0097] Based on the same concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a computer program product, including computer program instructions. When the computer program instructions are run on a computer, the computer executes the operating status prediction method of the pumped-storage unit as described in any of the above embodiments, which has the beneficial effects of the corresponding method embodiments and will not be repeated here.

[0098] It should be noted that the embodiments of the present application can be further described in the following manner:

[0099] It is understandable that before using the technical solutions of each embodiment of the present disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the user's authorization will be obtained.

[0100] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly remind the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can independently choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0101] As an optional but non-limiting implementation, in response to receiving the user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0102] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0103] A person skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0104] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0105] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0106] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the present application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the protection scope of the present application.

Claims

1. A method for predicting the operating state of a pumped storage unit, characterized in that: include: Obtain multiple predicted operating states corresponding to each unit in future periods; Based on the multiple predicted operating states corresponding to each unit, an objective function is constructed with the goal of minimizing the number of starts and stops of all units, and multiple constraints corresponding to the objective function are constructed; Based on the multiple constraints, the objective function is solved using a simulated annealing algorithm to obtain a target predicted operating state corresponding to each unit.

2. The method according to claim 1, characterized in that The multiple predicted operating states include power generation state, pumping state and shutdown state; The objective function is constructed based on the multiple predicted operating states corresponding to each unit with the goal of minimizing the number of starts and stops of all units, including: The objective function is determined by the following formula: Among them, Minimize Z means minimizing the number of starts and stops of all units, Z is the number of starts and stops of all units, N is the total number of all units, T is the number of scheduling periods included in the future period, and u i (t) is the predicted operating status of unit i in the scheduling period t, u i (t) = 1 means that unit i is in the power generation state during the scheduling period t, u i (t) = -1 means that unit i is in the pumping state during the dispatching period t, u i (t) = 0 means that unit i is in the shutdown state during the scheduling period t, u i (t-1) is the predicted operating status of unit i in the scheduling period t-1, u i (t-1)=1 means that unit i is in the power generation state in the scheduling period t-1, u i (t-1)=-1 means that unit i is in the pumping state during the scheduling period t-1, u i (t-1)=0 indicates that unit i is in the shutdown state during the scheduling period t-1.

3. The method according to claim 1, characterized in that: The plurality of constraints include: power balance constraint, output range constraint, minimum operation and downtime constraint, power station output limit and water balance constraint and upper reservoir capacity constraint; The multiple constraints corresponding to the objective function are constructed based on the multiple predicted operating states corresponding to each unit, including: The power balance constraint is determined by the following formula: Where T is the number of dispatch periods included in the future period, L(t) is the total load demand of all units in the dispatch period t, P i (t) is the load assigned to each unit, N is the total number of units; The output range constraint is determined by the following formula: P i hmin ≤P i (t)≤P i hmax , if u i (t) = 1 P i pmin ≤P i (t)≤P i pmax , if u i (t) = -1, Among them, P i hmin is the minimum power limit of unit i when the predicted operating state is the power generation state, P i hmax is the maximum power limit of unit i when the predicted operating state is the power generation state, P i pmin is the minimum power limit of unit i when the predicted operating state is the pumping state, P i pmax is the maximum power limit of unit i when the predicted operating state is the pumping state, u i (t) = 1 means that unit i is in the power generation state during the scheduling period t, u i (t) = -1 means that unit i is in the pumping state during the dispatching period t, P i (t) is the load assigned to unit i in the dispatch period t; The minimum operating and downtime constraints are determined by the following formula: Among them, P i on (t) is the operating time of unit i in the scheduling period t, P i off (t) is the shutdown time of unit i in the scheduling period t, T i on is the scheduled operating time of unit i in the scheduling period t, T i off is the scheduled shutdown time of unit i in the scheduling period t; The power plant output limit and water balance constraint are determined by the following formula: in, is the power generation flow of unit i in the dispatching period t, P i h (t) is the power generation power of unit i in the dispatching period t, H(t) is the power generation head in the dispatching period t, a0, a1, a2 are the binomial coefficients of the flow-power relationship when the predicted operating state is the power generation state, is the pumping flow of unit i in the dispatching period t, P i p (t) is the pumping power of unit i in the scheduling period t, b0, b1, b2 are the binomial coefficients of the relationship between flow and head when the predicted operating state is the pumping state, c0, c1, c2 are the binomial coefficients of the relationship between power and flow when the predicted operating state is the pumping state; The upper reservoir capacity constraint is determined by the following formula: In t up,min ≤V t up ≤V t up,max , Among them, V t up,min is the minimum storage capacity limit of the reservoir in the dispatching period t, V t up is the storage capacity limit of the reservoir during the dispatching period t, V t up,max is the maximum storage capacity limit of the reservoir during the dispatching period t, is the storage capacity limit of the reservoir in the dispatching period t+1, It is the water consumption of the reservoir for power generation or water pumping during the dispatching period t+1. It is positive during power generation and negative during water pumping.

4. The method according to claim 1, characterized in that: The objective function is solved based on the multiple constraints using a simulated annealing algorithm to obtain a target predicted operating state corresponding to each unit, including: Randomly determine a solution to the objective function, obtain an initial predicted operating state, and calculate an initial fitness value corresponding to the initial predicted operating state; Based on the initial predicted running state and the initial fitness value, multiple iterative searches are performed on the solution of the objective function, and for each iterative search: Randomly changing the initial predicted operating state to obtain a changed predicted operating state, and calculating a changed fitness value corresponding to the changed predicted operating state; Count the number of current iteration searches; In response to determining that the current iterative search number is greater than or equal to a predetermined number, exiting the iterative search, and determining the target predicted operating state based on the initial fitness value and the changed fitness value; In response to determining that the current iterative search number is less than the predetermined number, and determining that the initial fitness value is greater than the changed fitness value, using the changed predicted running state as the initial predicted running state for the next iterative search, and using the changed fitness value as the initial fitness value for the next iterative search; In response to determining that the current iterative search number is less than the predetermined number, and determining that the initial fitness value is less than or equal to the changed fitness value, the changed predicted operating state is used as the initial predicted operating state for the next iterative search according to dynamic probability, and the changed fitness value is used as the initial fitness value for the next iterative search.

5. The method according to claim 4, characterized in that The determining the target predicted operating state based on the initial fitness value and the changed fitness value includes: In response to determining that the initial fitness value is greater than the changed fitness value, determining the changed predicted operating state as the target predicted operating state; In response to determining that the initial fitness value is less than or equal to the changed fitness value, the initial predicted operating state is determined as the target predicted operating state.

6. The method according to claim 4, characterized in that The calculating the initial fitness value corresponding to the initial predicted running state includes: The initial fitness value is determined by the following formula: Wherein, f is the initial fitness value, Z' is the number of starts and stops of the unit in the initial predicted operating state, and λ k is the penalty factor, g k (x) indicates whether the kth constraint is satisfied. k (x) is denoted as a negative number. There are m constraints in total, and x is a variable in the constraints.

7. The method according to claim 4, characterized in that Also includes: The dynamic probability is determined by the following formula: Where G is the dynamic probability, exp represents the natural exponential function, and f new is the fitness value of the change, f current is the initial fitness value, and Te is the current temperature.

8. A device for predicting the operating state of a pumped storage unit, characterized in that: include: An acquisition module is configured to acquire a plurality of predicted operating states corresponding to each unit in a future period; A construction module is configured to construct an objective function based on multiple predicted operating states corresponding to each unit with the goal of minimizing the number of starts and stops of all units, and to construct multiple constraints corresponding to the objective function; The solution module is configured to solve the objective function based on the multiple constraints using a simulated annealing algorithm to obtain a target predicted operating state corresponding to each unit.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images